CN118070040A

CN118070040A - Steel mill data acquisition method and device, electronic equipment and storage medium

Info

Publication number: CN118070040A
Application number: CN202410218789.1A
Authority: CN
Inventors: 童俊; 周克; 孔大明
Original assignee: CISDI Engineering Co Ltd
Current assignee: CISDI Engineering Co Ltd
Priority date: 2024-02-28
Filing date: 2024-02-28
Publication date: 2024-05-24

Abstract

The invention relates to a steel mill data acquisition method, a device, electronic equipment and a storage medium, wherein the method is characterized in that time sequence data of the current production process of a steel mill are acquired, the time sequence data are input into a feature extraction model to obtain nonlinear data features, the feature extraction model is obtained by training a pre-constructed extraction model through sample data, a dynamic threshold value is determined based on a dynamic density estimated value of the nonlinear data features, and data acquisition frequency is adjusted according to a comparison result of the dynamic density estimated value and the dynamic threshold value so as to acquire data of the steel mill through the adjusted data acquisition frequency; the invention can adjust the data acquisition frequency according to the comparison result of the dynamic density estimation value and the dynamic threshold value, and solves the technical problems of excessive acquisition or insufficient acquisition quantity caused by adopting fixed frequency to acquire data of a steel mill.

Description

Steel mill data acquisition method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of data analysis technologies, and in particular, to a method and apparatus for acquiring data in a steel mill, an electronic device, and a storage medium.

Background

With the rapid development of industry 4.0 and intelligent manufacturing, steel mills are becoming increasingly more important as an important basic industrial production link for real-time acquisition and accurate analysis of data. The steelmaking process involves a number of complex steps such as smelting, continuous casting, rolling, etc., each of which is accompanied by a large amount of data. The data not only reflects the state of the production process, but also is closely related to key indexes such as the health condition, the production efficiency, the product quality and the like of the equipment.

The related data acquisition and analysis methods are often performed based on a fixed acquisition frequency and a predefined model, which to some extent limits the depth and breadth of the data analysis, with the following technical problems: (1) Because the production environment of the steel mill has high dynamic property and uncertainty, the data of the steel mill is acquired through fixed acquisition frequency, so that the acquisition is insufficient when the data change is severe, and the acquisition is excessive when the data change is slow, thereby wasting resources and possibly missing key information; (2) It is difficult to capture deep patterns and features in steel mill data, especially on different time scales; (3) Due to the complexity of the steelmaking process, the data often contains a large amount of noise and interference, and an effective identification and processing method for the interference part in the data may be lacking, so that the result of data analysis is interfered, and the accuracy is low.

Disclosure of Invention

In view of the above-mentioned drawbacks of the prior art, the present application provides a method, an apparatus, an electronic device and a storage medium for collecting data from a steel plant, so as to solve the above-mentioned technical problems.

The invention provides a steel mill data acquisition method, which comprises the following steps: acquiring time sequence data of the current production process of a steel mill; inputting the time sequence data into a feature extraction model to obtain nonlinear data features, wherein the feature extraction model is obtained by training a pre-built extraction model by sample data, the pre-built extraction model comprises a time sequence analysis layer for capturing structural features, a self-attention mechanism layer for identifying abnormal structural features and a nonlinear transformation layer for extracting nonlinear data features, and the sample data comprises all or part of time sequence data of a steel mill historical production process; determining a dynamic threshold based on the dynamic density estimation value of the nonlinear data characteristic; and adjusting the data acquisition frequency according to the comparison result of the dynamic density estimation value and the dynamic threshold value, so as to acquire the data of the steel plant through the adjusted data acquisition frequency.

In an embodiment of the present invention, after the data acquisition is performed on the steel mill by the adjusted data acquisition frequency, the steel mill data acquisition method includes: constructing a multi-level data vector field based on the acquired steel mill data, wherein the multi-level data vector field is used for extracting data characteristics of different levels; inputting the multi-level data vector field into a preset interference recognition function to obtain interference data; and eliminating the interference data from the steel mill data to obtain pure steel mill data.

In an embodiment of the present invention, the process of adjusting the data acquisition frequency according to the comparison result of the dynamic density estimation value and the dynamic threshold value includes: acquiring the current data acquisition frequency of the time sequence data;

If the dynamic density estimation value is smaller than or equal to the dynamic threshold value, judging that the data characteristic corresponding to the dynamic density estimation value is a normal data characteristic, and adjusting the current data acquisition frequency to be a first data acquisition frequency, wherein the first data acquisition frequency is smaller than the current data acquisition frequency; and if the dynamic density estimation value is larger than the dynamic threshold value, judging that the data characteristic corresponding to the dynamic density estimation value is an abnormal data characteristic, and adjusting the current data acquisition frequency to a second data acquisition frequency, wherein the second data acquisition frequency is larger than the current data acquisition frequency.

In an embodiment of the present invention, if the pre-built extraction model further includes a multi-scale analysis layer for extracting features of different scale data, training the pre-built extraction model through sample data to obtain a feature extraction model includes: inputting the sample data into the time sequence analysis layer to obtain structural characteristics; inputting the structural features into the self-attention mechanism layer to obtain abnormal structural features; inputting the abnormal structural characteristics into the nonlinear transformation layer to obtain nonlinear data characteristics; inputting the nonlinear data features into the multi-scale analysis layer to obtain data features with different scales; constructing a loss function based on the different scale data features and the time sequence data, and updating parameters of the time sequence analysis layer, the self-attention mechanism layer, the nonlinear transformation layer and the multiscale analysis layer with the aim of minimizing the loss function; and combining the time sequence analysis layer after parameter updating, the self-attention mechanism layer after parameter updating, the nonlinear transformation layer after parameter updating and the multi-scale analysis layer after parameter updating to obtain the feature extraction model.

In an embodiment of the present invention, the expression of the time-series analysis layer is: Wherein ts (x) represents a structural feature of time series data, x represents time series data, sigm represents an activation function, W _t represents a weight, b _t represents a bias, β represents a weight coefficient of gaussian integration, and T represents a transpose; the expression of the self-attention mechanism layer is as follows: /(I) Wherein Q, K, V represents a query matrix, a key matrix, and a value matrix in the self-attention mechanism layer, respectively, a (ts) represents an abnormal structural feature, T represents a transpose, d _k represents a dimension of a key, and ts represents a structural feature; the expression of the nonlinear transformation layer is as follows: Wherein f (a) represents a nonlinear data characteristic, W _f represents a weight matrix of a nonlinear transformation layer, b _f represents a bias vector of the nonlinear transformation layer, μ represents a regularization coefficient, a represents a weight coefficient of a sine function, W _r represents a regularized weight matrix, and a represents an abnormal structural characteristic; the expression of the multi-scale analysis layer is as follows: /(I) Wherein m (f) represents data features of different scales, W _i represents a weight matrix of an ith scale, sigma _i represents a standard deviation of the ith scale, and f represents a nonlinear data feature; the expression of the loss function is: /(I)Wherein L represents a loss function, μ ₁ and μ ₂ are regularization coefficients, h _i represents a state of a neuron where the ith scale is located, F represents a Frobenius norm, W _i represents a weight matrix of the ith scale, and x represents time series data; the calculation formula of the dynamic density estimation value is as follows: Wherein d _t (f) represents a dynamic density estimate of the nonlinear data feature f at time t, N represents the number of nonlinear data features, K represents a space-time kernel function for measuring the similarity in space and time between the nonlinear data features, u represents the spatial distance between the nonlinear data features, ω represents a time decay function, Δt represents the time difference between any time t ₀ of the nonlinear data features and the current time t; the calculation formula of the dynamic threshold value is as follows: where Φ represents a dynamic threshold,/> The mean value of the dynamic density estimation d _t representing the nonlinear data feature, θ represents a constant, and σ represents the standard deviation of the gaussian kernel function.

In one embodiment of the present invention, the process of constructing a multi-level data vector field based on the acquired steelworks data includes: performing dimension conversion on the steel mill data to obtain a data point set; calculating to obtain a data persistence graph based on the data point set; and calculating the multi-level data vector field based on the data persistence graph.

In an embodiment of the present invention, the expression of the data point set is: p (t) =m (U) =exp (-k ₁t²)U·sin(k₂t)+k₃ tU), where k ₁ represents a time attenuation factor, k ₂ represents a periodicity adjustment factor, t represents time, k ₃ represents a linear time influence factor, U represents steelworks data, M (U) represents a mapping function that dimensionally converts the steelworks data, and P (t) represents a set of data points, where the expression of the data persistence map is: Wherein λ represents an attenuation factor, P (t) represents a data point set, D (t) represents a data persistence map, and t represents time; the expression of the multi-level data vector field is as follows: /(I) Wherein V _k (t) represents the kth layer data vector field at time t,/>Representing a gradient operator, gamma representing a weight parameter, D _k (t ') representing a data persistence map of a kth layer at time t ', t ' e [0, t ]; the expression of the preset interference recognition function is as follows: /(I)Where Idf represents a preset interference recognition function, θ represents a threshold function, V _k (t) represents a k-th data vector field at time t,/>Representing the average vector of V _k (t), I _k (t) representing the interference data identified in the k-th layer data vector field at time t; the expression of the pure steel mill data is as follows: /(I)Where y (t) represents clean steelworks data at time t, w _kj represents the weight of the j-th interference vector of the K-th layer, I _kj represents the j-th interference vector identified by the K-th layer at time t, n _k represents the number of interference vectors of the K-th layer, K represents the total number of layers of the data vector field, δ represents the adjustment factor, U (t) represents steelworks data at time t, I _k (t) represents the combination of I _kj identified by the K-th layer at time t.

According to an aspect of the embodiments of the present invention, there is provided a steel mill data acquisition device including: the data acquisition module is used for acquiring time sequence data of the current production process of the steel mill; the feature extraction module is used for inputting the time sequence data into a feature extraction model to obtain nonlinear data features, the feature extraction model is obtained by training a pre-built extraction model through sample data, the pre-built extraction model comprises a time sequence analysis layer for capturing structural features, a self-attention mechanism layer for identifying abnormal structural features and a nonlinear transformation layer for extracting the nonlinear data features, and the sample data comprises all or part of time sequence data of a steel mill historical production process; the threshold determining module is used for determining a dynamic threshold based on the dynamic density estimated value of the nonlinear data characteristic; and the frequency determining module is used for adjusting the data acquisition frequency according to the comparison result of the dynamic density estimated value and the dynamic threshold value so as to acquire the data of the steel mill through the adjusted data acquisition frequency.

According to an aspect of an embodiment of the present invention, there is provided an electronic apparatus including: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic equipment is enabled to realize the steel mill data acquisition method.

According to an aspect of an embodiment of the present invention, there is provided a computer readable storage medium having stored thereon computer readable instructions which, when executed by a processor of a computer, cause the computer to perform the above-described steel mill data acquisition method.

The invention has the beneficial effects that: according to the invention, time sequence data of the current production process of the steel mill is acquired, the time sequence data is input into the feature extraction model, nonlinear data features are obtained, the feature extraction model is obtained by training a pre-constructed extraction model through sample data, a dynamic threshold value is determined based on a dynamic density estimated value of the nonlinear data features, and the data acquisition frequency is adjusted according to a comparison result of the dynamic density estimated value and the dynamic threshold value, so that the steel mill is subjected to data acquisition through the adjusted data acquisition frequency.

In addition, the characteristic extraction model combined with the time sequence analysis layer, the self-attention mechanism layer, the nonlinear transformation layer, the orthogonal constraint and the multi-scale analysis layer can deeply capture complex modes and characteristics of time sequence data, particularly capture the characteristics on different time scales, can consider the time dependence of the data, is more suitable for a data environment with high time dependence of a steelworks, and can analyze and process the time sequence data more accurately; based on the data topological structure and the multi-level data vector field, the interference part in the steel mill data is accurately identified, so that the accuracy of data acquisition is greatly improved, and the efficiency of data acquisition is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is evident that the drawings in the following description are only some embodiments of the present application and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:

FIG. 1 is a schematic diagram of an exemplary system architecture shown in accordance with an exemplary embodiment of the present application;

FIG. 2 is a flow chart illustrating a method of steel plant data acquisition according to an exemplary embodiment of the present application;

FIG. 3 is a flow chart illustrating a method of steel plant data acquisition according to another exemplary embodiment of the present application;

FIG. 4 is a block diagram of a feature extraction model shown in another exemplary embodiment of the application;

FIG. 5 is a block diagram of a steel plant data acquisition device according to an exemplary embodiment of the present application;

Fig. 6 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the application.

Detailed Description

Further advantages and effects of the present invention will become readily apparent to those skilled in the art from the disclosure herein, by referring to the accompanying drawings and the preferred embodiments. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be understood that the preferred embodiments are presented by way of illustration only and not by way of limitation.

It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.

In the following description, numerous details are set forth in order to provide a more thorough explanation of embodiments of the present invention, it will be apparent, however, to one skilled in the art that embodiments of the present invention may be practiced without these specific details, in other embodiments, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the embodiments of the present invention.

FIG. 1 is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the application.

Referring to fig. 1, a system architecture may include an acquisition device 101 and a computer device 102. Wherein the computer device 102 may be at least one of a desktop graphics processor (Graphic Processing Unit, GPU) computer, a GPU computing cluster, a neural network computer, or the like. The related technician can use the computer equipment 102 to input the time sequence data into the feature extraction model by acquiring the time sequence data of the current production process of the steel mill to obtain the nonlinear data feature, the feature extraction model is obtained by training a pre-constructed extraction model by sample data, the dynamic threshold value is determined based on the dynamic density estimated value of the nonlinear data feature, and the data acquisition frequency is adjusted according to the comparison result of the dynamic density estimated value and the dynamic threshold value so as to acquire the data of the steel mill through the adjusted data acquisition frequency. The acquisition device 101 is configured to acquire time series data, where the data acquisition device 101 acquires the time series data by using a sensor or the like in this embodiment, and provides the time series data to the computer device 102 for processing.

Illustratively, after the time sequence data in the acquisition device 101 is acquired, the computer device 102 inputs the time sequence data into the feature extraction model to obtain nonlinear data features, the feature extraction model is obtained by training a pre-constructed extraction model by sample data, a dynamic threshold is determined based on a dynamic density estimated value of the nonlinear data features, and the data acquisition frequency is adjusted according to a comparison result of the dynamic density estimated value and the dynamic threshold so as to acquire data of a steel mill through the adjusted data acquisition frequency.

It should be noted that, the method for acquiring steel mill data provided in the embodiment of the present application is generally executed by the computer device 102, and accordingly, the steel mill data acquisition device is generally disposed in the computer device 102.

The implementation details of the technical scheme of the embodiment of the application are described in detail below:

Fig. 2 is a flow chart of a steel plant data acquisition method, which may be performed by a computing processing device, which may be the computer device 102 shown in fig. 1, shown in an exemplary embodiment of the application. Referring to fig. 2, the steel plant data acquisition method at least includes steps S210 to S240, and is described in detail as follows:

In step S210, time series data of the current production process of the steelworks is acquired.

In an embodiment of the application, the time series data comprise parameter change data in the current production process of the steelworks, such as temperature change data over time, chemical composition change data over time, pressure change data over time, material flow change data over time, etc.

In step S220, the time series data is input into the feature extraction model to obtain nonlinear data features.

In this embodiment, the feature extraction model is obtained by training a pre-constructed extraction model from sample data, where the pre-constructed extraction model includes a time-series analysis layer for capturing structural features, a self-attention mechanism layer for identifying abnormal structural features, and a nonlinear transformation layer for extracting nonlinear data features, and the sample data includes all or part of time-series data of a steel mill history production process.

In the present embodiment, the structural features of the time series data include stationary structural features and non-stationary structural features, wherein the abnormal structural features (or key structural features) include non-stationary structural features, and the like.

In this embodiment, the feature extraction module extracts the nonlinear data feature of the time series data, thereby capturing the internal structural feature of the steel mill data, and being beneficial to reducing the dimension or complexity of the steel mill data.

In step S230, a dynamic threshold is determined based on the dynamic density estimate of the nonlinear data feature.

In this embodiment, the calculation formula of the dynamic density estimation value is:

Where d _t (f) represents the dynamic density estimate of the nonlinear data feature f at time t, N represents the number of nonlinear data features, K represents a space-time kernel function for measuring the similarity in space and time between the nonlinear data features, u represents the spatial distance between the nonlinear data features, ω represents a time decay function, Δt represents the time difference between any time t ₀ of the nonlinear data features and the current time t.

In this embodiment, a weight is assigned to each extracted nonlinear data feature by calculation of the dynamic density estimate, the weight being based on the time attribute of the nonlinear data feature, which means that the data feature closest to the anomalous data feature is given a higher weight.

In this embodiment, the expression of the time decay function is:

Omega (Δt) =e ^-βΔt (2)

Where β represents a constant that determines the decay rate of the weight, Δt represents the time difference between any time t ₀ of the nonlinear data feature and the current time t, ω represents the time decay function. Selecting an exponential decay function as the time decay function may ensure that data points closest to the outlier data feature are weighted more heavily.

In this embodiment, the expression of the space-time kernel function is:

Wherein σ represents the standard deviation of the gaussian kernel function, determines the width of the kernel function, s represents the dimension of the time series data, u represents the spatial distance between the nonlinear data features, ω represents the time decay function, Δt represents the time difference between any time t ₀ of the nonlinear data features and the current time t, and K represents the space-time kernel function.

In this embodiment, the space-time kernel function is used to measure the similarity in space and time between the nonlinear data features, and the space-time kernel function considers both the space and time attributes of the data, and in combination with the gaussian kernel function and the time decay function, the closer both the nonlinear data features are in space and time, the higher the similarity of the two nonlinear data features.

In this embodiment, the calculation formula of the dynamic threshold is:

wherein phi represents the dynamic threshold value, The mean value of the dynamic density estimation d _t representing the nonlinear data feature, θ represents a constant, and σ represents the standard deviation of the gaussian kernel function.

In this embodiment, the dynamic threshold is calculated based on the mean of the dynamic density estimates d _t of all nonlinear data features and the standard deviation of the gaussian kernel.

In step S240, the data acquisition frequency is adjusted according to the comparison result of the dynamic density estimation value and the dynamic threshold value, so as to perform data acquisition on the steel plant through the adjusted data acquisition frequency.

In this embodiment, for each nonlinear data feature, its dynamic density estimate d _t is compared to a dynamic threshold Φ, and if the dynamic density estimate for a certain nonlinear data feature is greater than the dynamic threshold, then that nonlinear data feature is considered an anomalous data feature (or key data feature). Once the abnormal data features are identified, increasing the data sampling frequency to obtain more detailed steelworks data; in contrast, if the dynamic density estimation value of the nonlinear data characteristic is smaller than or equal to the dynamic threshold value, the data sampling frequency is reduced to reduce the collection and processing burden of the steel mill data, so that the dynamic data density estimation method solves the technical problem of excessive collection or insufficient collection amount caused by adopting fixed frequency to collect the data of the steel mill, can more accurately identify abnormal data characteristics in time sequence data, can improve the collection efficiency of the steel mill data, and can help the steel mill to monitor and optimize the production process better.

In one embodiment of the present application, after data acquisition is performed on a steel mill by the adjusted data acquisition frequency, the steel mill data acquisition method includes:

and constructing a multi-level data vector field based on the acquired steel mill data, wherein the multi-level data vector field is used for extracting data features of different levels.

In this embodiment, a multi-level data vector field may reveal flow direction and pattern in the steelworks data. The data vector field for each layer is constructed based on different resolutions, thereby capturing different levels of data features.

And inputting the multi-level data vector field into a preset interference recognition function to obtain interference data.

In this embodiment, the expression of the preset interference recognition function is:

Wherein Idf represents a preset interference recognition function, θ represents a threshold function for screening V _k (t) and V _k (t) The disparity vector, V _k (t), represents the k-th layer data vector field at time t,/>Representing the average vector of V _k (t), I _k (t) represents the interference data identified in the k-th layer data vector field at time t.

In this embodiment, vectors which do not correspond to the normal data characteristic flow direction are identified by a preset interference identification function, and these vectors correspond to the interference parts in the steel mill data.

And removing the interference data from the steel mill data to obtain pure steel mill data.

In this example, the expression for the clean steelworks data is:

Where y (t) represents clean steelworks data at time t, w _kj represents the weight of the j-th interference vector of the K-th layer, I _kj represents the j-th interference vector identified by the K-th layer at time t, n _k represents the number of interference vectors of the K-th layer, K represents the total number of layers of the data vector field, δ represents the adjustment factor, U (t) represents steelworks data at time t, I _k (t) represents the combination of I _kj identified by the K-th layer at time t.

In the embodiment, the interference data in the acquired steel mill data is effectively reduced by eliminating the interference data from the steel mill data, so that the accuracy of the acquired steel mill data is ensured.

In an embodiment of the present application, the process of adjusting the data acquisition frequency according to the comparison result of the dynamic density estimation value and the dynamic threshold value includes:

and acquiring the current data acquisition frequency of the time sequence data.

In this embodiment, the current data acquisition frequency may be set according to a process stage, a production condition, etc. of the steel plant production, and will not be described herein.

If the dynamic density estimation value is smaller than or equal to the dynamic threshold value, judging that the data characteristic corresponding to the dynamic density estimation value is a normal data characteristic, and adjusting the current data acquisition frequency to be the first data acquisition frequency.

In this embodiment, the first data acquisition frequency is smaller than the current data acquisition frequency, and the first data acquisition frequency may be set according to the actual situation, which is not described herein.

In this embodiment, the data acquisition is performed on the steelworks at the first data acquisition frequency to reduce the burden of data acquisition and processing on the steelworks.

If the dynamic density estimation value is larger than the dynamic threshold value, judging that the data characteristic corresponding to the dynamic density estimation value is an abnormal data characteristic, and adjusting the current data acquisition frequency to be a second data acquisition frequency.

In this embodiment, the second data acquisition frequency is greater than the current data acquisition frequency, and the second data acquisition frequency may be set according to the actual situation, which is not described herein.

In this embodiment, the data acquisition is performed on the steel mill through the second data acquisition frequency, so as to obtain more detailed abnormal data, thereby not missing the abnormal data, improving the efficiency and accuracy of the data acquisition of the steel mill, and helping the steel mill to monitor and optimize the production process better.

In an embodiment of the present application, if the pre-built extraction model further includes a multi-scale analysis layer for extracting features of different scale data, training the pre-built extraction model through sample data to obtain a feature extraction model includes:

and inputting the sample data into a time sequence analysis layer to obtain the structural characteristics.

In this embodiment, the expression of the time-series analysis layer is:

Where tx (x) denotes a structural feature of time series data, x denotes time series data, sigm denotes an activation function, W _t denotes a weight, b _t denotes a bias, β denotes a weight coefficient of gaussian integration, and T denotes a transpose.

In this embodiment, the time series analysis layer processes the time series data, so that a local mode in the time series data can be captured, and the internal structural characteristics of the time series data can be better understood. For example, the steelmaking process is optimized by analyzing the temperature and chemical composition changes over time, predicting and adjusting furnace temperature and material placement.

And inputting the structural features into a self-attention mechanism layer to obtain abnormal structural features.

In this embodiment, the expression of the self-attention mechanism layer is:

Wherein Q, K, V represents a query matrix, a key matrix, and a value matrix in the self-attention mechanism layer, respectively, a (ts) represents an abnormal structural feature, T represents a transpose, d _k represents a dimension of a key, and ts represents a structural feature.

In this embodiment, the expression of the query matrix Q is:

q=w _q ts type (9)

Where ts represents structural features, W _q represents a weight matrix in the query matrix, and Q represents the query matrix in the self-attention mechanism layer.

In the present embodiment, the expression of the key matrix K is:

K=W _k ts type (10)

Where ts represents structural features, W _k represents a weight matrix in the key matrix, and K represents a key matrix in the self-attention mechanism layer.

In the present embodiment, the expression of the value matrix V is:

V=w _v ts type (11)

Where ts represents structural features, W _v represents a weight matrix in the value matrix, and V represents a value matrix in the self-attention mechanism layer.

In this embodiment, the self-attention mechanism layer can capture and pay attention to an abnormal time point or an abnormal structural feature in the time series data, and analyze an important influence factor in the steelmaking process after capturing the abnormal time point or the abnormal structural feature, thereby obtaining a cause of the abnormality. For example, potential production problems can be identified and handled in time when abnormal fluctuations in temperature occur.

And inputting the abnormal structural characteristics into a nonlinear transformation layer to obtain nonlinear data characteristics.

In this embodiment, the expression of the nonlinear transformation layer is:

Where f (a denotes a nonlinear data feature, W _f denotes a weight matrix of the nonlinear transformation layer, b _f denotes a bias vector of the nonlinear transformation layer, μ denotes a regularization coefficient, α denotes a weight coefficient of a sine function, W _r denotes a regularized weight matrix, and a denotes an abnormal structural feature.

In this embodiment, the addition of the nonlinear transformation layer enables the feature extraction model to process complex and interrelated production data, such as temperature, pressure, and material proportions, so as to ensure independence between the data, avoid redundancy and error accumulation, and introduce orthogonal constraints through a regularized weight matrix to ensure that the obtained data features are orthogonal.

And inputting the nonlinear data features into a multi-scale analysis layer to obtain the data features with different scales.

In this embodiment, the expression of the multi-scale analysis layer is:

Where m (f) represents the data features of different scales, W _i represents the weight matrix of the ith scale, σ _i represents the standard deviation of the ith scale, and f represents the nonlinear data features.

In this embodiment, the multi-scale analysis layer may capture the nonlinear data features of the time series data at different time scales, so as to obtain feature changes of the time series data at different time and space scales, such as rapid changes in a short period and long-term trends, so as to comprehensively monitor the production process.

Based on the different scale data features and the time sequence data, constructing a loss function, and updating parameters of a time sequence analysis layer, parameters of a self-attention mechanism layer, parameters of a nonlinear transformation layer and parameters of a multi-scale analysis layer by taking the minimized loss function as a target.

In this embodiment, the expression of the loss function is:

Where L represents a loss function, μ ₁ and μ ₂ are both regularization coefficients, h _i represents a state of a neuron where the i-th scale is located, F represents a Frobenius norm, W _i represents a weight matrix of the i-th scale, and x represents time series data.

In this embodiment, the loss function updates and optimizes parameters of the time series analysis layer, parameters of the self-attention mechanism layer, parameters of the nonlinear transformation layer and parameters of the multi-scale analysis layer by using a gradient descent method, and by minimizing the loss function value, it can be ensured that the feature extraction model can accurately capture structural features in the steel mill data, and key information in the steel mill data is reflected by the structural features, and meanwhile, dimensions and complexity of the steel mill data are reduced, so that subsequent data processing and analysis are more efficient and accurate.

And combining the time sequence analysis layer after parameter updating, the self-attention mechanism layer after parameter updating, the nonlinear transformation layer after parameter updating and the multi-scale analysis layer after parameter updating to obtain a feature extraction model.

In this embodiment, the feature extraction model combined with the time sequence analysis layer, the self-attention mechanism layer, the nonlinear transformation layer, the orthogonal constraint and the multi-scale analysis layer can deeply capture complex modes and features of time sequence data, particularly capture features on different time scales, can consider time dependence of the data, is more suitable for a data environment with high time dependence of a steelworks, and can analyze and process the time sequence data more accurately.

In one embodiment of the present application, the process of constructing a multi-level data vector field based on the acquired steelworks data comprises:

and carrying out dimension conversion on the steel mill data to obtain a data point set.

In this embodiment, the expression of the data point set is:

p (t) =m (U) =exp (-k ₁t²)U·sin(k₂t)+k₂ tU formula (15))

Where k ₁ denotes a time decay factor, k ₂ denotes a periodicity adjustment factor, t denotes time, k ₃ denotes a linear time influence factor, U denotes the steelworks data, M (U) denotes a mapping function that dimensionally transforms the steelworks data, and P (t) denotes a set of data points.

In this embodiment, k ₁ is used to control the decay rate of exp (-k ₁t²) term, k ₂ is used to influence the frequency of data change, k ₃ is used to control the linear change rate of data over time, exp (-k ₁t²) represents the effect of steel mill data decay over time, more directly reflects the effect of time change, sin (k ₂ t) is used to maintain capture of periodic changes, k ₃ tU is a linear term, directly relates a time factor to steel mill data U, and represents the trend of steel mill data U linearly increasing or decreasing over time.

And calculating to obtain a data persistence graph based on the data point set.

In this embodiment, the expression of the data persistence map is:

where λ represents an attenuation factor, P (t) represents a data point set, D (t) represents a data persistence map, and t represents time.

In this embodiment λ is used to balance the first derivative of the data point setAnd data Point set second derivative/>Based on the data point set, the method for obtaining the data persistence graph through calculation is a topology data analysis method, and the topology structure and the data characteristics of the steel mill data are further disclosed through the topology data analysis method.

And calculating to obtain a multi-level data vector field based on the data persistence graph.

In this embodiment, the expression of the multi-level data vector field is:

wherein V _k (t) represents the kth layer data vector field at time t, Representing a gradient operator, gamma representing a weight parameter, D _k (t ') representing a data persistence map of the kth layer at time t ', t ' e [0, t ].

In this embodiment, the gradient operatorRepresenting the directional characteristics of the steelworks data, the weight parameter gamma is used to balance the gradient term/>And quadratic term/>

In the embodiment, the interference part in the steel mill data is accurately identified based on the data topological structure and the multi-level data vector field, so that the accuracy of data acquisition is greatly improved, and the efficiency of data acquisition is improved.

Fig. 3 is a flowchart illustrating a steel plant data acquisition method according to another exemplary embodiment of the present application, as shown in fig. 3, including: (1) Constructing a feature extraction model, and capturing internal structural features in time sequence data through the feature extraction model; (2) Determining a dynamic threshold by adopting a data density estimation method based on time sequence characteristics and spatial distribution, identifying abnormal data characteristics according to a comparison result of the dynamic density estimation value and the dynamic threshold, and carrying out targeted data acquisition; (3) And acquiring the steel mill data according to the dynamically adjusted acquisition frequency, and removing interference data in the steel mill data based on the data topological structure and the processing method of the multi-level vector field.

In the embodiment, a feature extraction model is constructed, and internal structural features in time series data are captured through the feature extraction model, so that dimension or complexity of steel mill data is reduced.

In the embodiment, a data density estimation method based on time sequence characteristics and spatial distribution is adopted to determine a dynamic threshold value, and abnormal data characteristics are identified according to a comparison result of the dynamic density estimation value and the dynamic threshold value, so that the abnormal data characteristics can be subjected to targeted data acquisition, and abnormal data omission is avoided.

In the embodiment, the interference data in the steel mill data is removed based on the data topological structure and the multi-level vector field processing method, so that the accuracy of data acquisition is ensured.

In the embodiment, the acquisition equipment acquires data through the sensor, and dynamically adjusts the acquisition frequency of the steel mill data according to the nonlinear data characteristic of the time sequence data, so as to realize self-adaptive acquisition. For example, during smelting, when temperature and chemical composition change rapidly, the acquisition frequency is increased to obtain more accurate data; while at a relatively stable stage, the acquisition frequency is reduced to reduce the data processing burden.

In this embodiment, the edge computing node is connected to the collecting device through an interface, and monitors parameter change data, such as temperature change data, pressure change data, and material flow change data, in the steelmaking process in real time. Calculating the nonlinear data characteristic of the change data in real time, and increasing the data acquisition frequency when the nonlinear data characteristic exceeds a dynamic threshold value; when the nonlinear data characteristic is below the dynamic threshold, the data acquisition frequency is reduced.

FIG. 4 is a block diagram of a feature extraction model shown in another exemplary embodiment of the application, the feature extraction model including a time series analysis layer, a self-attention mechanism layer, a nonlinear transformation layer, and a multi-scale analysis layer, as shown in FIG. 4.

In this embodiment, the time series analysis layer is used to capture structural features in the time series data through convolution kernels, which is beneficial to better understand the internal structure of the data.

In this embodiment, the self-attention mechanism layer allows the data extraction model to focus on different parts of the time series data, and by focusing on abnormal time points or abnormal structural features in the production process, potential production problems can be identified and handled in time.

In this embodiment, the nonlinear transformation layer is used to enable the feature extraction model to process complex and interrelated production data, such as temperature, pressure, and material proportion, so as to ensure independence between the data, avoid redundancy and error accumulation, and introduce orthogonal constraints through a regularized weight matrix to ensure that the obtained data features are orthogonal.

In this embodiment, the multi-scale analysis layer is configured to capture nonlinear features of the time series data at different time scales, so as to obtain feature changes of the time series data at different time and space scales, such as rapid changes in a short period and long-term trends, so as to comprehensively monitor the production process.

The following describes an embodiment of the apparatus according to the application which can be used to carry out the method of collecting steel mill data according to the above-described embodiment of the application. For details not disclosed in the embodiments of the apparatus of the present application, please refer to the above-mentioned embodiments of the steel mill data acquisition method of the present application.

Fig. 5 is a block diagram of a steel plant data acquisition device according to an exemplary embodiment of the present application. The apparatus may be applied in the implementation environment shown in fig. 1 and is specifically configured in the computer device 102. The apparatus may also be adapted to other exemplary implementation environments and may be specifically configured in other devices, and the present embodiment is not limited to the implementation environments to which the apparatus is adapted.

As shown in fig. 5, the exemplary steel mill data collection device includes:

The data acquisition module 501 is used for acquiring time series data of the current production process of the steel mill.

The feature extraction module 502 is configured to input the time series data into a feature extraction model to obtain a nonlinear data feature.

The threshold determining module 503 is configured to determine a dynamic threshold based on the dynamic density estimation value of the nonlinear data feature.

The frequency determining module 504 is configured to adjust the data acquisition frequency according to the comparison result of the dynamic density estimation value and the dynamic threshold value, so as to perform data acquisition on the steel mill through the adjusted data acquisition frequency.

In the present embodiment, the structural features of the time series data include a stationary structural feature and a non-stationary structural feature, wherein the abnormal structural feature includes a non-stationary structural feature and the like.

In this embodiment, the calculation formula of the dynamic density estimation value is shown in formula (1), and will not be described here. By calculation of the dynamic density estimate, each extracted non-linear data feature is assigned a weight based on the temporal properties of the non-linear data feature, which means that the data feature closest to the outlier data feature is given a higher weight.

In this embodiment, the expression of the time-decay function is shown in formula (2), and will not be described here. The expression of the space-time kernel function is shown in formula (3), and will not be described here.

In this embodiment, the calculation formula of the dynamic threshold is shown in formula (4), and details thereof are omitted here. The dynamic threshold is calculated based on the mean of the dynamic density estimates d _t for all nonlinear data features and the standard deviation of the gaussian kernel.

In the present embodiment, for each nonlinear data feature, its dynamic density estimate d _t is compared with a dynamic threshold Φ, and if the dynamic density estimate of a certain nonlinear data feature is greater than the dynamic threshold, then that nonlinear data feature is considered to be an anomalous data feature (key data feature). Once the abnormal data features are identified, increasing the data sampling frequency to obtain more detailed steelworks data; in contrast, if the nonlinear data characteristic is smaller than or equal to the dynamic threshold value, the data sampling frequency is reduced to reduce the collection and processing burden of the steel mill data, so that the dynamic data density estimation method solves the technical problem of excessive collection or insufficient collection amount caused by adopting fixed frequency to collect the data of the steel mill, can more accurately identify the abnormal data characteristic in the time sequence data, can improve the collection efficiency of the steel mill data, and can help the steel mill to monitor and optimize the production process better.

It should be noted that, the steel mill data collection device provided in the foregoing embodiment and the steel mill data collection method provided in the foregoing embodiment belong to the same concept, and the specific manner in which each module and unit perform the operation has been described in detail in the method embodiment, which is not repeated here. In practical application, the steel plant data acquisition device provided in the above embodiment can distribute the functions to be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above, which is not limited herein.

The embodiment of the application also provides electronic equipment, which comprises: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic equipment realizes the steel mill data acquisition method provided in each embodiment.

Fig. 6 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the application. It should be noted that, the computer system 600 of the electronic device shown in fig. 6 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 6, the computer system 600 includes a central processing unit (Central Processing Unit, CPU) 601 that can perform various appropriate actions and processes, such as performing the methods in the above-described embodiments, according to a program stored in a Read-Only Memory (ROM) 602 or a program loaded from a storage portion 608 into a random access Memory (Random Access Memory, RAM) 603. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604. An Input/Output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid crystal display (Liquid CRYSTAL DISPLAY, LCD), and a speaker, etc.; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.

In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. When executed by a Central Processing Unit (CPU) 601, performs the various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), a flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

Another aspect of the application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform the method of steel mill data acquisition as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment or may exist alone without being incorporated in the electronic device.

Another aspect of the application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steel mill data acquisition method provided in the above embodiments.

The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. It is therefore intended that all equivalent modifications and changes made by those skilled in the art without departing from the spirit and technical spirit of the present invention shall be covered by the appended claims.

Claims

1. The steel mill data acquisition method is characterized by comprising the following steps of:

acquiring time sequence data of the current production process of a steel mill;

Inputting the time sequence data into a feature extraction model to obtain nonlinear data features, wherein the feature extraction model is obtained by training a pre-built extraction model by sample data, the pre-built extraction model comprises a time sequence analysis layer for capturing structural features, a self-attention mechanism layer for identifying abnormal structural features and a nonlinear transformation layer for extracting nonlinear data features, and the sample data comprises all or part of time sequence data of a steel mill historical production process;

determining a dynamic threshold based on the dynamic density estimation value of the nonlinear data characteristic;

And adjusting the data acquisition frequency according to the comparison result of the dynamic density estimation value and the dynamic threshold value, so as to acquire the data of the steel plant through the adjusted data acquisition frequency.

2. The steel mill data collection method according to claim 1, wherein after data collection of the steel mill by the adjusted data collection frequency, the steel mill data collection method comprises:

constructing a multi-level data vector field based on the acquired steel mill data, wherein the multi-level data vector field is used for extracting data characteristics of different levels;

Inputting the multi-level data vector field into a preset interference recognition function to obtain interference data;

And eliminating the interference data from the steel mill data to obtain pure steel mill data.

3. The steel mill data acquisition method according to claim 1 or 2, wherein the process of adjusting the data acquisition frequency according to the comparison result of the dynamic density estimation value and the dynamic threshold value comprises:

Acquiring the current data acquisition frequency of the time sequence data;

If the dynamic density estimation value is smaller than or equal to the dynamic threshold value, judging that the data characteristic corresponding to the dynamic density estimation value is a normal data characteristic, and adjusting the current data acquisition frequency to be a first data acquisition frequency, wherein the first data acquisition frequency is smaller than the current data acquisition frequency;

And if the dynamic density estimation value is larger than the dynamic threshold value, judging that the data characteristic corresponding to the dynamic density estimation value is an abnormal data characteristic, and adjusting the current data acquisition frequency to a second data acquisition frequency, wherein the second data acquisition frequency is larger than the current data acquisition frequency.

4. The steel mill data collection method according to claim 1 or 2, wherein if the pre-built extraction model further comprises a multi-scale analysis layer for extracting features of different scale data, training the pre-built extraction model by sample data, and obtaining the feature extraction model comprises:

Inputting the sample data into the time sequence analysis layer to obtain structural characteristics;

Inputting the structural features into the self-attention mechanism layer to obtain abnormal structural features;

inputting the abnormal structural characteristics into the nonlinear transformation layer to obtain nonlinear data characteristics;

Inputting the nonlinear data features into the multi-scale analysis layer to obtain data features with different scales;

constructing a loss function based on the different scale data features and the time sequence data, and updating parameters of the time sequence analysis layer, the self-attention mechanism layer, the nonlinear transformation layer and the multiscale analysis layer with the aim of minimizing the loss function;

and combining the time sequence analysis layer after parameter updating, the self-attention mechanism layer after parameter updating, the nonlinear transformation layer after parameter updating and the multi-scale analysis layer after parameter updating to obtain the feature extraction model.

5. The steel mill data collection method according to claim 4, wherein the expression of the time series analysis layer is:

Wherein ts (x) represents a structural feature of time series data, x represents time series data, sigm represents an activation function, W _t represents a weight, b _t represents a bias, β represents a weight coefficient of gaussian integration, and T represents a transpose;

The expression of the self-attention mechanism layer is as follows:

Wherein Q, K, V represents a query matrix, a key matrix, and a value matrix in the self-attention mechanism layer, respectively, a (ts) represents an abnormal structural feature, T represents a transpose, d _k represents a dimension of a key, and ts represents a structural feature;

the expression of the nonlinear transformation layer is as follows:

Wherein f (a) represents a nonlinear data characteristic, W _f represents a weight matrix of a nonlinear transformation layer, b _f represents a bias vector of the nonlinear transformation layer, μ represents a regularization coefficient, α represents a weight coefficient of a sine function, W _r represents a regularized weight matrix, and a represents an abnormal structural characteristic;

the expression of the multi-scale analysis layer is as follows:

Wherein m (f) represents data features of different scales, W _i represents a weight matrix of an ith scale, sigma _i represents a standard deviation of the ith scale, and f represents a nonlinear data feature;

The expression of the loss function is:

Wherein L represents a loss function, μ ₁ and μ ₂ are regularization coefficients, h _i represents a state of a neuron where the ith scale is located, F represents a Frobenius norm, W _i represents a weight matrix of the ith scale, and x represents time series data;

the calculation formula of the dynamic density estimation value is as follows:

Wherein d _t (f) represents a dynamic density estimate of the nonlinear data feature f at time t, N represents the number of nonlinear data features, K represents a space-time kernel function for measuring the similarity in space and time between the nonlinear data features, u represents the spatial distance between the nonlinear data features, ω represents a time decay function, Δt represents the time difference between any time t ₀ of the nonlinear data features and the current time t;

The calculation formula of the dynamic threshold value is as follows:

6. The steel mill data acquisition method according to claim 2, wherein the process of constructing a multi-level data vector field based on the acquired steel mill data comprises:

Performing dimension conversion on the steel mill data to obtain a data point set;

calculating to obtain a data persistence graph based on the data point set;

and calculating the multi-level data vector field based on the data persistence graph.

7. The steel mill data collection method of claim 6, wherein the expression of the data point set is:

P(t)＝M(U)＝exp(-k₁t²)U·sin(k₂t)+k₃tU

Wherein k ₁ represents a time attenuation factor, k ₂ represents a periodicity adjustment factor, t represents time, k ₃ represents a linear time influence factor, U represents steelworks data, M (U) represents a mapping function for dimensional transformation of the steelworks data, and P (t) represents a set of data points;

The expression of the data persistence map is as follows:

Wherein λ represents an attenuation factor, P (t) represents a data point set, D (t) represents a data persistence map, and t represents time;

the expression of the multi-level data vector field is as follows:

wherein V _k (t) represents the kth layer data vector field at time t, Representing a gradient operator, gamma representing a weight parameter, D _k (t ') representing a data persistence map of a kth layer at time t ', t ' e [0, t ];

the expression of the preset interference recognition function is as follows:

Where Idf represents a preset interference recognition function, θ represents a threshold function, V _k (t) represents the kth layer data vector field at time t, Representing the average vector of V _k (t), I _k (t) representing the interference data identified in the k-th layer data vector field at time t;

The expression of the pure steel mill data is as follows:

8. A steel mill data acquisition device, characterized in that the steel mill data acquisition device comprises:

the data acquisition module is used for acquiring time sequence data of the current production process of the steel mill;

The feature extraction module is used for inputting the time sequence data into a feature extraction model to obtain nonlinear data features, the feature extraction model is obtained by training a pre-built extraction model through sample data, the pre-built extraction model comprises a time sequence analysis layer for capturing structural features, a self-attention mechanism layer for identifying abnormal structural features and a nonlinear transformation layer for extracting the nonlinear data features, and the sample data comprises all or part of time sequence data of a steel mill historical production process;

The threshold determining module is used for determining a dynamic threshold based on the dynamic density estimated value of the nonlinear data characteristic;

And the frequency determining module is used for adjusting the data acquisition frequency according to the comparison result of the dynamic density estimated value and the dynamic threshold value so as to acquire the data of the steel mill through the adjusted data acquisition frequency.

9. An electronic device, comprising:

One or more processors;

Storage means for storing one or more programs which when executed by the one or more processors cause the electronic device to implement the steel mill data collection method of any one of claims 1 to 7.

10. A computer readable storage medium, having stored thereon computer readable instructions, which when executed by a processor of a computer, cause the computer to perform the steel mill data collection method of any one of claims 1 to 7.