Intelligent diagnosis report generation system for electrochemical energy storage lithium iron phosphate battery

Abstract

The invention discloses an intelligent diagnosis report generation system for an electrochemical energy storage lithium iron phosphate battery, and relates to the technical field of battery management, and the system comprises a traditional integrated hardware platform which is used for collecting real-time operation data monitored by a sensor; the intelligent diagnosis algorithm module is used for scoring the consistency, reliability and safety of the system, and performing integration in a weighted average mode according to the consistency, reliability and safety scores to obtain a comprehensive health score of the system; and the diagnosis report generation module is used for obtaining a system health comprehensive score by summarizing the scores of the ten key indexes, and presenting an index diagnosis level according to the system health comprehensive score. According to the method, the problems of inaccurate battery health assessment, low efficiency of fault diagnosis and inaccurate safety state assessment are solved, and the operation performance and safety of the energy storage system are enhanced while the user experience is improved through display in the form of a diagnosis report.

Description

Technical Field

[0001] The present invention relates to the technical field of battery management, and more specifically, to an intelligent diagnosis report generation system for lithium iron phosphate batteries in electrochemical energy storage. Background Art

[0002] With the development of electrochemical energy storage technology, especially in the field of lithium iron phosphate batteries, the application of intelligent and digital technologies faces challenges in terms of standardized preparation processes, high-quality technologies, intelligence, and digitization. Lithium iron phosphate batteries for electrochemical energy storage have been widely used in the fields of energy storage, electric vehicles, and renewable energy storage due to their high safety, long cycle life, good thermal stability, and environmental friendliness. The integration of intelligent diagnosis prediction and energy storage technology provides a new solution for the research and development of energy storage technology. Machine learning (ML), as a subfield of artificial intelligence, has been proven to be a powerful tool for obtaining insights from data, helping to reveal the relationship between the key structures or properties of batteries and their performance, and greatly accelerating the development of energy storage technology. Deficiencies of the prior art:

[0003] Safety issues have always been a top priority in the development of the energy storage industry, and the potential safety hazards of lithium-ion batteries are relatively prominent. In addition, the digital and intelligent applications of energy storage batteries, including battery design and manufacturing, intelligence, manufacturing intelligence, and management intelligence, have put forward higher requirements for improving the reliability, safety, durability, etc. of batteries. Therefore, the intelligent diagnosis report generation system for lithium iron phosphate batteries in electrochemical energy storage focuses on improving the accuracy of battery health assessment, enhancing the efficiency of fault diagnosis, optimizing the accuracy of safety status assessment, and presenting it in the form of fully automatic generation of diagnosis reports, improving the user experience while also enhancing the operating performance and safety of the energy storage system.

[0004] In view of the above problems, the present invention proposes a solution. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent diagnosis report generation system for lithium iron phosphate batteries in electrochemical energy storage, and solves the problems raised in the above background art through the intelligent diagnosis report generation system for lithium iron phosphate batteries in electrochemical energy storage.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] Intelligent Diagnosis Report Generation System for Lithium Iron Phosphate Batteries in Electrochemical Energy Storage, including a traditional integrated hardware platform, an intelligent diagnosis algorithm module, and a diagnosis report generation module. There are connections between the modules: The traditional integrated hardware platform is used to collect real-time operation data monitored by sensors; The intelligent diagnosis algorithm module is used to score the system's consistency, reliability, and security, and synthesize them in the form of a weighted average based on the scores of consistency, reliability, and security to obtain a comprehensive system health score; The diagnosis report generation module is used to obtain the comprehensive system health score by summarizing the scores of ten key indicators, present the indicator diagnosis level according to the comprehensive system health score, and display the operation overview, specific data analysis, and the detailed address of the faulty battery.

[0008] In a preferred embodiment, the traditional integrated hardware platform includes a sensor array, a data acquisition unit, and a communication interface.

[0009] In a preferred embodiment, the intelligent diagnosis algorithm module includes a data receiving unit, a data processing unit, and an intelligent diagnosis algorithm module unit.

[0010] In a preferred embodiment, the data receiving unit is used to receive the data transmitted by the communication interface; The data processing unit includes a data input unit, a data category correction unit, a data normalization unit, a data cleaning module unit, and a data output unit; The intelligent diagnosis algorithm module unit includes a system consistency algorithm module, a system reliability algorithm module, a system security algorithm module, and a comprehensive scoring algorithm module.

[0011] In a preferred embodiment, the data input unit is responsible for receiving the original data set to be processed and providing input for subsequent data cleaning and correction; The data category correction unit identifies and corrects errors in the data set to ensure the accuracy and consistency of the data; The data normalization unit converts the data into a unified format for subsequent processing and analysis; The data cleaning module unit adopts a sliding window mechanism, gradually moving the window data point by point until the entire time series is covered. For randomly missing data, a linear regression estimation method is used for filling. For sudden outlier data, the window size is determined according to the data characteristics and smoothing requirements. Starting from the beginning position of the time series, the data points within the window are summed and the average value is calculated, and the average value replaces the outlier; The data output unit is responsible for saving the preliminarily processed data and transmitting it to the intelligent diagnosis algorithm module through the communication interface to provide support for further data analysis and intelligent diagnosis.

[0012] In a preferred embodiment, the system consistency algorithm module includes voltage, temperature, internal resistance, and SOH consistency algorithm modules; by comparing the differences between the voltage and temperature of the real-time target battery and the median of multiple battery target parameters, as well as the differences between the internal resistance and SOH of the periodic target battery and the median of multiple battery target parameters, to determine whether a specific battery exhibits abnormalities; the internal resistance consistency algorithm module uses the forgetting factor least squares method to analyze all voltage and current data during the charge and discharge process of the battery, calculate the internal resistance value of each battery, and calculate for all batteries in the energy storage system in turn; the SOH consistency algorithm module uses a neural network algorithm to calculate the SOH (state of health of the battery) of each battery based on all voltage, current, and temperature data during the charge and discharge process of the battery, and cover the SOH of all batteries in the energy storage system.

[0013] In a preferred embodiment, the system reliability algorithm module includes self-discharge rate, dQ / dV curve, and temperature measurement point effectiveness algorithm modules; the self-discharge rate algorithm module uses the extended Kalman method to calculate the SOC (state of charge of the battery) of the battery based on the real-time voltage and current data during the charge and discharge process of the battery, and perform this calculation for all batteries in the energy storage system in turn to determine whether the self-discharge rate of the battery is abnormal; the dQ / dV curve algorithm module analyzes the slope change before the steady state by differentiating the Q / V curve during the charge and discharge process of the system, and discriminates the reliability of the battery according to the number of positive and negative mutations of the slope; the temperature measurement point effectiveness algorithm module randomly selects moments during the charge and discharge process of the battery for temperature distribution analysis, and judges the reliability of the temperature measurement point based on whether the temperature changes suddenly between adjacent sampling points under the condition that other factors are normal.

[0014] In a preferred embodiment, the system safety algorithm module includes device connection abnormality, overcharge / overdischarge risk prediction, and internal short circuit / thermal runaway risk prediction algorithm modules; by combining electrochemical impedance spectroscopy (EIS) and deep neural network (DNN), using machine learning algorithms to extract indicators for relevant features of self-discharge effect and abnormal temperature rise effect, to achieve early warning of potential faults, and predict the probabilities of occurrence of connection abnormalities, overcharge / overdischarge risks, internal short circuits / thermal runaways in the battery.

[0015] In a preferred embodiment, the comprehensive scoring module includes scoring the system consistency, reliability, and safety, and comprehensively scoring the system health.

[0016] In a preferred embodiment, the specific steps for presenting the diagnostic level of an indicator according to the comprehensive system health score are as follows: Compare and analyze the comprehensive system health score with a predetermined health score threshold, and present the diagnostic level of the indicator in four states: "excellent", "good", "pass", and "fail". If the comprehensive system health score is greater than or equal to the first health score threshold, the diagnostic level of the indicator is presented as "excellent"; if the comprehensive system health score is greater than or equal to the second health score threshold and less than the first threshold, the diagnostic level of the indicator is presented as "good"; if the comprehensive system health score is greater than or equal to the third health score threshold and less than the second threshold, the diagnostic level of the indicator is presented as "pass"; if the comprehensive system health score is less than the third threshold, the diagnostic level of the indicator is presented as "fail". When the diagnostic level is "pass" or "fail", the system will output the specific location information of the faulty battery cell.

[0017] Technical effects and advantages of the intelligent diagnostic report generation system for lithium iron phosphate batteries for electrochemical energy storage of the present invention:

[0018] 1. The present invention provides a tool for users to intuitively understand the health status of the energy storage system, and significantly improves the work efficiency of maintenance personnel. With its high recognition accuracy, user-friendly operation mode and fast response characteristics, the system provides valuable guidance and support for the operation and maintenance management of the energy storage power station. The system cleverly integrates a traditional integrated hardware platform, a cutting-edge intelligent diagnostic algorithm module and a diagnostic report generation module, realizes real-time monitoring of the core parameters of the energy storage system, and can automatically generate a detailed diagnostic report for any time period of the equipment operation. It covers the system real-time operation data accurately collected and efficiently transmitted by the hardware platform, as well as the in-depth analysis of these data by the intelligent diagnostic algorithm module, including identifying abnormal patterns and predicting potential faults, so as to realize early warning of faults.

[0019] 2. The present invention realizes real-time monitoring and calculation of the key parameters of the energy storage system, diagnoses and predicts the fault information of the energy storage system, and displays the above information in the form of a diagnostic report by integrating a traditional integrated hardware platform, a cutting-edge intelligent diagnostic algorithm module and a diagnostic report generation module. Ten key indicators are listed in detail, including system consistency (consistency of voltage, temperature, internal resistance and state of health SOH of the battery), system reliability (self-discharge rate, dQ / dV curve and effectiveness of temperature measurement points), and system security (abnormal device connection, overcharge / overdischarge risk prediction and internal short circuit / thermal runaway risk prediction). The algorithm is used to score each of them. It can clearly display the specific fault information, continuously diagnose and monitor the historical data and real-time operation data, and at the same time display the operation status of all batteries in real time. With its high recognition accuracy, user-friendly operation mode and fast response characteristics, the system provides valuable guidance and support for the operation and maintenance management of the energy storage power station. Description of the Drawings

[0020] Figure 1 This is a schematic diagram of the structure of the intelligent diagnosis report generation system for lithium iron phosphate batteries in electrochemical energy storage of the present invention.

[0021] Figure 2 This is a schematic diagram of ten key indicators of the intelligent diagnosis report generation system for lithium iron phosphate batteries in electrochemical energy storage of the present invention. Detailed implementation manners

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] Embodiment 1 Figure 1 The intelligent diagnosis report generation system for lithium iron phosphate batteries in electrochemical energy storage of the present invention is given.

[0024] A traditional integrated hardware platform is used to collect real-time operation data monitored by sensors;

[0025] The traditional integrated hardware platform includes a sensor array, a data acquisition unit, and a communication interface.

[0026] More specifically, the sensor array is composed of voltage, current, and temperature sensors, aiming to monitor the voltage, current, and temperature of all batteries in the electrochemical energy storage system in real time, so as to comprehensively monitor the charge and discharge state of the system.

[0027] The data acquisition unit is connected to the sensor array and is responsible for collecting the real-time operation data monitored by the sensors;

[0028] The communication interface is connected to the data acquisition unit and is responsible for transmitting the collected data to the intelligent diagnosis algorithm module for further analysis and processing.

[0029] Figure 2 A schematic diagram of ten key indicators of the intelligent diagnosis report generation system for lithium iron phosphate batteries in electrochemical energy storage of the present invention is given.

[0030] An intelligent diagnosis algorithm module is used to score the system consistency, reliability, and security, and comprehensively calculate the weighted average of the scores of the system consistency, reliability, and security to obtain the comprehensive system health score;

[0031] The intelligent diagnosis algorithm module includes a data receiving unit, a data processing unit, and an intelligent diagnosis algorithm module unit.

[0032] The data receiving unit is used to receive the data transmitted by the communication interface;

[0033] The data processing unit includes a data input unit, a data major category correction unit, a data standardization unit, a data cleaning module unit, and a data output unit;

[0034] Furthermore, the data input unit is responsible for receiving the original data set to be processed, providing input for subsequent data cleaning and correction;

[0035] The data major category correction unit identifies and corrects errors in the data set, including but not limited to spelling mistakes, format inconsistencies, etc., to ensure the accuracy and consistency of the data;

[0036] The data standardization unit converts the data into a unified format, such as a unified date format, unit, etc., for subsequent processing and analysis;

[0037] The data cleaning module unit adopts a sliding window mechanism, moving the window step by step for each data point until the entire time series is covered; for randomly missing data, a linear regression estimation method is used for filling; for sudden outlier data, the window size is determined according to the data characteristics and smoothing requirements, starting from the starting position of the time series, summing the data points within the window and calculating the average value to replace the outlier points;

[0038] The data output unit is responsible for saving the preliminarily processed data and transmitting it to the intelligent diagnosis algorithm module through the communication interface, providing support for further data analysis and intelligent diagnosis.

[0039] The intelligent diagnosis algorithm module unit includes a system consistency algorithm module, a system reliability algorithm module, a system security algorithm module, and a comprehensive scoring algorithm module;

[0040] Even further, the system consistency algorithm module includes: voltage, temperature, internal resistance, and SOH consistency algorithm modules;

[0041] Furthermore, the internal resistance consistency algorithm module first uses the forgetting factor least squares method to analyze all the voltage and current data of the battery during charge and discharge, thereby calculating the internal resistance value of each battery, and then performing this calculation process on all the batteries in the energy storage system in turn; the specific process is as follows:

[0042] First, collect the real-time voltage V(t) and current I(t) of the battery during charge and discharge;

[0043] According to the relationship between voltage, current, and internal resistance, the internal resistance of the battery is approximately represented by the Ohm's law model, and the formula is as follows: V1(t) = I(t)*R int (t) + SOC*V OCV(t); where V1(t) is the voltage approximated by Ohm's law model, I(t) is the real-time current during the charging and discharging process, V OCV (t) is the open-circuit voltage of the battery, R int (t) is the internal resistance of the battery, and SOC is the state of charge of the battery;

[0044] To estimate the internal resistance of the battery, we can use the least squares method to fit the voltage and current data;

[0045] Find a set of internal resistance values to minimize the error between the voltage in the model and the actually measured voltage data;

[0046] To increase the sensitivity of the algorithm to recent data and reduce the influence of long-term historical data on the calculation results, a forgetting factor is introduced to adjust the weight of historical data. Usually, λ ranges between [0, 1]. The larger λ is, the smaller the influence of historical data on the result;

[0047] For each battery in the energy storage system, calculate the internal resistance of each battery separately according to the above process.

[0048] The SOH (State of Health) is an important indicator used to describe the current health level of the battery. Especially during the long-term use of the battery, it reflects the comparison of the battery's capacity, performance, efficiency, etc. with the factory standard or initial state. SOH is usually used to evaluate whether the battery can still operate with the expected performance, or whether maintenance, replacement, or scrapping is required;

[0049] The SOH consistency algorithm module uses a neural network algorithm to calculate the SOH (battery health state) of each battery based on all voltage, current, and temperature data during the battery charging and discharging process. Similarly, this process will cover all batteries in the energy storage system;

[0050] The system consistency algorithm module determines whether a specific battery shows abnormalities by comparing the differences between the voltage and temperature of the real-time target battery and the median of multiple battery target parameters, as well as the differences between the internal resistance and SOH of the periodic target battery and the median of multiple battery target parameters;

[0051] The system reliability algorithm module includes: self-discharge rate, dQ / dV curve, and temperature measurement point effectiveness algorithm module;

[0052] The self-discharge rate algorithm module uses the extended Kalman method to calculate the SOC (state of charge of the battery) of the battery based on the real-time voltage and current data during the charging and discharging process of the battery, and then performs this calculation on all the batteries in the energy storage system in turn. According to the time interval of the data, this module calculates the change rate of the battery SOC and compares it with the standard value of 0.3% / month to determine whether the self-discharge rate of the battery is abnormal;

[0053] The dQ / dV curve algorithm module analyzes the slope change before the steady state by performing differential calculation on the Q / V curve during the charging and discharging process of the system. According to the number of positive and negative mutations of the slope, this module can discriminate the reliability of the battery;

[0054] The temperature measurement point effectiveness algorithm module randomly selects moments during the charging and discharging process of the battery to analyze the temperature distribution. Under the condition that other factors such as voltage and current are normal, this module determines the reliability of the temperature measurement point based on whether the temperature mutates between adjacent sampling points;

[0055] The system security algorithm module mentioned above includes: device connection abnormality, overcharge / overdischarge risk prediction, and internal short circuit / thermal runaway risk prediction algorithm modules.

[0056] The device connection abnormality, overcharge / overdischarge risk prediction, and battery internal short circuit prediction / thermal runaway risk prediction modules combine the electrochemical impedance spectroscopy (EIS) and the deep neural network (DNN), and use machine learning algorithms to extract indicators of the relevant characteristics of the self-discharge effect and the abnormal temperature rise effect, so as to realize early warning of potential faults and predict the probabilities of occurrence of connection abnormalities, overcharge / overdischarge risks, and battery internal short circuits / thermal runaways.

[0057] The comprehensive scoring module includes scoring the consistency, reliability, and security of the above system, and comprehensively scoring the system health.

[0058] The comprehensive scoring module assigns weights of 10% to each of the ten key indicators, and assigns a weight of 100% / number of batteries to each single battery;

[0059] The difference between the voltage, temperature, internal resistance, and SOH of the single battery for system consistency and the median of multiple battery target parameters is less than 0.5% of the median, which is a full score; between 0.5% - 1% of the median is 90 - 100 points; between 1% - 3% of the median is 80 - 90 points; between 3% - 5% of the median is 60 - 80 points; greater than 5% of the median is below 60 points;

[0060] The difference between the self-discharge rate of a single cell for system reliability and 0.3% / month is less than 0.5% of 0.3% / month, which is a full score. If it is between 0.5% - 1% of 0.3% / month, the score is 90 - 100. If it is between 1% - 3% of 0.3% / month, the score is 80 - 90. If it is between 3% - 5% of 0.3% / month, the score is 60 - 80. If it is greater than the median of 0.3% / month, the score is below 60;

[0061] For system reliability, when the number of positive and negative mutations in the slope of dQ / dV of a single cell before steady state is less than 5 times, it is a full score. If it is between 5 - 10 times, the score is 90 - 100. If it is between 10 - 20 times, the score is 80 - 90. If it is between 20 - 30 times, the score is 60 - 80. If it is greater than 30 times, the score is below 60;

[0062] For the temperature measurement point effectiveness of a single cell in system reliability, when the temperature difference between adjacent sampling points is less than 0.5°C, it is a full score. If it is between 0.5 - 1°C, the score is 90 - 100. If it is between 1 - 3°C, the score is 80 - 90. If it is between 3 - 5°C, the score is 60 - 80. If it is greater than 5°C, the score is below 60;

[0063] For system safety, when the probability value obtained by predicting connection anomalies, overcharge / overdischarge risks, internal short circuit / thermal runaway of a single cell is less than 0.05%, it is a full score. If it is between 0.5% - 0.1%, the score is 90 - 100. If it is between 0.1% - 0.3%, the score is 80 - 90. If it is between 0.3% - 0.5%, the score is 60 - 80. If it is greater than 0.5%, the score is below 60. Finally, the above basic scores are combined in the form of a weighted average to obtain the comprehensive system health score. The specific calculation formula for the comprehensive system health score is as follows: In the formula, S t is the comprehensive system health score, and S i is the score of ten key indicators, where i = 1, 2.....10.

[0064] The diagnostic report generation module is used to summarize the scores of ten key indicators, obtain the comprehensive system health score, and display the operation overview, specific data analysis, and detailed address of the faulty battery;

[0065] The diagnostic report generation module includes a comprehensive system health score display module, an operation overview display module, a specific data analysis display module, and a detailed address display module of the faulty battery.

[0066] The comprehensive system health score display module is responsible for summarizing the scores of ten key indicators and presenting them in a unified table.

[0067] By comparing and analyzing the comprehensive system health score with a predetermined health score threshold, the diagnostic levels of the indicators are presented in four states: "excellent", "good", "pass", and "fail";

[0068] If the comprehensive system health score is greater than or equal to the first health score threshold, the diagnostic level of the indicator shows "excellent";

[0069] If the comprehensive system health score is greater than or equal to the second health score threshold and less than the first threshold, the diagnostic level of the indicator shows "good";

[0070] If the comprehensive system health score is greater than or equal to the third health score threshold and less than the second threshold, the diagnostic level of the indicator shows "pass";

[0071] If the comprehensive system health score is less than the third threshold, the diagnostic level of the indicator shows "fail";

[0072] When the diagnostic level is "pass" or "fail", the system will output the specific location information of the faulty battery cells;

[0073] In addition, this module also provides the display of the comprehensive system health score.

[0074] The operation overview display module sequentially displays the charge and discharge status, operating voltage, current, and temperature at the system level, PACK level, and battery level in a curve form in real time. Among them, the battery level also includes the calculated SOC, internal resistance, and SOH;

[0075] The specific data analysis display module will display the voltage and temperature of the energy storage system predicted for the next 14 charge and discharge cycles in a curve form. In addition, the prediction results such as the probability of internal short circuit and thermal runaway occurring in each cycle are displayed in real time;

[0076] The detailed address display module of the faulty battery displays the reported battery fault information and the number of the battery in a way that combines a location schematic diagram with a summary of the fault information.

[0077] In verifying the accuracy and effectiveness of the intelligent diagnostic report generation system for lithium iron phosphate batteries in electrochemical energy storage of the present invention, we adopted a specific experimental setup. In the experiment, we selected the i ESS-CAB-W215H intelligent energy storage air-cooled integrated cabinet provided by Hongzheng Energy Storage. This system consists of 240 lithium iron phosphate batteries with a rated capacity of 280Ah produced by Ruipu Lan Jun Energy Co., Ltd.

[0078] In summary, the present invention provides an intelligent diagnostic report generation system for lithium iron phosphate batteries for electrochemical energy storage, aiming to provide users with a tool to intuitively understand the health status of the energy storage system and significantly improve the work efficiency of operation and maintenance personnel. The system ingeniously integrates a traditional integrated hardware platform, a cutting-edge intelligent diagnostic algorithm module, and a diagnostic report generation module, realizing real-time monitoring of the core parameters of the energy storage system and being able to automatically generate a detailed diagnostic report for any time period during which the equipment operates. The report content covers the system real-time operation data accurately collected and efficiently transmitted by the hardware platform, as well as the in-depth analysis of these data by the intelligent diagnostic algorithm module, including identifying abnormal patterns and predicting potential faults, thereby achieving early warning of faults. Ten key indicators are listed in detail in the report, including system consistency (consistency of voltage, temperature, internal resistance, and state of health SOH of the battery), system reliability (self-discharge rate, dQ / dV curve, and effectiveness of temperature measurement points), and system security (abnormal device connection, overcharge / overdischarge risk prediction, and internal short circuit / thermal runaway risk prediction), and the algorithm is used to score each of them. In addition, the report can clearly display specific fault information, continuously diagnose and monitor historical data and real-time operation data, and simultaneously display the operation status of all batteries in real time. With its high recognition accuracy, user-friendly operation method, and fast response characteristics, the system provides valuable guidance and support for the operation and maintenance management of energy storage power stations.

[0079] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0080] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product.

[0081] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0082] In addition, the functional modules in each embodiment of the present application can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0083] As described above, it is only the specific implementation manner of the present application. However, 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 all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.

[0084] Finally, the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent diagnosis report generation system for lithium iron phosphate batteries for electrochemical energy storage, characterized in that It includes a traditional integrated hardware platform, an intelligent diagnosis algorithm module, and a diagnostic report generation module, with connections between the modules: The traditional integrated hardware platform is used to collect real-time operation data monitored by sensors; The intelligent diagnosis algorithm module is used to score the system consistency, reliability, and security, and synthesize them in the form of a weighted average based on the consistency, reliability, and security scores to obtain a comprehensive system health score; The diagnostic report generation module is used to obtain the comprehensive system health score by summarizing the scores of ten key indicators, present the indicator diagnosis level according to the comprehensive system health score, and display the operation overview, specific data analysis, and the detailed address of the faulty battery.

2. The intelligent diagnostic report generation system for the lithium iron phosphate battery for electrochemical energy storage according to claim 1, wherein The traditional integrated hardware platform includes a sensor array, a data acquisition unit, and a communication interface.

3. The intelligent diagnostic report generation system for lithium iron phosphate batteries for electrochemical energy storage according to claim 2, wherein The intelligent diagnosis algorithm module includes a data receiving unit, a data processing unit, and an intelligent diagnosis algorithm module unit.

4. The intelligent diagnosis report generation system for lithium iron phosphate batteries for electrochemical energy storage according to claim 3, wherein, The data receiving unit is used to receive the data transmitted by the communication interface; The data processing unit includes a data input unit, a data major category correction unit, a data standardization unit, a data cleaning module unit, and a data output unit; The intelligent diagnosis algorithm module unit includes a system consistency algorithm module, a system reliability algorithm module, a system security algorithm module, and a comprehensive scoring algorithm module.

5. The intelligent diagnosis report generation system for lithium iron phosphate batteries for electrochemical energy storage according to claim 4, characterized in that, The data input unit is responsible for receiving the original data set to be processed and providing input for subsequent data cleaning and correction; The data major category correction unit identifies and corrects the errors in the data set to ensure the accuracy and consistency of the data; The data standardization unit converts the data into a unified format for subsequent processing and analysis; The data cleaning module unit adopts a sliding window mechanism, gradually moves the window by each data point until the entire time series is covered. For randomly missing data, a linear regression estimation method is used for filling. For sudden outlier data, the window size is determined according to the data characteristics and smoothing requirements. Starting from the beginning position of the time series, the data points within the window are summed and the average value is calculated, and the average value replaces the outlier; The data output unit is responsible for saving the preliminarily processed data and transmitting it to the intelligent diagnosis algorithm module through the communication interface to provide support for further data analysis and intelligent diagnosis.

6. The intelligent diagnosis report generation system for the lithium iron phosphate battery for electrochemical energy storage according to claim 5, wherein, The system consistency algorithm module includes voltage, temperature, internal resistance, and SOH consistency algorithm modules; By comparing the differences between the voltage and temperature of the real-time target battery and the median of multiple battery target parameters, and the differences between the internal resistance and SOH of the periodic target battery and the median of multiple battery target parameters, it is judged whether a specific battery shows abnormalities; The internal resistance consistency algorithm module uses the forgetting factor least squares method to analyze all voltage and current data during the charge and discharge process of the battery, calculates the internal resistance value of each battery, and calculates them for all batteries in the energy storage system in turn; The SOH consistency algorithm module adopts a neural network algorithm, calculates the SOH (state of health of the battery) of each battery based on all voltage, current, and temperature data during the charge and discharge process of the battery, and spreads to the SOH of all batteries in the energy storage system.

7. The intelligent diagnosis report generation system for the lithium iron phosphate battery for electrochemical energy storage according to claim 6, characterized in that, The system reliability algorithm module includes a self-discharge rate, dQ / dV curve, and temperature measurement point effectiveness algorithm module; The self-discharge rate algorithm module uses the extended Kalman method to calculate the SOC (state of charge) of the battery based on the real-time voltage and current data during the battery charging and discharging process, and performs this calculation on all the batteries in the energy storage system in sequence to determine whether the self-discharge rate of the battery is abnormal; The dQ / dV curve algorithm module analyzes the slope change before the steady state by performing differential calculation on the Q / V curve during the system charging and discharging process, and discriminates the reliability of the battery according to the number of positive and negative mutations of the slope; The temperature measurement point effectiveness algorithm module randomly selects moments during the battery charging and discharging process to analyze the temperature distribution. Under the condition that other factors are normal, it judges the reliability of the temperature measurement point based on whether the temperature changes suddenly between adjacent sampling points.

8. The intelligent diagnosis report generation system for lithium iron phosphate batteries for electrochemical energy storage according to claim 7, wherein The system security algorithm module includes device connection abnormality, overcharge / overdischarge risk prediction, and internal short circuit / thermal runaway risk prediction algorithm modules; By combining electrochemical impedance spectroscopy (EIS) and deep neural network (DNN), using machine learning algorithms to extract indicators for the relevant characteristics of the self-discharge effect and abnormal temperature rise effect, realizing early warning of potential faults, and predicting the probabilities of connection abnormality, overcharge / overdischarge risk, and internal short circuit / thermal runaway in the battery.

9. The intelligent diagnostic report generation system for the lithium iron phosphate battery for electrochemical energy storage according to claim 8, characterized in that The comprehensive scoring module includes scoring the system consistency, reliability, and security, and comprehensively scoring the system health; The specific calculation formula for the comprehensive system health score is as follows: In the formula, S t is the comprehensive system health score, and S i is the score of ten key indicators, where i = 1, 2.....

10.

10. The intelligent diagnosis report generation system for the lithium iron phosphate battery for electrochemical energy storage according to claim 9, characterized in that, The specific steps for presenting the index diagnosis level according to the comprehensive system health score are as follows: Compare and analyze the comprehensive system health score with a predetermined health score threshold, and present the diagnosis level of the index in four states: "excellent", "good", "pass", and "fail"; If the comprehensive system health score is greater than or equal to the first health score threshold, the diagnosis level of the index is presented as "excellent"; If the comprehensive system health score is greater than or equal to the second health score threshold and less than the first threshold, the diagnosis level of the index is presented as "good"; If the comprehensive system health score is greater than or equal to the third health score threshold and less than the second threshold, the diagnosis level of the index is presented as "pass"; If the comprehensive system health score is less than the third threshold, the diagnosis level of the index is presented as "fail"; When the diagnosis level is "pass" or "fail", the system will output the specific location information of the faulty battery cell.

Images