New energy automobile battery life prediction method and system

Abstract

The invention is suitable for the technical field of battery life prediction, and particularly relates to a new energy automobile battery life prediction method and system, and the method comprises the steps: recognizing a target object which needs the new energy automobile battery life prediction, determining a loading platform of the target object, reading the attribute data of the target object, and carrying out the new energy automobile battery life prediction. Wherein the attribute data at least comprises a battery code, a cycle index and a remaining service life, a use database of batteries of the same brand is constructed, a plurality of experience samples are selected from the use database through the cycle index, and the cycle index of the experience samples is larger than that of a target object; and configuring influence factors of life prediction. According to the method, by calculating the similarity and the weight, the residual use of the target object can be calculated by using an experience sample, the problem of insufficient early data of the new energy automobile battery is effectively solved, and meanwhile, the prediction accuracy is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of battery life prediction, and in particular to a method and system for predicting the battery life of a new energy vehicle. Background Art

[0002] The battery life of new energy vehicles is a key indicator of electric vehicle performance and economic efficiency, and is typically influenced by multiple factors, including battery type, operating environment, charging method, and frequency of use. Currently, mainstream power batteries are mainly ternary lithium batteries and lithium iron phosphate batteries. The former has high energy density but a relatively short cycle life, while the latter has a longer cycle life and is safer. Under ideal conditions, lithium iron phosphate batteries can achieve a cycle life of over 3,000 cycles, with a service life of more than 8 to 10 years, while the lifespan of ternary lithium batteries is around 1,500 to 2,000 cycles. In actual use, frequent fast charging, overcharging and over-discharging, and high or low temperature environments can accelerate battery degradation.

[0003] In the existing technology, a large amount of historical battery charge and discharge cycle data is generally used to train a model, establish a mapping relationship between battery status and life, and then use this model for life prediction. However, in the early stages of battery use, due to insufficient historical usage data, traditional data-driven life prediction models are difficult to accurately estimate the battery's health status and remaining life, which greatly affects the accuracy of the prediction.

[0004] Therefore, “how to use previous similar batteries to provide early stage operating data and calculate the battery life” is the technical problem that the present invention needs to solve. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for predicting the battery life of new energy vehicles to solve the problem raised in the above background technology: "how to use similar batteries to provide early stage operating data and calculate the battery life."

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for predicting the battery life of a new energy vehicle, the method comprising: Identify a target object for which new energy vehicle battery life prediction is required, determine a loading platform for the target object, read attribute data of the target object, wherein the attribute data at least includes: a battery code, a number of cycles, and a remaining service life, construct a usage database of batteries of the same brand, and select a plurality of experience samples from the usage database based on the number of cycles, wherein the number of cycles of the experience samples is greater than that of the target object; Configuring factors influencing life prediction, wherein the influencing factors include at least temperature, charge and discharge rate, and vehicle driving environment, using an anomaly detection algorithm to clean the experience samples, constructing a similarity calculation formula, and sequentially calculating the similarity between the target object and each experience sample; Integrate the preset weight formula and the similarity to calculate the weight of each experience sample, traverse the estimated remaining life of each experience sample from the usage database, calculate the prediction result of the target object based on the weight and the estimated remaining life, and send the prediction result to the preset terminal.

[0007] Furthermore, the steps of identifying the target object for which new energy vehicle battery life prediction is required, determining the loading platform of the target object, and reading the attribute data of the target object include: Creating a degradation model, collecting historical operating data of the loading platform, and training the degradation model; A time window is constructed, real-time operating condition data within the time window is collected, the real-time operating condition data and the prediction result are input into the degradation model, and a correction value is obtained as an output to correct the prediction result.

[0008] Furthermore, the step of selecting a plurality of experience samples from the usage database includes: Each attribute data is divided into several levels, where the target object and the experience sample have the same level; The number of experience samples is counted, and when the number is less than a threshold, the hierarchy is adjusted, wherein the adjustment at least includes: merging and re-segmenting.

[0009] Furthermore, the steps of using an anomaly detection algorithm to clean the experience samples, constructing a similarity calculation formula, and sequentially calculating the similarity between the target object and each experience sample include: Each influencing factor is cleaned in turn, wherein the cleaning comprises: using an anomaly detection algorithm to find outliers in each influencing factor, deleting the empirical samples corresponding to the outliers, and calculating the similarity using a similarity calculation formula; The similarity calculation formula is:

[0010] in is the similarity, is the difference between the number of cycles of the kth experience sample and the target object, is the difference between the SoH of the kth experience sample and the target object.

[0011] Furthermore, the step of integrating the preset weight formula and the similarity to calculate the weight of each experience sample includes: Inputting the similarity into a weight formula to calculate the weight of each experience sample; The weight formula is: ;in is the weight, For similarity.

[0012] Furthermore, the step of traversing the estimated remaining life of each experience sample and calculating the prediction result of the target object using the weight and the estimated remaining life includes: Reading the remaining useful life of each experience sample, and superimposing the remaining useful life and the product of the corresponding weight to obtain a prediction result; The prediction result is adjusted based on a preset frequency.

[0013] Furthermore, the method further comprises: Draw a fluctuation curve with time as the horizontal axis and the prediction result as the vertical axis, and insert labels generated by influencing factors into the fluctuation curve; Traverse the abnormal features in the fluctuation curve, record the occurrence time of the abnormal features, find out the influencing factors under the occurrence time, obtain the target factors, integrate the abnormal features and target factors, generate feedback, and send it to the preset terminal.

[0014] Furthermore, the system includes: a selection module for identifying a target object for which new energy vehicle battery life prediction is required, determining a loading platform for the target object, reading attribute data of the target object, wherein the attribute data includes at least a battery code, a number of cycles, and a remaining service life, constructing a usage database of batteries of the same brand, and selecting a plurality of experience samples from the usage database based on the number of cycles, wherein the number of cycles of the experience samples is greater than that of the target object; a configuration module configured to configure factors influencing life prediction, wherein the influencing factors include at least temperature, charge and discharge rate, and vehicle driving environment, clean the experience samples using an anomaly detection algorithm, construct a similarity calculation formula, and sequentially calculate the similarity between the target object and each experience sample; The sending module is used to integrate the preset weight formula and the similarity to calculate the weight of each experience sample, traverse the estimated remaining life of each experience sample from the usage database, calculate the prediction result of the target object based on the weight and the estimated remaining life, and send the prediction result to the preset terminal.

[0015] Furthermore, the selection module includes: A training unit, configured to create a degradation model, collect historical operating data of the loading platform, and train the degradation model; a correction unit, configured to construct a time window, collect real-time operating condition data within the time window, input the real-time operating condition data and the prediction result into a degradation model, output a correction value, and correct the prediction result; The segmentation unit is used to segment each attribute data into several levels, where the target object and the experience sample have the same corresponding level; The adjustment unit is configured to calculate the number of experience samples and adjust the level when the number is less than a threshold, wherein the adjustment includes at least merging and re-segmenting.

[0016] Furthermore, the configuration module includes: A cleaning unit is used to clean each influencing factor in turn, wherein the cleaning comprises: using an anomaly detection algorithm to find outliers in each influencing factor and deleting the experience samples corresponding to the outliers; The calculation unit is used to calculate the similarity using a similarity calculation formula; the similarity calculation formula is: ;in is the similarity, is the difference between the number of cycles of the kth experience sample and the target object, is the difference between the SoH of the kth experience sample and the target object.

[0017] Compared with the prior art, the present invention has the following beneficial effects: By determining the attribute data, personalized data can be provided for battery life prediction, improving the accuracy of the prediction. By creating a usage database, the performance evolution process of batteries of the same type can be determined, realizing full life cycle management and providing a data basis for battery life prediction. By determining the empirical sample, the control baseline of the target object can be determined to avoid prediction deviations due to battery differences, significantly improving the accuracy and stability of early battery life prediction. By calculating the similarity and weight, the empirical sample can be used to infer the remaining usage time of the target object, effectively solving the problem of insufficient early data on new energy vehicle batteries and greatly improving the accuracy of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of a method for predicting the life of a new energy vehicle battery provided by an embodiment of the present invention; Figure 2 A block diagram of the first sub-process of the new energy vehicle battery life prediction method provided by an embodiment of the present invention; Figure 3 A block diagram of the second sub-process of the new energy vehicle battery life prediction method provided by an embodiment of the present invention; Figure 4A block diagram of the third sub-process of the new energy vehicle battery life prediction method provided by an embodiment of the present invention; Figure 5 A block diagram of the new energy vehicle battery life prediction system provided by an embodiment of the present invention; Figure 6 A block diagram of the components of the selected modules in the new energy vehicle battery life prediction system provided by an embodiment of the present invention; Figure 7 A block diagram of the configuration module in the new energy vehicle battery life prediction system provided by an embodiment of the present invention; Figure 8 This is a block diagram of the composition of the sending module in the new energy vehicle battery life prediction system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] In Example 1, Figure 1 The implementation process of the new energy vehicle battery life prediction method provided by the embodiment of the present invention is shown and described in detail below: S100: Identify the target object for which new energy vehicle battery life prediction is required, determine the loading platform of the target object, read the attribute data of the target object, wherein the attribute data at least includes: battery code, number of cycles and remaining service life, build a usage database of batteries of the same brand, and select a number of experience samples from the usage database based on the number of cycles, wherein the number of cycles of the experience samples is greater than that of the target object.

[0021] In new energy vehicle batteries, the object for which life prediction is required is selected, namely the target object, where the target object should be a newer new energy vehicle battery that is in the early stage of battery use; the loading platform to which the target object is attached is determined, where the loading platform can be a car, truck or other new energy vehicle with loading function; the attribute data of the target object is read out, and the attribute data includes key indicators such as battery coding, number of cycles and remaining service life. Furthermore, the battery coding is mainly used to uniquely identify the individual battery, the number of cycles mainly shows the frequency of battery use, and the remaining service life is used to characterize the current state of the battery and the future available time; by determining the attribute data, a data basis can be provided for subsequent maintenance decisions, energy efficiency evaluation and platform scheduling. In this application, the previous similar batteries refer to experience samples.

[0022] Build a database consisting of usage data of batteries of the same brand, which collects historical operation data and status information of multiple batteries of the same brand; read the number of cycles of the target object, and filter out several empirical samples with a cycle number greater than the target object from the database. The empirical samples can provide the target object with a reference for performance trends in subsequent use; the empirical samples refer to batteries with a cycle number greater than the target object.

[0023] S200: Configuring influencing factors for life prediction, wherein the influencing factors include at least temperature, charge and discharge rate, and vehicle driving environment, using an anomaly detection algorithm to clean the experience samples, constructing a similarity calculation formula, and calculating the similarity between the target object and each experience sample in turn.

[0024] Based on the actual usage of new energy batteries, factors affecting the lifespan of new energy batteries, namely influencing factors, are determined, including temperature and charge and discharge rate. Anomaly detection algorithms are used to remove outliers in each influencing factor. For example, the operating temperature of each new energy vehicle battery is determined and sorted in descending order of operating temperature. Q1 (first quartile) and Q3 (third quartile) are found and the interquartile range (IQR) is calculated. New energy vehicle batteries corresponding to operating temperatures less than Q1-1.5×IQR or greater than Q3+1.5×IQR are found and the corresponding empirical samples are deleted. The battery is sorted in descending order of charge and discharge rate and outliers in the empirical samples are deleted again, and so on. The process of removing outliers is also called cleaning of the empirical samples. The similarity between the target object and each cleaned empirical sample is calculated in sequence, where each empirical sample corresponds to a similarity. The greater the similarity, the closer the battery's usage process is to the target object (but greater than the target object), and the greater its contribution to the target object's lifespan prediction.

[0025] S300: Integrate the preset weight formula and the similarity to calculate the weight of each experience sample, traverse the estimated remaining life of each experience sample from the usage database, calculate the prediction result of the target object based on the weight and the estimated remaining life, and send the prediction result to the preset terminal.

[0026] The weight of each experience sample is calculated. The larger the weight, the greater the impact on the remaining life prediction of the target battery. The estimated remaining life of each experience sample is read from the usage data. If the battery corresponding to the experience sample is also in the early stage of use, the corresponding experience sample is deleted. The experience samples and the corresponding weights are weighted averaged, and the obtained average value is defined as the prediction result. The prediction result is used as the life prediction value of the target object and the prediction result is sent to the preset terminal, where the preset terminal can be the battery management personnel terminal.

[0027] In Example 2, Figure 2 The implementation process of the new energy vehicle battery life prediction method provided by an embodiment of the present invention is shown. The following details the steps of identifying the target object for which new energy vehicle battery life prediction is required, determining the loading platform of the target object, and reading the attribute data of the target object. S101: creating a degradation model, collecting historical operating data of the loading platform, and training the degradation model.

[0028] Managers select appropriate data-driven models and use machine learning algorithms (such as regression analysis, support vector machines, random forests, etc.) to learn and obtain a degradation model. The degradation model is mainly used to predict the degradation process of new energy batteries; the degradation model is trained using historical operating data of loading platforms or new energy batteries.

[0029] S102: Constructing a time window, collecting real-time operating condition data within the time window, inputting the real-time operating condition data and the prediction result into a degradation model, outputting a correction value, and correcting the prediction result.

[0030] Set a time window (for example, 1 hour, 1 day, or longer). In each time window, monitor and collect operating condition data in real time. The operating condition data includes temperature, charge and discharge rate, duty cycle, loaded mileage, and other parameters related to battery degradation. Input the real-time operating condition data and the prediction results into the degradation model together. The degradation model will output a correction value based on the current operating condition data and historical information, combined with the degradation law during its training process. The correction value can reduce the deviation between the predicted result and the actual degradation result.

[0031] In Example 3, Figure 2 The implementation process of the new energy vehicle battery life prediction method provided by an embodiment of the present invention is shown. The steps of selecting several experience samples from the usage database are described in detail below: S103: Divide each attribute data into several levels, wherein the target object and the experience sample have the same corresponding level.

[0032] In each attribute data, select the experience samples at the same level; for example, there are four experience samples A, B, C and D. Taking the ambient operating temperature as an example, below -15℃ is defined as the first level, -15℃ to 0℃ is defined as the second level, and 0℃ to 10℃ is defined as the third level. Assuming that the target object, A and C all correspond to the third level, and B and D correspond to the first and second levels respectively, then B and D are no longer considered when selecting experience samples.

[0033] S104: Count the number of experience samples, and when the number is less than a threshold, adjust the level, wherein the adjustment at least includes: merging and re-segmenting.

[0034] If the number of selected experience samples is less than the threshold, the source of experience samples can be increased by merging levels; in actual prediction, if the number of experience samples is too small, it is easy to cause deviation and reduce the accuracy of the prediction.

[0035] In Example 4, Figure 3 The implementation process of the new energy vehicle battery life prediction method provided by an embodiment of the present invention is shown. The following details the steps of using an anomaly detection algorithm to clean the experience samples, construct a similarity calculation formula, and sequentially calculate the similarity between the target object and each experience sample. S201: Clean each influencing factor in turn, wherein the cleaning comprises: using an anomaly detection algorithm to find out abnormal values ​​in each influencing factor, and deleting the experience samples corresponding to the abnormal values.

[0036] In each influencing factor, the part corresponding to the value less than Q1−1.5×IQR or greater than Q3+1.5×IQR is defined as an outlier, and the empirical samples corresponding to the outlier are deleted.

[0037] S202: Calculate the similarity using a similarity calculation formula; the similarity calculation formula is: ;in is the similarity, is the difference between the number of cycles of the kth experience sample and the target object, is the difference between the SoH of the kth experience sample and the target object.

[0038] From the attribute data, the number of cycles, SoH and remaining service life of each experience sample and the target object are read out; and substituted into the similarity calculation formula to calculate the similarity between each experience sample and the target object; the denominator part of the similarity calculation formula can also include other attribute data, which is selected by the management personnel.

[0039] In Example 5, Figure 4 The implementation process of the new energy vehicle battery life prediction method provided by an embodiment of the present invention is shown. The steps of integrating the preset weight formula and the similarity to calculate the weight of each experience sample are described in detail below: S301: Input the similarity into a weight formula to calculate the weight of each experience sample. The weight formula is: ;in is the weight, For similarity.

[0040] The similarity of each experience sample is input into the weight formula to calculate the weight.

[0041] In Example 6, Figure 4 The implementation process of the new energy vehicle battery life prediction method provided by an embodiment of the present invention is shown. The following details the steps of traversing the estimated remaining life of each experience sample and calculating the prediction result of the target object based on the weight and the estimated remaining life. S302: Reading the remaining useful life of each experience sample, and superimposing the remaining useful life and the product of the corresponding weight to obtain a prediction result.

[0042] Multiply the remaining useful life of each experience sample by the corresponding weight to obtain the product corresponding to the experience sample, and superimpose all the products to obtain the prediction result.

[0043] S303: Adjust the prediction result based on a preset frequency.

[0044] The forecast results are updated based on a preset frequency, which can be set by management.

[0045] In Example 7, different from Example 1, in this embodiment of the present invention, the method further includes: Draw a fluctuation curve with time as the horizontal axis and the prediction result as the vertical axis, and insert labels generated by influencing factors into the fluctuation curve; Traverse the abnormal features in the fluctuation curve, record the occurrence time of the abnormal features, find out the influencing factors under the occurrence time, obtain the target factors, integrate the abnormal features and target factors, generate feedback, and send it to the preset terminal.

[0046] A fluctuation curve is drawn with time as the horizontal axis and the prediction result as the vertical axis. The fluctuation curve reflects the changing trend of the prediction result. The fluctuation curve is traversed to identify abnormal feature points, such as sudden drops, sudden increases, or fluctuations that do not conform to the normal degradation trend. The occurrence time corresponding to each abnormal feature is recorded, and the real-time operating condition data collected at this time point is retrieved and extracted using this time point as an index to further analyze the influencing factors that lead to abnormal features, such as abnormal charging and discharging rates.

[0047] Based on the influencing factors, the specific cause of the abnormality is determined, such as high-rate charging and discharging, battery damage, and battery management system failure. Based on the cause of the abnormality, targeted feedback is generated, such as adjusting the charging strategy, checking the cooling system, or optimizing driving behavior. The feedback is sent to the preset terminal in the form of text or charts, where the preset terminal is the management personnel terminal.

[0048] Figure 5The following is a structural block diagram of a new energy vehicle battery life prediction system according to an embodiment of the present invention. The new energy vehicle battery life prediction system 1 includes: The selection module 11 is configured to identify a target object for which a new energy vehicle battery life prediction is required, determine a loading platform for the target object, read attribute data of the target object, wherein the attribute data includes at least a battery code, a number of cycles, and a remaining service life, construct a usage database of batteries of the same brand, and select a plurality of experience samples from the usage database based on the number of cycles, wherein the number of cycles of the experience samples is greater than that of the target object; Configuration module 12 is used to configure factors affecting life prediction, wherein the factors include at least temperature, charge and discharge rate, and vehicle driving environment, clean the experience samples using an anomaly detection algorithm, construct a similarity calculation formula, and sequentially calculate the similarity between the target object and each experience sample; The sending module 13 is used to integrate the preset weight formula and the similarity to calculate the weight of each experience sample, traverse the estimated remaining life of each experience sample from the usage database, calculate the prediction result of the target object based on the weight and the estimated remaining life, and send the prediction result to the preset terminal.

[0049] Figure 6 The following is a structural block diagram of a new energy vehicle battery life prediction system according to an embodiment of the present invention. The selection module 11 includes: A training unit 111 is used to create a degradation model, collect historical operating data of the loading platform, and train the degradation model; The correction unit 112 is used to construct a time window, collect real-time operating condition data within the time window, input the real-time operating condition data and the prediction result into the degradation model, output a correction value, and correct the prediction result; A segmentation unit 113 is used to segment each attribute data into a plurality of levels, wherein the target object and the experience sample correspond to the same level; The adjusting unit 114 is configured to calculate the number of experience samples, and when the number is less than a threshold, adjust the level, wherein the adjustment includes at least merging and re-segmenting.

[0050] Figure 7 The following is a structural block diagram of the new energy vehicle battery life prediction system provided by an embodiment of the present invention. The configuration module 12 includes: The cleaning unit 121 is used to clean each influencing factor in turn, wherein the cleaning comprises: using an anomaly detection algorithm to find outliers in each influencing factor and deleting the experience samples corresponding to the outliers; The calculation unit 122 is used to calculate the similarity using a similarity calculation formula; the similarity calculation formula is: ;in is the similarity, is the difference between the number of cycles of the kth experience sample and the target object, is the difference between the SoH of the kth experience sample and the target object.

[0051] Figure 8 The structure block diagram of the new energy vehicle battery life prediction system provided by an embodiment of the present invention is shown. The sending module 13 includes: The input unit 131 is used to input the similarity into a weight formula to calculate the weight of each experience sample. The weight formula is: ;in is the weight, is similarity; The obtaining unit 132 is configured to read the remaining useful life of each experience sample and superimpose the remaining useful life and the product of the corresponding weight to obtain a prediction result; The adjusting unit 133 is configured to adjust the prediction result according to a preset frequency.

[0052] The selection module 11 is mainly used to complete step S100, the configuration module 12 is mainly used to complete step S200, and the sending module 13 is mainly used to complete step S300; The training unit 111 is mainly used to complete step S101, the correction unit 112 is mainly used to complete step S102, the segmentation unit 113 is mainly used to complete step S103, and the adjustment unit 114 is mainly used to complete step S104; The cleaning unit 121 is mainly used to complete step S201, and the calculation unit 122 is mainly used to complete step S202; The input unit 131 is mainly used to complete step S301, the obtaining unit 132 is mainly used to complete step S302, and the adjusting unit 133 is mainly used to complete step S303.

[0053] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0054] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0055] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting the battery life of a new energy vehicle, characterized in that: The method comprises: Identify a target object for which new energy vehicle battery life prediction is required, determine a loading platform for the target object, read attribute data of the target object, wherein the attribute data at least includes: a battery code, a number of cycles, and a remaining service life, construct a usage database of batteries of the same brand, and select a plurality of experience samples from the usage database based on the number of cycles, wherein the number of cycles of the experience samples is greater than that of the target object; Configuring factors influencing life prediction, wherein the influencing factors include at least temperature, charge and discharge rate, and vehicle driving environment, using an anomaly detection algorithm to clean the experience samples, constructing a similarity calculation formula, and sequentially calculating the similarity between the target object and each experience sample; Integrate the preset weight formula and the similarity to calculate the weight of each experience sample, traverse the estimated remaining life of each experience sample from the usage database, calculate the prediction result of the target object based on the weight and the estimated remaining life, and send the prediction result to the preset terminal.

2. The new energy vehicle battery life prediction method according to claim 1, characterized in that: The steps of identifying a target object for which new energy vehicle battery life prediction is required, determining a loading platform for the target object, and reading attribute data of the target object include: Creating a degradation model, collecting historical operating data of the loading platform, and training the degradation model; A time window is constructed, real-time operating condition data within the time window is collected, the real-time operating condition data and the prediction result are input into the degradation model, and a correction value is obtained as an output to correct the prediction result.

3. The new energy vehicle battery life prediction method according to claim 1, characterized in that: The step of selecting a plurality of experience samples from the usage database includes: Each attribute data is divided into several levels, where the target object and the experience sample have the same level; The number of experience samples is counted, and when the number is less than a threshold, the hierarchy is adjusted, wherein the adjustment at least includes: merging and re-segmenting.

4. The new energy vehicle battery life prediction method according to claim 1, characterized in that: The steps of using an anomaly detection algorithm to clean the experience samples, constructing a similarity calculation formula, and sequentially calculating the similarity between the target object and each experience sample include: Each influencing factor is cleaned in turn, wherein the cleaning comprises: using an anomaly detection algorithm to find outliers in each influencing factor, deleting the empirical samples corresponding to the outliers, and calculating the similarity using a similarity calculation formula; The similarity calculation formula is: ； in is the similarity between the kth experience sample and the target object, is the difference between the number of cycles of the kth experience sample and the target object, is the difference between the SoH of the kth experience sample and the target object.

5. The new energy vehicle battery life prediction method according to claim 4, characterized in that: The step of integrating the preset weight formula and the similarity to calculate the weight of each experience sample includes: Inputting the similarity into a weight formula to calculate the weight of each experience sample; The weight formula is: ; in is the weight, For similarity.

6. The new energy vehicle battery life prediction method according to claim 5, characterized in that: The step of traversing the estimated remaining life of each experience sample and calculating the prediction result of the target object based on the weight and the estimated remaining life includes: Reading the remaining useful life of each experience sample, and superimposing the remaining useful life and the product of the corresponding weight to obtain a prediction result; The prediction result is adjusted based on a preset frequency.

7. The new energy vehicle battery life prediction method according to claim 1, characterized in that: The method further comprises: Draw a fluctuation curve with time as the horizontal axis and the prediction result as the vertical axis, and insert labels generated by influencing factors into the fluctuation curve; Traverse the abnormal features in the fluctuation curve, record the occurrence time of the abnormal features, find out the influencing factors under the occurrence time, obtain the target factors, integrate the abnormal features and target factors, generate feedback, and send it to the preset terminal.

8. New energy vehicle battery life prediction system, characterized by: The system comprises: a selection module for identifying a target object for which new energy vehicle battery life prediction is required, determining a loading platform for the target object, reading attribute data of the target object, wherein the attribute data includes at least a battery code, a number of cycles, and a remaining service life, constructing a usage database of batteries of the same brand, and selecting a plurality of experience samples from the usage database based on the number of cycles, wherein the number of cycles of the experience samples is greater than that of the target object; a configuration module configured to configure factors influencing life prediction, wherein the influencing factors include at least temperature, charge and discharge rate, and vehicle driving environment, clean the experience samples using an anomaly detection algorithm, construct a similarity calculation formula, and sequentially calculate the similarity between the target object and each experience sample; The sending module is used to integrate the preset weight formula and the similarity to calculate the weight of each experience sample, traverse the estimated remaining life of each experience sample from the usage database, calculate the prediction result of the target object based on the weight and the estimated remaining life, and send the prediction result to the preset terminal.

9. The new energy vehicle battery life prediction system according to claim 8, characterized in that: The selection module includes: A training unit, configured to create a degradation model, collect historical operating data of the loading platform, and train the degradation model; a correction unit, configured to construct a time window, collect real-time operating condition data within the time window, input the real-time operating condition data and the prediction result into a degradation model, output a correction value, and correct the prediction result; The segmentation unit is used to segment each attribute data into several levels, where the target object and the experience sample have the same corresponding level; The adjustment unit is configured to calculate the number of experience samples and adjust the level when the number is less than a threshold, wherein the adjustment includes at least merging and re-segmenting.

10. The new energy vehicle battery life prediction system according to claim 8, characterized in that: The configuration module includes: A cleaning unit is used to clean each influencing factor in turn, wherein the cleaning comprises: using an anomaly detection algorithm to find outliers in each influencing factor and deleting the experience samples corresponding to the outliers; The calculation unit is used to calculate the similarity using a similarity calculation formula; the similarity calculation formula is: ;in is the similarity, is the difference between the number of cycles of the kth experience sample and the target object, is the difference between the SoH of the kth experience sample and the target object.

Images