Intelligent power battery discharge performance detection system and method

Abstract

The present invention discloses an intelligent power battery discharge performance detection system and method, which relate to the technical field of battery performance detection. The system comprises a simulated environment monitoring module, a power battery monitoring module, an information processing and analysis module, and a detection and early warning display module. The simulated environment monitoring module is used to build a simulated environment test platform, simulate the high temperature environment in summer and the low temperature environment in the tunnel, and control the temperature change frequency and the number of changes to simulate the real scene, monitor the environmental data of the car equipped with the power battery, and record the maximum value and the number of changes of the current temperature difference. The technical points are as follows: the present invention comprehensively utilizes environmental simulation, machine learning modeling, performance prediction and intelligent early warning technology, solves the key technical problems that the actual use environment is difficult to control and the battery performance is difficult to accurately predict, and significantly improves the performance evaluation and safety monitoring level of the power battery in a complex environment.

Description

Technical Field

[0001] The present invention relates to the field of battery performance detection and calculation technology, and in particular to an intelligent power battery discharge performance detection system and method. Background Art

[0002] Battery performance testing technology is a technology used to evaluate battery performance. It aims to determine information such as the battery's charge state, capacity, internal resistance, charge and discharge efficiency, and health status. When testing battery performance, it is necessary to calculate and process based on various data; this information is crucial for the design, manufacture, use and maintenance of batteries; the following are some commonly used battery performance testing technologies, such as: voltage measurement, current measurement, temperature detection, electrochemical impedance spectroscopy (EIS) analysis, and cycle performance testing; among them, voltage measurement is to evaluate the battery's charge state and capacity by measuring the battery's voltage; as the battery charges and discharges, the voltage will change accordingly, so the battery's state can be inferred based on the voltage curve; current measurement is to monitor the current during the battery's charge and discharge process to evaluate the battery's charge and discharge efficiency and the battery's internal resistance; current measurement can also be used to detect abnormal conditions, such as battery overload or short circuit; the above technologies are used in combination to comprehensively evaluate the battery's performance and health status, providing an important reference for the design, manufacture and application of batteries.

[0003] The existing application announcement number is CN103529402B, and the technical solution specified in the document named "System and method for low-temperature charging and discharging performance detection of power-type power lithium-ion batteries in high-cold areas" includes: a low-temperature constant temperature box, a battery charging and discharging test device and a battery performance test device; the battery performance test device controls the battery charging and discharging test device to perform nC rate charging and discharging tests on the power-type power lithium-ion battery to be tested, and calculates the charging capacity of the battery to be tested divided by the rated capacity of the battery to be tested according to the obtained voltage, current, temperature and charging time and discharge time, which is the nC rate charging capacity determination coefficient of the battery to be tested. n is a positive number greater than 2 and less than 20, and it is used to measure the charging and discharging performance of power-type power lithium-ion batteries in low temperature environments; the scenario targeted by this detection system is only high-cold areas.

[0004] In combination with the above documents and prior art, when testing the discharge performance of a power battery, it is necessary not only to consider its own operating parameters, such as the current and voltage during operation, but also to consider the external environment. Usually, a car equipped with a power battery is only in a relatively stable environment when driving. However, when driving on an island or a route with several tunnels, the power battery needs to pass through the tunnel frequently. In the high temperature environment in summer, the temperature in the tunnel will be about 5 to 10°C lower than the outside world. This will make the environment in which the power battery is located unstable. When the car frequently enters and exits the tunnel, a large temperature difference will occur, thereby affecting the performance stability of the power battery. At present, the performance test of the power battery only considers its own operating parameters and stable environmental data, and then calculates its comprehensive indicators to evaluate the performance of the power battery. In an environment with a temperature difference, the existing detection method cannot adapt, or the test results obtained during the test have large errors. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] In view of the shortcomings of the prior art, the present invention provides an intelligent power battery discharge performance detection system and method, which comprehensively utilizes technologies such as environmental simulation, machine learning modeling, performance prediction and intelligent early warning, solves the key technical problems that the actual use environment is difficult to control and the battery performance is difficult to accurately predict, significantly improves the performance evaluation and safety monitoring level of power batteries in complex environments, and solves the problems raised in the background technology.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] Intelligent power battery discharge performance detection system and method, including:

[0010] The simulation environment monitoring module builds a simulation environment test platform to simulate the high temperature environment in summer and the low temperature environment in the tunnel, and controls the frequency and number of temperature changes to simulate real scenes, monitor the environmental data of the car equipped with power batteries, and record the maximum value and number of changes of the current temperature difference;

[0011] The power battery monitoring module obtains the power battery operating parameters at the moment when the temperature difference reaches the maximum value each time;

[0012] The information processing and analysis module obtains the vehicle performance status index I at the corresponding moment of the maximum value of n changes from the high temperature environment in summer to the low temperature environment in the tunnel 高 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator predictions Tfy 高, synchronously obtain the vehicle performance status index I at the corresponding time of the maximum value of n changes from the low temperature environment in the tunnel to the high temperature environment in summer 低 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator prediction values ​​Tfy 低 ;

[0013] The detection and warning display module, when the power battery is actually running, if the car enters the tunnel from the outside, the predicted value of the car performance index Tfy will be obtained 高 Compared with the preset evaluation threshold group, if the vehicle performance index prediction value Tfy 高 If the evaluation threshold value group is exceeded, a warning signal is issued and an adjustment strategy is executed; if the car enters the outside world from the tunnel, the predicted value of the car performance index Tfy 低 Compared with the evaluation threshold group, if the predicted value of the vehicle performance index Tfy 低 If the assessment threshold group is exceeded, a warning signal is issued and an adjustment strategy is implemented.

[0014] Furthermore, the corresponding temperature range for simulating the high temperature environment in summer is 30°C to 40°C, and the corresponding temperature range for simulating the low temperature environment in the tunnel is 10°C to 20°C. The environmental data of the vehicle equipped with the power battery is monitored, including but not limited to the ambient temperature.

[0015] Furthermore, the operating parameters of the power battery include battery temperature, voltage, current and capacity.

[0016] Furthermore, the process of obtaining the power battery operating parameters at each time when the temperature difference reaches the maximum value is as follows:

[0017] S101, temperature difference detection: monitor the change of ambient temperature, and record the timestamp of the maximum value of the temperature difference obtained, and use it as the time point for analysis;

[0018] S102, power battery parameter acquisition: at the recorded time point, the operating parameters of the power battery are acquired, and the operating parameters are acquired by connecting to a matching battery management system BMS;

[0019] S103, data recording and processing: the acquired power battery parameters and corresponding timestamps are summarized and recorded, and subsequent data preprocessing is performed, and the data preprocessing is data cleaning.

[0020] Further, the vehicle performance status index I at the corresponding time of the maximum value of n changes from the high temperature environment in summer to the low temperature environment in the tunnel is obtained. 高Previously, it was necessary to extract the first operating data set and the current ambient temperature at the time when the maximum temperature difference was reached each time the power battery operating parameters changed from the high temperature environment in summer to the low temperature environment in the tunnel. Based on the first operating data set and the ambient temperature, an operating status analysis and calculation model was built to generate the vehicle performance status index I at the time corresponding to the maximum value of the change from the high temperature environment in summer to the low temperature environment in the tunnel. 高 , where n=1, 2, …, k, and k is a positive integer.

[0021] Further, the vehicle performance status index I at the time corresponding to the maximum value of the change from the high temperature environment in summer to the low temperature environment in the tunnel is generated. 高 , the formula is as follows:

[0022]

[0023] In formula (1), dw, ir, ur, rl represent battery temperature, voltage, current and capacity respectively, ir*ur represents real-time output power, w1, w2, w3 represent preset proportional coefficients of battery temperature, real-time output power and capacity respectively, and w1>w2>w3>0, the value range of w1, w2, w3 is 0~1, and ex represents correction value;

[0024] In formula (2), hw represents the ambient temperature, G represents the constant correction coefficient, and the value range of G is 0 to 1;

[0025] Calculate the vehicle performance status index I at the time of maximum change from the low temperature environment in the tunnel to the high temperature environment in summer 低 The formula used to calculate the vehicle performance status index I 高 The principle is the same.

[0026] Furthermore, the method for obtaining the predicted value of the automobile performance index is as follows:

[0027] S201. Select a machine learning algorithm to establish a predicted value Tfy for vehicle performance indicators 高 and vehicle performance status index I 高 The relationship between the vehicle performance index prediction value Tfy 低 and vehicle performance status index I 低 the relationship between;

[0028] The machine learning algorithm includes any one of regression analysis, decision tree and random forest;

[0029] S202, using the selected algorithm to train the data, establish a model to predict the corresponding vehicle performance index, and during the training process, the model learns and calculates the corresponding vehicle performance status index I 低 To predict the vehicle performance index prediction value Tfy低 , according to the vehicle performance status index I 高 To predict the vehicle performance index prediction value Tfy 高 ;

[0030] S203, using a cross-validation method to evaluate the trained model;

[0031] S204: Use the trained model to predict future vehicle performance index prediction values.

[0032] Furthermore, during the period of obtaining the predicted value of the vehicle performance index, the model formula used is as follows:

[0033] Tfy 高 =f(text{I 高})+eps

[0034] In the formula, f(text{I 高}) represents the model function, and the model function is a decision tree, eps represents the error factor; for the predicted value of the vehicle performance index Tfy 低 The same model formula is also used for calculation.

[0035] Furthermore, when a warning signal is issued, the adjustment strategy executed is: issuing a voice command of "please reduce the speed or stop for rest".

[0036] The intelligent power battery discharge performance detection method comprises the following steps:

[0037] S1. Build a simulated environment test platform to simulate the high temperature environment in summer and the low temperature environment in the tunnel, and control the frequency and number of temperature changes to simulate the real scene, monitor the environmental data of the car equipped with power battery, and record the maximum value and number of changes of the current temperature difference;

[0038] S2. Obtaining the power battery operating parameters at the time when each temperature difference reaches the maximum value, including battery temperature, voltage, current and capacity;

[0039] S3, obtaining the vehicle performance status index I at the time corresponding to the maximum value of n changes from the high temperature environment in summer to the low temperature environment in the tunnel 高 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator predictions Tfy 高 , synchronously obtain the vehicle performance status index I at the corresponding time of the maximum value of n changes from the low temperature environment in the tunnel to the high temperature environment in summer 低 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator prediction values ​​Tfy 低 ;

[0040] S4. When the power battery is actually running, if the car enters the tunnel from the outside, the predicted value of the car performance index Tfy 高 Compared with the preset evaluation threshold group, if the vehicle performance index prediction value Tfy 高 If the evaluation threshold value group is exceeded, a warning signal is issued and an adjustment strategy is executed; if the car enters the outside world from the tunnel, the predicted value of the car performance index Tfy 低 Compared with the evaluation threshold group, if the predicted value of the vehicle performance index Tfy 低 If the assessment threshold group is exceeded, a warning signal is issued and an adjustment strategy is implemented.

[0041] (III) Beneficial effects

[0042] The present invention provides an intelligent power battery discharge performance detection system and method, which has the following beneficial effects:

[0043] Through the simulated environmental test platform and power battery monitoring, temperature changes can be effectively controlled and environmental data can be obtained, thus solving the impact of uncontrollable environmental factors on battery performance evaluation in actual road tests; it can comprehensively evaluate the performance of power batteries in different temperature environments according to actual application scenarios, improving the detection accuracy and reliability of the system; at the same time, it can also provide important data support for vehicle performance optimization and fault diagnosis;

[0044] It can simulate the real hot and cold alternating environment and monitor the changes in ambient temperature to obtain the operating data of the battery in a complex environment. By using machine learning algorithms to build a model, it can accurately predict the predicted value of the vehicle performance index based on the real-time monitored power battery operating parameters and ambient temperature data, and compare it with the preset evaluation threshold group. When it exceeds the range of the evaluation threshold group, it will issue a warning in time and implement adjustment strategies. By timely discovering possible abnormal conditions in the power battery performance and taking corresponding remedial measures, the safety of the power battery in use is improved;

[0045] In summary, the solution comprehensively utilizes environmental simulation, machine learning modeling, performance prediction and intelligent early warning technologies to solve the key technical problems that the actual use environment is difficult to control and the battery performance is difficult to accurately predict, significantly improving the performance evaluation and safety monitoring level of power batteries in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the module structure of the intelligent power battery discharge performance detection system of the present invention;

[0047] Figure 2 It is a schematic diagram of the overall process of the intelligent power battery discharge performance detection method in the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Example 1: Please refer to Figure 1 This embodiment provides an intelligent power battery discharge performance detection system, which includes a simulated environment monitoring module, a power battery monitoring module, an information processing and analysis module, and a detection and early warning display module. The application scenario of the entire system is the situation when a car equipped with a power battery enters and exits several tunnels in a high temperature summer environment. A temperature difference will be generated during the process of entering and exiting the tunnel. The detection system specifically considers the impact of the temperature difference and the number of times it occurs on the battery discharge performance, and realizes the detection work by simulating the above scenario, which reflects the intelligent design of the system;

[0050] The simulation environment monitoring module builds a simulation environment test platform to simulate the high temperature environment in summer and the low temperature environment in the tunnel, and controls the frequency and number of temperature changes to simulate real scenes, monitor the environmental data of the car equipped with power batteries, and record the maximum value and number of changes of the current temperature difference;

[0051] Among them, the simulation of high temperature environment in summer and low temperature environment in tunnel is to simulate the scene of cars entering and exiting the tunnel and going through the alternating hot and cold conditions. During this period, the environment needs to be monitored in real time and data needs to be recorded;

[0052] Temperature control system: The simulated environment test platform needs to be equipped with a temperature control system, that is, temperature control equipment, such as a constant temperature box and a temperature controller, to control the temperature of the test environment. For simulating the high temperature environment in summer, a higher temperature range is set, such as 30℃ to 40℃; for simulating the low temperature environment in the tunnel, a lower temperature range is set, such as 10℃ to 20℃;

[0053] Environmental monitoring system: Install environmental monitoring sensors in the temperature control equipment, including temperature and humidity related sensors, to monitor the environmental data of the test environment in real time. These data will be used to evaluate the discharge performance of the power battery under different temperature environments;

[0054] Temperature change control: Control the rate and frequency of temperature change according to the requirements of the simulation scenario; in the scenario of simulating tunnel entry and exit, set a certain time interval, for example, change the temperature from high temperature to low temperature or vice versa every 30 minutes, and then change from low temperature to high temperature, and control the rate of temperature change to simulate the real scenario;

[0055] For example, suppose we want to simulate a car entering a tunnel;

[0056] First, we set up a temperature control system and adjusted the temperature to the low temperature range in the tunnel, such as 15°C. Then, we installed environmental monitoring sensors to monitor the temperature and set up temperature change control to change the temperature from 15°C to 35°C every 3 minutes, and then from 35°C to 15°C. The number of changes was set to 3 times to simulate the temperature changes when the vehicle enters and exits the tunnel. Specifically, by simulating the high temperature environment in summer and the low temperature environment in the tunnel, as well as controlling the frequency and number of temperature changes, we can more realistically simulate the performance of the car in different environments, which helps to more accurately evaluate the discharge performance of the power battery.

[0057] The power battery monitoring module obtains the power battery operating parameters at the moment when the temperature difference reaches the maximum value each time;

[0058] Among them, the power battery monitoring module is responsible for obtaining the power battery operating parameters at each time when the temperature difference reaches the maximum value, so as to analyze the response of the battery when the temperature changes; the specific steps are as follows:

[0059] S101, temperature difference detection: monitor the change of ambient temperature, and record the timestamp of the maximum value of the temperature difference obtained, and use it as the time point for analysis;

[0060] S102, power battery parameter acquisition: at the recorded time point, the operating parameters of the power battery are acquired, and the operating parameters include battery temperature, voltage, current and capacity, and these parameters are acquired by connecting to a battery management system BMS or other monitoring equipment;

[0061] S103, data recording and processing: the acquired power battery parameters and corresponding timestamps are summarized and recorded, and subsequent data preprocessing is performed; these data can be used to evaluate the discharge performance of the power battery when the temperature changes, such as the impact of temperature on the battery capacity, the change of the internal resistance of the battery, etc.; the data preprocessing includes data cleaning;

[0062] For example, suppose we are simulating the temperature changes when a car passes through a tunnel; during the simulation, it is detected that the ambient temperature at the tunnel exit suddenly rises and reaches the maximum temperature difference; at this time, the power battery monitoring module records the time of this moment and obtains the operating parameters of the power battery; for example, it records that the power battery temperature is 25°C, the voltage is 350V, the current is 50A, and the capacity is 80%; these data can be used for subsequent analysis to evaluate the discharge performance of the battery in a high temperature environment, and generate alarms or suggestions as needed.

[0063] Specifically, the power battery monitoring module can obtain the battery operating parameters when the ambient temperature change reaches its maximum value. These data help to more accurately evaluate the battery's discharge performance under different temperature environments, including parameters such as battery temperature, voltage, current and capacity, thereby improving the accuracy and reliability of battery performance evaluation.

[0064] This solution solves the problems of temperature change control and environmental data acquisition that are difficult to carry out in actual scenarios. Through the simulation of environmental test platform and power battery monitoring, it can effectively control temperature changes and acquire environmental data, thus solving the impact of uncontrollable environmental factors on battery performance evaluation in actual road tests; it can comprehensively evaluate the performance of power batteries in different temperature environments according to actual application scenarios, thereby improving the detection accuracy and reliability of the system; at the same time, it can also provide important data support for vehicle performance optimization and fault diagnosis.

[0065] The information processing and analysis module obtains the vehicle performance status index I at the corresponding moment of the maximum value of n changes from the high temperature environment in summer to the low temperature environment in the tunnel 高 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator predictions Tfy 高 , synchronously obtain the vehicle performance status index I at the corresponding time of the maximum value of n changes from the low temperature environment in the tunnel to the high temperature environment in summer 低 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator prediction values ​​Tfy 低 ; n = 1, 2, ..., k, k is a positive integer, and the purpose of obtaining n times is to provide a large number of numbers to facilitate model training, thereby improving the accuracy of training results;

[0066] Among them, the vehicle performance status index I at the corresponding moment of the maximum value of the n-time change from the high temperature environment in summer to the low temperature environment in the tunnel is obtained 高 Previously, it was necessary to extract the first operating data set and the current ambient temperature at the time when the maximum temperature difference was reached each time the power battery operating parameters changed from the high temperature environment in summer to the low temperature environment in the tunnel. Based on the first operating data set and the ambient temperature, an operating status analysis and calculation model was built to generate the vehicle performance status index I at the time corresponding to the maximum value of the change from the high temperature environment in summer to the low temperature environment in the tunnel. 高 , the formula is as follows:

[0067]

[0068] In formula (1), dw, ir, ur, rl represent battery temperature, voltage, current and capacity respectively, ir*ur represents real-time output power, w1, w2, w3 represent preset proportional coefficients of battery temperature, real-time output power and capacity respectively, and w1>w2>w3>0, the value range of w1, w2, w3 is 0~1, and ex represents correction value;

[0069] In formula (2), hw represents the ambient temperature, G represents the constant correction coefficient, the specific value of which can be adjusted and set by the user, or generated by analytical function fitting, and the value range of G is 0 to 1;

[0070] For vehicle performance status indicators I 低 The calculation method of is also based on the same principle;

[0071] Get the vehicle performance status index I at the time of the maximum value of n changes from the low temperature environment in the tunnel to the high temperature environment in summer 低 Previously, it was necessary to extract the second operating data set and the current ambient temperature at the time when the maximum temperature difference was reached each time from the low temperature environment in the tunnel to the high temperature environment in summer in the power battery operating parameters. Based on the second operating data set and the ambient temperature, an operating status analysis and calculation model was built to generate the vehicle performance status index I at the time corresponding to the maximum temperature difference from the low temperature environment in the tunnel to the high temperature environment in summer. 低 , the formula based on which the vehicle performance status index I is calculated 高 The principle is the same, so I won’t go into details here.

[0072] The predicted values ​​of vehicle performance indicators are obtained as follows:

[0073] S201. Select a machine learning algorithm to establish a predicted value Tfy for vehicle performance indicators 高 and vehicle performance status index I 高 The relationship between the vehicle performance index prediction value Tfy 低 and vehicle performance status index I 低 the relationship between;

[0074] The machine learning algorithm includes any one of regression analysis, decision tree and random forest;

[0075] S202, using the selected algorithm to train the data, and establish a model to predict the corresponding vehicle performance indicators. During the training process, the model will learn how to predict the corresponding vehicle performance indicators according to the vehicle performance status indicators. 低 To predict the vehicle performance index prediction value Tfy 低 , how to use the vehicle performance status indicator I 高 To predict the vehicle performance index prediction value Tfy 高 ;

[0076] S203. Evaluate the trained model using a validation set or cross-validation method to ensure that the model has good generalization ability and prediction performance;

[0077] S204, using the trained model to predict the future vehicle performance index prediction value, and performing corresponding operations or adjustments according to the prediction results; the model formula used during the process is as follows:

[0078] Tfy 高 =f(text{I 高})+eps

[0079] In the formula, f(text{I 高}) represents the model function, eps represents the error factor, and the value range of the error factor is -1 to 1;

[0080] A model function can be any function that can map input features to outputs. In machine learning, common model functions include linear functions, polynomial functions, decision trees, and neural networks. In linear functions, it is assumed that the relationship between features and outputs is linear. Polynomial functions can capture more complex nonlinear relationships. A decision tree is a tree structure that predicts outputs by recursively partitioning features, with each leaf node corresponding to an output value. A neural network consists of multiple layers of neurons, each of which performs a weighted combination of inputs and performs a nonlinear transformation through an activation function. The final output is given by the output layer. The model function specifically used in this embodiment is a decision tree. The error factor is set according to actual needs.

[0081] For the predicted value of automobile performance index Tfy 低 The same model formula is used for calculation and no further elaboration is given here.

[0082] For example, suppose we have collected the vehicle performance status index I at the time of the maximum value of the change from the high temperature environment in summer to the low temperature environment in the tunnel for n times 高 , we can use the random forest regression model to establish these values ​​and the predicted values ​​of the vehicle performance index Tfy 高 The relationship between the two is obtained by training and verifying the data, and then we can use the vehicle performance status index I 高 To predict the vehicle performance index prediction value Tfy 高 ; For example, when the vehicle performance status indicator I 高 When the value is 15, the predicted value of the vehicle performance index Tfy predicted by the model 高 is 32.

[0083] Detection and early warning display module, when the power battery is actually running;

[0084] If a car enters the tunnel from the outside, according to the car performance status index I 高 Predict the vehicle performance index prediction value Tfy 高 and the predicted value of vehicle performance index Tfy 高 Compared with the preset evaluation threshold group, if the vehicle performance index prediction value Tfy 高 If the evaluation threshold value is exceeded, a warning signal is issued and an adjustment strategy is executed; if the predicted value of the vehicle performance index Tfy 高 If the evaluation threshold group is not exceeded, the system will not take any response action;

[0085] If the car enters the outside world from the tunnel, according to the car performance status index I 低 Predict the vehicle performance index prediction value Tfy 低 and the predicted value of vehicle performance index Tfy 低 Compared with the preset evaluation threshold group, if the vehicle performance index prediction value Tfy 低 If the evaluation threshold value is exceeded, a warning signal is issued and an adjustment strategy is executed; if the predicted value of the vehicle performance index Tfy 低 If the evaluation threshold group is not exceeded, the system will not take any response action;

[0086] Among them, the evaluation threshold group represents the state indicator range corresponding to the power battery under normal working conditions, which can be set according to the historical data analysis extracted from the simulation environment test platform, and can also be adjusted accordingly according to actual needs;

[0087] When a warning signal is issued, it is usually flashing through a display screen on the car, and the adjustment strategy implemented is: a voice command of "please reduce speed or stop for repairs" is issued, and the driver of the car equipped with a power battery continues to reduce the speed according to the voice command until the voice command stops. If the voice command continues to be issued, the driver finds a suitable location to stop for repairs based on road conditions, and can contact the car staff for remote guidance or request on-site maintenance.

[0088] Specifically, the solution can simulate a real alternating hot and cold environment and monitor changes in ambient temperature to obtain the operating data of the battery in a complex environment. By using a machine learning algorithm to establish a model, the predicted value of the vehicle performance indicator can be accurately predicted based on the real-time monitored power battery operating parameters and ambient temperature data. The predicted value is compared with the preset evaluation threshold group and an early warning is issued in time when it exceeds the range of the evaluation threshold group, and an adjustment strategy is implemented. By promptly discovering possible abnormal conditions in the power battery performance and taking corresponding remedial measures, the safety of the power battery during use is improved.

[0089] In summary, the solution comprehensively utilizes technologies such as environmental simulation, machine learning modeling, performance prediction and intelligent early warning, which solves the key technical problems that the actual use environment is difficult to control and the battery performance is difficult to accurately predict, and significantly improves the performance evaluation and safety monitoring level of power batteries in complex environments.

[0090] Example 2: Please refer to Figure 2 Based on Example 1, this embodiment also provides an intelligent power battery discharge performance detection method, including the following specific steps:

[0091] S1. Build a simulated environment test platform to simulate the high temperature environment in summer and the low temperature environment in the tunnel, and control the frequency and number of temperature changes to simulate the real scene, monitor the environmental data of the car equipped with power battery, and record the maximum value and number of changes of the current temperature difference;

[0092] S2. Obtaining the power battery operating parameters at the time when each temperature difference reaches the maximum value, including battery temperature, voltage, current and capacity;

[0093] S3, obtaining the vehicle performance status index I at the time corresponding to the maximum value of n changes from the high temperature environment in summer to the low temperature environment in the tunnel 高 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator predictions Tfy 高 , synchronously obtain the vehicle performance status index I at the corresponding time of the maximum value of n changes from the low temperature environment in the tunnel to the high temperature environment in summer 低 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator prediction values ​​Tfy 低 ;

[0094] S4. When the power battery is actually running, if the car enters the tunnel from the outside, the predicted value of the car performance index Tfy 高 Compared with the preset evaluation threshold group, if the vehicle performance index prediction value Tfy 高 If the evaluation threshold value group is exceeded, a warning signal is issued and an adjustment strategy is executed; if the car enters the outside world from the tunnel, the predicted value of the car performance index Tfy 低 Compared with the evaluation threshold group, if the predicted value of the vehicle performance index Tfy 低 If the assessment threshold group is exceeded, a warning signal is issued and an adjustment strategy is implemented.

[0095] In the application, the several formulas involved are all calculated by removing the dimensions and taking their numerical values. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The formula is set by technical personnel in this field according to actual conditions.

[0096] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0097] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. Intelligent power battery discharge performance detection system, characterized by: The system includes: The simulation environment monitoring module builds a simulation environment test platform to simulate the high temperature environment in summer and the low temperature environment in the tunnel, and controls the frequency and number of temperature changes to simulate real scenes, monitor the environmental data of the car equipped with power batteries, and record the maximum value and number of changes of the current temperature difference; The power battery monitoring module obtains the power battery operating parameters at the moment when the temperature difference reaches the maximum value each time; the power battery operating parameters include battery temperature, voltage, current and capacity; The information processing and analysis module obtains the vehicle performance status index I at the corresponding moment of the maximum value of n changes from the high temperature environment in summer to the low temperature environment in the tunnel 高 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator predictions Tfy 高 , synchronously obtain the vehicle performance status index I at the corresponding time of the maximum value of n changes from the low temperature environment in the tunnel to the high temperature environment in summer 低 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator prediction values ​​Tfy 低 ; Generate the vehicle performance status index I at the time of the maximum value of the change from the high temperature environment in summer to the low temperature environment in the tunnel 高 , the formula is as follows: In formula (1), dw, ir, ur, rl represent battery temperature, voltage, current and capacity respectively, ir*ur represents real-time output power, w1, w2, w3 represent preset proportional coefficients of battery temperature, real-time output power and capacity respectively, and w1>w2>w3>0, the value range of w1, w2, w3 is 0~1, and ex represents correction value; In formula (2), hw represents the ambient temperature, G represents the constant correction coefficient, and the value range of G is 0 to 1; Calculate the vehicle performance status index I at the time of maximum change from the low temperature environment in the tunnel to the high temperature environment in summer 低 The formula used to calculate the vehicle performance status index I 高 The principle is the same; The predicted values ​​of vehicle performance indicators are obtained as follows: S201. Select a machine learning algorithm to establish a predicted value Tfy for vehicle performance indicators 高 and vehicle performance status index I 高 The relationship between the vehicle performance index prediction value Tfy 低 and vehicle performance status index I 低 the relationship between; The machine learning algorithm includes any one of regression analysis, decision tree and random forest; S202, using the selected algorithm to train the data, establish a model to predict the corresponding vehicle performance index, and during the training process, the model learns and calculates the corresponding vehicle performance status index I 低 To predict the vehicle performance index prediction value Tfy 低 , according to the vehicle performance status index I 高 To predict the vehicle performance index prediction value Tfy 高 ; S203, using a cross-validation method to evaluate the trained model; S204, using the trained model to predict future vehicle performance index prediction values; When obtaining the predicted values ​​of vehicle performance indicators, the model formula used is as follows: Tfy 高 =f(text{I 高 })+eps In the formula, f(text{I 高 }) represents the model function, and the model function is a decision tree, eps represents the error factor; for the predicted value of the vehicle performance index Tfy 低 The same model formula is also used for calculation; The detection and warning display module, when the power battery is actually running, if the car enters the tunnel from the outside, the predicted value of the car performance index Tfy will be obtained 高 Compared with the preset evaluation threshold group, if the vehicle performance index prediction value Tfy 高 If the evaluation threshold value group is exceeded, a warning signal is issued and an adjustment strategy is executed; if the car enters the outside world from the tunnel, the predicted value of the car performance index Tfy 低 Compared with the evaluation threshold group, if the predicted value of the vehicle performance index Tfy 低 If the assessment threshold group is exceeded, a warning signal is issued and an adjustment strategy is implemented.

2. The intelligent power battery discharge performance detection system according to claim 1 is characterized in that: The corresponding temperature range for simulating the high temperature environment in summer is 30℃ to 40℃, and the corresponding temperature range for simulating the low temperature environment in the tunnel is 10℃ to 20℃. The environmental data of the car equipped with the power battery are monitored, including but not limited to the ambient temperature.

3. The intelligent power battery discharge performance detection system according to claim 2 is characterized in that: The process of obtaining the power battery operating parameters at each time when the temperature difference reaches the maximum value is as follows: S101, temperature difference detection: monitor the change of ambient temperature, and record the timestamp of the maximum value of the temperature difference obtained, and use it as the time point for analysis; S102, power battery parameter acquisition: at the recorded time point, the operating parameters of the power battery are acquired, and the operating parameters are acquired by connecting to a matching battery management system BMS; S103, data recording and processing: the acquired power battery parameters and corresponding timestamps are summarized and recorded, and subsequent data preprocessing is performed, and the data preprocessing is data cleaning.

4. The intelligent power battery discharge performance detection system according to claim 3 is characterized in that: Get the vehicle performance status index I at the time corresponding to the maximum value of n changes from the high temperature environment in summer to the low temperature environment in the tunnel 高 Previously, it was necessary to extract the first operating data set and the current ambient temperature at the time when the maximum temperature difference was reached each time the power battery operating parameters changed from the high temperature environment in summer to the low temperature environment in the tunnel. Based on the first operating data set and the ambient temperature, an operating status analysis and calculation model was built to generate the vehicle performance status index I at the time corresponding to the maximum value of the change from the high temperature environment in summer to the low temperature environment in the tunnel. 高 , where n=1, 2, …, k, and k is a positive integer.

5. The intelligent power battery discharge performance detection system according to claim 4 is characterized in that: When a warning signal is issued, the adjustment strategy implemented is: issuing a voice command of "please reduce speed or stop for repairs".

6. An intelligent power battery discharge performance detection method, using any system described in claims 1 to 5, characterized in that: The steps include: S1. Build a simulated environment test platform to simulate the high temperature environment in summer and the low temperature environment in the tunnel, and control the frequency and number of temperature changes to simulate the real scene, monitor the environmental data of the car equipped with power battery, and record the maximum value and number of changes of the current temperature difference; S2. Obtaining the power battery operating parameters at the time when each temperature difference reaches the maximum value, including battery temperature, voltage, current and capacity; S3, obtaining the vehicle performance status index I at the time corresponding to the maximum value of n changes from the high temperature environment in summer to the low temperature environment in the tunnel 高 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator predictions Tfy 高 , synchronously obtain the vehicle performance status index I at the corresponding time of the maximum value of n changes from the low temperature environment in the tunnel to the high temperature environment in summer 低 , use machine learning algorithms to build models to predict vehicle performance indicators and obtain real-time vehicle performance indicator prediction values ​​Tfy 低 ; Generate the vehicle performance status index I at the time of the maximum value of the change from the high temperature environment in summer to the low temperature environment in the tunnel 高 , the formula is as follows: In formula (1), dw, ir, ur, rl represent battery temperature, voltage, current and capacity respectively, ir*ur represents real-time output power, w1, w2, w3 represent preset proportional coefficients of battery temperature, real-time output power and capacity respectively, and w1>w2>w3>0, the value range of w1, w2, w3 is 0~1, and ex represents correction value; In formula (2), hw represents the ambient temperature, G represents the constant correction coefficient, and the value range of G is 0 to 1; Calculate the vehicle performance status index I at the time of maximum change from the low temperature environment in the tunnel to the high temperature environment in summer 低 The formula used to calculate the vehicle performance status index I 高 The principle is the same; The predicted values ​​of vehicle performance indicators are obtained as follows: S201. Select a machine learning algorithm to establish a predicted value Tfy for vehicle performance indicators 高 and vehicle performance status index I 高 The relationship between the vehicle performance index prediction value Tfy 低 and vehicle performance status index I 低 the relationship between; The machine learning algorithm includes any one of regression analysis, decision tree and random forest; S202, using the selected algorithm to train the data, establish a model to predict the corresponding vehicle performance index, and during the training process, the model learns and calculates the corresponding vehicle performance status index I 低 To predict the vehicle performance index prediction value Tfy 低 , according to the vehicle performance status index I 高 To predict the vehicle performance index prediction value Tfy 高 ; S203, using a cross-validation method to evaluate the trained model; S204, using the trained model to predict future vehicle performance index prediction values; When obtaining the predicted values ​​of vehicle performance indicators, the model formula used is as follows: Tfy 高 =f(text{I 高 })+eps In the formula, f(text{I 高 }) represents the model function, and the model function is a decision tree, eps represents the error factor; for the predicted value of the vehicle performance index Tfy 低 The same model formula is also used for calculation; S4. When the power battery is actually running, if the car enters the tunnel from the outside, the predicted value of the car performance index Tfy 高 Compared with the preset evaluation threshold group, if the vehicle performance index prediction value Tfy 高 If the evaluation threshold value group is exceeded, a warning signal is issued and an adjustment strategy is executed; if the car enters the outside world from the tunnel, the predicted value of the car performance index Tfy 低 Compared with the evaluation threshold group, if the predicted value of the vehicle performance index Tfy 低 If the assessment threshold group is exceeded, a warning signal is issued and an adjustment strategy is implemented.

Images