Method for realizing remote monitoring of equipment based on cloud platform
Through the cloud-based remote monitoring method of equipment, combined with the analysis of environmental abnormality and equipment utilization, the production environment and equipment parameters are optimized, and the impact of changes in the production environment of lithium batteries on output is solved, and the stability of the lithium battery production process is achieved. Improve efficiency.
Patent Information
- Application Number
- CN202411277681.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-12
AI Technical Summary
The existing remote monitoring methods for equipment lack deep consideration of temperature, humidity and pollutant concentration changes in the lithium battery production environment, making it difficult to ensure or positive feedback on production volume data, especially when environmental parameters change greatly. .
Based on the cloud platform method, by analyzing the correlation coefficients of environmental anomalies and equipment utilization, we select optimization strategies, including optimization of production environment conditions, optimization of production equipment operation parameters and fault maintenance, and use digital twin models for simulation tests. If the optimization coefficient is If the threshold is not exceeded, a reminder command will be issued to achieve maximum optimization effect.
Dynamic evaluation and optimization of the lithium battery production process is achieved, the utilization rate and operation efficiency of production equipment are improved, fault maintenance time is reduced, and the stability and safety of output are ensured.
Smart Images

Figure CN118795854B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of remote monitoring of equipment, and in particular to a method for implementing remote monitoring of equipment based on a cloud platform. Background Art
[0002] In modern lithium battery production lines, industrial Internet of Things technology is profoundly changing the production model. By deploying industrial Internet of Things gateways, we can achieve remote real-time monitoring of production equipment. Whether it is the operating status of the equipment, key production parameters or potential fault warnings, they can be collected and transmitted to the cloud in real time. In the remote monitoring center, with the help of advanced cloud platforms and configuration software, when the equipment encounters a fault, the system can immediately trigger an alarm and quickly notify relevant personnel with the help of network communication technology, winning valuable time for rapid response and troubleshooting.
[0003] Remote control of lithium battery production equipment not only improves production efficiency and response speed, but also significantly reduces maintenance costs and enhances equipment safety. Through remote maintenance and debugging functions, technicians can troubleshoot equipment, upgrade software or adjust parameters without having to visit the site. Real-time monitoring and data analysis help identify potential safety hazards in advance, effectively preventing equipment failures and downtime accidents.
[0004] In the Chinese invention patent with application publication number CN116700021A, a remote control method and device for smart devices are disclosed, the method comprising: when it is detected that an operation and maintenance operation needs to be performed on a target smart device, determining the operation and maintenance information of the target smart device; determining the target operation and maintenance personnel of the target smart device according to the operation and maintenance information; generating an operation and maintenance prompt for the target smart device according to the operation and maintenance information, and sending the operation and maintenance prompt to the target operation and maintenance personnel, the operation and maintenance prompt is used to prompt the target operation and maintenance personnel to perform remote operation and maintenance operations on the target smart device. It can be seen that when the present invention determines that an operation and maintenance smart device needs to be operated and maintained, it automatically determines the operation and maintenance personnel matched with the smart device, and sends the remote operation and maintenance prompt of the smart device to the smart device, so that the operation and maintenance personnel can remotely operate and maintain the smart device, thereby improving the operation and maintenance processing efficiency and convenience of the smart device and improving the user stickiness of the smart device.
[0005] Combined with the above application and the contents of the prior art:
[0006] Considering that the production process of lithium batteries and related products is dangerous, it is necessary to accurately control the production process. Therefore, there are many automated equipment involved in the production process. During the production process, managers or production personnel can monitor the production process by remotely controlling the production equipment.
[0007] In the existing methods of remote monitoring of equipment, various control parameters of production equipment are usually adjusted and set in advance, and the output data is monitored. When the output data is abnormal, the control parameters of the production equipment can be optimized through fuzzy control to achieve positive feedback on the output change; however, when the production environment of lithium batteries is abnormal, especially when environmental parameters such as temperature, humidity and pollutant concentration in the production area undergo large changes and affect the utilization rate of the production equipment, the existing methods of remote monitoring of equipment lack in-depth consideration of changes in the production environment. When production-related data continue to produce abnormalities, they can only adjust the control parameters of the production equipment, which makes it difficult to achieve the guarantee or positive feedback of the production volume data.
[0008] To this end, the present invention provides a method for realizing remote monitoring of equipment based on a cloud platform. Summary of the invention
[0009] 1. Technical issues to be resolved
[0010] In view of the deficiencies of the prior art, the present invention provides a method for realizing remote monitoring of equipment based on a cloud platform. According to the relationship between the alarm density and the warning threshold, the corresponding optimization response strategy is selected for the production process of lithium batteries and related products, including one or more combinations of production environment condition optimization, production equipment operation parameter optimization and operation fault maintenance; the lithium battery production digital twin model simulates and tests the optimization response strategy, obtains the test data on each test node and constructs the optimization coefficient. If the optimization coefficient does not exceed the optimization threshold, a reminder instruction is issued. Different optimization strategies are selected and combined to maximize the optimization effect when optimizing the production process; thereby solving the technical problems recorded in the background technology.
[0011] (II) Technical solution
[0012] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for realizing remote monitoring of equipment based on a cloud platform includes: collecting environmental condition data in a target area at a monitoring node and then constructing an environmental anomaly degree , analyze and obtain the degree of environmental abnormality Correlation coefficient with equipment utilization , if the correlation coefficient When the relevant threshold is exceeded, a data collection instruction is issued to the outside;
[0013] A sensor network is deployed in the target area. Before sending the collected data to the cloud platform, the frequency of reading the collected data is constrained, and an encryption scheme is randomly selected from the pre-built encryption scheme library to encrypt the data to be sent.
[0014] Use the trained abnormal data recognition model to identify abnormal data in the production status data of the production equipment. If abnormal data exists, build the alarm density in each sub-cycle based on the distribution status of the time node where the abnormal data was generated. And the warning threshold ;
[0015] According to the alarm intensity With warning threshold Based on the relationship between the two, select corresponding optimization strategies for the production process of lithium batteries and related products, including one or more combinations of production environment conditions optimization, production equipment operation parameter optimization and operation fault maintenance;
[0016] The lithium battery production digital twin model simulates and tests the optimization response strategy, obtains the test data at each test node, and constructs the optimization coefficient , if the optimization coefficient If the optimization threshold is not exceeded, a reminder instruction will be issued to the outside.
[0017] Furthermore, the abnormal difference of environmental conditions on the monitoring nodes is used to construct the environmental abnormality degree on each monitoring node. , among which, for abnormal difference Perform linear normalization and map the corresponding data values to the interval According to the following method:
[0018] ;
[0019] in, , is the number of environmental condition parameters; For the i The abnormal difference of environmental condition parameters, is the acceptable value of abnormal difference, weight coefficient, , ,and .
[0020] Furthermore, the utilization rate of equipment is collected at each monitoring node, among which the degree of environmental abnormality is Equipment utilization Perform linear normalization and map the corresponding data values to the interval According to the following method:
[0021] ;
[0022] Weight coefficient, , ,and , , is the number of monitoring nodes, For the i The degree of environmental abnormality on the monitoring nodes, For the i Monitor the device utilization on each node.
[0023] Further, after receiving the data collection instruction, a sensor network is arranged in the target area, and the production status data is collected in the target area using the sensor network;
[0024] Based on the correlation coefficient Constrain the frequency of reading the stored production status data, read the data at the reading nodes that meet the constraints, and send the read data to the cloud platform.
[0025] Furthermore, the data reading frequency is constrained as follows:
[0026] ;
[0027] Weight coefficient, , ; is the correlation coefficient, The number of nodes for data reading, It is i Read nodes to j The time interval between reading nodes, is the average value of the time interval.
[0028] Furthermore, when the production equipment is in production state, the production state data is collected in real time and summarized to generate a production state data set; the production state data is used as input, and the trained abnormal data recognition model is used to identify abnormal data, and if abnormal data exists, an alarm instruction is pushed to the outside;
[0029] After receiving the alarm instruction, feature extraction is performed on the real-time and historical production status data to obtain the corresponding abnormal features; based on the correspondence between the abnormal features and the emergency strategies, the emergency strategy library outputs the corresponding emergency strategies.
[0030] Furthermore, the time node when the alarm instruction is received in the sub-cycle is recorded and used as the alarm node to construct the alarm density in each sub-cycle. , as follows:
[0031] ;
[0032] Where: , weight coefficient, , ,and ; The value is 2.718;
[0033] is the diameter of the subperiod, It is i The weighted value of the alarm node, It is i Alarm nodes to j The time interval for each alarm node.
[0034] Furthermore, the alarm density Mark the sub-periods and set alarms based on the alarm density in each sub-period. Constructing alert thresholds , as follows:
[0035] ;
[0036] in, , is the number of sub-periods, For the i The alarm density within a sub-cycle, is the mean value of the alarm density.
[0037] Furthermore, if the alarm density Below the warning threshold If the environment is abnormal Higher than expected to reduce environmental abnormality As the optimization target, the linear regression algorithm is used to optimize the production environment conditions in the production area;
[0038] If the alarm intensity At the warning threshold If the equipment utilization rate of production equipment is Lower than expected; to improve equipment utilization As the optimization target, the genetic algorithm is used to optimize the operating parameters of the production equipment;
[0039] If the alarm intensity Above the warning threshold , monitor and collect the operation and control data of production equipment, take the operation-related data of production equipment as input, use the trained fault identification model to perform fault identification, and issue fault maintenance instructions if there is an operation fault.
[0040] Furthermore, taking the fault maintenance of lithium battery production equipment as the target word, an equipment maintenance knowledge graph is pre-constructed; after receiving the fault maintenance instruction, the fault maintenance features are obtained after feature extraction of the production equipment operation related data, and the equipment maintenance knowledge graph outputs the corresponding production equipment fault maintenance plan to maintain the production equipment.
[0041] Furthermore, after collecting the lithium battery production and operation data, a digital twin model of lithium battery production is constructed;
[0042] Taking one or more combinations of optimized production environment conditions, optimized operating parameters and production equipment fault maintenance plans as input; the lithium battery production digital twin model is used to test it, and the collected test data is aggregated to generate a production test data set.
[0043] Furthermore, the production volume at each test node Sort by timeline, by production volume The change of generates the optimization coefficient corresponding to the optimization response strategy before or after the combination , as follows:
[0044] ;
[0045] in, For the i Production volume on test nodes, is the initial value of production volume, is the acceptable value for production volume; For the i The optimal intermediate value, is its mean value; , is the number of test nodes, weight coefficient: , and .
[0046] (III) Beneficial effects
[0047] The present invention provides a method for realizing remote monitoring of equipment based on a cloud platform, which has the following beneficial effects:
[0048] 1. Determine the abnormality of the current environment. If the abnormality is high, it can be dealt with in a timely manner; determine the impact of environmental conditions on lithium battery production. If the impact exceeds expectations, when it is necessary to increase the output of lithium batteries and other products, adjust the environmental conditions in the target area to improve the utilization rate of production equipment.
[0049] 2. By constraining the frequency of data reading and storage, the reading frequency is adapted to the actual production status, thereby improving data reading efficiency. By randomly selecting encryption schemes for data encryption, different encryption schemes are selected for different production data, and encryption schemes are switched and replaced to fully protect data security.
[0050] 3. Use the trained abnormal data recognition model to identify abnormal data, and judge whether there is an abnormality in the current production status. If there is an abnormality, it can be processed in time to avoid the abnormal production status from being maintained for a long time.
[0051] 4. Based on alarm density With warning threshold When the lithium battery production status continues, the abnormal degree of production status in the target area is dynamically evaluated. Different treatment methods are adopted according to the different abnormalities of the production status to ensure the production status and increase production.
[0052] 5. By optimizing the production environment conditions in the target area, we can avoid the impact of environmental conditions on the production status of production equipment and achieve an increase in output; by optimizing the operating parameters of production equipment, we can improve the operating status of production equipment, improve the operating efficiency of production equipment, and ensure production volume.
[0053] 6. Output the corresponding production equipment failure maintenance plan through the equipment maintenance knowledge graph, quickly obtain targeted maintenance plans, improve the maintenance efficiency of production equipment, and then shorten the downtime of production equipment to achieve an increase in production.
[0054] 7. After conducting single tests or combined tests on different optimization strategies, several groups of different test data can be obtained. Different optimization strategies can be selected and combined based on the test data. When optimizing the production process, the optimization effect can be maximized and the output of lithium batteries can be increased to the greatest extent.
[0055] 8. Judge the optimization effect of the production process and confirm whether the optimization effect has achieved the expected effect. On the basis of remote monitoring and control of production equipment, realize multi-process optimization and improvement of lithium batteries and related products, and ensure the production volume of lithium batteries.
[0056] 9. Identify the operating faults of the current production equipment, and implement timely maintenance of the faults by issuing fault maintenance instructions to the outside, thereby reducing the duration of the production equipment failure and increasing production. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] Figure 1 The figure is a flow chart of the method for remote monitoring of equipment of the present invention. DETAILED DESCRIPTION
[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0059] See also Figure 1 The present invention provides a method for realizing remote monitoring of equipment based on a cloud platform, comprising:
[0060] Step 1: Collect environmental condition data in the target area at the monitoring node and construct the environmental anomaly degree , analyze and obtain the degree of environmental abnormality Correlation coefficient with equipment utilization , if the correlation coefficient When the relevant threshold is exceeded, a data collection instruction is issued to the outside;
[0061] The step 1 includes the following contents:
[0062] Step 101: After determining the production area of lithium batteries and related products, take it as the target area; pre-set a monitoring cycle including several monitoring nodes, monitor the environmental condition data in the target area at the monitoring nodes, including environmental parameters such as temperature, humidity and pollutant concentration, and construct a production environment condition data set after aggregation;
[0063] Step 102: After determining the acceptable range of each environmental condition parameter, the shortest distance between the real-time value of the environmental condition parameter on the monitoring node and the acceptable range is used as the abnormal difference;
[0064] The environmental anomaly degree of each monitoring node is constructed by the abnormal difference of environmental conditions , among which, for abnormal difference Perform linear normalization and map the corresponding data values to the interval According to the following method:
[0065] ;
[0066] in, , is the number of environmental condition parameters; For the i The abnormal difference of environmental condition parameters, is the acceptable value of abnormal difference, weight coefficient, , ,and , the weight coefficient can be obtained by referring to the hierarchical analysis method;
[0067] When in use, after the lithium battery enters the production state and the corresponding environmental conditions are determined, the environmental abnormality degree is constructed based on the acquired environmental condition data. , according to the degree of environmental abnormality The abnormality of the current environment can be judged, and if the abnormality is high, it can be handled in a timely manner;
[0068] Step 103: Collect the utilization rate of equipment at each monitoring node, and analyze and obtain the correlation coefficient between the environmental abnormality and the equipment utilization rate. , among which, the degree of environmental abnormality Equipment utilization Perform linear normalization and map the corresponding data values to the interval According to the following method:
[0069] ;
[0070] Weight coefficient, , ,and , the weight coefficient is consistent with the previous value; , is the number of monitoring nodes, For the i The degree of environmental abnormality on the monitoring nodes, For the i Equipment utilization on each monitoring node;
[0071] Based on historical data and expectations for abnormal value management in the production environment, relevant thresholds are set in advance; if the correlation coefficient If the relevant threshold is exceeded, it means that the environmental conditions in the target area have a certain degree of impact on the production of lithium batteries and related products. At this time, a data collection instruction is issued to the outside;
[0072] When using, combine the contents in steps 101 to 103:
[0073] Generate a correlation coefficient after continuously obtaining the equipment utilization and environmental abnormality of several monitoring nodes , according to the correlation coefficient The degree of impact of environmental conditions on lithium battery production can be determined. If the degree of impact exceeds expectations and the output of lithium batteries and other products needs to be increased, the environmental conditions in the target area can be adjusted to improve the utilization rate of production equipment.
[0074] In the existing methods of remote monitoring of equipment, various control parameters of production equipment are usually pre-adjusted and set, and the output data is monitored. When the output data is abnormal, the control parameters of the production equipment are optimized through fuzzy control to achieve positive feedback on the output change. However, when the production environment of lithium batteries is abnormal, especially when environmental parameters such as temperature, humidity and pollutant concentration in the production area undergo large changes and affect the utilization rate of the production equipment, the existing methods of remote monitoring of equipment lack in-depth consideration of changes in the production environment. When production-related data continue to produce abnormalities, they can only adjust the control parameters of the production equipment, which makes it difficult to achieve guarantee or positive feedback on the production volume data.
[0075] Step 2: Deploy a sensor network in the target area. Before sending the collected data to the cloud platform, constrain the reading frequency of the collected data, and randomly select an encryption scheme from the pre-built encryption scheme library to encrypt the data to be sent.
[0076] The step 2 includes the following contents:
[0077] Step 201: after receiving the data collection instruction, a sensor network is arranged in the target area, such as a temperature sensor, an air pressure sensor, a vibration sensor, an air quality sensor, etc.; the production status data is collected and stored in the target area using the sensor network;
[0078] Based on the correlation coefficient Constrain the frequency of reading the stored production status data, read the data at the reading nodes that meet the constraint conditions, and send the read data to the cloud platform; the constraint method for the data reading frequency is as follows:
[0079] ;
[0080] Weight coefficient, , ;The weight coefficient can be obtained by referring to the hierarchical analysis method;
[0081] is the correlation coefficient, The number of nodes for data reading, It is i Read nodes to j The time interval between reading nodes, is the time interval average;
[0082] When in use, after completing data collection, the frequency of data reading and storage is constrained to ensure that the reading frequency is adapted to the actual production status, avoiding excessive invalid reading caused by high-frequency data reading and improving data reading efficiency.
[0083] Step 202: Encrypt the production status data before sending it to the cloud platform, wherein several different encryption schemes are collected and summarized in advance to generate an encryption scheme library; randomly extract an encryption scheme from the pre-built encryption scheme library, and encrypt the data to be sent according to the extracted encryption scheme;
[0084] When using, combine the contents in steps 201 and 202:
[0085] When production status data needs to be sent, data encryption is performed by randomly selecting an encryption scheme, different encryption schemes are selected for different production data, and the encryption schemes are switched and replaced, thereby fully ensuring data security.
[0086] Step 3: Use the trained abnormal data recognition model to identify abnormal data in the production status data of the production equipment. If abnormal data exists, build the alarm density in each sub-cycle based on the distribution of the time nodes where the abnormal data was generated. And the warning threshold ;
[0087] The step three includes the following contents:
[0088] Step 301: When the production equipment is in production, the production status data, such as the output of the target product, the production speed and the downtime of the production equipment, are collected in real time, and the production status data set is generated;
[0089] After training the convolutional neural network with the labeled sample data, the trained abnormal data recognition model is obtained; the production status data is used as input, and the trained abnormal data recognition model is used to identify abnormal data. If abnormal data exists, an alarm instruction is pushed to the outside;
[0090] When in use, after collecting the production status data of lithium batteries, the trained abnormal data recognition model is used to identify abnormal data, so as to judge whether there is an abnormality in the current production status. If there is an abnormality, it can be processed in time to avoid the abnormal production status from being maintained for a long time.
[0091] Step 302: After receiving the alarm instruction, extract the features of the real-time and historical production status data to obtain the corresponding abnormal features; obtain several emergency strategies through online retrieval, offline formulation and collection, and generate an emergency strategy library after aggregation;
[0092] According to the correspondence between abnormal characteristics and emergency strategies, the emergency strategy library outputs the corresponding emergency strategy; with the emergency strategy as a reference, the abnormal state in the production process can be processed;
[0093] When in use, when there is an abnormality in the production status, targeted processing can be achieved through the emergency strategies prepared in advance;
[0094] Step 303: Record the time node when the alarm instruction is received in the sub-period and use it as the alarm node to construct the alarm density in each sub-period. , as follows:
[0095] ;
[0096] Where: , weight coefficient, , ,and ; The value is 2.718;
[0097] The weight coefficient is consistent with the previous value; is the diameter of the subperiod, It is i The weighted value of the alarm node is proportional to the abnormal degree of the abnormal data at the alarm node. ; It is i Alarm nodes to j The time interval of each alarm node;
[0098] By alarm intensity After marking the sub-periods, according to the alarm density in each sub-period Constructing alert thresholds , as follows:
[0099] ;
[0100] in, , is the number of sub-periods, For the i The alarm density within a sub-cycle, is the mean value of alarm density;
[0101] When using, combine the contents in steps 301 to 303:
[0102] According to the alarm intensity With warning threshold When the lithium battery production status continues, the abnormal degree of production status in the target area can be dynamically evaluated. According to the different abnormalities of the production status, different processing methods can be adopted to ensure the production status and increase production.
[0103] Step 4: Based on the alarm density With warning threshold Based on the relationship between the two, select corresponding optimization strategies for the production process of lithium batteries and related products, including one or more combinations of production environment conditions optimization, production equipment operation parameter optimization and operation fault maintenance;
[0104] The step 4 includes the following contents:
[0105] Step 401: If the alarm density Below the warning threshold , issue production environment optimization instructions to the outside world;
[0106] After receiving the production environment optimization instruction, if the environment is abnormal Higher than the preset abnormal threshold to reduce the degree of environmental abnormality As the optimization target, a linear regression algorithm is used to optimize the production environment conditions in the production area to obtain the optimized production environment conditions;
[0107] When in use, by optimizing the production environment conditions in the target area, the environmental conditions are prevented from affecting the production status of the production equipment, thereby achieving an increase in production;
[0108] Step 402: If the alarm density At the warning threshold Internally, send equipment optimization instructions to the outside;
[0109] After receiving the equipment optimization instruction, if the equipment utilization rate of the production equipment Lower than the preset utilization threshold; to improve equipment utilization As the optimization target, after identifying and collecting the various operating parameters of the production equipment, the genetic algorithm is used to optimize the operating parameters of the production equipment, and the operating status of the production equipment is adjusted according to the optimized operating parameters;
[0110] When the utilization rate of production equipment is insufficient, such as when the failure frequency is high and the downtime is long, the production volume can be guaranteed by optimizing the operating parameters of the production equipment, improving the operating status of the production equipment, and improving the operating efficiency of the production equipment;
[0111] Step 403: If the alarm density Above the warning threshold , monitor and collect the operation and control data of production equipment, train the machine learning algorithm with the labeled sample data, and obtain the trained fault identification model; use the operation-related data of the production equipment as input, use the trained fault identification model to identify the fault, and issue a fault maintenance instruction if there is an operation fault;
[0112] Step 404: Taking the fault maintenance of lithium battery production equipment as the target word, after deep retrieval and entity relationship building, pre-build the equipment maintenance knowledge graph;
[0113] After receiving the fault maintenance instruction, the fault maintenance features are obtained by extracting the features of the production equipment operation related data; according to the correspondence between the fault maintenance features and the fault maintenance plan, the equipment maintenance knowledge graph outputs the corresponding production equipment fault maintenance plan, and the production equipment is maintained after execution;
[0114] When in use, the corresponding production equipment failure maintenance plan is output through the equipment maintenance knowledge map. When the production equipment needs to be maintained, the targeted maintenance plan can be quickly obtained to improve the maintenance efficiency of the production equipment, thereby shortening the downtime of the production equipment and achieving an increase in production.
[0115] When using, combine the contents in steps 401 to 404:
[0116] After dynamic evaluation, when the alarm frequency is high and exceeds the dynamic warning threshold, the operating data of the production equipment is identified to identify the operating faults of the current production equipment. If an operating fault exists, a fault maintenance instruction can be issued to the outside to achieve timely maintenance of the fault, reduce the duration of the production equipment fault, and achieve an increase in production.
[0117] Step 5: Use the lithium battery production digital twin model to simulate and test the optimization response strategy, obtain the test data at each test node, and then construct the optimization coefficient , if the optimization coefficient If the optimization threshold is not exceeded, a reminder instruction will be issued to the outside;
[0118] The step five includes the following contents:
[0119] Step 501: collect operation control data, environmental condition data, generation status data and production process data of lithium battery production equipment, and summarize them as a set of lithium battery production operation data;
[0120] Extract part of the lithium battery production and operation data set as sample data, train the machine learning algorithm with the sample data, and build a digital twin model for lithium battery production;
[0121] Taking one or more combinations of optimized production environment conditions, optimized operating parameters and production equipment failure maintenance solutions as input; the lithium battery production digital twin model tests it, and aggregates the collected test data to generate a production test data set;
[0122] When in use, after optimizing the lithium battery production process from different angles, by performing single tests or combined tests on different optimization strategies, several groups of different test data are obtained. Different optimization strategies can be selected and combined based on the test data. When optimizing the production process, on the basis of remote monitoring of production equipment, the optimization effect is maximized, and the output of lithium batteries is increased to the greatest extent;
[0123] Step 502: pre-set a test cycle including several test nodes, and set the production volume on each test node Sort by timeline, by production volume The change of generates the optimization coefficient corresponding to the optimization response strategy before or after the combination , as follows:
[0124] ;
[0125] in, For the i Production volume on test nodes, is the initial value of production volume, is the acceptable value for production volume; For the i The optimal intermediate value, is its mean value;
[0126] , is the number of test nodes, weight coefficient: , and ;The weight coefficient remains consistent with the previous value;
[0127] Based on historical data and management expectations of optimization effects, the optimization threshold is set in advance; if the optimization coefficient If the optimization threshold is not exceeded, it means that the current single optimization or combined optimization effect has not met expectations, the output has not improved or the degree of improvement has not met expectations, and the optimization coefficient When the optimization threshold is exceeded, a corresponding combined optimization response strategy is used as the target strategy; at this time, a reminder instruction is issued to the outside to facilitate the next step of processing;
[0128] When using, combine the contents in steps 501 to 503:
[0129] Construct optimization coefficients from acquired test data After that, by optimizing the coefficient The optimization effect of the production process can be judged to confirm whether the optimization effect has achieved the expected effect and whether the change in output has met expectations. If it has, on the basis of remote monitoring and control of production equipment, multi-process optimization and improvement of lithium batteries and related products can be achieved, thereby ensuring the production volume of lithium batteries.
[0130] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.
[0131] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.
[0132] The construction method of the knowledge graph of lithium battery production equipment fault maintenance can refer to the following:
[0133] It is necessary to clarify the goal of building the knowledge graph, that is, what problem do you want to solve through the knowledge graph, such as improving the efficiency and accuracy of equipment fault maintenance, or providing intelligent decision-making support for equipment maintenance.
[0134] Data source selection: The data sources for constructing the knowledge graph of lithium battery production equipment failure maintenance mainly include the following categories:
[0135] Structured data: such as equipment maintenance records, fault reports, equipment parameter tables, etc. Semi-structured data: such as equipment instruction manuals, technical manuals, etc. Unstructured data: such as expert experience, fault case analysis, technical forum discussions, etc.
[0136] Data preprocessing: Data preprocessing is an important step in building a knowledge graph, including data cleaning, format conversion, data integration, etc., to ensure the quality and consistency of the data. Specific steps may include: Noise removal: Deleting irrelevant or duplicate data. Data conversion: Converting data in different formats into a unified format for subsequent processing. Data integration: Integrating data from different data sources to form a complete data set.
[0137] Knowledge extraction: Knowledge extraction is the process of extracting entities, attributes, and relationships from data sources, and is the core step in building a knowledge graph. Specific methods include: Entity extraction: Use named entity recognition (NER) technology to extract specific entities from text, such as equipment name, fault type, component name, etc. Attribute extraction: Extract attribute information related to entities, such as equipment model, production date, fault phenomenon, etc. Relationship extraction: Identify the relationship between entities, such as the causal relationship between faults and causes, and the composition relationship between components.
[0138] Knowledge fusion: Due to the diversity of data sources, the extracted knowledge may be repeated or inconsistent. The purpose of knowledge fusion is to eliminate these ambiguities and form a unified and accurate knowledge representation. Specific methods include: Entity alignment: Determine whether entities in different data sources point to the same objective object. Attribute value filling: For different values of the same attribute in different data sources, make decisions based on the credibility of the data source and fill in the most accurate attribute value.
[0139] Knowledge processing: Knowledge processing is to further build the model layer of the knowledge graph based on knowledge extraction and fusion, including ontology construction and quality assessment. Specific steps may include: Ontology construction: Based on domain knowledge, define the entity type, attribute type and relationship type in the knowledge graph to form the ontology of the knowledge graph. Quality assessment: Perform quality assessment on the extracted and fused knowledge to ensure the accuracy and consistency of the knowledge.
[0140] Knowledge graph storage and query: Finally, the constructed knowledge graph is stored in a graph database management system, such as Neo4j, JanusGraph, etc., for subsequent query and application. At the same time, a query interface for the knowledge graph is also required so that users can easily retrieve and use the information in the knowledge graph.
[0141] Continuous updating and maintenance: The construction of a knowledge graph is not a one-time task, but requires continuous updating and maintenance as data is updated and domain knowledge develops. Specific methods include regularly updating data sources, optimizing knowledge extraction and fusion algorithms, and fixing errors in knowledge graphs.
[0142] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0143] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0144] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0145] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0146] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0147] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0148] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.
[0149] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. Methods for realizing remote monitoring of equipment based on cloud platform, Features: include, After collecting environmental condition data in the target area at the monitoring node, the environmental anomaly degree is constructed. , analyze and obtain the degree of environmental abnormality Correlation coefficient with equipment utilization , if the correlation coefficient If the relevant threshold is exceeded, a data collection instruction is issued to the outside; the utilization rate of the equipment is collected at each monitoring node, and the degree of environmental abnormality is Equipment utilization Perform linear normalization and map the corresponding data values to the interval According to the following method: ; Weight coefficient, , ,and , , is the number of monitoring nodes, For the The degree of environmental abnormality on the monitoring nodes, For the Equipment utilization on each monitoring node; A sensor network is deployed in the target area. Before sending the collected data to the cloud platform, the reading frequency of the collected data is constrained, and an encryption scheme is randomly selected from the pre-built encryption scheme library to encrypt the data to be sent. Use the trained abnormal data recognition model to identify abnormal data in the production status data of the production equipment. If abnormal data exists, build the alarm density in each sub-cycle based on the distribution status of the time node where the abnormal data was generated. And the warning threshold ; Among them, the alarm density Mark the sub-periods and set alarms based on the alarm density in each sub-period. Constructing alert thresholds , as follows: ; in, , is the number of sub-periods, For the The alarm density within a sub-cycle, is the mean value of alarm density; According to the alarm intensity With warning threshold The relationship between them is used to select the corresponding optimization response strategy for the production process of lithium batteries and related products. Below the warning threshold If the environment is abnormal Higher than expected to reduce environmental abnormality As the optimization target, the linear regression algorithm is used to optimize the production environment conditions in the production area; If the alarm intensity At the warning threshold If the equipment utilization rate of production equipment is Lower than expected; to improve equipment utilization As the optimization target, the genetic algorithm is used to optimize the operating parameters of the production equipment; If the alarm intensity Above the warning threshold , monitor and collect the operation and control data of production equipment, use the operation-related data of production equipment as input, use the trained fault identification model to identify faults, and issue fault maintenance instructions if there is an operation fault; The lithium battery production digital twin model simulates and tests the optimization response strategy, obtains the test data at each test node, and constructs the optimization coefficient , if the optimization coefficient If the optimization threshold is not exceeded, a reminder instruction is issued to the outside, where the production volume on each test node Sort by timeline, by production volume The change of generates the optimization coefficient corresponding to the optimization response strategy before or after the combination , as follows: ; in, is the production volume on the i-th test node, is the initial value of production volume, is the acceptable value for production volume; For the The optimal intermediate value, is its mean value; , is the number of test nodes, weight coefficient: , ,and .
2. The method for realizing remote monitoring of equipment based on a cloud platform according to claim 1, Features: The abnormal difference of environmental conditions on the monitoring nodes is used to construct the environmental abnormality degree on each monitoring node. , among which, for abnormal difference Perform linear normalization and map the corresponding data values to the interval According to the following method: ; in, , is the number of environmental condition parameters; is the abnormal difference of the i-th environmental condition parameter, is the acceptable value of abnormal difference, weight coefficient, , ,and .
3. The method for realizing remote monitoring of equipment based on a cloud platform according to claim 2, Features: After receiving the data collection instruction, a sensor network is deployed in the target area, and the sensor network is used to collect production status data in the target area; according to the correlation coefficient Constrain the frequency of reading the stored production status data, read the data at the reading nodes that meet the constraints, and send the read data to the cloud platform.
4. The method for realizing remote monitoring of equipment based on a cloud platform according to claim 3, characterized in that: in, The frequency of data reading is constrained as follows: ; Weight coefficient, , ; is the correlation coefficient, The number of nodes for data reading, It is Read nodes to The time interval between reading nodes, is the average value of the time interval.
5. The method for realizing remote monitoring of equipment based on a cloud platform according to claim 4, Features: When the production equipment is in production state, the production status data is collected in real time and summarized to generate a production status data set; Taking production status data as input, the trained abnormal data recognition model is used to identify abnormal data. If abnormal data exists, an alarm instruction is pushed to the outside. After receiving the alarm instruction, feature extraction is performed on the real-time and historical production status data to obtain the corresponding abnormal features; based on the correspondence between the abnormal features and the emergency strategies, the emergency strategy library outputs the corresponding emergency strategies.
6. The method for realizing remote monitoring of equipment based on a cloud platform according to claim 5, Features: Record the time node when the alarm instruction is received in the sub-cycle and use it as the alarm node to build the alarm density in each sub-cycle , as follows: ; Where: , weight coefficient, , ,and ; The value is 2.718; is the diameter of the subperiod, The weighted value of the i-th alarm node is the time interval from the i-th alarm node to the j-th alarm node.
7. The method for realizing remote monitoring of equipment based on a cloud platform according to claim 6, Features: Taking the fault maintenance of lithium battery production equipment as the target word, a knowledge graph of equipment maintenance is pre-built; After receiving the fault maintenance instruction, the fault maintenance features are obtained by extracting features from the relevant data of the production equipment operation, and the corresponding production equipment fault maintenance plan is output from the equipment maintenance knowledge graph to maintain the production equipment.
8. The method for realizing remote monitoring of equipment based on a cloud platform according to claim 7, Features: After collecting lithium battery production and operation data, a digital twin model of lithium battery production is constructed; Taking one or more combinations of optimized production environment conditions, optimized operating parameters and production equipment fault maintenance plans as input, the lithium battery production digital twin model tests it, and summarizes the collected test data to generate a production test data set.
