CN117370919B - Remote monitoring system for sewage treatment equipment - Google Patents
Remote monitoring system for sewage treatment equipment Download PDFInfo
- Publication number
- CN117370919B CN117370919B CN202311675845.6A CN202311675845A CN117370919B CN 117370919 B CN117370919 B CN 117370919B CN 202311675845 A CN202311675845 A CN 202311675845A CN 117370919 B CN117370919 B CN 117370919B
- Authority
- CN
- China
- Prior art keywords
- sewage treatment
- time sequence
- feature
- treatment equipment
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000010865 sewage Substances 0.000 title claims abstract description 186
- 238000012544 monitoring process Methods 0.000 title claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000010586 diagram Methods 0.000 claims description 80
- 238000005728 strengthening Methods 0.000 claims description 57
- 238000012549 training Methods 0.000 claims description 57
- 238000000034 method Methods 0.000 claims description 27
- 238000013527 convolutional neural network Methods 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 23
- 239000013598 vector Substances 0.000 claims description 22
- 238000004065 wastewater treatment Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000012800 visualization Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 8
- 230000002787 reinforcement Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 2
- 238000010606 normalization Methods 0.000 claims 2
- 238000004422 calculation algorithm Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 5
- 230000005856 abnormality Effects 0.000 abstract description 4
- 230000036541 health Effects 0.000 abstract description 3
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000012300 Sequence Analysis Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 21
- 238000009826 distribution Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 14
- 238000011176 pooling Methods 0.000 description 11
- 238000007689 inspection Methods 0.000 description 8
- 230000004913 activation Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 238000005273 aeration Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 241000098700 Sarcocheilichthys parvus Species 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003657 drainage water Substances 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 235000020188 drinking water Nutrition 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000012851 eutrophication Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000012633 leachable Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009022 nonlinear effect Effects 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The utility model discloses a sewage treatment equipment remote monitoring system, it is through the equipment data of the sewage treatment equipment (such as air-blower, water pump and mechanical grid etc.) among the real-time supervision collection sewage treatment plant, wherein including equipment running state, equipment start-stop information, equipment operating parameter and equipment operation cycle etc. and introduce data processing and analysis algorithm at the rear end and carry out time sequence analysis to the equipment data of the sewage treatment equipment who gathers, thereby judge whether this sewage treatment equipment's operating condition has the abnormality, through such a mode, can the real-time operation condition of remote monitoring sewage treatment plant equipment, report to the police when equipment is unusual or trouble automatically, remind the managers to take corresponding measure, in order to ensure sewage treatment equipment's normal operating and treatment effect. Therefore, the operation efficiency and the management level of the sewage treatment plant can be improved, the waste of human resources is reduced, and meanwhile, the environment and the health of residents can be better protected.
Description
Technical Field
The present application relates to the field of intelligent monitoring, and more particularly, to a remote monitoring system for a sewage treatment plant.
Background
With the continuous perfection of rural village and town construction and the improvement of the living standard of people, the discharge amount of various sewage in rural areas is in a year-by-year growing trend. The sewage components become more complex, and the new problems caused by various sewage in rural areas cannot be ignored. Untreated rural sewage is not only a potential threat of drinking water source, but also an important cause of eutrophication of rivers and lakes.
The operating efficiency and safety of sewage treatment plants directly affect the ecological environment in rural areas and the health of residents. However, the conventional monitoring system for the sewage treatment plant has some problems, particularly, the conventional inspection method requires manual periodic on-site inspection, which consumes time and manpower resources. Meanwhile, the manual inspection mode is easily affected by subjective factors of operators, and misjudgment on the state of sewage treatment equipment can be caused. In addition, the manual inspection mode may not be capable of timely finding out faults and anomalies of the equipment, so that the faults of the equipment are further deteriorated, and the sewage treatment effect is affected.
Accordingly, a remote monitoring system for a wastewater treatment facility is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems.
According to one aspect of the present application, there is provided a sewage treatment apparatus remote monitoring system comprising:
The device data acquisition module is used for acquiring device data of the sewage treatment device at a plurality of preset time points in a preset time period, wherein the device data comprise device running states, device start-stop information, device running parameters and device running periods;
the device data arrangement module is used for arranging the device data of the plurality of preset time points into a sewage treatment device operation data time sequence matrix according to the time dimension and the sample dimension;
the sewage treatment equipment operation time sequence feature extraction module is used for performing feature extraction on the sewage treatment equipment operation data time sequence matrix through a time sequence associated feature extractor based on a deep neural network model so as to obtain a sewage treatment equipment operation time sequence feature diagram;
the equipment operation time sequence characteristic strengthening module is used for carrying out characteristic association strengthening treatment on the sewage treatment equipment operation time sequence characteristic diagram so as to obtain strengthened sewage treatment equipment operation time sequence characteristics;
and the equipment working state detection module is used for determining whether the working state of the sewage treatment equipment is abnormal or not based on the operation time sequence characteristics of the enhanced sewage treatment equipment.
Compared with the prior art, the remote monitoring system for the sewage treatment equipment provided by the application is used for monitoring and collecting equipment data of sewage treatment equipment (such as a blower, a water pump, a mechanical grid and the like) in a sewage treatment plant in real time, wherein the equipment data comprise equipment running states, equipment start-stop information, equipment running parameters, equipment running periods and the like, and a data processing and analyzing algorithm is introduced into the rear end to perform time sequence analysis on the collected equipment data of the sewage treatment equipment, so that whether the working state of the sewage treatment equipment is abnormal or not is judged. Therefore, the operation efficiency and the management level of the sewage treatment plant can be improved, the waste of human resources is reduced, and meanwhile, the environment and the health of residents can be better protected.
Drawings
The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a block diagram of a remote monitoring system for a wastewater treatment facility according to an embodiment of the present application;
FIG. 2 is a system architecture diagram of a remote monitoring system for a wastewater treatment facility according to an embodiment of the present application;
FIG. 3 is a block diagram of a training phase of a remote monitoring system for a wastewater treatment facility according to an embodiment of the present application;
fig. 4 is a block diagram of an equipment operation time sequence characteristic strengthening module in the remote monitoring system of the sewage treatment equipment according to the embodiment of the application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
The conventional monitoring system for the sewage treatment plant has some problems, particularly, the conventional inspection method needs to be manually and periodically checked on site, and time and manpower resources are consumed. Meanwhile, the manual inspection mode is easily affected by subjective factors of operators, and misjudgment on equipment states can be caused. In addition, the manual inspection mode may not be capable of timely finding out faults and anomalies of the equipment, so that the faults of the equipment are further deteriorated, and the sewage treatment effect is affected. Accordingly, a remote monitoring system for a wastewater treatment facility is desired.
In the technical scheme of this application, a sewage treatment device remote monitoring system is provided. Fig. 1 is a block diagram of a remote monitoring system for a wastewater treatment facility according to an embodiment of the present application. Fig. 2 is a system architecture diagram of a remote monitoring system for a sewage treatment apparatus according to an embodiment of the present application. As shown in fig. 1 and 2, a sewage treatment apparatus remote monitoring system 300 according to an embodiment of the present application includes: an equipment data acquisition module 310, configured to acquire equipment data of a sewage treatment equipment at a plurality of predetermined time points within a predetermined time period, where the equipment data includes an equipment operation state, equipment start-stop information, equipment operation parameters and an equipment operation period; an equipment data arrangement module 320, configured to arrange the equipment data at the plurality of predetermined time points into a sewage treatment equipment operation data time sequence matrix according to a time dimension and a sample dimension; a sewage treatment equipment operation time sequence feature extraction module 330, configured to perform feature extraction on the sewage treatment equipment operation data time sequence matrix through a time sequence correlation feature extractor based on a deep neural network model to obtain a sewage treatment equipment operation time sequence feature map; the equipment operation time sequence characteristic strengthening module 340 is configured to perform characteristic association strengthening treatment on the sewage treatment equipment operation time sequence characteristic map to obtain a strengthened sewage treatment equipment operation time sequence characteristic; the device working state detection module 350 is configured to determine whether an abnormality exists in the working state of the sewage treatment device based on the operation time sequence feature of the enhanced sewage treatment device.
In particular, the device data acquisition module 310 is configured to acquire device data of the sewage treatment device at a plurality of predetermined time points within a predetermined period of time, where the device data includes a device operation state, device start-stop information, a device operation parameter, and a device operation period. It should be understood that the device data can reflect information such as an operation state and an operation parameter of the device, and can reflect specific situations of the device at a plurality of predetermined time points within the predetermined time period.
In particular, the device data arrangement module 320 is configured to arrange the device data at the plurality of predetermined time points into a sewage treatment device operation data timing matrix according to a time dimension and a sample dimension. Considering that each data item in the equipment data of the sewage treatment equipment has a time sequence change characteristic in the time dimension, the data items also have an association relation between samples. Therefore, in order to analyze and describe the time sequence correlation characteristics of the device data more fully, in the technical scheme of the application, the device data of the plurality of preset time points needs to be arranged into a sewage treatment device operation data time sequence matrix according to a time dimension and a sample dimension, so as to integrate the distribution information of the device data in the time dimension and the sample dimension.
In particular, the sewage treatment apparatus operation time sequence feature extraction module 330 is configured to perform feature extraction on the sewage treatment apparatus operation data time sequence matrix through a time sequence correlation feature extractor based on a deep neural network model to obtain a sewage treatment apparatus operation time sequence feature map. In consideration of certain time sequence relativity among equipment data items at different time points in the operation data of the sewage treatment equipment, for example, a periodic operation mode of the equipment, a change trend of operation parameters and the like. Therefore, the sewage treatment equipment operation data time sequence matrix is further subjected to feature mining in a time sequence correlation feature extractor based on a convolutional neural network model so as to extract time sequence correlation feature distribution information among data items in equipment data of the sewage treatment equipment, and thus a sewage treatment equipment operation time sequence feature diagram is obtained and used for representing operation state time sequence correlation features of the sewage treatment equipment. Specifically, each layer using the time sequence correlation feature extractor based on the convolutional neural network model performs the following steps on input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature images based on the local feature matrix to obtain pooled feature images; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the time sequence correlation characteristic extractor based on the convolutional neural network model is a time sequence characteristic diagram of the sewage treatment equipment operation, and the input of the first layer of the time sequence correlation characteristic extractor based on the convolutional neural network model is a data time sequence matrix of the sewage treatment equipment operation.
Notably, convolutional neural networks (Convolutional Neural Network, CNN for short) are a deep learning model widely used for image processing and computer vision tasks. The core idea of CNN is to extract and combine features of data through the convolutional layer, pooling layer, and fully-connected layer. The following are the main components of CNN: convolution layer: the convolution layer carries out convolution operation on input data by applying a group of leachable filters (convolution kernels), so that local features are extracted, and the convolution operation can effectively capture the spatial local correlation in the image; pooling layer: the pooling layer is used to reduce the spatial size of the feature map and preserve important features, the most common pooling operation is maximum pooling and average pooling, which selects the maximum value in each region as the pooling result; activation function: nonlinear activation functions (such as ReLU, sigmoid, or Tanh) are typically used between the convolutional layer and the fully-connected layer to introduce nonlinear properties to enhance the expressive power of the model; full tie layer: the fully connected layer connects the outputs of the convolutional and pooling layers and passes them as inputs to the next layer, which is typically used for the final classification task, mapping the high-level features to the target classes. The training process of CNNs typically uses a back-propagation algorithm for parameter optimization. Through a large amount of marking data and loss functions, the CNN can automatically learn a feature representation that is appropriate for a particular task.
In particular, the device operation time sequence feature strengthening module 340 is configured to perform feature association strengthening treatment on the sewage treatment device operation time sequence feature map to obtain a strengthened sewage treatment device operation time sequence feature. In particular, in one specific example of the present application, as shown in fig. 4, the apparatus operation timing characteristic enhancing module 340 includes: a channel characteristic strengthening unit 341, configured to pass the operation time sequence characteristic diagram of the sewage treatment device through a channel attention module to obtain an operation time sequence characteristic diagram of the sewage treatment device with a channel visualization; and the characteristic autocorrelation correlation strengthening unit 342 is configured to perform characteristic autocorrelation correlation strengthening treatment on the operation time sequence characteristic diagram of the channel visualization sewage treatment device so as to obtain a re-strengthening operation time sequence characteristic diagram of the sewage treatment device, which is used as the operation time sequence characteristic of the strengthening sewage treatment device.
Specifically, the channel characteristic strengthening unit 341 is configured to pass the operation time sequence characteristic diagram of the sewage treatment apparatus through a channel attention module to obtain an operation time sequence characteristic diagram of the sewage treatment apparatus with a channel visualization. It should be appreciated that in the wastewater treatment facility operational timing diagram, different channels may have different importance and contribution. Some channels may contain more critical information while other channels may be relatively unimportant. By means of the channel attention module, the importance of each channel can be evaluated and adjusted, thus highlighting important channel information. Therefore, in the technical scheme of the application, the operation time sequence characteristic diagram of the sewage treatment equipment is further processed through the channel attention module to obtain the operation time sequence characteristic diagram of the sewage treatment equipment with the channel display. The channel-development sewage treatment equipment operation time sequence feature diagram obtained through the channel attention module can highlight key information in equipment operation, so that the equipment operation condition can be observed and analyzed more intuitively, the understanding and judging capability of a system on the equipment operation state can be improved, and the equipment operation mode, key features and abnormal behaviors can be recognized quickly. More specifically, the sewage treatment equipment operation time sequence characteristic diagram is passed through a channel attention module to obtain a channel visualization sewage treatment equipment operation time sequence characteristic diagram, which comprises the following steps: carrying out global average pooling on each feature matrix of the running time sequence feature diagram of the sewage treatment equipment along the channel dimension to obtain a channel feature vector; inputting the channel feature vector into a Softmax activation function to obtain a channel attention weight vector; and weighting each characteristic matrix of the sewage treatment equipment operation time sequence characteristic diagram along the channel dimension by taking the characteristic value of each position in the channel attention weight vector as a weight so as to obtain the channel visualization sewage treatment equipment operation time sequence characteristic diagram.
It is worth mentioning that the channel attention module (Channel Attention Module) is a module for enhancing the performance of Convolutional Neural Networks (CNNs) that automatically learns and weights the feature representations of different channels. The main purpose of the channel attention module is to adaptively adjust the importance of each channel by learning the correlation between channels. This is very useful for improving the feature expression ability of the model on different channels, helping to reduce redundant information and enhance the representation of useful information. Through the channel attention module, the CNN can adaptively learn the importance of each channel, and the attention of the model to the features on different channels is improved. It should be noted that the channel attention module is a module that can be embedded in the CNN and can be designed and adjusted according to the specific task and the requirements of the network structure. It can be used as part of CNN, combined with other modules (such as convolution layer, pooling layer, etc.), to improve the performance of the model.
Specifically, the characteristic autocorrelation correlation strengthening unit 342 is configured to perform characteristic autocorrelation correlation strengthening treatment on the channel-developed sewage treatment device operation time sequence characteristic diagram to obtain a re-strengthened sewage treatment device operation time sequence characteristic diagram as the strengthened sewage treatment device operation time sequence characteristic. It should be understood that, in order to further enhance the expression capability of the features and the accuracy of abnormality detection, in the technical scheme of the application, the operation time sequence feature diagram of the channel visualization sewage treatment device is obtained by using a feature autocorrelation correlation enhancement module so as to re-enhance the operation time sequence feature diagram of the sewage treatment device. It should be understood that in the operation time sequence characteristic diagram of the channel visualization sewage treatment equipment, certain correlation and dependency relationship exist among different channels. Through the processing of the characteristic autocorrelation correlation strengthening module, the correlation between channels in the characteristic diagram can be captured, and the correlation is further strengthened so as to improve the expression capacity of the characteristics. Therefore, by re-strengthening the operation time sequence characteristic diagram of the sewage treatment equipment, key characteristics and abnormal behaviors in the operation of the equipment can be better captured, and meanwhile, the strengthened characteristic diagram has higher expression capacity and discrimination, so that whether the operation state of the equipment is abnormal or not can be accurately identified. More specifically, the method for obtaining the operation time sequence characteristic diagram of the re-reinforced sewage treatment equipment by using the operation time sequence characteristic diagram of the channel visualization sewage treatment equipment through a characteristic autocorrelation correlation reinforcement module comprises the following steps: the operation time sequence characteristic diagram of the channel visualization sewage treatment equipment passes through a first convolution layer of the characteristic autocorrelation strengthening module to obtain a first characteristic diagram; passing the first feature map through a second convolution layer of the feature autocorrelation strengthening module to obtain a second feature map; expanding each feature matrix of the second feature map along the channel dimension into feature vectors to obtain a sequence of first feature vectors; calculating cosine similarity between any two first feature vectors in the sequence of the first feature vectors to obtain a cosine similarity feature map; normalizing the cosine similarity feature map through a softmax function to obtain a normalized cosine similarity feature map; multiplying the normalized cosine similarity feature map and the cosine similarity feature map according to position points to obtain a similarity mapping optimization feature map; the similarity mapping optimization feature map passes through a first convolution layer of the feature autocorrelation strengthening module to obtain a first deconvolution feature map; calculating element-by-element sums of the first deconvolution feature map and the first feature map to obtain a first fusion feature map; passing the first fusion feature map through a second convolution layer of the feature autocorrelation strengthening module to obtain a second deconvolution feature map; and calculating element-by-element sums of the second deconvolution characteristic diagram and the channel visualization sewage treatment equipment operation time sequence characteristic diagram to obtain the re-reinforcement sewage treatment equipment operation time sequence characteristic diagram.
It should be noted that, in other specific examples of the present application, the characteristic association strengthening treatment may be performed on the operation time sequence characteristic diagram of the sewage treatment apparatus in other manners to obtain a strengthening operation time sequence characteristic of the sewage treatment apparatus, for example: collecting operation time sequence data of sewage treatment equipment, including sensor data, operation records and the like; preprocessing the collected data, including data cleaning, missing value filling, outlier processing and the like; features are extracted from the preprocessed data, and various feature extraction methods such as statistical features (mean, variance and the like), frequency domain features, time domain features and the like can be used, and a proper feature extraction method is selected according to the characteristics and task requirements of sewage treatment equipment; the extracted features are subjected to association processing to capture the correlation among the features, the correlation among the features can be measured by using methods such as correlation coefficients, mutual information and the like, and features with the highest correlation can be selected by adopting feature selection algorithms such as chi-square inspection, L1 regularization and the like; on the basis of feature association, feature strengthening treatment is carried out to improve the expression capacity of the features, dimension reduction technology such as principal component analysis, linear discriminant analysis and the like can be used to reduce the dimension of the features and retain the most representative information, and feature combination such as feature intersection, feature product and the like can be carried out to generate new features; the reinforced features are applied to the operation time sequence data analysis of the sewage treatment equipment, and tasks such as classification, regression or anomaly detection can be performed by using a machine learning algorithm such as a support vector machine, a random forest and the like.
In particular, the device operation state detection module 350 is configured to determine whether an abnormality exists in the operation state of the sewage treatment device based on the operation time sequence feature of the enhanced sewage treatment device. In the technical scheme of the application, the operation time sequence characteristic diagram of the re-reinforced sewage treatment equipment is used for obtaining a classification result through a classifier, and the classification result is used for indicating whether the working state of the sewage treatment equipment is abnormal or not. That is, the characteristic-enhanced operation state time sequence related characteristic information of the sewage treatment equipment is subjected to classification treatment, so that whether the operation state of the sewage treatment equipment is abnormal or not is judged, by the mode, the real-time operation condition of the sewage treatment plant equipment can be monitored remotely, and when equipment is abnormal or fails, an alarm is automatically given to remind a manager to take corresponding measures so as to ensure the normal operation and treatment effect of the sewage treatment equipment. Specifically, the operation time sequence characteristic diagram of the re-reinforced sewage treatment equipment is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the sewage treatment equipment is abnormal or not, and the method comprises the following steps: expanding the operation time sequence characteristic diagram of the re-enhanced sewage treatment equipment into classification characteristic vectors based on row vectors or column vectors; performing full-connection coding on the classification feature vectors by using a plurality of full-connection layers of the classifier to obtain coded classification feature vectors; and; and the coding classification feature vector is passed through a Softmax classification function of the classifier to obtain the classification result.
A classifier refers to a machine learning model or algorithm that is used to classify input data into different categories or labels. The classifier is part of supervised learning, which performs classification tasks by learning mappings from input data to output categories.
Fully connected layers are one type of layer commonly found in neural networks. In the fully connected layer, each neuron is connected to all neurons of the upper layer, and each connection has a weight. This means that each neuron in the fully connected layer receives inputs from all neurons in the upper layer, and weights these inputs together, and then passes the result to the next layer.
The Softmax classification function is a commonly used activation function for multi-classification problems. It converts each element of the input vector into a probability value between 0 and 1, and the sum of these probability values equals 1. The Softmax function is commonly used at the output layer of a neural network, and is particularly suited for multi-classification problems, because it can map the network output into probability distributions for individual classes. During the training process, the output of the Softmax function may be used to calculate the loss function and update the network parameters through a back propagation algorithm. Notably, the output of the Softmax function does not change the relative magnitude relationship between elements, but rather normalizes them. Thus, the Softmax function does not change the characteristics of the input vector, but simply converts it into a probability distribution form.
It should be appreciated that training of the convolutional neural network model-based time-series correlation feature extractor, the channel attention module, the feature autocorrelation correlation enhancement module, and the classifier is required prior to inference using the neural network model described above. That is, the sewage treatment apparatus remote monitoring system 300 according to the present application further includes a training stage 400 for training the time-series correlation feature extractor, the channel attention module, the feature autocorrelation correlation reinforcement module, and the classifier based on the convolutional neural network model.
Fig. 3 is a block diagram of a training phase of a remote monitoring system for a wastewater treatment facility according to an embodiment of the present application. As shown in fig. 3, a sewage treatment apparatus remote monitoring system 300 according to an embodiment of the present application includes: training phase 400, comprising: a training data obtaining unit 410, configured to obtain training data, where the training data includes training device data of a sewage treatment device at a plurality of predetermined time points within a predetermined time period, where the training device data includes a device operation state, device start-stop information, a device operation parameter, and a device operation period; a training data arrangement unit 420, configured to arrange the training device data at the plurality of predetermined time points into a training sewage treatment device operation data timing matrix according to a time dimension and a sample dimension; a training feature extraction unit 430, configured to perform feature extraction on the training sewage treatment apparatus operation data timing matrix through a timing sequence correlation feature extractor based on a deep neural network model, so as to obtain a training sewage treatment apparatus operation timing sequence feature map; a training feature strengthening unit 440, configured to perform feature association strengthening treatment on the training sewage treatment apparatus operation time sequence feature map to obtain a training re-strengthening sewage treatment apparatus operation time sequence feature map; the feature optimization unit 450 is configured to perform position-by-position feature value optimization on the training re-enhanced sewage treatment equipment operation time sequence feature map to obtain the training optimized re-enhanced sewage treatment equipment operation time sequence feature map; a classification loss unit 460, configured to pass the training optimized re-intensified sewage treatment apparatus operation time sequence feature map through the classifier to obtain a classification loss function value; and a training unit 470, configured to train the time-series correlation feature extractor, the channel attention module, the feature autocorrelation correlation strengthening module, and the classifier based on the classification loss function value.
Wherein, the categorised loss unit is used for: and calculating a cross entropy loss function value between the training classification result and a true value of whether the working state of the sewage treatment equipment is abnormal or not as the classification loss function value.
Particularly, in the technical scheme of the application, after the sewage treatment equipment operation data time sequence matrix passes through the time sequence correlation feature extractor based on the convolutional neural network model, each feature matrix of the obtained sewage treatment equipment operation time sequence feature diagram expresses the local correlation feature of equipment data in the time sequence-sample cross dimension, and the feature matrices conform to the channel distribution of the convolutional neural network model, so that after the sewage treatment equipment operation time sequence feature diagram passes through the channel attention module and the feature autocorrelation strengthening expression module, the whole spatial distribution expression of some feature matrices can be promoted on the channel distribution, the channel dimension is restrained based on the time sequence-sample cross dimension local correlation of the feature matrix in the spatial distribution dimension, and the whole operation time sequence feature diagram of the re-strengthening sewage treatment equipment has the local correlation feature distribution based on the cross dimension. However, considering that the difference of the local associated feature distribution in the cross dimension brings local feature distribution sparsification to the overall feature representation of the operation time sequence feature diagram of the re-enhanced sewage treatment equipment, namely, the sub-manifold is thinned out of the distribution relative to the overall high-dimensional feature manifold, so that when the operation time sequence feature diagram of the re-enhanced sewage treatment equipment is subjected to class probability regression mapping through a classifier, the convergence from the operation time sequence feature diagram of the re-enhanced sewage treatment equipment to the predetermined class probability class representation in the probability space is poor, and the accuracy of the classification result is affected. Therefore, preferably, the operation time sequence characteristic diagram of the re-enhanced sewage treatment equipment is optimized by position characteristic values, specifically:
；
Wherein the method comprises the steps ofIs the operational time sequence characteristic diagram of the re-enhanced sewage treatment equipment>Is each characteristic value of the operation time sequence characteristic diagram of the re-enhanced sewage treatment equipment, +.>Index operation representing vector,/->Is a time sequence characteristic diagram for training, optimizing and re-strengthening the operation of the sewage treatment equipment. That is, sparse distribution in a high-dimensional feature space is processed by regularization based on heavy probability to activate the operational time sequence feature map of the re-enhanced sewage treatment device>Natural distribution transfer of geometric manifold to probability space in high-dimensional feature space, thereby operating time sequence feature diagram of the re-enhanced sewage treatment equipmentThe method for carrying out the smooth regularization based on the heavy probability on the distributed sparse sub-manifold of the high-dimensional characteristic manifold improves the category convergence of the complex high-dimensional characteristic manifold with high space sparsity under the preset category probability, thereby improving the re-strengthSewage treatment equipment operation time sequence characteristic diagram ∈>The accuracy of the classification result obtained by the classifier. Like this, can the real-time operation condition of remote monitoring sewage treatment plant equipment, report to the police automatically when equipment is unusual or trouble appears and remind the managers to take corresponding measure to ensure sewage treatment plant's normal operating and treatment effect, through this kind of mode, can improve sewage treatment plant's operating efficiency and management level, reduce the waste of manpower resources, also can protect environment and village and town resident healthy better simultaneously.
As described above, the sewage treatment apparatus remote monitoring system 300 according to the embodiment of the present application may be implemented in various wireless terminals, such as a server having a sewage treatment remote monitoring algorithm, and the like. In one possible implementation, the wastewater treatment facility remote monitoring system 300 according to embodiments of the present application may be integrated into the wireless terminal as a software module and/or hardware module. For example, the wastewater treatment facility remote monitoring system 300 may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the wastewater treatment facility remote monitoring system 300 may also be one of a number of hardware modules of the wireless terminal.
Alternatively, in another example, the wastewater treatment facility remote monitoring system 300 and the wireless terminal may be separate devices, and the wastewater treatment facility remote monitoring system 300 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a agreed data format.
In one example, the overall process supervision platform of a rural sewage treatment plant is basically as follows:
1. The application range is as follows: the technology is suitable for all sewage treatment plants and other sites needing industry supervision, and can also be used as a supervision platform for a sewage discharge enterprise by a government functional department.
2. The process route is as follows:
(1) And selecting equipment and a communication mode for collecting operation parameter data of the field equipment.
(2) And selecting a remote transmission module with cloud storage and data processing.
(3) Selecting data link network devices and software matching the devices and remote transmission modules mentioned in (1) and (2).
(4) Software with remote monitoring, data processing and storage functions and a monitoring computer are selected.
(5) And reasonably designed and selected video monitoring points and network transmission equipment.
(6) And selecting to remotely adjust the operating parameters of the equipment of the monitored facility, and confirming that the equipment is shut down and is in operation when an emergency occurs.
(7) And designing a programming method of software required by constructing a remote monitoring platform and a debugging method of platform system equipment.
3. The main contaminants of control: the following pollutant reduction of the sewage treatment plant is facilitated: COD, ammonia nitrogen, total phosphorus, SS, PH, BOD, etc.
4. Pollution control effect: because the remote supervision is realized on the rural sewage treatment plant, a plurality of automatic control links are added in the supervision software, the key equipment operates under the automatic working condition, the misoperation caused by human factors is effectively avoided, meanwhile, through the remote supervision, the operation parameters of the operation equipment can be timely known, the alarm can be automatically generated on the nearby out-of-standard parameters, the operators are prompted to adjust in time, the up-to-standard emission of the sewage treatment plant is guaranteed, good supervision, guidance and guarantee effects are achieved, and meanwhile, the operators are reduced.
For the direct economic benefit of simultaneously supervising a plurality of sewage treatment plants, not only the omnibearing supervision function is realized, but also the management personnel, the operation personnel and the maintenance personnel of other secondary stations except the main station are saved.
5. Main process operation and control parameters:
(1) And when the liquid level of all the processing devices reaches the upper limit of the process, automatically generating alarm information, and simultaneously starting the lifting pump.
(2) When the first-stage lifting pump of the device is started, the dosing device is started to dose according to the lifting flow automatically and the dosing quantity corresponding to the dosing device.
(3) The air quantity of the air blower of the aeration tank is automatically regulated according to the water inflow and ORP detection values, so that the aeration optimization control is realized, and the energy consumption is reduced.
(4) And automatically detecting the operation of the equipment on site and remotely, and automatically generating alarm information when abnormal parameters occur to prompt operators to adjust the equipment conditions in time.
(5) And parameters of all operating equipment and process detection instruments automatically generate a historical trend chart so as to provide a basis for process technicians and management personnel to trace back equipment and process operating parameters in a period of time, and to summarize and adjust the process and trace back accidents.
(6) Automatically generating an alarm (exceeding technological parameters, abnormal equipment stopping operation, etc.) record.
(7) The equipment operation record is automatically generated so as to trace and check the equipment operation condition (whether the equipment is operated under an automatic condition or under manual intervention) before the emergency, so that the reasons of the emergency can be searched and the occurrence of the emergency is stopped.
(8) The operation condition and the technological parameters of all the equipment can be remotely monitored.
6. Relevant standards that the technology can reach: the equipment and the software are all equipment and software which accord with national standards.
The specific functions which can be realized by the application are as follows:
the device operating status (when to start, when to stop) of each station under the supervisory platform is indicated in the form of indicator lights (red to stop, green to start) at the flow chart interface, while the operating status of the device is kept in the operation record (information of when the device starts, starts or stops, whether it is operated automatically or manually, etc.).
The operation parameters of the detection instruments of each station under the supervision platform are displayed in a digital form on each relevant process picture, when abnormal process parameters occur, alarm information (in a list, alarm time, real-time parameters, time for the alarm parameters to recover to normal values and the like are recorded), meanwhile, in each monitoring picture, parameter values during the alarm become red flash, and alarm prompt sounds are sent out to remind operators and managers to pay attention, and abnormal or adjustment processes are timely processed.
3. All key technological parameter information automatically generates a trend chart, and parameters related to a technological process are designed in the same trend chart, so that operators and technicians can judge technological conditions, and technological problems can be traced, inquired and summarized. The trend graph can be stored in a local control computer, a control center computer and a cloud storage unit for a long time so as to be convenient for inquiring and retrieving, and the reliability of data storage is ensured.
4. The geographical position of the facilities under the platform is marked in the map so as to be known by the consulting staff. When the position of the facility marked in the map is clicked by a mouse, key operation parameter forms (such as inflow water quantity, drainage water quantity, water quality and the like of the sewage treatment plant) of the facility can be automatically popped up, and red flickering numbers can appear on the exceeding parameters so as to prompt operators and managers to pay attention.
5. The key equipment can realize remote control and parameter correction (operation level setting and password protection) so as to enable a technician (or authorized personnel) to remotely control the key equipment parameters.
6. The video monitoring system for key parts of each facility can see the monitored video information at the interfaces of the local control station, the remote monitoring station and the mobile terminal, so that a manager can know the conditions of personnel and equipment facilities at the monitored point at any time and any place.
7. The functions can be realized on an APP interface of the mobile terminal through cloud transmission and cloud storage technologies.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (6)
1. A remote monitoring system for a wastewater treatment facility, comprising:
the device data acquisition module is used for acquiring device data of the sewage treatment device at a plurality of preset time points in a preset time period, wherein the device data comprise device running states, device start-stop information, device running parameters and device running periods;
the device data arrangement module is used for arranging the device data of the plurality of preset time points into a sewage treatment device operation data time sequence matrix according to the time dimension and the sample dimension;
The sewage treatment equipment operation time sequence feature extraction module is used for performing feature extraction on the sewage treatment equipment operation data time sequence matrix through a time sequence associated feature extractor based on a deep neural network model so as to obtain a sewage treatment equipment operation time sequence feature diagram;
the equipment operation time sequence characteristic strengthening module is used for carrying out characteristic association strengthening treatment on the sewage treatment equipment operation time sequence characteristic diagram so as to obtain strengthened sewage treatment equipment operation time sequence characteristics;
the equipment working state detection module is used for determining whether the working state of the sewage treatment equipment is abnormal or not based on the operation time sequence characteristics of the enhanced sewage treatment equipment;
wherein, the equipment operation time sequence characteristic strengthening module includes:
the channel characteristic strengthening unit is used for enabling the operation time sequence characteristic diagram of the sewage treatment equipment to pass through the channel attention module to obtain the operation time sequence characteristic diagram of the sewage treatment equipment with the channel visualization;
the characteristic autocorrelation correlation strengthening unit is used for carrying out characteristic autocorrelation correlation strengthening treatment on the running time sequence characteristic diagram of the channel visualization sewage treatment equipment to obtain a re-strengthening sewage treatment equipment running time sequence characteristic diagram which is used as the strengthening sewage treatment equipment running time sequence characteristic;
The characteristic autocorrelation correlation strengthening unit is used for: the operation time sequence characteristic diagram of the channel visualization sewage treatment equipment is subjected to a characteristic autocorrelation correlation strengthening module to obtain the operation time sequence characteristic diagram of the re-strengthening sewage treatment equipment;
wherein, the characteristic autocorrelation association strengthening unit includes:
the first convolution subunit is used for enabling the running time sequence characteristic diagram of the channel visualization sewage treatment equipment to pass through a first convolution layer of the characteristic autocorrelation strengthening module to obtain a first characteristic diagram;
a second convolution subunit, configured to pass the first feature map through a second convolution layer of the feature autocorrelation strengthening module to obtain a second feature map;
a spreading subunit, configured to spread each feature matrix of the second feature map along a channel dimension into feature vectors to obtain a sequence of first feature vectors;
the cosine similarity calculation subunit is used for calculating cosine similarity between any two first feature vectors in the sequence of the first feature vectors to obtain a cosine similarity feature map;
the normalization subunit is used for carrying out normalization processing on the cosine similarity feature map through a softmax function so as to obtain a normalized cosine similarity feature map;
The similarity mapping optimization subunit is used for multiplying the normalized cosine similarity feature map and the cosine similarity feature map according to position points to obtain a similarity mapping optimization feature map;
a first deconvolution subunit, configured to pass the similarity mapping optimization feature map through a first deconvolution layer of the feature autocorrelation strengthening module to obtain a first deconvolution feature map;
a first fused feature calculation subunit, configured to calculate an element-by-element sum of the first deconvolution feature map and the first feature map to obtain a first fused feature map;
a second deconvolution subunit, configured to pass the first fused feature map through a second deconvolution layer of the feature autocorrelation enhancement module to obtain a second deconvolution feature map;
and the reinforcingprocessing equipment operation time sequence characteristic calculating subunit is used for calculating element-by-element sums of the second deconvolution characteristic diagram and the channel visualization sewage processing equipment operation time sequence characteristic diagram so as to obtain the reinforcingprocessing equipment operation time sequence characteristic diagram.
2. The remote monitoring system of sewage treatment equipment according to claim 1, wherein the deep neural network model is a convolutional neural network model.
3. The remote monitoring system of a sewage treatment apparatus according to claim 2, wherein the apparatus operation state detection module is configured to: and the operation time sequence characteristic diagram of the re-reinforced sewage treatment equipment passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the sewage treatment equipment is abnormal or not.
4. The wastewater treatment facility remote monitoring system of claim 3, further comprising a training module for training the convolutional neural network model-based time-series-associated feature extractor, the channel attention module, the feature autocorrelation-associated reinforcement module, and the classifier.
5. The remote monitoring system of a wastewater treatment facility of claim 4, wherein the training module comprises:
the sewage treatment device comprises a training data acquisition unit, a control unit and a control unit, wherein the training data acquisition unit is used for acquiring training data, the training data comprises training device data of a plurality of preset time points of the sewage treatment device in a preset time period, and the training device data comprises a device running state, device start-stop information, device running parameters and a device running period;
the training data arrangement unit is used for arranging the training equipment data of the plurality of preset time points into a training sewage treatment equipment operation data time sequence matrix according to the time dimension and the sample dimension;
The training feature extraction unit is used for extracting features of the training sewage treatment equipment operation data time sequence matrix through a time sequence associated feature extractor based on a deep neural network model so as to obtain a training sewage treatment equipment operation time sequence feature map;
the training characteristic strengthening unit is used for carrying out characteristic association strengthening treatment on the training sewage treatment equipment operation time sequence characteristic diagram so as to obtain a training re-strengthening sewage treatment equipment operation time sequence characteristic diagram;
the feature optimization unit is used for optimizing the position-by-position feature values of the operation time sequence feature map of the training re-strengthening sewage treatment equipment so as to obtain the operation time sequence feature map of the training optimization re-strengthening sewage treatment equipment;
the classification loss unit is used for enabling the training optimization re-strengthening sewage treatment equipment operation time sequence characteristic diagram to pass through the classifier so as to obtain a classification loss function value;
the training unit is used for training the time sequence correlation feature extractor, the channel attention module, the feature autocorrelation correlation strengthening module and the classifier based on the convolutional neural network model based on the classification loss function value;
the training re-strengthening sewage treatment equipment operation time sequence feature diagram is subjected to position-by-position feature value optimization, and the method specifically comprises the following steps:
;
Wherein the method comprises the steps ofIs the operation time sequence characteristic diagram of the training re-strengthening sewage treatment equipment>Is what is shown asTraining to strengthen each characteristic value of the running time sequence characteristic diagram of the sewage treatment equipment>Index operation representing vector,/->Is a time sequence characteristic diagram for training, optimizing and re-strengthening the operation of the sewage treatment equipment.
6. The remote monitoring system of a sewage treatment plant according to claim 5, wherein the classification loss unit is configured to:
processing the training re-strengthening sewage treatment equipment operation time sequence characteristic diagram by using the classifier to obtain a training classification result:
and calculating a cross entropy loss function value between the training classification result and a true value of whether the working state of the sewage treatment equipment is abnormal or not as the classification loss function value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311675845.6A CN117370919B (en) | 2023-12-08 | 2023-12-08 | Remote monitoring system for sewage treatment equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311675845.6A CN117370919B (en) | 2023-12-08 | 2023-12-08 | Remote monitoring system for sewage treatment equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117370919A CN117370919A (en) | 2024-01-09 |
| CN117370919B true CN117370919B (en) | 2024-03-01 |
Family
ID=89406328
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311675845.6A Active CN117370919B (en) | 2023-12-08 | 2023-12-08 | Remote monitoring system for sewage treatment equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117370919B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118010391B (en) * | 2024-02-20 | 2024-07-16 | 浙江莱恩过滤系统有限公司 | Full-automatic sampling test system of filter |
| CN117787511B (en) * | 2024-02-28 | 2024-05-10 | 福州工小四物联科技有限公司 | Industrial high-density aquaculture monitoring and early warning method and system thereof |
| CN118311915B (en) * | 2024-06-11 | 2024-08-30 | 山东金呈阳建设工程有限公司 | Sewage treatment equipment operation monitoring method and system based on big data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114818515A (en) * | 2022-06-24 | 2022-07-29 | 中国海洋大学 | Multidimensional time sequence prediction method based on self-attention mechanism and graph convolution network |
| CN115204359A (en) * | 2022-05-31 | 2022-10-18 | 韶关学院 | Parallel deep convolution neural network optimization method based on Winograd convolution |
| CN115811048A (en) * | 2022-12-07 | 2023-03-17 | 东南大学 | Power transmission section out-of-limit control method based on space-time characteristic enhanced sensing network |
| CN116502164A (en) * | 2023-04-24 | 2023-07-28 | 哈尔滨工程大学 | Multidimensional time series data anomaly detection method, device and medium based on countermeasure training and frequency domain improvement self-attention mechanism |
| CN116700193A (en) * | 2023-07-20 | 2023-09-05 | 江西斯源科技股份有限公司 | Factory workshop intelligent monitoring management system and method thereof |
| CN116821661A (en) * | 2023-07-24 | 2023-09-29 | 中国电信股份有限公司 | Time sequence data monitoring method and device, electronic equipment and nonvolatile storage medium |
| CN116821619A (en) * | 2023-06-25 | 2023-09-29 | 广州市香港科大霍英东研究院 | Time sequence anomaly detection method based on multi-element time sequence relation learning |
| CN117034175A (en) * | 2023-10-07 | 2023-11-10 | 北京麟卓信息科技有限公司 | Time sequence data anomaly detection method based on channel fusion self-attention mechanism |
| CN117045424A (en) * | 2023-09-28 | 2023-11-14 | 开封市中心医院 | Auxiliary device is alleviated to tumour patient's hand and foot syndrome |
-
2023
- 2023-12-08 CN CN202311675845.6A patent/CN117370919B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115204359A (en) * | 2022-05-31 | 2022-10-18 | 韶关学院 | Parallel deep convolution neural network optimization method based on Winograd convolution |
| CN114818515A (en) * | 2022-06-24 | 2022-07-29 | 中国海洋大学 | Multidimensional time sequence prediction method based on self-attention mechanism and graph convolution network |
| CN115811048A (en) * | 2022-12-07 | 2023-03-17 | 东南大学 | Power transmission section out-of-limit control method based on space-time characteristic enhanced sensing network |
| CN116502164A (en) * | 2023-04-24 | 2023-07-28 | 哈尔滨工程大学 | Multidimensional time series data anomaly detection method, device and medium based on countermeasure training and frequency domain improvement self-attention mechanism |
| CN116821619A (en) * | 2023-06-25 | 2023-09-29 | 广州市香港科大霍英东研究院 | Time sequence anomaly detection method based on multi-element time sequence relation learning |
| CN116700193A (en) * | 2023-07-20 | 2023-09-05 | 江西斯源科技股份有限公司 | Factory workshop intelligent monitoring management system and method thereof |
| CN116821661A (en) * | 2023-07-24 | 2023-09-29 | 中国电信股份有限公司 | Time sequence data monitoring method and device, electronic equipment and nonvolatile storage medium |
| CN117045424A (en) * | 2023-09-28 | 2023-11-14 | 开封市中心医院 | Auxiliary device is alleviated to tumour patient's hand and foot syndrome |
| CN117034175A (en) * | 2023-10-07 | 2023-11-10 | 北京麟卓信息科技有限公司 | Time sequence data anomaly detection method based on channel fusion self-attention mechanism |
Non-Patent Citations (1)
| Title |
|---|
| Non-local Neural Networks;Xiaolong Wang et al;《arXiv》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117370919A (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117370919B (en) | Remote monitoring system for sewage treatment equipment | |
| CN116129366B (en) | Digital twinning-based park monitoring method and related device | |
| CN210895538U (en) | Intelligent water quality supervision device and equipment | |
| CN116862081B (en) | Operation and maintenance method and system for pollution treatment equipment | |
| CN115865992A (en) | Wisdom water conservancy on-line monitoring system | |
| CN114023399A (en) | Air particulate matter analysis early warning method and device based on artificial intelligence | |
| CN117314709A (en) | Intelligent monitoring system for sewage treatment progress | |
| CN111506635A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive naive Bayes algorithm | |
| CN117739288A (en) | Oil gas pipeline station integrity management system | |
| CN117351659A (en) | Hydrogeological disaster monitoring device and monitoring method | |
| CN113887749A (en) | Cloud edge cooperation-based multi-dimensional monitoring and disposal method, device and platform for power internet of things | |
| CN118194142B (en) | Post-earthquake repair engineering analysis method and system for intelligent pipe network | |
| CN118096131B (en) | Operation and maintenance inspection method based on electric power scene model | |
| CN118015839B (en) | Expressway road domain risk prediction method and device | |
| CN110807174B (en) | Effluent analysis and abnormity identification method for sewage plant group based on statistical distribution | |
| CN113313365A (en) | Degradation early warning method and device for primary air fan | |
| CN118313728A (en) | Intelligent chemical engineering quality detection system and method | |
| CN116484219A (en) | Water supply network water quality abnormal pollution source identification method based on gate control graph neural network | |
| CN115328986A (en) | Power plant safety early warning data analysis processing method and system | |
| CN115100592A (en) | Method and device for identifying hidden danger of external damage of power transmission channel and storage medium | |
| CN114372500A (en) | Intelligent factory control system based on big data | |
| CN114471170A (en) | Ceramic membrane automatic dosing cleaning system and method based on Internet of things | |
| CN117035230B (en) | Sewage treatment equipment running state evaluation method based on big data analysis | |
| CN115035328B (en) | Converter image increment automatic machine learning system and building training method thereof | |
| CN117172559B (en) | Risk identification early warning method, system and storage medium for Internet of things data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |