A method for realizing automatic mixing of materials in intelligent manufacturing

Through the automatic batching and mixing zone in intelligent manufacturing, using precise weighing and environmental monitoring technology, the safety risks and low efficiency problems in traditional artificial batching and mixing processes are solved, and the efficiency and safety of lithium battery electrode sheets are achieved. Production improves product quality and production efficiency.

CN118113000BActive Publication Date: 2024-11-15CHENGDU SHUZHI CARBON TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410141177.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-31
Publication Date
2024-11-15
Estimated Expiration
2044-01-31

AI Technical Summary

Technical Problem

Traditional artificial ingredients and mixing processes pose safety risks, low production efficiency and difficult to ensure product quality in lithium battery manufacturing.

Method used

Using the automatic ingredient zone in intelligent manufacturing, precise and fast ingredient and mixing are achieved through weighing equipment, environmental monitoring equipment and intelligent calibration equipment. The weighing data is corrected using filtering algorithms, compensation algorithms and adaptive algorithms to obtain the ingredient quality evaluation coefficient. and mixing quality evaluation coefficient, adjust ingredients and mixing processes in real time.

Benefits of technology

It improves the efficiency and product quality of electrode sheet production, reduces the cost and safety risks of lithium battery production, provides risk control and management decision support, and enhances market competitiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118113000B_ABST
    Figure CN118113000B_ABST
Patent Text Reader

Abstract

The invention discloses a method for realizing automatic mixing of materials in intelligent manufacturing, and specifically relates to the technical field of electrode sheet manufacturing, comprising: obtaining the degree of accuracy loss of a weighing device, a reliability index of a batching device under a standard environment, and a reliability index of a batching device under a non-standard environment by monitoring and analyzing an automatic batching area before automatic batching; obtaining a batching quality assessment coefficient Pz of the automatic batching area based on the degree of accuracy loss of the weighing device, the reliability index of the batching device under a standard environment, and the reliability index of the batching device under a non-standard environment; taking corresponding measures based on the relationship between the degree of accuracy loss of the weighing device, the reliability index of the batching device under a standard environment, the reliability index of the batching device under a non-standard environment, the batching quality assessment coefficient, and a preset value; realizing accurate, fast, and real-time batching control; improving the efficiency and product quality of electrode sheet production, and reducing the production cost and safety risks of lithium batteries.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electrode sheet manufacturing, and more specifically, to a method for realizing automatic material mixing in intelligent manufacturing. Background Art

[0002] The preparation process of lithium battery materials is quite complicated and requires multiple steps to complete. Temperature, humidity, and pressure parameters need to be controlled during the preparation process to ensure product quality and consistency. The quality of the electrode slurry of lithium battery materials affects battery performance. The electrode slurry preparation process is: mix the electrode active material, binder, and solvent together, and form a slurry after stirring and dispersing. Among them, the positive electrode slurry usually includes lithium salt, conductive agent, binder, and positive electrode material, while the negative electrode slurry is mainly composed of negative electrode material, conductive agent, and binder.

[0003] The traditional manual batching and mixing process requires a lot of manual operation, and companies need to hire a large number of workers. There are also certain safety risks, which leads to the fact that the safety and stability of battery production cannot be guaranteed. The performance and safety of the battery are directly affected by the quality of batching and mixing. The traditional mixing process relies on manual operation, which is not only time-consuming and labor-intensive, but also difficult to ensure accuracy.

[0004] Therefore, with the continuous development of battery manufacturing technology, the pursuit of production efficiency and product quality is getting higher and higher, and the application prospects of automatic mixing in the battery manufacturing industry are very broad. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method for realizing automatic compounding of materials in intelligent manufacturing to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: A method for realizing automatic compounding in intelligent manufacturing, comprising the following steps:

[0007] Analysis of automatic batching area: Through monitoring and analysis of the automatic batching area, the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, and the batching reliability index Nst_p under non-standard environment are obtained;

[0008] Evaluation of automatic batching area: Based on the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under the standard environment, and the batching reliability index Nst_p under the non-standard environment, the batching quality evaluation coefficient Pz of the automatic batching area is obtained;

[0009] Judgment of automatic batching area: take corresponding measures based on the relationship between the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, the batching reliability index Nst_p under non-standard environment, the batching quality assessment coefficient Pz and the preset value;

[0010] Automatic weighing and batching: According to the preset formula ratio, the raw materials are weighed and batched in the automatic batching area, and the preset weight of the ingredients is obtained through weighing equipment, environmental monitoring equipment, and intelligent calibration equipment, and the preset weight of the ingredients is transmitted to the automatic mixing area through material conveying equipment;

[0011] Execution of automatic mixing: receiving materials delivered from the automatic batching area, mixing the materials together in a preset order and under preset process conditions, forming electrode slurry after stirring and dispersing, and completing automatic mixing.

[0012] Preferably, the automatic batching area includes weighing equipment, environmental monitoring equipment, intelligent calibration equipment, and material conveying equipment; the weighing equipment is used to weigh the weight of the material, automatically record the weighing data, and transmit the collected weighing data to the intelligent calibration equipment; the environmental monitoring equipment is used to collect weighing environmental parameters, including temperature, humidity, vibration amplitude, and vibration frequency, and transmit the collected environmental data to the intelligent calibration equipment; the intelligent calibration equipment corrects the weighing data based on the collected environmental data, and outputs the corrected material weight; the material output equipment is used to transmit the weighed material to the automatic mixing area.

[0013] Preferably, the intelligent calibration device corrects the weighing data based on one or a combination of filtering algorithm, compensation algorithm, and adaptive algorithm; reduces noise and interference in the weighing data through the filtering algorithm; corrects weighing errors caused by temperature, humidity, vibration frequency, vibration amplitude, and time through the compensation algorithm, and the compensation algorithm includes linear compensation and nonlinear compensation algorithms. Nonlinear compensation is performed on the weighing data through machine learning, and errors in the weighing data are predicted and corrected by training the machine learning model; the adaptive algorithm automatically adjusts parameters according to changes in the environment or equipment status to maintain weighing accuracy.

[0014] Preferably, the process of obtaining the ingredient quality assessment coefficient Pz includes the following steps:

[0015] The average accuracy of the weighing equipment is obtained by weight calibration. After several weight calibrations, the actual accuracy of the weighing equipment is obtained by taking the average. The accuracy loss degree Js of the weighing device is calculated, where yj represents the preset accuracy of the weighing device and sj represents the actual accuracy of the weighing device;

[0016] The batching reliability index is obtained by conducting a pre-batch test under standard conditions. Assume that there are m types of batching required, i represents the batching number, the theoretical batching weight of the i-th batching is lzi, and the actual weighing weight of the i-th batching is szi; through the formula Obtain batching reliability parameters under standard environment, perform pre-batch several times, obtain several groups of batching reliability parameters, and obtain batching reliability index St_p under standard environment by averaging;

[0017] The batching reliability index is obtained by conducting a pre-batch test in a non-standard environment, and the test environment parameter combination is obtained based on the actual batching environment; the test environment is built based on the test environment parameter combination, and the batching reliability index Nst_p in the non-standard environment is obtained by analyzing the test results;

[0018] Based on the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, and the batching reliability index Nst_p under non-standard environment, the formula Get the batching quality assessment coefficient Pz of the automatic batching process,

[0019] Among them, 0<δ1<1, 0<δ2<1, and δ1+δ2=1.0, δ1 and δ2 are the ingredient quality assessment coefficient Pz obtained by weight calculation.

[0020] Preferably, the process of obtaining the batching reliability index Nst_p in a non-standard environment includes the following steps:

[0021] The maximum and minimum values ​​of temperature, humidity, vibration amplitude and vibration frequency in the automatic batching area are obtained, and several groups of parameters of temperature, humidity, vibration amplitude and vibration frequency are obtained through gradient value selection; after random permutation and combination, n groups of test environment parameter combinations are generated; for example, temperature, humidity, vibration amplitude and vibration frequency are each divided into 4 gradients, and a maximum of 256 different test environments are generated;

[0022] Build a test environment for weighing tests, record the environmental parameters of each test, and record the weighing data of each test;

[0023] Analyze the recorded environmental parameters to obtain the environmental anomaly index for each test, with j representing the test number, and the formula Get the environmental anomaly description parameters of the test environment, where hxc represents the test value of the environmental parameter, hx0 represents the preset standard environmental parameter, and μ represents the influencing factor of the specific type of environmental parameter; the environmental anomaly description parameters corresponding to the temperature, humidity, vibration amplitude, and vibration frequency in the jth test are recorded as hy1, hy2, hy3, and hy4 respectively, and the formula is used Calculate the j-th test environment abnormality index hyj;

[0024] By formula Obtain the batching reliability index Nst_p under non-standard environment, where wci represents the error degree of the jth test and n represents the number of tests.

[0025] Preferably, when the precision loss degree Js of the weighing equipment exceeds the preset value tha1, it indicates that the precision of the weighing equipment is abnormal, and an early warning is issued to the management personnel to remind them to repair and maintain the weighing equipment; when the batching reliability index St_p under the standard environment is lower than the preset value tha2, it indicates that the automatic batching area is abnormal, and an early warning is issued to the management personnel to remind them to inspect the automatic batching area; when the batching reliability index Nst_p under the non-standard environment is lower than the preset value tha3, it indicates that there is an abnormality in the environmental monitoring equipment or the intelligent calibration equipment, and the management personnel are reminded to debug the environmental monitoring equipment or the intelligent calibration equipment; when the batching quality evaluation coefficient Pz of the automatic batching process does not meet the preset Pz 预 , indicating that there is a risk of abnormal operation in the automatic batching area, warning the management personnel and prompting them to terminate the automatic batching measures.

[0026] Preferably, before the automatic mixing is performed, the steps of automatic mixing area analysis, automatic mixing area evaluation, and automatic mixing area judgment are included, wherein the automatic mixing area analysis: analyzing the equipment in the automatic mixing area, obtaining the abnormal accuracy description parameters and failure rate of the automatic mixing equipment;

[0027] Automatic mixing area evaluation: The mixing quality evaluation coefficient Hz is obtained by joint analysis based on the automatic mixing equipment accuracy anomaly description parameters, failure rate, mixing equipment accuracy anomaly evaluation index HJ, and automatic mixing area failure description index Gm;

[0028] Automatic mixing area judgment: When the mixing equipment accuracy abnormality evaluation index HJ, the automatic mixing area fault description index Gm, and the mixing quality evaluation coefficient Hz all meet the preset conditions, proceed to the next step; otherwise, debug the automatic mixing equipment until it meets the preset requirements.

[0029] Preferably, the mixture quality assessment coefficient Hz is obtained as follows:

[0030] The accuracy abnormality description parameters of the automatic mixing area including the discharge equipment, stirring equipment, and environmental parameter maintenance equipment are obtained respectively. After linear normalization, the accuracy abnormality description parameters of the discharge equipment, the accuracy abnormality description parameters of the stirring equipment, and the accuracy abnormality description parameters of the environmental parameter maintenance equipment are recorded as Fm, Jm, and Hm, respectively. The abnormal evaluation index HJ of mixing equipment accuracy is calculated;

[0031] The operation data of the automatic mixing area is analyzed, and the fault identification conditions of the discharge equipment, the stirring equipment, and the environmental parameter maintenance equipment are set respectively. The fault identification conditions at least include the discharge sequence error, the stirring time error, and the stirring frequency error. The discharge equipment fault frequency is recorded as gp1, the stirring equipment fault frequency is recorded as gp2, and the environmental parameter maintenance equipment fault frequency is recorded as gp3. The formula The fault description index Gm of the automatic mixing area is calculated;

[0032] Based on the abnormal evaluation index HJ of mixing equipment accuracy and the fault description index Gm of automatic mixing area, the formula The mixture quality assessment coefficient Hz is obtained by joint analysis, where ψ1, ψ2, and ψ3 represent the proportional coefficients of each item respectively.

[0033] Preferably, when the mixing equipment accuracy abnormality evaluation index HJ is higher than the preset value thb1, it indicates that the accuracy of the mixing equipment does not meet the requirements, and the management personnel are prompted to repair the mixing equipment; when the automatic mixing area fault description index Gm is higher than the preset value thb2, it indicates that the mixing equipment has a high fault frequency and is not suitable for mixing operations; when the mixing quality evaluation coefficient Hz does not meet the preset Hz 预 This indicates that there is a risk of abnormal operation in the automatic mixing area, prompting managers to pay attention to the mixing equipment.

[0034] Preferably, the method comprises a mixing risk warning step, based on the ingredient quality assessment coefficient Pz and the mixing quality assessment coefficient Hz, by the formula FX = (Pz-Pz 预 ) 2 +(Hz-Hz 预 ) 2 The automatic mixing risk factor FX is calculated and corresponding measures are taken based on the obtained automatic mixing risk factor.

[0035] Technical effects and advantages of the present invention:

[0036] (1) The present invention provides a method for realizing automatic mixing of materials in intelligent manufacturing, wherein an automatic mixing area is formed by a weighing device, an environmental monitoring device, an intelligent calibration device, and a material conveying device; before automatic mixing, the accuracy loss degree Js of the weighing device, the mixing reliability index St_p under a standard environment, and the mixing reliability index Nst_p under a non-standard environment are obtained by monitoring and analyzing the automatic mixing area; based on the accuracy loss degree Js of the weighing device, the mixing reliability index St_p under a standard environment, and the mixing reliability index Nst_p under a non-standard environment, a mixing quality assessment coefficient Pz of the automatic mixing area is obtained; corresponding measures are taken based on the relationship between the accuracy loss degree Js of the weighing device, the mixing reliability index St_p under a standard environment, the mixing reliability index Nst_p under a non-standard environment, the mixing quality assessment coefficient Pz and a preset value; accurate, fast, and real-time mixing control is achieved; the efficiency of electrode sheet production and product quality are improved, and the production cost and safety risks of lithium batteries are reduced.

[0037] (2) The present invention provides a method for realizing automatic mixing in intelligent manufacturing, analyzing the equipment in the automatic mixing area, obtaining the automatic mixing equipment precision abnormality description parameters and failure rate; based on the automatic mixing equipment precision abnormality description parameters, failure rate, mixing equipment precision abnormality evaluation index HJ, and automatic mixing area failure description index Gm, a mixing quality evaluation coefficient Hz is obtained by joint analysis; when the mixing equipment precision abnormality evaluation index HJ, the automatic mixing area failure description index Gm, and the mixing quality evaluation coefficient Hz all meet the preset conditions, proceed to the next step; otherwise, the automatic mixing equipment is debugged until the preset requirements are met, and accurate, fast, and real-time mixing control is achieved; the efficiency of electrode sheet production and product quality are improved, and the production cost and safety risks of lithium batteries are reduced.

[0038] (3) The present invention provides a method for realizing automatic compounding in intelligent manufacturing. By controlling the risk of compounding and mixing, corresponding measures can be taken based on the risk, providing technical support for the decision-making of managers, helping enterprises to reduce production costs and improve market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The figure is a flow chart of automatic batching based on intelligent calibration equipment of the present invention.

[0040] Figure 2 The figure is a flow chart of automatic batching based on automatic mixing zone evaluation of the present invention.

[0041] Figure 3 The present invention is a flow chart of a method for realizing automatic compounding of materials in intelligent manufacturing. DETAILED DESCRIPTION

[0042] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0043] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0044] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0045] Computer systems / servers may be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. In general, program modules may include routines, programs, object programs, components, logic, data structures, which perform specific tasks or implement specific abstract data types. Computer systems / servers may be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules may be located on local or remote computing system storage media including storage devices.

[0046] Example 1

[0047] See also Figure 1 The present invention provides a method for realizing automatic mixing of materials in intelligent manufacturing, comprising the following steps:

[0048] Analysis of automatic batching area: Through monitoring and analysis of the automatic batching area, the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, and the batching reliability index Nst_p under non-standard environment are obtained;

[0049] Evaluation of automatic batching area: Based on the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under the standard environment, and the batching reliability index Nst_p under the non-standard environment, the batching quality evaluation coefficient Pz of the automatic batching area is obtained;

[0050] Judgment of automatic batching area: take corresponding measures based on the relationship between the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, the batching reliability index Nst_p under non-standard environment, the batching quality assessment coefficient Pz and the preset value;

[0051] Automatic weighing and batching: According to the preset formula ratio, the raw materials are weighed and batched in the automatic batching area, and the preset weight of the ingredients is obtained through weighing equipment, environmental monitoring equipment, and intelligent calibration equipment, and the preset weight of the ingredients is transmitted to the automatic mixing area through material conveying equipment;

[0052] Execution of automatic mixing: receiving materials delivered from the automatic batching area, mixing the materials together in a preset order and under preset process conditions, forming electrode slurry after stirring and dispersing, and completing automatic mixing.

[0053] What needs to be further explained in the embodiments of the present invention is that the automatic batching area includes a weighing device, an environmental monitoring device, an intelligent calibration device, and a material conveying device; the weighing device is used to weigh the weight of the material, automatically record the weighing data, and transmit the collected weighing data to the intelligent calibration device; the environmental monitoring device is used to collect weighing environmental parameters, including temperature, humidity, vibration amplitude, and vibration frequency, and transmit the collected environmental data to the intelligent calibration device; the intelligent calibration device corrects the weighing data based on the collected environmental data, and outputs the corrected material weight; the material output device is used to transmit the weighed material to the automatic mixing area.

[0054] What needs to be further explained in the embodiments of the present invention is that the intelligent calibration device corrects the weighing data based on one or a combination of a filtering algorithm, a compensation algorithm, and an adaptive algorithm; reduces noise and interference in the weighing data through a filtering algorithm; corrects weighing errors caused by temperature, humidity, vibration frequency, vibration amplitude, and time through a compensation algorithm, and the compensation algorithm includes a linear compensation algorithm and a nonlinear compensation algorithm. Nonlinear compensation is performed on the weighing data through machine learning, and errors in the weighing data are predicted and corrected by training a machine learning model; the adaptive algorithm automatically adjusts parameters according to changes in the environment or equipment status to maintain weighing accuracy.

[0055] It needs to be further explained in the embodiment of the present invention that the process of obtaining the ingredient quality evaluation coefficient Pz includes the following steps:

[0056] The average accuracy of the weighing equipment is obtained by weight calibration. After several weight calibrations, the actual accuracy of the weighing equipment is obtained by taking the average. The accuracy loss degree Js of the weighing device is calculated, where yj represents the preset accuracy of the weighing device and sj represents the actual accuracy of the weighing device;

[0057] The batching reliability index is obtained by conducting a pre-batch test under standard conditions. Assume that there are m types of batching required, i represents the batching number, the theoretical batching weight of the i-th batching is lzi, and the actual weighing weight of the i-th batching is szi; through the formula Obtain batching reliability parameters under standard environment, perform pre-batch several times, obtain several groups of batching reliability parameters, and obtain batching reliability index St_p under standard environment by averaging;

[0058] The batching reliability index is obtained by conducting a pre-batch test in a non-standard environment, and the test environment parameter combination is obtained based on the actual batching environment; the test environment is built based on the test environment parameter combination, and the batching reliability index Nst_p in the non-standard environment is obtained by analyzing the test results;

[0059] Based on the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, and the batching reliability index Nst_p under non-standard environment, the formula Get the batching quality assessment coefficient Pz of the automatic batching process,

[0060] Among them, 0<δ1<1, 0<δ2<1, and δ1+δ2=1.0, δ1 and δ2 are weighted calculations to obtain the ingredient quality assessment coefficient Pz.

[0061] It needs to be further explained in the embodiment of the present invention that the process of obtaining the batching reliability index Nst_p in a non-standard environment includes the following steps:

[0062] The maximum and minimum values ​​of temperature, humidity, vibration amplitude and vibration frequency in the automatic batching area are obtained, and several groups of parameters of temperature, humidity, vibration amplitude and vibration frequency are obtained through gradient value selection; after random permutation and combination, n groups of test environment parameter combinations are generated; for example, temperature, humidity, vibration amplitude and vibration frequency are each divided into 4 gradients, and a maximum of 256 different test environments are generated;

[0063] Build a test environment for weighing tests, record the environmental parameters of each test, and record the weighing data of each test;

[0064] Analyze the recorded environmental parameters to obtain the environmental anomaly index for each test, with j representing the test number, and the formula Get the environmental anomaly description parameters of the test environment, where hxc represents the test value of the environmental parameter, hx0 represents the preset standard environmental parameter, and μ represents the influencing factor of the specific type of environmental parameter; the environmental anomaly description parameters corresponding to the temperature, humidity, vibration amplitude, and vibration frequency in the jth test are recorded as hy1, hy2, hy3, and hy4 respectively, and the formula is used Calculate the j-th test environment abnormality index hyj;

[0065] By formula Obtain the batching reliability index Nst_p under non-standard environment, where wci represents the error degree of the jth test and n represents the number of tests.

[0066] It needs to be further explained in the embodiment of the present invention that when the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under the standard environment, and the batching reliability index Nst_p under the non-standard environment, the batching quality assessment coefficient Pz of the automatic batching process is obtained and meets the preset requirements at the same time, the next step is entered; otherwise, the automatic batching area is debugged by debugging the weighing equipment and the intelligent calibration equipment until the preset requirements are met;

[0067] What needs to be further explained in the embodiments of the present invention is that when the precision loss degree Js of the weighing equipment exceeds the preset value tha1, it indicates that the precision of the weighing equipment is abnormal, and an early warning is issued to the management personnel to remind them to repair and maintain the weighing equipment; when the batching reliability index St_p under the standard environment is lower than the preset value tha2, it indicates that the automatic batching area is abnormal, and an early warning is issued to the management personnel to remind them to inspect the automatic batching area; when the batching reliability index Nst_p under the non-standard environment is lower than the preset value tha3, it indicates that there is an abnormality in the environmental monitoring equipment or the intelligent calibration equipment, and the management personnel are reminded to debug the environmental monitoring equipment or the intelligent calibration equipment; when the batching quality evaluation coefficient Pz of the automatic batching process does not meet the preset Pz 预 , indicating that there is a risk of abnormal operation in the automatic batching area, warning the management personnel and prompting them to terminate the automatic batching measures.

[0068] Example 2

[0069] See also Figure 2 The present invention provides an automatic batching process flow chart based on automatic mixing zone evaluation, and provides a method for realizing automatic batching in intelligent manufacturing, comprising the following steps:

[0070] Automatic weighing and batching: According to the preset formula ratio, the raw materials are weighed and batched in the automatic batching area, the preset weight of the ingredients is obtained through the weighing equipment, and the preset weight of the ingredients is transmitted to the automatic mixing area through the material conveying equipment;

[0071] Automatic mixing area analysis: Analyze the equipment in the automatic mixing area to obtain the abnormal accuracy description parameters and failure rate of the automatic mixing equipment;

[0072] Automatic mixing area evaluation: The mixing quality evaluation coefficient Hz is obtained by joint analysis based on the automatic mixing equipment accuracy anomaly description parameters, failure rate, mixing equipment accuracy anomaly evaluation index HJ, and automatic mixing area failure description index Gm;

[0073] Automatic mixing area judgment: When the mixing equipment accuracy abnormality evaluation index HJ, the automatic mixing area fault description index Gm, and the mixing quality evaluation coefficient Hz all meet the preset conditions, proceed to the next step; otherwise, debug the automatic mixing equipment until it meets the preset requirements;

[0074] Automatic mixing execution: receiving materials delivered from the automatic batching area, mixing the materials together in a preset order and under preset process conditions, forming electrode slurry after stirring and dispersing, and completing automatic mixing.

[0075] It needs to be further explained in the embodiments of the present invention that the automatic mixing area includes a discharging device, a stirring device, and an environmental parameter maintenance device. The discharging device adds different types of materials into the stirring device in a preset order, time, weight, and speed according to the discharging instruction. The discharging equipment has various forms, such as quantitative discharging controlled by a solenoid valve and nozzle discharging controlled by compressed air; the stirring device is used to stir the materials in the stirring device, and according to the stirring instruction, the materials are stirred at a preset stirring speed and time; the environmental parameter maintenance device is used to provide the required stirring environment for the mixing process, and the stirring environment includes the pressure, temperature, vibration frequency, and gas atmosphere required for stirring.

[0076] It needs to be further explained in the embodiment of the present invention that the mixture quality evaluation coefficient Hz is obtained as follows:

[0077] The accuracy abnormality description parameters of the automatic mixing area including the discharge equipment, stirring equipment, and environmental parameter maintenance equipment are obtained respectively. After linear normalization, the accuracy abnormality description parameters of the discharge equipment, the accuracy abnormality description parameters of the stirring equipment, and the accuracy abnormality description parameters of the environmental parameter maintenance equipment are recorded as Fm, Jm, and Hm, respectively. The abnormal evaluation index HJ of mixing equipment accuracy is calculated;

[0078] The operation data of the automatic mixing area is analyzed, and the fault identification conditions of the discharge equipment, the stirring equipment, and the environmental parameter maintenance equipment are set respectively. The fault identification conditions at least include the discharge sequence error, the stirring time error, and the stirring frequency error. The discharge equipment fault frequency is recorded as gp1, the stirring equipment fault frequency is recorded as gp2, and the environmental parameter maintenance equipment fault frequency is recorded as gp3. The formula The fault description index Gm of the automatic mixing area is calculated;

[0079] Based on the abnormal evaluation index HJ of mixing equipment accuracy and the fault description index Gm of automatic mixing area, the formula The mixture quality assessment coefficient Hz is obtained by joint analysis, where ψ1, ψ2, and ψ3 represent the proportional coefficients of each item respectively.

[0080] It is necessary to further explain in the embodiment of the present invention that when the accuracy abnormality evaluation index HJ of the mixing equipment is higher than the preset value thb1, it indicates that the accuracy of the mixing equipment does not meet the requirements, and the management personnel are prompted to repair the mixing equipment; when the fault description index Gm of the automatic mixing area is higher than the preset value thb2, it indicates that the mixing equipment has a high fault frequency and is not suitable for mixing operations; when the mixing quality evaluation coefficient Hz does not meet the preset Hz 预 This indicates that there is a risk of abnormal operation in the automatic mixing area, prompting managers to pay attention to the mixing equipment.

[0081] Example 3

[0082] See also Figure 3 A method for realizing automatic compounding in intelligent manufacturing is provided in the embodiment of the present invention, and the method comprises the following steps:

[0083] Analysis of automatic batching area: Through monitoring and analysis of the automatic batching area, the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, and the batching reliability index Nst_p under non-standard environment are obtained;

[0084] Evaluation of automatic batching area: Based on the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under the standard environment, and the batching reliability index Nst_p under the non-standard environment, the batching quality evaluation coefficient Pz of the automatic batching area is obtained;

[0085] Judgment of automatic batching area: take corresponding measures based on the relationship between the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, the batching reliability index Nst_p under non-standard environment, the batching quality assessment coefficient Pz and the preset value;

[0086] Automatic weighing and batching: According to the preset formula ratio, the raw materials are weighed and batched in the automatic batching area, and the preset weight of the ingredients is obtained through weighing equipment, environmental monitoring equipment, and intelligent calibration equipment, and the preset weight of the ingredients is transmitted to the automatic mixing area through material conveying equipment;

[0087] Automatic mixing area analysis: Analyze the equipment in the automatic mixing area to obtain the abnormal accuracy description parameters and failure rate of the automatic mixing equipment;

[0088] Automatic mixing area evaluation: The mixing quality evaluation coefficient Hz is obtained by joint analysis based on the automatic mixing equipment accuracy anomaly description parameters, failure rate, mixing equipment accuracy anomaly evaluation index HJ, and automatic mixing area failure description index Gm;

[0089] Automatic mixing area judgment: When the mixing equipment accuracy abnormality evaluation index HJ, the automatic mixing area fault description index Gm, and the mixing quality evaluation coefficient Hz all meet the preset conditions, proceed to the next step; otherwise, debug the automatic mixing equipment until it meets the preset requirements;

[0090] Execution of automatic mixing: receiving materials delivered from the automatic batching area, mixing the materials together in a preset order and under preset process conditions, forming electrode slurry after stirring and dispersing, and completing automatic mixing.

[0091] It is necessary to further explain in the embodiment of the present invention that the mixed material risk warning step includes, based on the ingredient quality assessment coefficient Pz and the mixed material quality assessment coefficient Hz, the formula FX = (Pz-Pz 预 ) 2 +(Hz-Hz 预 ) 2 The automatic mixing risk factor FX is calculated and corresponding measures are taken based on the obtained automatic mixing risk factor.

[0092] For example, managers allocate supervision resources based on the automatic batching risk factor FX, or adjust the matching of the automatic batching area and the automatic mixing area. Managers use the automatic batching risk factor FX to allocate supervision resources and adjust the matching of the automatic batching area and the automatic mixing area accordingly to ensure the safety and efficiency of the production process. In this way, managers can identify potential risk factors and take effective measures to prevent or reduce accidents. At the same time, reasonable area matching can also help improve production efficiency and product quality, thereby creating greater value for the enterprise. In addition, using the automatic batching risk factor FX as the basis for allocating supervision resources can ensure that resources are reasonably used in high-risk areas, thereby better controlling potential risks. This data-based decision-making method helps improve management efficiency and production safety, and is one of the commonly used methods in modern production management.

[0093] Furthermore, electrode sheets are prepared: the prepared electrode slurry is evenly coated on a current collector, such as aluminum foil or copper foil, and dried to form an electrode sheet; the appearance quality abnormality evaluation index of the electrode sheet is obtained through appearance inspection, and the performance quality abnormality evaluation index of the electrode sheet is obtained through physical property testing; when the ingredient quality evaluation coefficient Pz and the mixing quality evaluation coefficient Hz are normal, but the performance quality abnormality evaluation index and the appearance quality abnormality evaluation index of the electrode sheet are abnormal, the management personnel are prompted to adjust the material ratio and the mixing process.

[0094] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for realizing automatic compounding in intelligent manufacturing, characterized in that: The following steps are involved: Analysis of automatic batching area: Through monitoring and analysis of the automatic batching area, the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, and the batching reliability index Nst_p under non-standard environment are obtained; Evaluation of automatic batching area: Based on the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under the standard environment, and the batching reliability index Nst_p under the non-standard environment, the batching quality evaluation coefficient Pz of the automatic batching area is obtained; Judgment of automatic batching area: take corresponding measures based on the relationship between the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, the batching reliability index Nst_p under non-standard environment, the batching quality assessment coefficient Pz and the preset value; Automatic weighing and batching: According to the preset formula ratio, the raw materials are weighed and batched in the automatic batching area, and the preset weight of the ingredients is obtained through weighing equipment, environmental monitoring equipment, and intelligent calibration equipment, and the preset weight of the ingredients is transmitted to the automatic mixing area through material conveying equipment; Execution of automatic mixing: receiving materials delivered by the automatic batching area, mixing the materials together in a preset order and under preset process conditions, forming electrode slurry after stirring and dispersing, and completing automatic batching; The automatic batching area includes weighing equipment, environmental monitoring equipment, intelligent calibration equipment, and material conveying equipment; the weighing equipment is used to weigh the weight of the material, automatically record the weighing data, and transmit the collected weighing data to the intelligent calibration equipment; the environmental monitoring equipment is used to collect weighing environmental parameters, including temperature, humidity, vibration amplitude, and vibration frequency, and transmit the collected environmental data to the intelligent calibration equipment; the intelligent calibration equipment corrects the weighing data based on the collected environmental data and outputs the corrected material weight; the material output equipment is used to transmit the weighed material to the automatic mixing area; Intelligent calibration equipment corrects weighing data based on one or a combination of filtering algorithm, compensation algorithm, adaptive algorithm, etc.; filtering algorithm is used to reduce noise and interference in weighing data; Compensation algorithms are used to correct weighing errors caused by temperature, humidity, vibration frequency, vibration amplitude, and time. Compensation algorithms include linear compensation and nonlinear compensation algorithms. Machine learning is used to perform nonlinear compensation on weighing data. Machine learning models are trained to predict and correct errors in weighing data. Adaptive algorithms automatically adjust parameters according to changes in the environment or equipment status to maintain weighing accuracy. The process of obtaining the ingredient quality assessment coefficient Pz includes the following steps: The average accuracy of the weighing equipment is obtained by weight calibration. After several weight calibrations, the actual accuracy of the weighing equipment is obtained by taking the average. The accuracy loss degree Js of the weighing device is calculated, where yj represents the preset accuracy of the weighing device and sj represents the actual accuracy of the weighing device; The batching reliability index is obtained by conducting a pre-batch test under standard conditions. Assume that there are m types of batching required, i represents the batching number, the theoretical batching weight of the i-th batching is lzi, and the actual weighing weight of the i-th batching is szi; through the formula Obtain batching reliability parameters under standard environment, perform pre-batch several times, obtain several groups of batching reliability parameters, and obtain batching reliability index St_p under standard environment by averaging; The batching reliability index is obtained by conducting a pre-batch test in a non-standard environment, and the test environment parameter combination is obtained based on the actual batching environment; the test environment is built based on the test environment parameter combination, and the batching reliability index Nst_p in the non-standard environment is obtained by analyzing the test results; Based on the accuracy loss degree Js of the weighing equipment, the batching reliability index St_p under standard environment, and the batching reliability index Nst_p under non-standard environment, the formula Get the batching quality assessment coefficient Pz of the automatic batching process, Among them, 0<δ1<1, 0<δ2<1, and δ1+δ2=1.0, δ1 and δ2 are weighted calculations to obtain the ingredient quality assessment coefficient Pz; The process of obtaining the batching reliability index Nst_p under non-standard environment includes the following steps: Obtain the maximum and minimum values ​​of temperature, humidity, vibration amplitude, and vibration frequency in the automatic batching area, and obtain several groups of parameters of temperature, humidity, vibration amplitude, and vibration frequency through gradient value taking; after random permutation and combination, generate n groups of test environmental parameter combinations; Build a test environment for weighing tests, record the environmental parameters of each test, and record the weighing data of each test; Analyze the recorded environmental parameters to obtain the environmental anomaly index for each test, with j representing the test number, and the formula Get the environmental anomaly description parameters of the test environment, where hxc represents the test value of the environmental parameter, hx0 represents the preset standard environmental parameter, and μ represents the influencing factor of the specific type of environmental parameter; the environmental anomaly description parameters corresponding to the temperature, humidity, vibration amplitude, and vibration frequency in the jth test are recorded as hy1, hy2, hy3, and hy4 respectively, and the formula is used Calculate the j-th test environment abnormality index hyj; By formula Obtain the batching reliability index Nst_p under non-standard environment, where wci represents the error degree of the jth test and n represents the number of tests; When the precision loss degree Js of the weighing equipment exceeds the preset value tha1, it indicates that the precision of the weighing equipment is abnormal, and an early warning is issued to the management personnel to remind them to repair and maintain the weighing equipment; when the batching reliability index St_p under the standard environment is lower than the preset value tha2, it indicates that the automatic batching area is abnormal, and an early warning is issued to the management personnel to remind them to inspect the automatic batching area; when the batching reliability index Nst_p under the non-standard environment is lower than the preset value tha3, it indicates that there is an abnormality in the environmental monitoring equipment or the intelligent calibration equipment, and the management personnel are reminded to debug the environmental monitoring equipment or the intelligent calibration equipment. When the batching quality evaluation coefficient Pz of the automatic batching process does not meet the preset Pz 预 , indicating that there is a risk of abnormal operation in the automatic batching area, warning the management personnel and prompting them to stop the automatic batching measures; Before the execution of automatic mixing, it includes automatic mixing area analysis, automatic mixing area evaluation, and automatic mixing area judgment steps. Among them, automatic mixing area analysis: analyze the equipment in the automatic mixing area to obtain the abnormal description parameters and failure rate of the automatic mixing equipment accuracy; Automatic mixing area evaluation: The mixing quality evaluation coefficient Hz is obtained by joint analysis based on the automatic mixing equipment accuracy anomaly description parameters, failure rate, mixing equipment accuracy anomaly evaluation index HJ, and automatic mixing area failure description index Gm; Automatic mixing area judgment: When the mixing equipment accuracy abnormality evaluation index HJ, the automatic mixing area fault description index Gm, and the mixing quality evaluation coefficient Hz all meet the preset conditions, proceed to the next step; otherwise, debug the automatic mixing equipment until it meets the preset requirements; The mixture quality assessment coefficient Hz is obtained as follows: The accuracy abnormality description parameters of the automatic mixing area including the discharge equipment, stirring equipment, and environmental parameter maintenance equipment are obtained respectively. After linear normalization, the accuracy abnormality description parameters of the discharge equipment, the accuracy abnormality description parameters of the stirring equipment, and the accuracy abnormality description parameters of the environmental parameter maintenance equipment are recorded as Fm, Jm, and Hm, respectively. The abnormal evaluation index HJ of mixing equipment accuracy is calculated; The operation data of the automatic mixing area is analyzed, and the fault identification conditions of the discharge equipment, the stirring equipment, and the environmental parameter maintenance equipment are set respectively. The fault identification conditions at least include the discharge sequence error, the stirring time error, and the stirring frequency error. The discharge equipment fault frequency is recorded as gp1, the stirring equipment fault frequency is recorded as gp2, and the environmental parameter maintenance equipment fault frequency is recorded as gp3. The formula The fault description index Gm of the automatic mixing area is calculated; Based on the abnormal evaluation index HJ of mixing equipment accuracy and the fault description index Gm of automatic mixing area, the formula The mixture quality assessment coefficient Hz is obtained by joint analysis, where ψ1, ψ2, and ψ3 represent the proportional coefficients of each item respectively; When the mixing equipment accuracy abnormality evaluation index HJ is higher than the preset value thb1, it indicates that the mixing equipment accuracy does not meet the requirements, prompting the management personnel to repair the mixing equipment; when the automatic mixing area fault description index Gm is higher than the preset value thb2, it indicates that the mixing equipment has a high fault frequency and is not suitable for mixing operations; when the mixing quality evaluation coefficient Hz does not meet the preset Hz 预 This indicates that there is a risk of abnormal operation in the automatic mixing area, prompting managers to pay attention to the mixing equipment; Including the mixing risk warning step, based on the ingredient quality assessment coefficient Pz and the mixing quality assessment coefficient Hz, through the formula FX = (Pz-Pz 预 ) 2 +(Hz-Hz 预 ) 2 The automatic mixing risk factor FX is calculated and corresponding measures are taken based on the obtained automatic mixing risk factor.