A Cloud Monitoring and Management Method, System and Device for a Lithium Electronic Battery Separator Equipment

Abstract

The present invention discloses a cloud monitoring and management method, system and device for a lithium electronic battery separator device, which relates to the technical field of device cloud monitoring and management. It monitors the environmental conditions in the target area in real time, identifies abnormal environments in the target area, and issues multi-level alarms to the outside if there are abnormalities in the environmental conditions in the target area. It analyzes the degree of influence of the environmental condition data on the product production volume. If the influence degree exceeds the expectation, it uses the trained adjustment automatic control model to control the environmental improvement equipment to optimize the environmental conditions in the target area. It identifies the operating status of the device based on the operating parameters of the device. If there are abnormalities in the operating status, it predicts and identifies potential faults of the device. If there are potential faults, it maintains the device when the device is in a shutdown state. By constructing a multi-level alarm mechanism, it adjusts the production process of the battery separator to achieve the monitoring and management of the battery separator device.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment cloud monitoring and management, and particularly to a cloud monitoring and management method, system and equipment for lithium-ion battery separator equipment. Background Art

[0002] Lithium-ion battery separator equipment, as the core equipment in lithium battery production, integrates all-round functions such as material handling, solution preparation, precision coating, high-efficiency curing, precise cutting and environmental protection packaging, ensuring the quality and safety of the separator as the key separator between the positive and negative electrodes of the battery. These devices not only realize the fully automated production process from raw materials to finished diaphragms, improve production efficiency and cost control, but also meet the growing demand for lithium battery performance in fields such as new energy vehicles, energy storage systems and power tools through high-precision technologies.

[0003] In the Chinese invention patent with the application publication number CN115857397A, a monitoring and management system for the production and processing of aluminum-air batteries is disclosed. The system includes a data acquisition module, an equipment on-line monitoring module and a general control module which are electrically connected; the data acquisition module is used to collect dynamic data in the production environment, as well as information on the performance of raw materials and finished batteries. According to the collected environmental dynamic data and the information on the performance of raw materials and finished products; by collecting dynamic data in the production environment, as well as information on the performance of raw materials and finished batteries, it is convenient to control the normal operation of the production and processing procedures. Through the equipment on-line monitoring module, the working states of environmental management equipment, processing equipment and conveying equipment are monitored, providing a prerequisite for the normal operation of the equipment. Through the coordination of the general control module, the orderly progress of production and processing is ensured.

[0004] Combined with the above application and the content in the prior art:

[0005] When producing lithium-ion battery separators through production equipment, in order to ensure product quality and reduce pollutant emissions, the operating status of the production equipment is usually monitored and managed in real time, and various control parameters of the production equipment are adjusted according to changes in the actual production process and production tasks.

[0006] In the existing cloud monitoring and management methods for lithium-ion battery separator equipment, after real-time monitoring of the operating data of the equipment, it is judged whether the equipment has an abnormality, and when an abnormality occurs, fault repair is carried out to ensure the normal operation of the equipment; however, when there are certain abnormalities in the environment within the production area, especially when the temperature and humidity fluctuate greatly within the area, and there are more dust or chemical pollutants in the production area, in this case, if the equipment is still in a long-term high-load operating state, the risk of equipment failure will increase significantly.

[0007] To this end, the present invention provides a cloud monitoring and management method, system and device for a lithium electronic battery separator device. Summary of the Invention

[0008] (I) Technical problems to be solved

[0009] In view of the deficiencies of the prior art, the present invention provides a cloud monitoring and management method, system and device for a lithium electronic battery separator device. By identifying abnormal environments in the target area, if the environmental conditions in the target area are abnormal, multi-level alarms are sent to the outside; the degree of influence of environmental condition data on product production volume is analyzed. If the influence degree exceeds the expectation, the trained adjustment automatic control model is used to control the environmental improvement device to optimize the environmental conditions in the target area; the operating status of the device is identified based on the various operating parameters of the device. If the operating status is abnormal, potential faults of the device are predicted and identified. If there are potential faults, the device is maintained when the device is in a shutdown state; by constructing a multi-level alarm mechanism, the production process of the battery separator is adjusted, thereby solving the technical problems raised in the background art.

[0010] (II) Technical solutions

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] A cloud monitoring and management method for a lithium electronic battery separator device includes: real-time monitoring of environmental conditions in the target area, identifying abnormal environments in the target area, and if the environmental conditions in the target area are abnormal, sending multi-level alarms to the outside;

[0013] Analyzing the degree of influence of environmental condition data on product production volume, and if the influence degree exceeds the expectation, using the trained adjustment automatic control model to control the environmental improvement device to optimize the environmental conditions in the target area;

[0014] Identifying the operating status of the device based on the various operating parameters of the device. If the operating status is abnormal, predicting and identifying potential faults of the device. If there are potential faults, maintaining the device when the device is in a shutdown state.

[0015] Further, using device-related data as input, after predicting and obtaining the operating load of the device, using a pre-trained genetic algorithm to optimize the working time and task allocation of the device;

[0016] Using a digital twin model for battery separator production to simulate and test the production process of the battery separator. If the difference between the obtained test emission data and the production emission data is greater than expected, optimizing the production process of the battery separator.

[0017] Furthermore, a sensor network is arranged within the target area. The sensor network conducts real-time monitoring of the environmental conditions within the target area, obtains the corresponding environmental condition data, and generates an environmental condition data set after summarization.

[0018] Using the environmental condition data as input, an abnormal environment recognition model after training is used for abnormal environment recognition. If there are abnormalities in the environmental conditions within the target area, a first-level alarm instruction is sent to the outside.

[0019] Furthermore, the time node when the first-level alarm instruction is received is used as an abnormal node. When the number of abnormal nodes within the abnormal observation period exceeds the expectation, an environmental abnormality degree is generated based on the abnormal nodes and the degree of environmental abnormality after each alarm instruction is issued; if the obtained environmental abnormality degree exceeds the expectation, a second-level alarm instruction is sent to the outside.

[0020] Furthermore, when the second-level alarm instruction is received or several first-level alarm instructions are continuously received, the environmental condition data, equipment operation data, and product production data are summarized as an equipment status data set, and the data in the equipment status data set are encrypted and then sent to the cloud data analysis platform.

[0021] Furthermore, taking the environmental condition data as the independent variable and the production volume as the dependent variable, multiple linear regression analysis is carried out to obtain the corresponding linear regression equation.

[0022] Taking the sum of the regression coefficients corresponding to each environmental condition parameter in the linear regression equation as the influence value, if the influence value exceeds the preset influence threshold, an automatic adjustment instruction is sent to the outside.

[0023] Furthermore, environmental improvement equipment is arranged within the target area. After receiving the automatic adjustment instruction, parameter thresholds are preset for each environmental condition, and the real-time environmental condition data within the target area is used as input to control the environmental improvement equipment.

[0024] Furthermore, various operation parameters of the equipment are recorded in real time. Taking the operation parameters as input, an abnormal state recognition model after training is used to identify the operation state of the equipment.

[0025] If there are abnormalities in the operation state of the equipment, using the operation data of the equipment as input, a trained fault prediction model is used to predict and identify potential faults of the equipment. If there are potential faults in the equipment, a maintenance instruction is sent to the outside.

[0026] Furthermore, after receiving the maintenance instruction, the maintenance frequency of the equipment is restricted, and the equipment is maintained at the maintenance nodes that meet the constraint conditions, and the detailed information of each maintenance is recorded and summarized to establish an equipment maintenance file.

[0027] Further, collect the operation data, production task data, and environmental condition data within the target area of the equipment, use them as inputs, and use the trained equipment operation load prediction model to predict the operation load of the equipment to obtain the operation load prediction value; taking reducing the equipment load operation as the optimization goal, using the operation load prediction value, operation data, production data, and environmental data of the equipment as inputs, use the pre-trained genetic algorithm to optimize the working time and task allocation of the equipment.

[0028] Further, pre-set the environmental conditions in the target area that are the same as the actual production scenario, and after setting the corresponding control parameters for the equipment, use the digital twin model for battery separator production to simulate and test the production process of the battery separator to obtain the test emission data during the production process.

[0029] Collect the production emission data in the actual production scenario, and after analyzing the similarity between the test emission data and the production emission data within the sub-cycle, obtain the corresponding emission similarity.

[0030] Further, after obtaining a continuous number of emission similarities, construct a similarity coefficient. If the similarity coefficient is lower than the similarity threshold, optimize each parameter of the battery separator production process.

[0031] A cloud monitoring and management system for a lithium-ion battery separator equipment, including an environmental anomaly recognition unit that monitors the environmental conditions in the target area in real time, recognizes abnormal environments in the target area, and if there are abnormalities in the environmental conditions in the target area, sends multi-level alarms to the outside.

[0032] An environmental regulation unit that analyzes the degree of influence of environmental condition data on product production volume. If the degree of influence exceeds the expectation, use the trained regulation automatic control model to control the environmental improvement equipment to optimize the environmental conditions in the target area.

[0033] A fault prediction unit that identifies the operation state of the equipment based on various operation parameters of the equipment. If there are abnormalities in the operation state, predict and identify potential faults of the equipment. If there are potential faults, maintain the equipment.

[0034] A load optimization unit that uses the equipment-related data as inputs, and after predicting the operation load of the equipment, uses the pre-trained genetic algorithm to optimize the working time and task allocation of the equipment.

[0035] A test unit that uses the digital twin model for battery separator production to simulate and test the production process of the battery separator. If the difference between the obtained test emission data and the production emission data is greater than expected, optimize the production process of the battery separator.

[0036] A cloud monitoring and management device for a lithium-ion battery separator equipment, including at least one processor.

[0037] A memory for storing executable instructions, which are executed by the at least one processor to cause the at least one processor to perform the steps of a cloud monitoring and management method for a lithium-ion battery separator device.

[0038] A computer-readable storage medium stores a computer program, and the computer program is executed by a processor to perform the steps of a cloud monitoring and management method for a lithium-ion battery separator device.

[0039] (III) Beneficial effects

[0040] The present invention provides a cloud monitoring and management method, system and device for a lithium-ion battery separator device, having the following beneficial effects:

[0041] 1. When abnormal environmental conditions occur in the target area, the abnormal environmental conditions are processed in a timely manner to avoid the impact of abnormal environmental conditions on the production process; a secondary alarm instruction is constructed based on receiving several primary alarm instructions in succession to implement a multi-level alarm mechanism, and the abnormal environmental conditions in the target area are processed hierarchically to avoid the long-term impact of abnormal environmental conditions on the production state.

[0042] 2. Determine whether the environmental conditions have a certain impact on the production state of the device, and when there is an impact, the environmental conditions in the target area can be adjusted to ensure the production state.

[0043] 3. Use the trained adjustment automatic control model to control the environmental improvement device, automatically adjust the environmental condition parameters in the target area, and achieve automatic response when receiving an alarm instruction, which can reduce the impact of abnormal environmental conditions on the battery separator and realize the automatic adjustment of the battery separator production environment.

[0044] 4. By monitoring the changes in operating parameters, identify the abnormal operating state of the device, and when the device is operating abnormally, it can be processed in a timely manner.

[0045] 5. Identify potential operating faults of the device based on the obtained prediction data. If potential faults are identified, maintenance can be carried out in a timely manner to ensure the normal operation of the device. The maintenance frequency of the device is restricted by the degree of the fault, making the maintenance frequency of the device more reasonable, and avoiding the negative impact of over-maintenance on the actual production process.

[0046] 6. Use the trained device operating load prediction model to predict the operating load of the device. If the device has been operating at a high load, the abnormal operating state of the device will continue, and it is difficult to achieve the expected effect when executing the preset control conditions, which affects the actual production of the device.

[0047] 7. By allocating and adjusting the original production tasks, reducing the operating load of the current equipment, optimizing the working state of the equipment, the risk of equipment abnormalities can be reduced, and the continuity of the production state can be ensured; judging the necessity of process optimization, reducing the ineffective optimization process, optimizing the production process of the battery separator, and realizing the automatic control and adjustment of the battery separator production equipment.

[0048] 8. By constructing a multi-level alarm mechanism and a multi-level emergency handling mechanism, adjusting the current production process of the battery separator in different aspects and levels, realizing the monitoring and management of the battery separator equipment, with less pollution emissions, lower risk of equipment abnormalities, and better actual monitoring and management effects. Description of the Drawings

[0049] Figure 1 It is a schematic flow chart of the cloud monitoring and management method of the present invention;

[0050] Figure 2 It is a schematic structural diagram of the cloud monitoring and management system of the present invention;

[0051] Figure 3 It is a schematic structural diagram of the cloud monitoring and management equipment of the present invention. Detailed Embodiments

[0052] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0053] Please refer to Figure 1 , the present invention provides a cloud monitoring and management method for lithium-ion battery separator equipment, including,

[0054] Step 1: Real-time monitor the environmental conditions in the target area, identify abnormal environments in the target area, and send multi-level alarms to the outside if there are abnormalities in the environmental conditions in the target area;

[0055] The content of the first step is as follows:

[0056] Step 101: Take the area where the device is located as the target area, and deploy a sensor network in the target area. The sensor network includes temperature sensors, humidity sensors, air quality sensors, etc. The sensor network monitors the environmental conditions in real time in the target area to obtain corresponding environmental condition data. For example, environmental temperature, environmental humidity, dust concentration, VOCs, light intensity, noise level, device vibration, and air pressure, etc. After summarizing the obtained environmental condition data, an environmental condition data set is generated.

[0057] Step 102: Train a convolutional neural network with the labeled sample data to obtain a trained abnormal environment recognition model. Use the real-time environmental condition data as input, and use the trained abnormal environment recognition model to identify abnormal environments. If there are abnormalities in the environmental conditions in the target area, send a first-level alarm instruction to the outside.

[0058] During use, after obtaining the environmental condition data by real-time monitoring in the target area, when abnormalities occur in the environmental conditions in the target area, promptly process the abnormal environmental conditions to avoid the impact of abnormal environmental conditions on the production process.

[0059] Step 103: Preset an abnormal observation period, take the time node when the first-level alarm instruction is received as the abnormal node. When the number of abnormal nodes within the abnormal observation period exceeds the expectation, based on the abnormal nodes and the degree of abnormality of the environmental conditions after each alarm instruction is issued. Among them, the degree of abnormality can be determined by the sum of the difference ratios between each environmental condition parameter and the corresponding environmental parameter threshold; generate the environmental abnormality degree in the following manner :

[0060]

[0061] In the formula: n is the number of environmental parameters, is the i th environmental parameter at time t The actual measured value, is the i th qualified value of the environmental parameter, is the i th weight of the environmental parameter, and the value falls within , is the time decay factor, , is the j th Fourier transform of the environmental parameter, m is the number of environmental parameters that need to be Fourier-transformed; The value falls within ; K represents the length of the time window used to calculate the environmental abnormality degree;

[0062] Set an abnormal threshold in advance based on historical data and management expectations for environmental conditions; if the obtained environmental abnormality exceeds the abnormal threshold, it indicates that the environmental abnormality frequency and degree are relatively high in the target area at the current stage. At this time, send a secondary alarm instruction to the outside;

[0063] When in use, combine the content in steps 101 to 103:

[0064] Considering that production personnel cannot immediately adjust the abnormal environment in the target area, or the duration of abnormal environmental conditions is relatively short and the negative impact is relatively small. In this scenario, build a secondary alarm instruction based on receiving several primary alarm instructions continuously, implement a multi-level alarm mechanism, and handle it hierarchically when the environmental conditions in the target area are abnormal, so as to avoid the long-term impact of abnormal environmental conditions on the production status.

[0065] In the existing cloud monitoring and management method for lithium-ion battery separator equipment, after real-time monitoring of the operation data of the equipment, judge whether the equipment has abnormalities, and perform fault repair when abnormalities occur to ensure the normal operation of the equipment. However, there are certain abnormalities in the environment in the production area, especially when the temperature and humidity fluctuations in the area are relatively large, and the dust or chemical pollutants in the production area are relatively large. In this case, if the equipment is still in a long-term high-load operation state, the risk of equipment failure will increase significantly, and it will even have a certain impact on the production quality of the final product and pollution emissions.

[0066] Step 2: Analyze the degree of influence of environmental condition data on product production volume. If the degree of influence exceeds the expectation, use the trained adjustment automatic control model to control the environmental improvement equipment and optimize the environmental conditions in the target area;

[0067] The said step 2 includes the following content:

[0068] Step 201: When receiving a secondary alarm instruction or receiving several primary alarm instructions continuously, summarize the environmental condition data, equipment operation data, and product production data collected by the sensor network as the equipment status data set. After encrypting each data in the equipment status data set, send the encrypted data to the cloud data analysis platform;

[0069] When in use, on the basis of completing the collection of various data, encrypting the collected data can ensure the security of the data.

[0070] Step 202: Using the environmental condition data as the independent variable and the production volume of the product as the dependent variable, perform multiple linear regression analysis to obtain the corresponding linear regression equation; taking the sum of the regression coefficients corresponding to each environmental condition parameter in the linear regression equation as the influence value, if the influence value exceeds the preset influence threshold, it indicates that the environmental conditions have a greater impact on the production volume, and an automatic adjustment instruction is sent to the outside;

[0071] During use, judge whether the environmental conditions have a certain impact on the production status of the equipment through multiple linear regression analysis. If there is an impact, the environmental conditions in the target area can be adjusted to ensure the production status;

[0072] Step 203: Arrange air purification equipment in the target area, such as high-efficiency air filters, activated carbon adsorption devices, and photocatalytic oxidation equipment, and equip high-efficiency air-conditioning systems and humidification / dehumidification equipment, etc.; regard the above-mentioned equipment as environmental improvement equipment and mark its location in the target area;

[0073] Train the convolutional neural network with the marked sample data to obtain the trained adjustment automatic control model;

[0074] After receiving the automatic adjustment instruction, preset the corresponding parameter thresholds for the environmental conditions in the target area. Using the real-time environmental condition data in the target area as the input, use the trained adjustment automatic control model to control the environmental improvement equipment to optimize the environmental conditions in the target area;

[0075] During use, combine the content in Steps 201 to 203:

[0076] When the environmental conditions in the target area are abnormal and affect the production status of the equipment, based on the preset parameter thresholds, use the trained adjustment automatic control model to control the environmental improvement equipment, automatically adjust the environmental condition parameters in the target area, and achieve automatic response when receiving the alarm instruction, which can reduce the impact of abnormal environmental conditions on the battery separator and realize the automatic adjustment of the battery separator production environment.

[0077] Step 3: Identify the operating status of the equipment based on the operating parameters of the equipment. If the operating status is abnormal, predict and identify potential faults of the equipment. If there are potential faults, maintain the equipment when the equipment is in a shutdown state;

[0078] The said Step 3 includes the following content:

[0079] Step 301: Record various operating parameters of the device in real time within a preset observation period, such as startup time, stop time, load rate, temperature, current, voltage and other parameters; train a convolutional neural network with the labeled sample data to obtain a trained abnormal state recognition model;

[0080] Use the operating parameters as inputs, and use the trained abnormal state recognition model to identify the operating state of the device. If the operating state of the device is abnormal, send an external fault prediction instruction;

[0081] When in use, on the basis of controlling the abnormal environmental conditions in the target area, monitor the changes in the operating parameters to identify the abnormal operating state of the device. When the device is operating abnormally, it can be processed in a timely manner;

[0082] Step 302: Train a machine learning algorithm with the labeled sample data to obtain a trained fault prediction model; after receiving a fault prediction instruction, use the operating data of the device as inputs, and use the trained fault prediction model to predict and identify potential faults of the device. If the device has potential faults, send an external maintenance instruction for early maintenance;

[0083] Step 303: After receiving a maintenance instruction, maintain the device when it is in a shutdown state, including regular inspections, lubrication, replacement of vulnerable parts, etc.; constrain the maintenance frequency of the device The constraint method is as follows:

[0084]

[0085] In the formula: is the weight coefficient, , n is the number of fault nodes where faults are predicted to occur, is the i th fault node to the j th fault node time interval, is the average time interval;

[0086] Maintain the device at the maintenance nodes that meet the constraint conditions, and record the detailed information of each maintenance, such as maintenance date, maintenance reason, maintenance content, repair measures, test results and device health status, etc. After summarization, establish a device maintenance file;

[0087] When in use, combine the content in Steps 301 to 303:

[0088] When the device generates several anomalies continuously, it indicates a relatively high risk of device failure. At this time, based on the obtained prediction data, identify the possible operating faults of the device. If potential faults are identified, maintenance can be carried out in a timely manner to ensure the normal operation of the device. At the same time, the maintenance frequency of the device is restricted according to the degree of the fault, making the maintenance frequency of the device more reasonable and avoiding the negative impact of over-maintenance on the actual production process.

[0089] Step Four: Use the device-related data as input. After predicting and obtaining the operating load of the device, use the pre-trained genetic algorithm to optimize the working time and task allocation of the device.

[0090] The said Step Four includes the following contents:

[0091] Step 401: Collect the operating data of the device, including parameters such as start time, stop time, load rate, temperature, current, and voltage; collect the production task data of the device, including production plans, task completion times, product quantities, and qualities; environmental condition data within the target area, including temperature, humidity, and air quality, etc.

[0092] Train the LSTM neural network with the labeled sample data to obtain the trained device operating load prediction model; use the operating data, environmental condition data, and production task data of the device as input, and use the trained device operating load prediction model to predict the operating load of the device to obtain the operating load prediction value.

[0093] When in use, when the operating state of the device is abnormal, considering that the long-term high-load operation of the device will increase the risk of abnormal operation of the device, use the trained device operating load prediction model to predict the operating load of the device. If the device still remains in high-load operation all the time, the abnormal operating state of the device will still continue. When executing the preset control conditions, it is difficult to achieve the expected effect and it will affect the actual production of the device.

[0094] Step 402: Take making the operating load of the device fluctuate within a preset range and avoiding long-term high-load operation as the optimization goal; use the operating load prediction value, operating data, production data, and environmental data of the device as input, and use the pre-trained genetic algorithm to optimize the working time and task allocation of the device, and adjust the production plan and device operating time in real time to ensure the flexibility and response speed of the production process.

[0095] When in use, combine the contents in Steps 401 to 402:

[0096] By optimizing the working tasks and working hours of the equipment through an optimization algorithm, when there are several similar devices, the original production tasks are allocated and adjusted to reduce the operating load of the current device, optimize the working state of the equipment, reduce the risk of equipment anomalies, and ensure the continuity of the production state.

[0097] Step Five: Use the digital twin model of battery separator production to simulate and test the production process of the battery separator. If the difference between the obtained test emission data and the production emission data is greater than expected, optimize the production process of the battery separator;

[0098] The above Step Five includes the following content:

[0099] Step 501: Train a machine learning algorithm with sample data to construct a digital twin model of battery separator production; pre-set environmental conditions identical to the actual production scenario in the target area, and after setting corresponding control parameters for the equipment, use the digital twin model of battery separator production to simulate and test the production process of the battery separator, and obtain the test emission data during the production process, such as: real-time monitoring of emission data such as waste gas and wastewater, and real-time monitoring of the emission of harmful substances during the production process, such as waste gas, wastewater, and solid waste;

[0100] Collect the production emission data in the actual production scenario. After analyzing the similarity between the test emission data and the production emission data in the sub-period, obtain the corresponding emission similarity.

[0101] In use, considering that abnormal environments and equipment failures will all have a certain impact on the production state, especially when it is difficult for the control parameters of the equipment to be consistent with the actual settings, there will also be a certain degree of difference in the production products during the production process. For example, more pollutants are generated than expected. Therefore, after improving the environmental conditions and equipment, it is also necessary to adjust the production process.

[0102] Step 502: Construct a similarity coefficient after obtaining several consecutive emission similarities , and under the preset control conditions, judge the similarity between the expected emission and the actual emission based on the similarity coefficient, where

[0103] Perform linear normalization on the emission similarity and map the corresponding data values to the interval according to the following formula:

[0104]

[0105] where is the emission similarity in the i th sub-period, is the corresponding mean value, is the number of sub - cycles, is the weight coefficient, ; the weight coefficient remains the same as the previous value;

[0106] According to historical data and the expected management of pollutant emissions during the production of battery diaphragms by the equipment, a similarity threshold is set in advance;

[0107] If the similarity coefficient is lower than the similarity threshold, it indicates that under the preset control conditions, the pollutant emissions of the battery diaphragm are inconsistent with the expectations, may be more than expected, and the emissions pollution is more serious. In addition to controlling the equipment, the current production process is optimized. For example, through multi - objective optimization algorithms or simulated annealing algorithms, etc., on the basis of combining the digital twin model of battery diaphragm production, various parameters of the battery diaphragm production process are optimized. Through the optimization of the production process, the emission pollution caused during the production of battery diaphragms is ultimately reduced.

[0108] When in use, combine the content in steps 501 and 502:

[0109] By constructing a similarity coefficient based on a number of consecutive emission similarity degrees , on the basis of simulation tests, according to the similarity coefficient judge the necessity of process optimization, reduce the ineffective optimization process, and ultimately realize the optimization of the battery diaphragm production process, and realize the automatic control and adjustment of the battery diaphragm production equipment.

[0110] Combining the above content, when considering that there may be more pollutants in the current production process, by constructing a multi - level alarm mechanism and a multi - level emergency treatment mechanism, adjust the current production process of battery diaphragms in different aspects and levels, realize the monitoring and management of battery diaphragm equipment, with less pollution emissions, lower risk of equipment anomalies, and better actual monitoring and management effects.

[0111] Please refer to Figure 2 , the present invention provides a cloud monitoring and management system for lithium - ion battery diaphragm equipment, including,

[0112] An environmental anomaly identification unit, which monitors the environmental conditions in the target area in real time, identifies abnormal environments in the target area, and issues multi - level alarms to the outside if there are abnormal environmental conditions in the target area;

[0113] An environmental regulation unit, which analyzes the degree of influence of environmental condition data on the product production volume. If the influence degree exceeds the expectation, it controls the environmental improvement equipment using the trained adjustment automatic control model to optimize the environmental conditions in the target area;

[0114] A fault prediction unit identifies the operating state of a device based on various operating parameters of the device. If the operating state is abnormal, it predicts and identifies potential faults of the device. If there are potential faults, it maintains the device.

[0115] A load optimization unit takes device-related data as input. After predicting and obtaining the operating load of the device, it uses a pre-trained genetic algorithm to optimize the working time and task allocation of the device.

[0116] A testing unit uses a digital twin model of battery separator production to simulate and test the production process of battery separators. If the difference between the obtained test emission data and the production emission data is greater than expected, it optimizes the production process of battery separators.

[0117] Please refer to Figure 3 , based on the same inventive concept, according to another aspect of the present invention, the present invention further provides a cloud monitoring and management device for a lithium-ion battery separator device, including at least one processor;

[0118] A memory for storing executable instructions, which are executed by the at least one processor to enable the at least one processor to execute the steps of the cloud monitoring and management method for a lithium-ion battery separator device.

[0119] Please refer to Figure 3 , based on the same inventive concept, according to another aspect of the present invention, the present invention further provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to execute the steps of the cloud monitoring and management method for a lithium-ion battery separator device.

[0120] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using 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 processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. 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 (such as infrared, wireless, microwave, etc.) means. 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 includes one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0121] Those of ordinary skill in the art will appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0122] 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 foregoing method embodiments and will not be repeated here.

[0123] 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 merely illustrative. For example, the division of the units is only for some logical function divisions, and there can be other division methods in actual implementation. For example, 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 displayed or discussed couplings, direct couplings, or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0124] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0125] In addition, in each embodiment of the present application, each functional unit may be integrated in a processing unit, may exist separately physically for each unit, or two or more units may be integrated in one unit.

[0126] 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 such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0127] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A cloud monitoring and management method for a lithium - electron battery separator device, characterized in that: Including, Real-time monitor the environmental conditions in the target area, identify abnormal environments in the target area. If there are abnormalities in the environmental conditions in the target area, send multi-level alarms to the outside; if there are abnormalities in the environmental conditions in the target area, send a first-level alarm instruction to the outside. Take the time node when the first-level alarm instruction is received as an abnormal node. When the number of abnormal nodes within the abnormal observation period exceeds the expectation, generate an environmental abnormality degree based on the abnormal nodes and the degree of environmental abnormality after each alarm instruction is issued. If the obtained environmental abnormality degree exceeds the expectation, send a second-level alarm instruction to the outside. Analyze the impact degree of environmental condition data on the product production volume. If the impact degree exceeds the expectation, use the trained adjustment automatic control model to control the environmental improvement equipment and optimize the environmental conditions in the target area. If a second-level alarm instruction is received or several first-level alarm instructions are continuously received, summarize the environmental condition data, equipment operation data, and product production data as the equipment status data set, encrypt each data in the equipment status data set, and send it to the cloud data analysis platform. Perform multiple linear regression analysis with environmental condition data as the independent variable and production volume as the dependent variable to obtain the corresponding linear regression equation. Take the sum of the regression coefficients corresponding to each environmental condition parameter in the linear regression equation as the impact value. If the impact value exceeds the preset impact threshold, send an automatic adjustment instruction to the outside to control the environmental improvement equipment. Identify the operating status of the equipment based on the operating parameters of the equipment. If the operating status is abnormal, predict and identify potential faults of the equipment. If there are potential faults, maintain the equipment when the equipment is in a shutdown state. Use the equipment-related data as input. After predicting the operating load of the equipment, use the pre-trained genetic algorithm to optimize the working time and task allocation of the equipment. Use the digital twin model of battery separator production to simulate and test the production process of battery separator. If the difference between the obtained test emission data and the production emission data is greater than the expectation, optimize the production process of battery separator.

2. The cloud monitoring and management method according to claim 1, characterized in that: Arrange a sensor network in the target area. The sensor network performs real-time monitoring of environmental conditions in the target area, obtains the corresponding environmental condition data, and generates an environmental condition data set after summarization. Use the trained abnormal environment recognition model to recognize abnormal environments with environmental condition data as input.

3. The cloud monitoring and management method according to claim 2, characterized in that: Arrange environmental improvement equipment in the target area. After receiving the automatic adjustment instruction, preset parameter thresholds for each environmental condition, and use the real-time environmental condition data in the target area as input to control the environmental improvement equipment. Record the operating parameters of the device in real time. Using the operating parameters as input, identify the operating state of the device using the trained abnormal state recognition model. If the operating state of the device is abnormal, use the operating data of the device as input, and use the trained fault prediction model to predict and identify potential faults of the device. If the device has potential faults, send a maintenance instruction to the outside.

4. The cloud monitoring and management method according to claim 3, wherein: After receiving the maintenance instruction, constrain the maintenance frequency of the device, perform maintenance on the device at the maintenance nodes that meet the constraint conditions, and record the detailed information of each maintenance. After summarization, establish a device maintenance file. Collect the operating data, production task data, and environmental condition data in the target area of the device. Using them as input, use the trained device operating load prediction model to predict the operating load of the device and obtain the operating load prediction value. Taking reducing the device load operation as the optimization goal, using the operating load prediction value, operating data, production data, and environmental data of the device as input, use the pre-trained genetic algorithm to optimize the working time and task allocation of the device.

5. The cloud monitoring and management method according to claim 4, wherein: Pre-set the environmental conditions in the target area that are the same as the actual production scenario, and set corresponding control parameters for the device. Then use the digital twin model of battery separator production to simulate and test the production process of the battery separator, and obtain the test emission data during the production process. Collect the production emission data in the actual production scenario. After analyzing the similarity between the test emission data and the production emission data in the sub-cycle, obtain the corresponding emission similarity. After obtaining a continuous number of emission similarities, construct a similarity coefficient. If the similarity coefficient is lower than the similarity threshold, optimize each parameter of the battery separator production process.

6. A cloud monitoring and management system for a lithium - ion battery separator device, applying the cloud monitoring and management method described in any one of claims 1 to 5, characterized in that: Including, An environmental anomaly recognition unit that monitors the environmental conditions in the target area in real time, recognizes abnormal environments in the target area, and sends multi-level alarms to the outside if the environmental conditions in the target area are abnormal. An environmental regulation unit that analyzes the influence degree of environmental condition data on the product production volume. If the influence degree exceeds the expectation, use the trained regulation automatic control model to control the environmental improvement equipment and optimize the environmental conditions in the target area. A fault prediction unit that identifies the operating state of the device based on the operating parameters of the device. If the operating state is abnormal, predict and identify potential faults of the device. If there are potential faults, maintain the device. A load optimization unit that uses the device-related data as input. After predicting the operating load of the device, use the pre-trained genetic algorithm to optimize the working time and task allocation of the device. A test unit that uses the digital twin model of battery separator production to simulate and test the production process of the battery separator. If the difference between the obtained test emission data and the production emission data is greater than expected, optimize the production process of the battery separator.

7. A cloud monitoring and management device for a lithium-ion battery separator device, characterized in that: Including, At least one processor; A memory for storing executable instructions, the instructions being executed by at least one of the processors to cause at least one of the processors to perform the steps of the method according to any one of claims 1 to 5.

Images