CN116401585B - Energy storage battery failure risk assessment method based on big data - Google Patents
Energy storage battery failure risk assessment method based on big data Download PDFInfo
- Publication number
- CN116401585B CN116401585B CN202310424785.4A CN202310424785A CN116401585B CN 116401585 B CN116401585 B CN 116401585B CN 202310424785 A CN202310424785 A CN 202310424785A CN 116401585 B CN116401585 B CN 116401585B
- Authority
- CN
- China
- Prior art keywords
- energy storage
- storage battery
- battery
- data
- performance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 213
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012502 risk assessment Methods 0.000 title claims abstract description 19
- 208000032953 Device battery issue Diseases 0.000 title claims abstract description 8
- 230000005611 electricity Effects 0.000 claims abstract description 16
- 231100000279 safety data Toxicity 0.000 claims abstract description 16
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000007599 discharging Methods 0.000 claims abstract description 7
- 238000011234 economic evaluation Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000012423 maintenance Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 17
- 230000036541 health Effects 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 3
- 238000011217 control strategy Methods 0.000 description 3
- 229910001416 lithium ion Inorganic materials 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 239000002253 acid Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- BNOODXBBXFZASF-UHFFFAOYSA-N [Na].[S] Chemical compound [Na].[S] BNOODXBBXFZASF-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- OJIJEKBXJYRIBZ-UHFFFAOYSA-N cadmium nickel Chemical compound [Ni].[Cd] OJIJEKBXJYRIBZ-UHFFFAOYSA-N 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000009849 deactivation Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000007772 electrode material Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005622 photoelectricity Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention discloses an energy storage battery failure risk assessment method based on big data, which comprises the following steps: s1, acquiring electricity parameters in the charging and discharging process of an energy storage battery by using a battery management system; s2, classifying parameter data in the electricity consumption parameters into safety data and performance data; s3, respectively constructing a safety failure model and a performance failure model by combining big data and historical data; s4, calculating the risk level of the battery by combining the safety score and the performance score output by the failure model; and S5, setting an acceptable risk criterion according to the risk level, and carrying out economic evaluation on the battery replacement. According to the energy storage battery risk assessment method combining the performance failure model and the safety failure model, the safety and the performance of the battery can be comprehensively considered, the risk level of the battery can be comprehensively assessed, and the accuracy is higher; based on the battery parameter data of big data, a more accurate model can be established, and further the accuracy of the evaluation result is improved.
Description
Technical Field
The invention relates to the technical field of battery risk assessment, in particular to an energy storage battery failure risk assessment method based on big data.
Background
The energy storage battery is a battery capable of converting electric energy into chemical energy and storing the chemical energy, and is used for storing electric energy generated by new energy sources such as a power grid, wind power, photoelectricity and the like so as to solve the problem that the new energy sources have larger fluctuation and are uncontrollable. With the continuous increase of the power generation of new energy, the demand of energy storage batteries is also increasing. Energy storage battery technology is well established, and mainly includes lead-acid batteries, lithium ion batteries, sodium-sulfur batteries, flow batteries, supercapacitors and the like.
Currently, an energy storage battery is a key energy storage device and is widely applied to the fields of renewable energy sources, smart grids, electric automobiles and the like. With the continuous development of technology, the performance of the energy storage battery is continuously improved, but due to the chemical nature and the complex internal structure, certain failure and safety risks exist. Therefore, the failure risk assessment of the energy storage battery has important practical significance and scientific value.
In order to effectively evaluate the failure risk of the energy storage battery, the development history and the related technical background of the energy storage battery need to be known. Currently, the primary energy storage battery technologies include lead-acid batteries, nickel-cadmium batteries, nickel-hydrogen batteries, lithium ion batteries, and the like. Among them, lithium ion batteries have become the most commonly used energy storage battery technology because of their advantages of high energy density, long life, rapid charge and discharge, etc.
The failure risk assessment of the energy storage battery refers to analysis and assessment of possible failures and safety problems of the energy storage battery in the use process, and aims to improve the reliability and safety of the energy storage battery. The failure and safety problems of the energy storage battery mainly comprise self-discharge, internal resistance increase, pole corrosion, electrode material deactivation, overhigh temperature, battery short circuit, combustion explosion and the like. Therefore, risk assessment of the energy storage battery is a necessary means for ensuring normal operation and use safety of the energy storage battery.
The failure of the energy storage battery brings great economic and environmental losses, so that risk assessment is required. The failure reasons of the energy storage battery include internal short circuit, overcharge, overdischarge, overhigh temperature and the like, and the problems may cause safety problems such as battery short circuit, electric leakage, explosion and the like. Aiming at the problems, failure risk assessment of the energy storage battery is needed, the risk level is determined, and corresponding measures are taken to ensure safe operation of the energy storage battery.
The existing energy storage battery risk assessment method mainly comprises an experimental method, a modeling and simulation method and a reliability analysis method. The experimental method is to perform experimental tests and analysis, such as discharge tests, cycle life tests, temperature tests and the like, on the energy storage battery. The modeling and simulation method is to analyze and evaluate the performance and failure risk of the energy storage battery by using computer simulation. The reliability analysis method is to analyze the structure and the performance of the energy storage battery so as to determine the probability and the influence of the failure.
However, the experimental method requires a lot of time and cost, and it is difficult to evaluate the full life of the energy storage battery. In addition, experimental methods may suffer from test errors and test result repeatability problems. The accuracy and reliability of modeling and simulation methods need to be improved, and multi-level and multi-scale simulation and verification are needed. The reliability analysis method needs to rely on reliability theory and data, and is difficult to apply to different types of energy storage batteries and different application scenes. Therefore, a more reasonable and comprehensive risk assessment method for the energy storage battery is needed, and the energy storage battery is monitored in all aspects, so that the purpose of no risk and no loss is achieved.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides an energy storage battery failure risk assessment method based on big data, so as to overcome the technical problems existing in the prior related art.
For this purpose, the invention adopts the following specific technical scheme:
an energy storage battery failure risk assessment method based on big data comprises the following steps:
s1, acquiring electricity parameters in the charging and discharging process of an energy storage battery by using a battery management system;
s2, classifying parameter data in the electricity consumption parameters into safety data and performance data;
s3, respectively constructing a safety failure model and a performance failure model by combining big data and historical data;
s4, calculating the risk level of the battery by combining the safety score and the performance score output by the failure model;
and S5, setting an acceptable risk criterion according to the risk level, and carrying out economic evaluation on the battery replacement.
Further, the method for respectively constructing the safety failure model and the performance failure model by combining the big data and the historical data comprises the following steps:
s31, inquiring and collecting the electricity parameters of the batteries of the same type as the energy storage battery by using a big data platform, and constructing a battery database;
s32, recording all electricity consumption parameters of the history operation process of the energy storage battery as history data;
s33, constructing a safety failure model, and calculating the safety score of the energy storage battery by utilizing the safety data;
s34, constructing a performance failure model, and calculating the performance score of the energy storage battery by using the performance data.
Further, constructing a safety failure model, and calculating the safety score of the energy storage battery by using the safety data comprises the following steps:
s331, screening a typical case with a safety fault in a battery database;
s332, constructing a safe failure model for failure probability calculation;
s333, respectively calculating the failure probability of each typical case under the premise of being used with the energy storage battery by using a safe failure model, and calculating a probability average value;
s334, calculating current safety data of the energy storage battery by using a safety failure model to obtain self failure probability, and taking the ratio of the failure probability to the probability average value as a safety score.
Further, constructing a security failure model for failure probability calculation includes the following steps:
s3321, collecting security data in a typical case as sample data;
s3322, extracting the use time length data of the energy storage battery in the sample data, and synchronizing the use time length and the corresponding safety data in each typical case;
s3323, in sample data, the total number of safety failure faults of the energy storage battery obeys poisson distribution, and a calculation formula is as follows:
s3324, obtaining an average failure rate in sample data and standard deviation of differences among multiple samples in the sample data, constructing a safe failure model, and calculating the safe failure probability of the energy storage battery, wherein the calculation formula is as follows:
wherein P (r|lambda) represents the total number of safety failure faults in the sample data, lambda represents the safety failure probability of the energy storage battery, M represents the average failure rate in the sample data, V represents the standard deviation of the difference among multiple samples in the sample data, T represents the accumulated use time length of the energy storage battery, and r represents the number of safety failures of the energy storage battery.
Further, constructing a performance failure model, and calculating a performance score of the energy storage battery by using the performance data comprises the following steps:
s341, setting a plurality of equidistant time nodes, calculating and dividing the use time length of the energy storage battery in each group of performance data in the battery database, and determining the respective performance parameters of the energy storage battery of each time node;
s342, selecting 70% of performance data in the battery database as a training data set, and selecting the remaining 30% of performance data in the battery database as a test data set;
s343, constructing a performance failure model by using the training data set, and testing the performance failure model by using the testing data set;
and S344, analyzing and processing the performance data of the energy storage battery by using the performance failure model to obtain the performance health of the energy storage battery, and taking the performance health as a performance score.
Further, utilizing the training data set and constructing the performance failure model includes the steps of:
s3431, acquiring the health temperature of the energy storage battery in an ideal state, and extracting the internal resistance data and the variation of the energy storage battery in the training data;
s3432, obtaining the output power and the battery temperature of the energy storage battery in the training data, and calculating the ratio between the output power and the heat;
s3433, acquiring battery capacity data and variation thereof of the energy storage battery in the training data, and calculating a battery capacity attenuation speed coefficient by utilizing a time relation of time nodes;
s3434, acquiring the cycle times of the energy storage battery, and calculating the decay speed coefficient of the service life of the energy storage battery.
Further, the calculation formula of the performance failure model is as follows:
wherein Q represents the performance health of the energy storage battery, C 0 Indicating a healthy temperature T 0 The battery capacity of the lower energy storage battery, R represents the internal resistance of the energy storage battery, k h Represents the ratio of the output power to the heat of the energy storage battery, k e Represents a battery capacity decay rate coefficient, k, of the energy storage battery S The decay speed coefficient representing the service life of the energy storage battery, S represents the current service life of the energy storage battery, S 0 Indicating energy storage battery healthKang Wendu T 0 Theoretical life of T 0 A healthy temperature T representing the theoretical condition of the energy storage battery a Representing the ambient temperature in the current performance data of the energy storage battery.
Further, the step of calculating the risk level of the battery by combining the safety score and the performance score output by the failure model comprises the following steps:
s41, setting five security levels and recording as A, wherein A= {1,2,3,4,5}, a scoring level corresponding table is established according to the values of the security scores, and the security levels corresponding to different security scores are determined;
s42, setting five performance levels and recording as B, wherein B= {1,2,3,4,5}, a scoring level corresponding table is established according to the numerical value of the security score, and the security level corresponding to the different performance scores is determined;
s43, calculating the risk level of the energy storage battery by integrating the safety level and the performance level, wherein the calculation formula is as follows:
F=αA+βB
wherein F represents a risk level of the energy storage battery, a represents a safety level, B represents a performance level, α represents a weight value of the safety level, β represents a weight value of the performance level, and α+β=1.
Further, setting an acceptable risk criterion according to the risk level, and performing economic evaluation on the battery replacement comprises the following steps:
s51, setting an acceptable risk criterion of the energy storage battery according to the risk level and the user demand;
s52, monitoring the energy storage battery in real time according to an acceptable risk criterion;
s53, judging whether maintenance and replacement of the energy storage battery are needed according to the real-time monitoring result;
s54, acquiring cost parameters of the energy storage battery, and performing economic evaluation on maintenance and replacement of the energy storage battery.
Further, acquiring cost parameters of the energy storage battery, and performing economic evaluation on maintenance and replacement of the energy storage battery comprises the following steps:
s541, acquiring purchase cost, use cost and residual value cost of the original energy storage battery, and calculating the comprehensive cost of the original energy storage battery under the current risk level;
s542, distributing the purchase cost of the original energy storage battery to each charging period according to the service life of the original energy storage battery, and calculating the depreciation value of each period of the battery;
s543, acquiring battery cost, labor cost and maintenance cost of replacing the energy storage battery, calculating average annual cost of replacing the battery, comparing the average annual cost with the original energy storage battery cost, and selecting an optimal maintenance replacement scheme.
The beneficial effects of the invention are as follows:
1. by constructing the energy storage battery risk assessment method combining the performance failure model and the safety failure model, the safety and performance of the battery can be comprehensively considered, the risk level of the battery can be comprehensively assessed, and the accuracy is higher; the battery parameter data based on big data can establish a more accurate model, further improve the accuracy of an evaluation result, dynamically evaluate the whole service life of the energy storage battery, discover potential risks in time and reduce accidents. Compared with the traditional evaluation method, only single factors such as the performance or the safety of the battery are often considered, and the risk of the energy storage battery can be evaluated more comprehensively by combining the performance failure model and the safety failure model, so that the performance and the safety condition of the energy storage battery can be predicted more accurately, and the risk of the battery can be evaluated more accurately.
2. Through designing the evaluation results of different grades and setting acceptable risk criteria, the energy storage battery can be effectively maintained and managed according to the evaluation results, the maintenance cost and economic loss are reduced, the use strategy, the control strategy and the replacement maintenance strategy of the energy storage battery are optimized, the service efficiency and the service life of the battery are improved, in addition, references can be provided for the design and the manufacture of the energy storage battery, manufacturers are helped to optimize the product design, and the product quality and the safety are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for evaluating risk of failure of an energy storage battery based on big data according to an embodiment of the present invention.
Detailed Description
According to the embodiment of the invention, an energy storage battery failure risk assessment method based on big data is provided.
The invention will be further described with reference to the accompanying drawings and detailed description, as shown in fig. 1, a method for evaluating failure risk of an energy storage battery based on big data according to an embodiment of the invention, the method includes the following steps:
s1, acquiring electricity parameters in the charging and discharging process of the energy storage battery by using a battery management system.
A battery management system (Battery Management System, BMS) is a device or software system for monitoring, controlling and protecting batteries. The BMS can monitor and control parameters such as electric quantity, current, temperature and voltage of the battery in real time, so that reliability, safety and service life of the battery are improved. The BMS is generally composed of two parts, namely hardware and software, wherein the hardware part mainly comprises a sampling module, a control module, a protection module and the like, and the software part mainly comprises data acquisition, data processing, state estimation, fault diagnosis and the like.
The electricity consumption parameters comprise voltage, current, temperature, SOC (State of Charge), SOH (State of Health), equivalent circuit model parameters, charge and discharge power, internal resistance of the battery, times of short circuit, liquid leakage, bulge and the like.
S2, classifying the parameter data in the electricity consumption parameters into safety data and performance data.
Depending on the nature and purpose of the electrical parameters, they can be divided into safety data (safety failure class data) and performance data (performance failure class data):
security failure class data: such data is mainly related to the safety of the battery, including the conditions of internal short circuit, overcharge, overdischarge, leakage, swelling and the like of the battery. These data are critical to the safety of the battery and if they occur, they may lead to serious consequences such as damage to the battery and even fire.
Performance failure class data: such data is primarily related to the performance of the battery, including parameters such as the charge, voltage, current, temperature, capacity, discharge power, etc. of the battery. These data are very important for the performance of the battery and can reflect the service life, reliability, stability, etc. of the battery.
In a Battery Management System (BMS), both types of data are monitored and processed. For the safety failure data, BMS monitors in real time through means such as a sensor and an algorithm to ensure the safe operation of the battery; for the performance failure data, the BMS adopts a corresponding control strategy according to the monitoring result, a preset threshold value and other parameters so as to optimize the performance and the service life of the battery.
The security failure data and the performance failure data are not completely independent, and have certain relevance. For example, over-charge or over-discharge of the battery may result in reduced capacity and service life of the battery, and thus these data belong to both safety failure class data and performance failure class data. Therefore, in battery management and evaluation, it is necessary to comprehensively consider these two types of data for optimal performance and safety.
S3, respectively constructing a safety failure model and a performance failure model by combining big data and historical data, wherein the method comprises the following steps of:
s31, inquiring and collecting the electricity consumption parameters of the battery of the same type as the energy storage battery by using the big data platform, and constructing a battery database.
S32, recording all electricity consumption parameters of the history operation process of the energy storage battery as history data.
S33, constructing a safety failure model, calculating the safety score of the energy storage battery by utilizing safety data, and comprising the following steps of:
s331, screening a typical case with a safety fault in a battery database.
S332, constructing a safe failure model for failure probability calculation, which comprises the following steps:
s3321, collecting security data in a typical case as sample data.
S3322, extracting the use time length data of the energy storage battery in the sample data, and synchronizing the use time length and the corresponding safety data in each typical case.
S3323, in sample data, the total number of safety failure faults of the energy storage battery obeys poisson distribution, and a calculation formula is as follows:
s3324, obtaining an average failure rate in sample data and standard deviation of differences among multiple samples in the sample data, constructing a safe failure model, and calculating the safe failure probability of the energy storage battery, wherein the calculation formula is as follows:
wherein P (r|lambda) represents the total number of safety failure faults in the sample data, lambda represents the safety failure probability of the energy storage battery, M represents the average failure rate in the sample data, V represents the standard deviation of the difference among multiple samples in the sample data, T represents the accumulated use time length of the energy storage battery, and r represents the number of safety failures of the energy storage battery.
S333, calculating the failure probability of each typical case under the premise of being used with the energy storage battery by using a safety failure model, and calculating a probability average value.
S334, calculating current safety data of the energy storage battery by using a safety failure model to obtain self failure probability, and taking the ratio of the failure probability to the probability average value as a safety score.
S34, constructing a performance failure model, calculating a performance score of the energy storage battery by using performance data, and comprising the following steps:
s341, setting a plurality of equidistant time nodes, calculating and dividing the use time length of the energy storage battery in each group of performance data in the battery database, and determining the respective performance parameters of the energy storage battery of each time node.
S342, selecting 70% of performance data in the battery database as a training data set, and selecting the remaining 30% of performance data in the battery database as a test data set.
S343, constructing a performance failure model by using the training data set, and testing the performance failure model by using the testing data set.
Wherein utilizing the training data set and constructing the performance failure model comprises the steps of:
s3431, acquiring the health temperature of the energy storage battery in the ideal state, and extracting the internal resistance data and the variation of the energy storage battery in the training data.
The healthy temperature of the energy storage battery in an ideal state can be realized by controlling the temperature of the energy storage battery in a laboratory. The energy storage battery is usually placed in an incubator or a temperature control chamber, and the temperature of the energy storage battery is controlled by controlling the temperature of the incubator or the temperature control chamber. In this process, a temperature sensor is required to measure the temperature of the energy storage battery to ensure that it is at a healthy temperature under ideal conditions.
The battery management system can acquire the internal resistance information of the battery by monitoring and analyzing the current and the voltage in the discharging process of the battery. Generally, the larger the internal resistance of the battery, the larger the voltage drop when the battery is discharged, and the current when the battery is discharged is also affected, so the internal resistance value of the battery can be calculated by monitoring the voltage and current signals during the discharging process of the battery.
S3432, obtaining the output power and the battery temperature of the energy storage battery in the training data, and calculating the ratio of the output power to the heat.
The battery management system may obtain the output power of the energy storage battery by monitoring the current and voltage signals during the discharge of the battery. Specifically, the output power of the battery is calculated using the following formula: p=v×i, where P represents the output power of the battery, V represents the output voltage of the battery, and I represents the output current of the battery.
In addition, the battery management system monitors the temperature of the battery in real time through a sensor or the like, and records the data. These data are used to calculate the average temperature or the trend of temperature change of the battery, evaluate the state of health and the service life of the battery, etc.
The ratio between the output power and the heat is calculated, and the calculation can be performed according to the efficiency of the battery. The efficiency of a battery refers to the ratio between the power output by the battery and the energy input, and generally decreases with increasing battery temperature. Therefore, the efficiency of the battery can be calculated using the output power and temperature data acquired by the battery management system, and then the ratio between the battery output power and the heat can be estimated based on the efficiency of the battery.
S3433, acquiring battery capacity data and variation of the energy storage battery in the training data, and calculating a battery capacity attenuation speed coefficient by using a time relation of the time nodes.
The battery management system may obtain the capacity data of the energy storage battery by monitoring current and voltage signals during discharging and charging of the battery. Specifically, the battery management system may be used to record data such as the discharge and charge time, current and voltage of the battery, and then process and analyze the data through a mathematical model to calculate the capacity of the battery. In order to calculate the battery capacity attenuation speed coefficient, the time relation of the time node acquired by the battery management system can be utilized to divide the capacity data of the battery into different time periods, then the attenuation speed of the battery capacity in each time period is calculated respectively, and finally the battery capacity attenuation speed coefficient is obtained.
S3434, acquiring the cycle times of the energy storage battery, and calculating the decay speed coefficient of the service life of the energy storage battery.
The battery management system calculates a life decay rate coefficient of the battery by monitoring the number of charge and discharge cycles of the energy storage battery. Specifically, the life decay rate coefficient of the battery can be calculated using the following formula:
wherein k is S Indicating the decay speed coefficient of the service life of the battery, N 1 And N 2 Respectively representing the charge and discharge cycle times of the battery at two time points, C 1 And C 2 The time elapsed between these two time points (may be in days, hours, minutes, etc.), respectively.
And S344, analyzing and processing the performance data of the energy storage battery by using the performance failure model to obtain the performance health of the energy storage battery, and taking the performance health as a performance score.
The calculation formula of the performance failure model is as follows:
wherein Q represents the performance health of the energy storage battery, C 0 Indicating a healthy temperature T 0 The battery capacity of the lower energy storage battery, R represents the internal resistance of the energy storage battery, k h Represents the ratio of the output power to the heat of the energy storage battery, k e Represents a battery capacity decay rate coefficient, k, of the energy storage battery S The decay speed coefficient representing the service life of the energy storage battery, S represents the current service life of the energy storage battery, S 0 Indicating the health temperature T of the energy storage battery 0 Theoretical life of T 0 A healthy temperature T representing the theoretical condition of the energy storage battery a Representing the ambient temperature in the current performance data of the energy storage battery.
S4, calculating the risk level of the battery by combining the safety score and the performance score output by the failure model, wherein the method comprises the following steps of:
s41, setting five security levels and recording as A, wherein A= {1,2,3,4,5}, a scoring level corresponding table is established according to the values of the security scores, and the security levels corresponding to different security scores are determined.
S42, setting five performance levels and recording as B, wherein B= {1,2,3,4,5}, establishing a scoring level corresponding table according to the values of the security scores, and determining the security levels corresponding to the different performance scores.
S43, calculating the risk level of the energy storage battery by integrating the safety level and the performance level, wherein the calculation formula is as follows:
F=αA+βB
wherein F represents a risk level of the energy storage battery, a represents a safety level, B represents a performance level, α represents a weight value of the safety level, β represents a weight value of the performance level, and α+β=1.
S5, setting an acceptable risk criterion according to the risk level, and carrying out economical evaluation on the electricity replacement, wherein the method comprises the following steps:
s51, setting an acceptable risk criterion of the energy storage battery according to the risk level and the user demand.
And S52, monitoring the energy storage battery in real time according to an acceptable risk criterion.
And S53, judging whether the energy storage battery needs to be maintained and replaced according to the real-time monitoring result.
S54, acquiring cost parameters of the energy storage battery, and performing economic evaluation on maintenance and replacement of the energy storage battery, wherein the method comprises the following steps of:
s541, acquiring purchase cost, use cost and residual value cost of the primary energy storage battery, and calculating the comprehensive cost of the primary energy storage battery under the current risk level.
S542, distributing the purchase cost of the primary energy storage battery to each charging period according to the service life of the primary energy storage battery, and calculating the depreciation value of each period of the battery.
S543, acquiring battery cost, labor cost and maintenance cost of replacing the energy storage battery, calculating average annual cost of replacing the battery, comparing the average annual cost with the original energy storage battery cost, and selecting an optimal maintenance replacement scheme.
In summary, by means of the technical scheme, the energy storage battery risk assessment method combining the performance failure model and the safety failure model is constructed, so that the safety and the performance of the battery can be comprehensively considered, the risk level of the battery can be comprehensively assessed, and the accuracy is higher; the battery parameter data based on big data can establish a more accurate model, further improve the accuracy of an evaluation result, dynamically evaluate the whole service life of the energy storage battery, discover potential risks in time and reduce accidents. Compared with the traditional evaluation method, only single factors such as the performance or the safety of the battery are often considered, and the risk of the energy storage battery can be evaluated more comprehensively by combining the performance failure model and the safety failure model, so that the performance and the safety condition of the energy storage battery can be predicted more accurately, and the risk of the battery can be evaluated more accurately. Through designing the evaluation results of different grades and setting acceptable risk criteria, the energy storage battery can be effectively maintained and managed according to the evaluation results, the maintenance cost and economic loss are reduced, the use strategy, the control strategy and the replacement maintenance strategy of the energy storage battery are optimized, the service efficiency and the service life of the battery are improved, in addition, references can be provided for the design and the manufacture of the energy storage battery, manufacturers are helped to optimize the product design, and the product quality and the safety are improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. The energy storage battery failure risk assessment method based on big data is characterized by comprising the following steps of:
s1, acquiring electricity parameters in the charging and discharging process of an energy storage battery by using a battery management system; s2, classifying parameter data in the electricity consumption parameters into safety data and performance data; s3, respectively constructing a safety failure model and a performance failure model by combining big data and historical data; s4, calculating the risk level of the battery by combining the safety score and the performance score output by the failure model; s5, setting an acceptable risk criterion according to the risk level, and carrying out economical evaluation on the battery replacement;
the step S3 specifically includes: s31, inquiring and collecting electricity consumption parameters of the energy storage batteries of the same type as the energy storage batteries by using a big data platform, and constructing a battery database; s32, recording all electricity consumption parameters of the history operation process of the energy storage battery as history data; s33, constructing a safety failure model, and calculating the safety score of the energy storage battery by using the safety data; s34, constructing a performance failure model, and calculating the performance score of the energy storage battery by using the performance data;
for step S33, it specifically includes: s331, screening typical cases with safety faults in the battery database; s332, constructing a safe failure model for failure probability calculation; the step S332 further specifically includes:
s3321, collecting the security data in the typical case as sample data;
s3322, extracting the use time length data of the energy storage battery in the sample data, and performing time synchronization on the use time length and the corresponding safety data in each typical case;
s3323, in the sample data, the total number of the safety failure faults of the energy storage battery obeys poisson distribution, and the calculation formula is as follows:
s3324, obtaining an average failure rate in the sample data and standard deviation of differences among multiple samples in the sample data, constructing a safety failure model, and calculating safety failure probability of the energy storage battery, wherein a calculation formula is as follows:
wherein P (r|lambda) represents the total number of fail-safe faults occurring in the sample data; λ represents a safety failure probability of the energy storage battery; m represents the average failure rate in the sample data; v represents the standard deviation of the differences between multiple samples in the sample data; t represents the accumulated use time of the energy storage battery; r represents the number of safety failures of the energy storage battery;
for step S34, it specifically includes: s341, setting a plurality of equidistant time nodes, calculating and dividing the use time length of the energy storage battery in each group of performance data in the battery database, and determining the respective performance parameters of the energy storage battery of each time node; s342, selecting 70% of performance data in the battery database as a training data set, and selecting the remaining 30% of performance data in the battery database as a test data set; s343, constructing a performance failure model by utilizing the training data set; the step S343 further specifically includes:
s3431, acquiring the health temperature of the energy storage battery in an ideal state, and extracting the internal resistance data and the variation of the energy storage battery in the training data;
s3432, obtaining the output power and the battery temperature of the energy storage battery in the training data, and calculating the ratio between the output power and the heat;
s3433, acquiring battery capacity data and variation of the energy storage battery in the training data, and calculating a battery capacity attenuation speed coefficient by utilizing the time relation of the time nodes;
s3434, acquiring the cycle times of the energy storage battery, and calculating the decay speed coefficient of the service life of the energy storage battery;
the calculation formula of the performance failure model is as follows:
wherein Q represents the performance health of the energy storage battery; c (C) 0 Indicating a healthy temperature T 0 The battery capacity of the lower energy storage battery; r represents the internal resistance of the energy storage battery; k (k) h Representing the ratio of the output power of the energy storage battery to the heat; k (k) e Representing a battery capacity decay rate coefficient of the energy storage battery; k (k) S A decay rate coefficient indicative of a lifetime of the energy storage battery; s represents the current service life of the energy storage battery; s is S 0 Indicating the health temperature T of the energy storage battery 0 The theoretical life of the following; t (T) 0 A healthy temperature indicative of a theoretical condition of the energy storage battery; t (T) a Representing the ambient temperature in the current performance data of the energy storage battery.
2. The method for evaluating the failure risk of an energy storage battery based on big data according to claim 1, wherein the constructing a safety failure model and calculating the safety score of the energy storage battery by using the safety data further comprises the following steps:
s333, respectively calculating the failure probability of each typical case under the premise of being used with the energy storage battery by using the safety failure model, and calculating a probability average value;
s334, calculating current safety data of the energy storage battery by using the safety failure model to obtain self failure probability, and taking the ratio of the failure probability to the probability average value as a safety score.
3. The method according to claim 1, wherein the step S343 is further performed with the test data set to test the performance failure model; the step S34 further includes a step S344 of analyzing and processing the performance data of the energy storage battery by using the performance failure model, so as to obtain the performance health of the energy storage battery, and using the performance health as a performance score.
4. The method for evaluating the risk of failure of the energy storage battery based on big data according to claim 1, wherein the calculation of the risk level of the battery by the safety score and the performance score output by the comprehensive failure model comprises the following steps:
s41, setting five security levels and recording as A, wherein A= {1,2,3,4,5}, a scoring level corresponding table is established according to the values of the security scores, and the security levels corresponding to different security scores are determined;
s42, setting five performance levels and recording as B, wherein B= {1,2,3,4,5}, a scoring level corresponding table is established according to the numerical value of the security score, and the security level corresponding to different performance scores is determined;
s43, calculating the risk level of the energy storage battery by integrating the security level and the performance level, wherein the calculation formula is as follows:
F=αA+βB
wherein F represents the risk level of the energy storage battery;
a represents a security level;
b represents a performance level;
alpha represents a weight value of the security level;
β represents a weight value of the performance level, and α+β=1.
5. The method for evaluating risk of failure of an energy storage battery based on big data according to claim 1, wherein the step of setting an acceptable risk criterion according to the risk level and evaluating the economy of the battery replacement comprises the steps of:
s51, setting an acceptable risk criterion of the energy storage battery according to the risk level and the user demand;
s52, monitoring the energy storage battery in real time according to the acceptable risk criterion;
s53, judging whether maintenance and replacement of the energy storage battery are needed according to the real-time monitoring result;
s54, acquiring cost parameters of the energy storage battery, and performing economic evaluation on maintenance and replacement of the energy storage battery.
6. The method for evaluating the failure risk of the energy storage battery based on big data according to claim 5, wherein the step of acquiring the cost parameter of the energy storage battery and evaluating the economical efficiency of the maintenance and replacement of the energy storage battery comprises the following steps:
s541, acquiring purchase cost, use cost and residual value cost of the original energy storage battery, and calculating the comprehensive cost of the original energy storage battery under the current risk level;
s542, distributing the purchase cost of the original energy storage battery to each charging period according to the service life of the original energy storage battery, and calculating the depreciation value of each period of the battery;
s543, acquiring battery cost, labor cost and maintenance cost of replacing the energy storage battery, calculating average annual cost of replacing the battery, comparing the average annual cost with the original energy storage battery cost, and selecting an optimal maintenance replacement scheme.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310424785.4A CN116401585B (en) | 2023-04-19 | 2023-04-19 | Energy storage battery failure risk assessment method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310424785.4A CN116401585B (en) | 2023-04-19 | 2023-04-19 | Energy storage battery failure risk assessment method based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116401585A CN116401585A (en) | 2023-07-07 |
CN116401585B true CN116401585B (en) | 2023-11-10 |
Family
ID=87017810
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310424785.4A Active CN116401585B (en) | 2023-04-19 | 2023-04-19 | Energy storage battery failure risk assessment method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116401585B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116736139B (en) * | 2023-07-13 | 2024-02-02 | 江苏果下科技有限公司 | SOC estimation method of household energy storage system |
CN117013606B (en) * | 2023-08-14 | 2024-05-17 | 欧米勒电气有限公司 | Intelligent energy storage control system for photovoltaic power generation based on artificial intelligence |
CN116755978A (en) * | 2023-08-21 | 2023-09-15 | 深圳惠科存储科技有限公司 | Memory running state evaluation method, electronic equipment and readable storage medium |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110687452A (en) * | 2019-09-05 | 2020-01-14 | 南京理工大学 | Lithium battery capacity online prediction method based on K-means clustering and Elman neural network |
CN111308376A (en) * | 2020-02-24 | 2020-06-19 | 上海蔚来汽车有限公司 | Power battery insulation monitoring method, system and device |
WO2020191800A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Method for predicting remaining service life of lithium-ion battery employing wde-optimized lstm network |
CN112477698A (en) * | 2020-11-17 | 2021-03-12 | 中山大学 | Active thermal management system for power battery and control method |
CN112684349A (en) * | 2021-01-25 | 2021-04-20 | 中国第一汽车股份有限公司 | Analysis method, verification method, device, equipment and medium for battery monomer failure |
WO2021208309A1 (en) * | 2020-04-17 | 2021-10-21 | 许继集团有限公司 | Method and system for online evaluation of electrochemical cell of energy storage power station |
CN113569402A (en) * | 2021-07-23 | 2021-10-29 | 四川大学 | Multi-level comprehensive evaluation method for safety state of high-capacity battery energy storage system |
CN114284589A (en) * | 2022-03-01 | 2022-04-05 | 深圳市海雷新能源有限公司 | Lithium battery intelligent monitoring management system based on internet |
CN114371408A (en) * | 2022-01-26 | 2022-04-19 | 上海玫克生储能科技有限公司 | Estimation method of battery charge state, and extraction method and device of charging curve |
CN114372417A (en) * | 2022-01-12 | 2022-04-19 | 青岛科技大学 | Electric vehicle battery health state and remaining life evaluation method based on charging network |
CN114386537A (en) * | 2022-03-23 | 2022-04-22 | 中国华能集团清洁能源技术研究院有限公司 | Lithium battery fault diagnosis method and device based on Catboost and electronic equipment |
CN114734873A (en) * | 2022-04-18 | 2022-07-12 | 北京航空航天大学 | Power battery unit thermal runaway early warning method based on cloud online data |
CN114879052A (en) * | 2022-06-01 | 2022-08-09 | 徐州市恒源电器有限公司 | Lithium ion battery thermal runaway safety evaluation method under vibration working condition |
CN115684936A (en) * | 2022-08-03 | 2023-02-03 | 北京航空航天大学 | Power battery health failure probability calculation and health failure map establishment method based on machine learning |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101942647B1 (en) * | 2017-04-04 | 2019-01-25 | 한국전력공사 | Apparatus for asset management of power transformers |
-
2023
- 2023-04-19 CN CN202310424785.4A patent/CN116401585B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020191800A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Method for predicting remaining service life of lithium-ion battery employing wde-optimized lstm network |
CN110687452A (en) * | 2019-09-05 | 2020-01-14 | 南京理工大学 | Lithium battery capacity online prediction method based on K-means clustering and Elman neural network |
CN111308376A (en) * | 2020-02-24 | 2020-06-19 | 上海蔚来汽车有限公司 | Power battery insulation monitoring method, system and device |
WO2021208309A1 (en) * | 2020-04-17 | 2021-10-21 | 许继集团有限公司 | Method and system for online evaluation of electrochemical cell of energy storage power station |
CN112477698A (en) * | 2020-11-17 | 2021-03-12 | 中山大学 | Active thermal management system for power battery and control method |
CN112684349A (en) * | 2021-01-25 | 2021-04-20 | 中国第一汽车股份有限公司 | Analysis method, verification method, device, equipment and medium for battery monomer failure |
CN113569402A (en) * | 2021-07-23 | 2021-10-29 | 四川大学 | Multi-level comprehensive evaluation method for safety state of high-capacity battery energy storage system |
CN114372417A (en) * | 2022-01-12 | 2022-04-19 | 青岛科技大学 | Electric vehicle battery health state and remaining life evaluation method based on charging network |
CN114371408A (en) * | 2022-01-26 | 2022-04-19 | 上海玫克生储能科技有限公司 | Estimation method of battery charge state, and extraction method and device of charging curve |
CN114284589A (en) * | 2022-03-01 | 2022-04-05 | 深圳市海雷新能源有限公司 | Lithium battery intelligent monitoring management system based on internet |
CN114386537A (en) * | 2022-03-23 | 2022-04-22 | 中国华能集团清洁能源技术研究院有限公司 | Lithium battery fault diagnosis method and device based on Catboost and electronic equipment |
CN114734873A (en) * | 2022-04-18 | 2022-07-12 | 北京航空航天大学 | Power battery unit thermal runaway early warning method based on cloud online data |
CN114879052A (en) * | 2022-06-01 | 2022-08-09 | 徐州市恒源电器有限公司 | Lithium ion battery thermal runaway safety evaluation method under vibration working condition |
CN115684936A (en) * | 2022-08-03 | 2023-02-03 | 北京航空航天大学 | Power battery health failure probability calculation and health failure map establishment method based on machine learning |
Non-Patent Citations (3)
Title |
---|
电动汽车动力电池特性仿真系统;羌嘉曦;敖国强;何建辉;陈自强;杨林;;上海交通大学学报(08);全文 * |
锂电池失效分析与研究进展;王其钰;王朔;周格;张杰男;郑杰允;禹习谦;李泓;;物理学报(第12期);全文 * |
锂离子电池安全性测试与评价方法分析;田君;田崔钧;王一拓;佟蕾;赵鼎;胡道中;高洪波;陈芬;高申;王子冬;刘家亮;;储能科学与技术(第06期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN116401585A (en) | 2023-07-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112731159B (en) | Method for pre-judging and positioning battery faults of battery compartment of energy storage power station | |
CN116401585B (en) | Energy storage battery failure risk assessment method based on big data | |
CN111584952B (en) | Method and system for online evaluation of electrochemical cells of energy storage power station | |
CN109725266B (en) | Method and device for calculating SOH (state of health) of battery | |
CN113933732B (en) | New energy automobile power battery health state analysis method, system and storage medium | |
CN114371409B (en) | Training method of battery state prediction model, battery state prediction method and device | |
WO2008128426A1 (en) | An expert diagnostic method for analyzing performance of an accumulator cell | |
CN111257755B (en) | Method for preventive detection and diagnosis of battery pack | |
CN116381541B (en) | Health assessment method and system for energy storage lithium battery system | |
CN115267555A (en) | Battery SOH (State of health) evaluation system of energy storage system based on battery multipoint temperature measurement | |
CN113687251B (en) | Double-model-based lithium ion battery pack voltage abnormality fault diagnosis method | |
CN116845391A (en) | Lithium battery energy storage management system | |
CN115616425A (en) | Battery performance analysis method, electronic equipment and energy storage system | |
CN115480180A (en) | New energy battery health diagnosis and analysis method | |
CN115061058A (en) | Method and system for measuring and calculating gradient utilization residual life of retired power battery | |
CN116754984A (en) | Battery consistency detection method and related device | |
CN115128468A (en) | Chemical energy storage battery PHM undervoltage fault prediction method | |
CN114755595A (en) | Cloud energy storage full-capacity cell internal resistance calculation and evaluation method | |
CN114545275A (en) | Indirect prediction method for remaining service life of lithium ion battery | |
CN117686935A (en) | Battery RUL prediction method based on voltage probability density | |
CN117007975A (en) | Method for performing reinforcement learning on battery capacity attenuation assessment by collecting multi-point temperatures of battery cells of energy storage battery | |
CN115656837A (en) | Fault prediction method for series-connected battery | |
CN115318683A (en) | Screening method and device for whole-package batteries | |
CN115308609B (en) | Lithium ion battery thickness prediction method and device and lithium ion battery | |
Gu | Health State Estimation of Electric Vehicle Power Battery Based on K-means Algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |