CN118400396A

CN118400396A - Industrial Internet security monitoring method and system based on big data

Info

Publication number: CN118400396A
Application number: CN202410819876.2A
Authority: CN
Inventors: 张昕伟; 黄军山; 王成; 王伟; 龙能文
Original assignee: Clp Digital Technology Co ltd
Current assignee: Clp Digital Technology Co ltd
Priority date: 2024-06-24
Filing date: 2024-06-24
Publication date: 2024-07-26
Anticipated expiration: 2044-06-24
Also published as: CN118400396B

Abstract

The invention relates to the technical field of light industrial networking monitoring, in particular to an industrial Internet security monitoring method and system based on big data. The method comprises the following steps: constructing a multisource heterogeneous internet of things sensing layer in a clothing processing workshop to obtain a distributed heterogeneous sensing network; acquiring full-flow multidimensional data of a clothing processing workshop based on a distributed heterogeneous perception network to obtain a multi-source heterogeneous big data set, wherein the multi-source heterogeneous big data set comprises order data, raw material inventory data, equipment operation data and logistics data; performing order completion degree risk assessment analysis on the clothing processing workshop based on the order data and the raw material inventory data to obtain an order completion degree risk value; and carrying out intelligent decision support on the clothing processing workshop according to the order completion degree risk value to obtain a coping decision scheme. The invention can realize more efficient real-time monitoring and intelligent analysis, thereby improving the production efficiency and reducing the safety risk and the cost.

Description

Industrial Internet security monitoring method and system based on big data

Technical Field

The invention relates to the technical field of light industrial networking monitoring, in particular to an industrial Internet security monitoring method and system based on big data.

Background

With the rapid development of the modern clothing processing industry, shortening of the production cycle and the frequency of order changes place higher demands on safety monitoring. The traditional safety monitoring method has limitations in terms of data acquisition, transmission and processing speed, so that the requirement of real-time monitoring cannot be met, and further, the safety risk cannot be identified and dealt with in time. In conventional industrial internet security monitoring systems, data acquisition relies primarily on a limited number of sensors and monitoring devices, which have limited sampling frequency and data transmission speed. In addition, the traditional monitoring system has limited processing capacity for mass data, and potential safety risks cannot be analyzed and identified in real time. This limitation is particularly pronounced in the modern clothing processing industry, where the production process is complex, involves multiple links and devices, and produces large amounts of data and changes rapidly. In addition, the traditional safety monitoring method often lacks intelligent analysis and prediction capabilities, and abnormal events cannot be timely early-warned and dealt with. This results in the occurrence of safety accidents and the creation of serious consequences, which pose a serious threat to the production order and safety of the enterprise.

Disclosure of Invention

Based on the above, the present invention is needed to provide an industrial internet security monitoring method and system based on big data, so as to solve at least one of the above technical problems.

In order to achieve the above purpose, an industrial internet security monitoring method based on big data comprises the following steps:

Step S1: constructing a multisource heterogeneous internet of things sensing layer in a clothing processing workshop to obtain a distributed heterogeneous sensing network; acquiring full-flow multidimensional data of a clothing processing workshop based on a distributed heterogeneous perception network to obtain a multi-source heterogeneous big data set, wherein the multi-source heterogeneous big data set comprises order data, raw material inventory data, equipment operation data and logistics data;

Step S2: performing order completion degree risk assessment analysis on the clothing processing workshop based on the order data and the raw material inventory data to obtain an order completion degree risk value; intelligent decision support is carried out on the clothing processing workshop according to the order completion degree risk value, and a coping decision scheme is obtained;

Step S3: carrying out production and marketing balance evaluation analysis on a clothing processing workshop according to the logistics data to obtain production and marketing deviation data; intelligent inventory allocation is carried out on the clothing processing workshop according to the production and marketing deviation data, and an allocation optimization scheme is obtained;

step S4: performing equipment health state evaluation on the clothing processing workshop according to the equipment operation data to obtain equipment risk data; performing equipment maintenance decision support on the clothing processing workshop according to the equipment risk data to obtain a maintenance decision scheme;

Step S5: performing intelligent fusion analysis on the clothing processing workshop according to the order completion degree risk value, the production and marketing deviation data and the equipment risk data to obtain comprehensive safety early warning data; transmitting the order completion degree risk value, the production and marketing deviation data, the equipment risk data, the comprehensive safety early warning data, the coping decision scheme, the allocation optimization scheme and the maintenance decision scheme to a preset unified safety monitoring platform.

According to the invention, through establishing the multi-source heterogeneous internet of things sensing layer and full-flow multi-dimensional data acquisition, order data, raw material inventory data, equipment operation data and logistics data can be collected and analyzed in real time, so that real-time monitoring of the production process is realized. This can identify potential security risks in time, such as order completion risk, production and marketing deviations, and equipment health status issues. According to the order completion degree risk value, the production and marketing deviation data and the equipment risk data, intelligent decision support can be carried out, and corresponding coping decision schemes, allocation optimization schemes and maintenance decision schemes are provided. The method can help enterprises make more intelligent decisions when facing risks, optimize production flows and resource allocation, and reduce security risks. And integrating the order completion degree risk value, the production and marketing deviation data and the equipment risk data through intelligent fusion analysis to generate comprehensive safety early warning data. The potential safety risk can be early warned in advance, enterprises are helped to take corresponding measures to prevent the potential safety risk, and therefore safety accidents are avoided, and production order and safety are guaranteed. And transmitting each item of data and the decision scheme to a unified safety monitoring platform to realize centralized management and unified monitoring of the data. The monitoring efficiency and the management level can be improved, so that enterprises can more comprehensively know the production condition and the safety condition and timely make corresponding countermeasures. In conclusion, the invention can realize more efficient real-time monitoring and intelligent analysis, thereby improving the production efficiency, reducing the safety risk and the cost and improving the competitiveness of enterprises.

Preferably, the present invention also provides a big data based industrial internet security monitoring system for performing the big data based industrial internet security monitoring method as described above, the big data based industrial internet security monitoring system comprising:

The sensing layer construction module is used for constructing a multi-source heterogeneous internet of things sensing layer of the clothing processing workshop to obtain a distributed heterogeneous sensing network; acquiring full-flow multidimensional data of a clothing processing workshop based on a distributed heterogeneous perception network to obtain a multi-source heterogeneous big data set, wherein the multi-source heterogeneous big data set comprises order data, raw material inventory data, equipment operation data and logistics data;

The order risk assessment module is used for carrying out order completion degree risk assessment analysis on the clothing processing workshop based on the order data and the raw material inventory data to obtain an order completion degree risk value; intelligent decision support is carried out on the clothing processing workshop according to the order completion degree risk value, and a coping decision scheme is obtained;

the production and marketing balance evaluation module is used for carrying out production and marketing balance evaluation analysis on the clothing processing workshop according to the logistics data to obtain production and marketing deviation data; intelligent inventory allocation is carried out on the clothing processing workshop according to the production and marketing deviation data, and an allocation optimization scheme is obtained;

The equipment health evaluation module is used for evaluating the equipment health state of the clothing processing workshop according to the equipment operation data to obtain equipment risk data; performing equipment maintenance decision support on the clothing processing workshop according to the equipment risk data to obtain a maintenance decision scheme;

the comprehensive safety early warning module is used for carrying out intelligent fusion analysis on the clothing processing workshop according to the order completion degree risk value, the production and marketing deviation data and the equipment risk data to obtain comprehensive safety early warning data; transmitting the order completion degree risk value, the production and marketing deviation data, the equipment risk data, the comprehensive safety early warning data, the coping decision scheme, the allocation optimization scheme and the maintenance decision scheme to a preset unified safety monitoring platform.

According to the invention, through the construction of the perception layer and the acquisition of multi-source heterogeneous data, the comprehensive monitoring of the production process of the clothing processing workshop can be realized, and the data of various aspects such as orders, raw material inventory, equipment operation and logistics are covered. Through the order risk assessment module and the production and marketing balance assessment module, risks in the production process can be assessed and analyzed, intelligent decision support is provided, enterprises are helped to formulate a coping scheme and allocate optimization strategies, and production efficiency and safety are improved. Through the equipment health evaluation module, the equipment of the clothing processing workshop can be subjected to health state evaluation, equipment operation abnormality can be found in time, decision support is provided for equipment maintenance, and normal operation of production equipment is guaranteed. Through the comprehensive safety early warning module, intelligent fusion analysis can be carried out on order completion degree, production and marketing deviation and equipment health state data, potential safety risks are early warned in time, and related data and decision schemes are transmitted to a unified safety monitoring platform, so that comprehensive safety risk management is realized. Through the intelligent allocation optimization scheme and the equipment maintenance decision scheme, inventory allocation and equipment maintenance plans can be optimized, resources are reasonably allocated, production efficiency is improved, and cost is reduced. By transmitting various data and decision schemes to the unified safety monitoring platform, centralized management and unified monitoring of the data are realized, the monitoring efficiency and management level are improved, and more comprehensive information support is provided for enterprise decisions.

Drawings

Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of the non-limiting implementation, made with reference to the accompanying drawings.

Fig. 1 is a schematic flow chart of steps of an industrial internet security monitoring method based on big data according to an embodiment.

Fig. 2 shows a detailed step flow diagram of step S2 of an embodiment.

Fig. 3 shows a detailed step flow diagram of step S25 of an embodiment.

Detailed Description

The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.

Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.

It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

In order to achieve the above objective, referring to fig. 1 to 3, the present invention provides an industrial internet security monitoring method based on big data, comprising the following steps:

In this embodiment, various sensors and sensing devices, such as temperature sensors, humidity sensors, acceleration sensors, RFID tags, may be installed in a garment manufacturing plant. The equipment can collect various data in the workshop, including temperature, humidity, equipment operating state and raw material inventory. The devices are connected to a distributed sensing network through a wireless network, and data is transmitted to a central server for processing and storage. And (5) performing risk assessment analysis on the order completion degree by collecting order data and raw material inventory data. According to the progress of the order and the stock condition of the raw materials, a risk value of the order completion degree can be calculated. If the risk value is higher, the order cannot be completed on time, and corresponding decision measures need to be taken. For example, production plans may be adjusted in advance, raw materials may be purchased expeditiously, or personnel schedules may be adjusted. This may be generated and transmitted to the relevant personnel by the intelligent decision support system. And carrying out production and marketing balance evaluation analysis on the clothing processing workshop by using the logistics data, and determining the deviation of production and marketing. From the analysis results, it is possible to derive which products are more productive and less sales or more sales and less inventory. For these situations, optimal allocation may be performed by an intelligent inventory allocation system to reduce inventory backlogs or increase sales. Inventory allocation schemes may be generated based on the analysis and transmitted to the relevant personnel via the system. And evaluating the health state of equipment in the clothing processing workshop by using the equipment operation data. By analyzing the operating conditions, failure rate and maintenance records of the equipment, risk data of the equipment can be obtained. Based on the risk data, maintenance decision-making schemes for the device may be formulated, including periodic maintenance, preventive maintenance, or replacement of the device. These maintenance decision schemes may be generated by the system and transmitted to the relevant personnel. And carrying out intelligent fusion analysis according to the order completion degree risk value, the production and marketing deviation data and the equipment risk data. Comprehensive analysis is carried out on the information of different data sources, so that comprehensive safety early warning data can be obtained. These early warning data can be used to monitor the operational status and safety risks of the entire garment process plant. Meanwhile, the coping decision scheme, the allocation optimization scheme and the maintenance decision scheme are transmitted to a unified safety monitoring platform so that relevant personnel can take actions in time.

Preferably, step S1 comprises the steps of:

Step S11: acquiring a workshop topology distribution map; performing sensing point planning on a clothing processing workshop based on a workshop topology distribution map to obtain sensing planning data;

Specifically, CAD software (e.g., autoCAD) or other suitable software may be used to map the plan layout of the garment process plant and label the uses of the various areas, including raw material storage areas, production facility areas, worker activity areas, finished product storage areas. The logistics channels, the product flow paths and the key equipment positions are marked on the layout diagram to establish a topology distribution diagram of the workshop, and the topology distribution diagram is saved or printed out through CAD software. The plant topology map is reviewed to determine the locations and numbers of suitable sensors to deploy. And performing perception point planning by using professional perception planning software (such as MATLAB, python) in combination with workshop layout information. In the planning process, the type of parameter and coverage area to be monitored are considered to determine the position of each sensing point and the type of sensor. Finally, perceptual planning data is generated, including coordinates of the perceived points, sensor types, and deployment scenarios.

Step S12: heterogeneous sensor deployment is carried out on a clothing processing workshop according to the perception planning data, and a distributed heterogeneous perception network is obtained;

In particular, suitable sensor devices may be selected based on the perceptual planning data, including but not limited to temperature sensors, humidity sensors, pressure sensors. And deploying sensor equipment in the workshop according to the position specified in the perception planning data, and ensuring that each perception point is covered by a corresponding sensor. During deployment, a laser rangefinder or positioning system is used to ensure accurate position of the sensor.

Step S13: and carrying out full-flow multidimensional data acquisition on the clothing processing workshop based on the distributed heterogeneous perception network to obtain a multi-source heterogeneous big data set, wherein the multi-source heterogeneous big data set comprises order data, raw material inventory data, equipment operation data and logistics data.

In particular, this may be done through a production management system (e.g., ERP system) within the enterprise. And accessing an interface or a database of the ERP system to extract order related information. The key field data of order numbers, client information, order quantity and delivery date are extracted from the order management module by using SQL sentences or API calling modes. The extracted order data is stored in a data collection server as part of a multi-source heterogeneous large data set. And acquiring inventory information by accessing a warehouse management system or a material management system interface or a database. The name, stock quantity, storage location data of the raw material are extracted using SQL queries or API calls. The extracted raw material inventory data is integrated into the data collection system and correlated with the order data. And using sensor data acquisition software in the distributed heterogeneous sensing network to monitor the running state, the working parameters and the fault information of the equipment in real time. And transmitting the collected equipment operation data to a data collection server for storage and processing to form a part of the multi-source heterogeneous big data set. And accessing a logistics management system or a transportation monitoring system interface or a database, and acquiring real-time position, transportation route and transportation state data of the transportation vehicle by using an API call or a data grabbing tool. The extracted logistics data are integrated with other data and stored in a data acquisition system to be used as a part of a multi-source heterogeneous big data set.

According to the invention, the layout positions of the sensing points can be ensured to be more reasonable and accurate by acquiring the workshop topology distribution map and planning the sensing points based on the workshop topology distribution map. The method can effectively cover the key area of the whole workshop, and improves the coverage rate and monitoring effect of the sensing network. By performing heterogeneous sensor deployment on workshops according to the perception planning data, efficient coverage and network deployment of perception points can be achieved. The method can ensure the balance and the integrity of the sensing network and improve the efficiency and the accuracy of data acquisition. The full-flow multidimensional data acquisition is carried out based on the distributed heterogeneous sensing network, so that the comprehensive data acquisition of various aspects of orders, raw material inventory, equipment operation and logistics can be realized. Through accurate perception point planning and efficient perception network deployment, real-time monitoring and data acquisition to the production process can be realized, problems and anomalies in the production process can be found, timely adjustment and treatment can be performed, and production efficiency and product quality are improved.

Preferably, step S11 comprises the steps of:

Step S111: labeling a workshop topology distribution map to obtain a labeled workshop topology distribution map, wherein the labeling comprises raw material storage area labeling, personnel activity area labeling, personnel working post site labeling, equipment point labeling, product storage area labeling and material flow channel labeling;

Specifically, a plan layout of the plant is opened using Computer Aided Design (CAD) software, and the drawing is labeled using a labeling tool provided by the software. Different labels or colors are used for different areas or elements. And labeling various elements in the workshop, including a raw material storage area, a personnel activity area, personnel working positions, equipment positions, a product storage area and a logistics channel. And after the labeling is completed, storing the labeled workshop topology distribution map.

Step S112: performing workshop operation flow simulation description on the clothing processing workshop based on the labeling workshop topology distribution map to obtain dynamic operation flow data;

specifically, using process simulation software (e.g., simul8, anyLogic), a simulation description of the plant workflow is performed according to the annotated plant topology profile. And importing each labeling area, equipment and personnel elements into flow simulation software, and setting the attribute and behavior rule of the labeling area, the equipment and the personnel elements. The simulated time period and experimental parameters, such as simulated time period, order quantity and personnel work efficiency, are set. And starting a simulation program to simulate the workshop operation flow. In the simulation process, software automatically simulates the operation conditions of all links in a workshop according to set parameters and rules. In the simulation process, the dynamic change of the workshop operation flow is observed through a visual interface provided by flow simulation software. And checking the states of all areas of the workshop, the running condition of equipment and the activity track information of personnel in real time. In the simulation process, the flow simulation software records and generates various data in real time, such as process completion time, equipment utilization rate and order processing efficiency.

Step S113: extracting key monitoring points from a clothing processing workshop according to dynamic operation flow data to obtain a key monitoring point data set, wherein the key monitoring point data set comprises a plurality of key monitoring point data;

specifically, key monitoring points are identified according to the simulation result of workshop operation flow, and the monitoring points are key nodes in the production process or positions where problems easily occur in the production link. Data generated during the simulation is analyzed using data analysis software (e.g., pandas library in Python, MATLAB). Based on the analysis results, it is determined which locations or parameters are to be monitored and focused. And extracting a key monitoring point data set comprising positions and parameters.

Step S114: traversing the key monitoring point data set, and carrying out sensor modal planning determination on the monitoring points corresponding to the key monitoring point data to obtain a sensing mode data set, wherein the sensing mode data set comprises a plurality of sensing mode data;

Specifically, key monitor point data is extracted one by one from the key monitor point data set. And (3) writing a script by using a programming language (such as Python) to realize the traversing operation on the key monitoring point data set. And in the traversal process, the position information, the attribute characteristic data and the monitoring requirement of each key monitoring point are acquired one by one. And determining a proper sensor mode according to the position, the characteristics and the monitoring requirement of each key monitoring point. And using professional sensor selection software to automatically select the optimal sensor mode according to the characteristics of the monitoring points. After the sensor mode is determined, sensing mode data corresponding to each key monitoring point is recorded, wherein the sensing mode data comprises sensor type and arrangement mode information.

Step S115: and marking the key monitoring point data corresponding to the key monitoring point data set by using the sensing mode data in the sensing mode data set to obtain sensing planning data.

Specifically, professional labeling tools or software are adopted to carry out association labeling on the perception mode data and the key monitoring point data. And associating the marked key monitoring point data with the perception mode data to form perception planning data.

The invention can realize the fine description of the workshop structure by marking the workshop topology distribution map, including the raw material storage area, the personnel activity area, the equipment points and the product storage area. And carrying out workshop operation flow simulation description based on the labeling workshop topology distribution diagram to obtain dynamic operation flow data, so that the actual operation condition of the workshop can be reflected more truly. According to the dynamic workflow data, key monitoring points in the workshop, including important nodes and key equipment in the production flow, can be extracted. The key areas and key equipment to be monitored can be determined in a targeted manner, and the monitoring efficiency and accuracy are improved. Traversing the key monitoring point data set, determining the sensor modal planning of the monitoring points according to the sensing mode data set, and obtaining the sensing mode data set. The method can select a proper sensing mode and a proper sensor type according to the characteristics of the monitoring points and the monitoring requirements, and improves the monitoring efficiency and accuracy. And marking the key monitoring point data by using the sensing mode data set to obtain sensing planning data. This allows to determine the arrangement and the position of the sensing points based on the position and the characteristics of the monitoring points.

Preferably, step S2 comprises the steps of:

Step S21: extracting key data from the order data to obtain data of the order quantity to be completed and delivery date;

Specifically, the order data table is opened using a database query tool (e.g., SQL) or data processing software (e.g., excel). And extracting the order quantity to be completed and the delivery date key data from the order data according to the requirements. The SQL statement or data screening function is used to screen out the required order data and export the order data into a new data file or data table.

Step S22: acquiring order completed quantity data and current time data;

specifically, order completed amount data is obtained by querying a database inside the enterprise. The current time data may be obtained by a system time function.

Step S23: carrying out differential calculation according to the data of the amount of the order to be completed and the data of the amount of the order completed to obtain data of the amount of the order to be completed;

specifically, the order quantity data to be completed and the completed quantity data are imported into a data processing tool by utilizing a pandas library of Excel or Python. In the data processing tool, the corresponding function or operator is used for differential calculation, namely, the order needed completion quantity is subtracted by the completed quantity, and order to-be-completed quantity data is obtained. If Excel is used, formulas can be created in the new table to calculate the order to be completed; if the pandas library of Python is used, the data can be directly vectorized for computation.

Step S24: calculating the time distance according to the current time data and the delivery date data to obtain the remaining delivery date data;

specifically, a time distance between the current time and the delivery date is calculated using a date and time processing tool (e.g., datetime modules in Python) or a date calculation function (e.g., DATEDIF function in Excel). And converting the delivery date data into a date and time format, comparing the date and time format with the current time to obtain the time distance of the remaining delivery date, and recording the time distance as the remaining delivery date data.

Step S25: performing order completion degree risk assessment analysis on the clothing processing workshop based on raw material inventory data, order to-be-completed amount data and remaining exchange period data to obtain an order completion degree risk value;

specifically, the present embodiment refers specifically to the substep of step S25.

Step S26: and carrying out intelligent decision support on the clothing processing workshop according to the order completion degree risk value to obtain a coping decision scheme.

Specifically, the present embodiment refers specifically to the substep of step S26.

The invention obtains the data of the order quantity to be completed and the date of delivery by extracting the key data of the order data. This allows a clear knowledge of the production needs and delivery time of the order. And carrying out differential calculation according to the order quantity data to be completed, the order quantity data to be completed and the current time data to obtain order quantity data to be completed, and carrying out time distance calculation according to the current time data and the delivery date data to obtain the remaining delivery date data. This allows real-time knowledge of the completion of the order and the time from the delivery period, providing accurate data support for the assessment of order completion. And carrying out order completion degree risk assessment analysis on the clothing processing workshop based on the raw material inventory data, the order quantity data to be completed and the remaining exchange period data to obtain an order completion degree risk value. This allows for a comprehensive assessment of the relationship between order completion and delivery period, identifying potential risk factors. And carrying out intelligent decision support on the clothing processing workshop according to the order completion degree risk value to obtain a coping decision scheme. According to the real-time order situation and the risk assessment result, corresponding countermeasures can be timely adopted, and the punctual completion of the order is guaranteed.

Preferably, step S25 comprises the steps of:

Step S251: carrying out material demand calculation on the data of the quantity to be completed of the order to obtain required raw material data;

Specifically, order to-do volume data is processed using a material demand planning (MRP) system, such as a material management module in the MRP system. In the MRP system, order quantity data to be completed is input, and corresponding production and purchase parameters, such as safety stock level and purchase lead time, are set. The MRP system automatically generates a material demand plan according to the order demand, the production plan and the inventory condition, and calculates the required raw material data.

Step S252: carrying out raw material matching analysis according to the required raw material data and raw material inventory data to obtain raw material gap data;

Specifically, the required raw material data and raw material inventory data were imported using the pandas library in Microsoft Excel or Python. And carrying out matching analysis on the required raw material data and the raw material inventory data to determine the required quantity and the inventory quantity of each raw material. The gap amount of each raw material, that is, the difference between the required raw material data and the stock data is calculated.

Step S253: if the gap data of the raw materials show no gap, taking the risk-free value data as an order completion degree risk value;

Specifically, if it is determined that all raw materials have sufficient inventory to meet the order requirements, the order completion risk value is set to a no risk value. The no risk value is a predetermined constant indicating that the order completion is not affected by shortage of raw materials, or a qualitative assessment indicating that the order completion is not severely affected.

Step S254: if the raw material gap data shows that gaps exist, performing gap detail analysis according to the raw material inventory data and the raw material gap data to obtain raw material gap detail data;

Specifically, the raw material inventory data and the raw material gap data are compared and analyzed to find out the types and the quantity of the raw materials with gaps. The specific cause and influence of the gap, such as whether due to a supplier's delayed delivery, production plan change factor, is further analyzed according to the type and number of raw materials of the gap. And determining the detail information of the gaps of each raw material, wherein the detail information comprises the number of the gaps, the reasons of the gaps and the types of the gaps. Creating a data table by using the Exce, arranging the analyzed raw material gap detail information into a data table or a report form, and recording the detail of each raw material gap.

Step S255: acquiring raw material purchasing data;

specifically, raw material purchase data, such as purchase order, purchase quantity, purchase date information, is extracted from a purchase management system within the enterprise using a database query tool (e.g., SQL) or a data export function.

Step S256: and carrying out order completion degree risk assessment analysis on the clothing processing workshop according to the order to-be-completed amount data, the remaining exchange period data, the raw material gap detail data and the raw material purchasing data to obtain an order completion degree risk value.

Specifically, the data of the order to be completed, the data of the remaining exchange period, the data of the gap details of the raw materials and the purchasing data of the raw materials are integrated into a unified data set, and based on the integrated data set, the risk assessment analysis of the order completion degree is carried out by using a data analysis tool or a programming language (such as Python and R). And obtaining an order completion degree risk value according to the analysis result. This risk value is a classification such as low risk, medium risk, high risk.

According to the method, the material demand calculation is carried out on the data of the quantity to be completed of the order, so that the required raw material data are obtained. This allows accurate calculation of the amount of raw material required according to the order situation. And carrying out matching analysis according to the required raw material data and the raw material inventory data to obtain raw material gap data. The supply and demand relation of the raw materials can be found in time, and whether the raw material gap exists or not is judged. And if the gap data of the raw materials show no gap, taking the risk-free value data as an order completion degree risk value. The method can rapidly judge whether the order has a raw material gap or not, and avoid the influence on the order completion degree. If the raw material gap data shows that the gap exists, gap detail analysis is carried out according to the raw material inventory data and the raw material gap data, and raw material gap detail data is obtained. This allows a detailed understanding of the specific cause and effect of the gap. Raw material purchase data are acquired and used for evaluating and analyzing the risk of order completion. This allows for comprehensive consideration of the raw material supply, further assessing the risk of order completion. And carrying out order completion degree risk assessment analysis on the clothing processing workshop according to the order to-be-completed amount data, the remaining exchange period data, the raw material gap detail data and the raw material purchasing data to obtain an order completion degree risk value. This allows for an accurate assessment of the risk level of order completion, taking into account the production and raw material supply of the order in its entirety.

Preferably, step S256 includes the steps of:

Step S2561: extracting the geographical position of the purchasing point from the raw material purchasing data to obtain raw material purchasing address distribution data; and associating the extracted geographic position coordinates with raw material purchasing data to obtain raw material purchasing address distribution data.

Specifically, geographic location coordinates of each purchase point are extracted for an address in vendor information in raw material purchase data by using GIS software.

Step S2562: carrying out space correlation on raw material purchasing address distribution data according to raw material gap detail data to obtain a gap purchasing point data set, wherein the gap purchasing point data set comprises a plurality of gap purchasing point data;

Specifically, space correlation analysis is carried out on the raw material gap detail data and the raw material purchasing address distribution data by utilizing space inquiry in GIS software, and purchasing points related to the gap raw materials are found out. And extracting the purchasing point data related to the gap to form a gap purchasing point data set, wherein the gap purchasing point data set comprises purchasing point information related to the gap.

Step S2563: carrying out purchase record extraction on raw material purchase data according to the gap purchase point data set to obtain a gap purchase record data set, wherein the gap purchase record data set comprises a plurality of gap purchase record data; the gap purchase point data and the gap purchase record data are in one-to-one or one-to-many relation;

specifically, a database query language (such as SQL) or a data processing tool (such as Pandas) is used to correlate the purchase points in the gap purchase point dataset with raw material purchase data, and purchase records related to the gap are screened out. And extracting the purchase records related to the gap to form a gap purchase record data set, wherein the gap purchase record data set comprises purchase record information related to the gap.

Step S2564: based on the gap purchase record data set, respectively carrying out average purchase time calculation on the purchase points corresponding to each gap purchase point data to obtain a gap purchase time data set, wherein the gap purchase time data set comprises a plurality of gap purchase time data;

Specifically, statistical analysis software (such as Pandas, MATLAB, R of Python) is used to perform time series analysis on the purchase record data of each gap purchase point and calculate the average purchase duration of each purchase point. And the calculated average purchasing duration data are arranged into a data set to form a gap purchasing duration data set, wherein the gap purchasing duration data set comprises the average purchasing duration information of each gap purchasing point.

Step S2565: estimating the working procedure time of the data of the quantity to be completed of the order to obtain the time data required by the completion of the order;

Specifically, according to the technological process of the product and the working condition of the production line, the production schedule software (such as a production scheduling module in an ERP system and professional production schedule software) is used for estimating the working procedure time of the production procedure of each order. And arranging the process time estimation result of each order into a data set to form time data required by order completion, wherein the time data comprise total time information required by order completion.

Step S2566: performing time comparison analysis according to time data required by order completion and remaining delivery date to obtain acceptable maximum purchasing duration data;

Specifically, the remaining date of delivery data for the order, i.e., how much time remains from the delivery date, is obtained from the enterprise's order management system or production planning system. The time required for the order to complete is compared to the remaining time of delivery using a data analysis tool (e.g., excel, python's Pandas library) to determine if the order has enough time to complete production. And determining the acceptable maximum purchasing duration, namely the allowable maximum purchasing duration in the remaining delivery period according to the time comparison analysis result.

Step S2567: if the gap purchase time length data set has gap purchase time length data larger than the acceptable maximum purchase time length data, taking the high risk value data as an order completion degree risk value;

Specifically, the gap purchase duration dataset is traversed using a data analysis tool or programming language (e.g., python, R) to compare the purchase duration of each gap purchase point to an acceptable maximum purchase duration. If a gap purchase point exists, the purchase time length of which is longer than the maximum acceptable purchase time length, the corresponding order is marked as high risk value data.

Step S2568: and if the gap purchase time length data set does not have the gap purchase time length data which is larger than the acceptable maximum purchase time length data, taking the low risk value data as an order completion degree risk value.

Specifically, the gap purchase duration dataset is traversed using a data analysis tool or programming language (e.g., python, R) to compare the purchase duration of each gap purchase point to an acceptable maximum purchase duration. And if no gap purchase point with the purchase time longer than the acceptable maximum purchase time exists, marking the corresponding order as low risk value data.

The raw material purchasing address distribution data is obtained by extracting the geographical position of the purchasing point of the raw material purchasing data. The geographical position distribution condition of the raw material purchasing points can be clearly known. And obtaining a gap purchase point data set by carrying out space correlation on raw material purchase address distribution data according to the raw material gap detail data. This allows finding the purchase point associated with the notched raw material. And carrying out purchase record extraction on the raw material purchase data according to the gap purchase point data set to obtain a gap purchase record data set. This can determine a procurement record associated with the notched raw material, providing a data basis for subsequent procurement duration calculations. And calculating average purchasing time length of purchasing points corresponding to each piece of notch purchasing point data based on the notch purchasing record data set to obtain a notch purchasing time length data set. This allows to know the average time for purchasing a certain raw material. And obtaining time data required by order completion by estimating the process time of the order to-be-completed quantity data. This may estimate the total time required for the order to complete. And obtaining the acceptable maximum purchasing duration data by performing time comparison analysis according to the time data required by order completion and the remaining delivery date. This may determine a maximum purchase duration that can be accepted for the remaining time. And judging whether high risk exists according to whether the situation that the gap purchasing time length data set is larger than the acceptable maximum purchasing time length data exists or not, so that the order completion degree risk value is determined. This allows a comprehensive assessment of the time risk of raw material procurement.

Preferably, step S26 includes the steps of:

step S261: if the order completion degree risk value is the risk value-free data, executing a conventional production plan, and maintaining the current process flow;

Specifically, if the order completion risk value is no risk value data, i.e., is lower than a set threshold value, a conventional production plan is executed, wherein the conventional production plan is executed by a production planning department according to order requirements and production resources, and a pre-established production plan is executed.

Step S262: if the order completion degree risk value is low risk value data, starting a preset alternative provider coordination mechanism to obtain a coping decision scheme;

Specifically, monitoring the risk value of the order completion, if the risk value is low risk value data, a preset alternative provider coordination mechanism needs to be started, and the alternative provider coordination is specifically: the pre-established alternative suppliers are contacted to check whether they can provide the required raw materials or parts. Raw material supply is coordinated using a supply chain management system or a related platform that contacts the suppliers. And making a coping decision scheme according to the coordination result with the alternative suppliers, wherein the coping decision scheme comprises the steps of adjusting a purchasing plan and changing a production plan.

Step S263: if the order completion degree risk value is high risk value data, the order completion degree risk value is sent to a preset monitoring user and a manual intervention decision is received, so that a coping decision scheme is obtained.

Specifically, the risk value of the order completion is monitored, and if the risk value is high risk value data, a manual intervention decision needs to be made. And sending the order completion degree risk value to a preset monitoring user, such as a production manager and a supply chain manager, through an E-mail or a short message. And after receiving the risk value notification, the monitoring user performs manual intervention decisions including adjusting production plans, increasing production resources and coordinating supply chains. Meeting or online discussion is required to make countermeasures. And obtaining a coping decision scheme according to the decision result of the monitoring user.

In the invention, if the order completion degree risk value is no risk value data, namely the order completion condition is normal, the conventional production plan can be executed, and the current process flow is maintained. This can maintain stability and efficiency of production, avoid unnecessary adjustments and interventions, and improve production efficiency and cost effectiveness. If the order completion risk value is low risk value data, a certain order completion risk exists, but the risk degree is low, and a preset alternative provider coordination mechanism can be started. The method can communicate and coordinate with alternative suppliers in time, ensure the stability and timeliness of raw material supply, lighten the risk of order completion and ensure order completion on time. If the order completion risk value is high risk value data, the higher order completion risk is indicated, and the order completion on time can be influenced. In this case, the order completion risk value is sent to a preset monitoring user and a manual intervention decision is received. The method can report the order completion situation to relevant responsible personnel in time, discuss coping strategies together, and take necessary measures to solve the problem so as to ensure the smooth completion of the order.

Preferably, step S3 comprises the steps of:

Step S31: ETL processing is carried out on the logistics data to obtain raw material purchasing logistics data and product transportation logistics data;

Specifically, using an ETL (extraction, conversion, loading) tool, such as Informatica, talend, raw logistics data is extracted from different sources (e.g., vendor systems, carrier systems). And importing the original data into a data processing platform in a structured format, and classifying the original logistics data to obtain raw material purchasing logistics data and product transportation logistics data.

Step S32: carrying out logistics data warehouse construction according to raw material purchasing logistics data and product transportation logistics data to obtain a logistics data warehouse;

specifically, the structure of the logistics data warehouse is designed based on business needs and data analysis targets. And integrating the raw material purchasing logistics data and the product transportation logistics data into a unified data warehouse by using an ETL tool, thereby obtaining a logistics data warehouse.

Step S33: performing raw material arrival rhythm time sequence analysis on a clothing processing workshop based on a logistics data warehouse to obtain raw material periodic arrival mode data;

specifically, SQL queries are used to extract time and quantity data of raw materials to the shipment from the logistics data warehouse. And carrying out statistical analysis on the raw material arrival time series data by using a moving average method in a time series analysis technology, exploring a periodic pattern in the raw material arrival time series data, and identifying the periodic pattern of raw material arrival so as to obtain raw material periodic arrival pattern data.

Step S34: carrying out product shipment period grouping analysis on a clothing processing workshop based on a logistics data warehouse to obtain product type shipment period data;

Specifically, SQL queries are used to screen data related to the shipment of the product, such as order information, shipment date, from the data warehouse. And carrying out grouping analysis on the product shipment period by using clustering analysis, and classifying the products according to the shipment period characteristics. Analyzing the shipment cycle characteristics of each product category, such as common cycles and abnormal cycles; and interpreting the distribution condition of the shipment period of each product category, thereby obtaining the shipment period data of the product type.

Step S35: performing deviation calculation on the periodic arrival mode data of the raw materials and the shipment period data of the product types to obtain production and marketing deviation data;

Specifically, calculating deviation between the periodic arrival pattern data of the raw materials and the shipment cycle data of the product types by using average absolute deviation (MAE) to obtain production and marketing deviation data; the product pin deviation data refers to the difference or deviation between the raw material arrival pattern and the product shipment cycle. These data reflect the degree of mismatch between production and sales, resulting in problems with stock backlog or production starvation.

Step S36: if the production pin deviation data shows supply and demand matching, maintaining the current production plan;

Specifically, if the production pin deviation data shows a supply-demand match, the current production plan is maintained without adjustment.

Step S37: if the production and sales deviation data show that the product is in a stagnation state, carrying out stagnation amount estimation on a clothing processing workshop based on the logistics data warehouse to obtain product stagnation amount data;

Specifically, if the product sales deviation data indicates that there is a product lag, data related to the sales of the product, such as sales orders, shipping records, is extracted from the stream data warehouse. And estimating the sales hysteresis of the product according to the historical sales data and the current sales condition.

Step S38: acquiring workshop inventory layout data; and carrying out intelligent inventory allocation on the clothing processing workshop according to the workshop inventory layout data and the product sales volume data to obtain an allocation optimization scheme.

Specifically, a genetic algorithm is adopted to combine the product sales data and the inventory layout data, and the allocation planning is carried out with the aim of minimizing inventory cost or maximizing profit, so as to determine an optimal inventory allocation scheme, and thus an allocation optimization scheme is obtained.

According to the invention, the logistics data of raw material purchase and transportation are obtained by carrying out ETL (extract-transform-load) processing on the logistics data. This can extract and convert useful information from the raw stream data. And carrying out logistics data warehouse construction according to the raw material purchasing logistics data and the product transportation logistics data to obtain a logistics data warehouse. The logistics data can be stored and managed, subsequent inquiry and analysis are facilitated, and the utilization efficiency of the data is improved. And carrying out raw material arrival rhythm time sequence analysis on the clothing processing workshop based on the logistics data warehouse to obtain the raw material periodic arrival mode data. The method can be used for knowing the arrival rhythm and periodical change condition of the raw materials and providing basis for subsequent production planning and inventory management. And carrying out product shipment period grouping analysis on the clothing processing workshop based on the logistics data warehouse to obtain product type shipment period data. The method can classify the products according to the characteristics of the shipment cycle, know shipment rules of different product types, and provide guidance for production planning and inventory management. And obtaining production and marketing deviation data by calculating deviation of the periodic arrival mode data of the raw materials and the shipment period data of the product types. The deviation between actual production and sales conditions and expected conditions can be compared, and the problem of supply and demand mismatch can be found in time. If the production pin deviation data shows a supply-demand match, the current production plan is maintained. This can ensure that the production plan accords with the actual demand, avoids unnecessary adjustment, improves production efficiency. If the production and sales deviation data show that the product is in a stagnation state, the clothing processing workshop is subjected to stagnation amount estimation based on the logistics data warehouse, and the product stagnation amount data are obtained. The method can find out the diapause products in time and provide basis for subsequent inventory management and sales strategy adjustment. And (3) acquiring workshop inventory layout data, and intelligently allocating inventory to the clothing processing workshop according to the workshop inventory layout data and the product sales volume data to obtain an allocation optimization scheme. The inventory system can reasonably allocate the inventory, optimize the inventory structure, reduce the diapause products, reduce the inventory cost and improve the fund utilization efficiency.

Preferably, step S4 comprises the steps of:

Step S41: classifying the equipment operation data according to the equipment ID to obtain a plurality of single-equipment operation data;

Specifically, the device operation data is classified according to the device ID, one data set for each device, and one data set is recorded as single device operation data.

Step S42: acquiring a device operation parameter standard value, and performing operation index calculation on single device operation data according to the device operation parameter standard value to obtain a device operation health index;

Specifically, the standard values of the operating parameters of the device are obtained from a document or database provided by the device manufacturer. And (3) applying a proper algorithm or model to the single-device operation data of each device to calculate operation indexes of the device, such as the device utilization rate, the failure rate and the average maintenance time. And comparing the actual operation index of each device with the corresponding standard value one by one. For example, for device utilization, if the actual utilization is higher than a standard value, it indicates that the device is in a good state; if the actual utilization rate is lower than the standard value, the problem of low production efficiency is indicated. And according to the comparison result, distributing corresponding weight to each operation index according to a preset weight distribution proportion, and then converting the health degree of each index into a comprehensive health index. And recording the calculated equipment health index to obtain the equipment health index.

Step S43: if the equipment operation health index is greater than or equal to a preset equipment operation health threshold, marking the corresponding equipment as healthy equipment, and taking the equipment operation health index as equipment risk data;

specifically, if the device operation health index is greater than or equal to a preset device operation health threshold, the healthy device is marked as a healthy device, and the health index is recorded as device risk data.

Step S44: if the equipment operation health index is smaller than a preset equipment operation health threshold, estimating the abnormal duration according to the single equipment operation data and equipment corresponding to the equipment operation parameter standard value to obtain equipment abnormal duration data;

specifically, if the equipment operation health index is smaller than a preset equipment operation health threshold, abnormal conditions in the equipment operation data, such as faults and shutdown, are detected according to the single equipment operation data and the equipment operation parameter standard value by using statistical analysis. And estimating the duration of the detected abnormal condition, and determining the duration of the abnormality. Recording the abnormal duration data of each device to obtain the abnormal duration data of the device.

Step S45: comparing and judging the equipment abnormal duration time data with a preset abnormal duration time interval to obtain equipment risk data, wherein the comparing and judging process specifically comprises the following steps:

If the equipment abnormal duration time data is smaller than the lower limit of the preset abnormal duration time interval, taking the primary risk value as equipment risk data;

if the equipment abnormal duration time data is in a preset abnormal duration time interval, taking the secondary risk value as equipment risk data;

If the equipment abnormal duration time data is larger than the upper limit of the preset abnormal duration time interval, taking the three-level risk value as equipment risk data;

the level of the third-level risk value is higher than the second-level risk value, and the level of the second-level risk value is higher than the first-level risk value;

Specifically, the equipment abnormal duration data is compared with a preset abnormal duration interval, and the risk level of the equipment is judged. If the equipment abnormal duration time data is smaller than the lower limit of the preset abnormal duration time interval, taking the primary risk value as equipment risk data; if the equipment abnormal duration time data is in a preset abnormal duration time interval, taking the secondary risk value as equipment risk data; if the equipment abnormal duration time data is larger than the upper limit of the preset abnormal duration time interval, taking the three-level risk value as equipment risk data; the level of the third-level risk value is higher than the second-level risk value, and the level of the second-level risk value is higher than the first-level risk value.

Step S46: and carrying out equipment maintenance decision support on the clothing processing workshop according to the equipment risk data to obtain a maintenance decision scheme.

Specifically, different maintenance strategies are formulated according to the equipment risk level and the actual situation of the equipment risk data display, including but not limited to preventive maintenance and repairable maintenance.

According to the method, the device operation data are classified according to the device ID, so that a plurality of single device operation data are obtained. This allows the operation of different devices to be analyzed and compared, and subsequent health assessment and maintenance decisions to be made in a targeted manner. And calculating the operation index of the single-equipment operation data according to the equipment operation parameter standard value by acquiring the equipment operation parameter standard value to obtain the equipment operation health index. The method can quantitatively evaluate the running state of the equipment and timely find out the equipment with poor health condition. And if the equipment operation health index is greater than or equal to a preset equipment operation health threshold, marking the corresponding equipment as healthy equipment, and taking the equipment operation health index as equipment risk data. This allows for a fast identification of a device with good health status, reducing the need for maintenance decisions. If the equipment operation health index is smaller than a preset equipment operation health threshold value, carrying out abnormal duration estimation on equipment corresponding to the single equipment operation data and the equipment operation parameter standard value to obtain equipment abnormal duration data. This may identify devices that are running abnormally and evaluate the length of time that the abnormality persists. And comparing and judging the equipment abnormal duration time data with a preset abnormal duration time interval to obtain equipment risk data. The equipment risks are divided into three levels according to the duration of the abnormality, and the risks represent risks of different degrees respectively. The risk degree of the assessment equipment can be quantified, and a basis is provided for subsequent maintenance decision. And carrying out equipment maintenance decision support on the clothing processing workshop according to the equipment risk data to obtain a maintenance decision scheme. And (3) according to the health condition and the risk level of the equipment, a corresponding maintenance plan and strategy are formulated, the normal operation of the equipment is ensured, the equipment faults and the downtime are reduced, and the production efficiency and the equipment utilization rate are improved.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The industrial Internet security monitoring method based on big data is characterized by comprising the following steps of:

2. The industrial internet security monitoring method based on big data according to claim 1, wherein the step S1 comprises the steps of:

3. The industrial internet security monitoring method based on big data according to claim 2, wherein step S11 comprises the steps of:

4. The industrial internet security monitoring method based on big data according to claim 1, wherein the step S2 comprises the steps of:

Step S22: acquiring order completed quantity data and current time data;

5. The industrial internet security monitoring method based on big data according to claim 4, wherein the step S25 comprises the steps of:

Step S255: acquiring raw material purchasing data;

6. The big data based industrial internet security monitoring method of claim 5, wherein step S256 comprises the steps of:

step S2561: extracting the geographical position of the purchasing point from the raw material purchasing data to obtain raw material purchasing address distribution data;

7. The industrial internet security monitoring method based on big data according to claim 4, wherein the step S26 comprises the steps of:

8. The industrial internet security monitoring method based on big data according to claim 1, wherein the step S3 comprises the steps of:

9. The industrial internet security monitoring method based on big data according to claim 1, wherein the step S4 comprises the steps of:

10. A big data based industrial internet security monitoring system for performing the big data based industrial internet security monitoring method of claim 1, the big data based industrial internet security monitoring system comprising: