CN114236412B - BP neural network-based battery health state diagnosis method and system - Google Patents

Abstract

The present invention discloses a battery health status diagnosis method and system based on BP neural network, the method comprising: collecting data of charging piles and electric vehicle batteries to construct an original data sequence; performing first-order accumulation on the original data sequence to generate a data time series; using a part of the data time series as a model input and the other part as a model output, performing model training, and constructing a BP neural network model; the system comprises a data acquisition module, a data processing module, a data analysis module, and a prediction module, and a healthy prediction of the battery health status is achieved through the logical connection between the modules; the present invention has ingenious conception and accurate prediction, and provides a technical reference for battery health management.

Description

A battery health status diagnosis method and system based on BP neural network

Technical Field

The present application relates to the technical field of electric vehicle battery detection, and in particular to a battery health status diagnosis method and system based on a BP neural network.

Background technique

Electric vehicle batteries are divided into two categories, storage batteries and fuel cells. Storage batteries are suitable for pure electric vehicles, including lead-acid batteries, nickel-metal hydride batteries, sodium-sulfur batteries, secondary lithium batteries, air batteries, and ternary lithium batteries.

Fuel cells are specifically used in fuel cell electric vehicles, including alkaline fuel cells (AFC), phosphoric acid fuel cells (PAFC), molten carbonate fuel cells (MCFC), solid oxide fuel cells (SOFC), proton exchange membrane fuel cells (PEMFC), direct methanol fuel cells (DMFC)

There are slight differences depending on the type of electric vehicle. In a pure electric vehicle equipped with only batteries, the battery serves as the sole power source for the vehicle's drive system. In a hybrid vehicle equipped with a traditional engine (or fuel cell) and a battery, the battery can serve as both the main power source and the auxiliary power source for the vehicle's drive system. It can be seen that at low speeds and when starting, the battery serves as the main power source for the vehicle's drive system; when accelerating at full load, it serves as an auxiliary power source; and when driving normally or decelerating or braking, it serves as an energy storage system.

With the widespread use of electric vehicles, the health management of electric vehicle batteries will be beneficial to the maintenance of electric vehicles and the development of industry technology. In the existing technology, there are many health management methods for electric vehicle batteries, but most of them achieve health management by detecting the performance of the battery itself, which is inconvenient for practical applications. Since electric vehicles need to be charged from time to time, and charging piles are essential charging equipment, a battery health management method can be designed to predict battery performance by collecting charging data of electric vehicles.

Summary of the invention

In order to solve the above problems, the present invention provides a battery health status diagnosis method based on BP neural network, comprising the following steps:

Collect the battery operation data of electric vehicles throughout their life cycle and construct the first original data sequence;

Performing first-order accumulation on the first original data sequence to generate a first data sequence, wherein the first data sequence includes a first time series and a second time series, and the first time series and the second time series are used to represent a first data set within a specific time period of the entire life cycle of the battery;

The first time series is used as the model input, and the second time series is used as the model output, and the model training is performed to construct a first BP neural network model;

Collect high-frequency charging data of the charging pile and construct a second original data sequence;

Performing accumulation on the second original data sequence to generate a second data sequence, wherein the second data sequence includes a third time series and a fourth time series, and the third time series and the fourth time series are used to represent a second data set of high-frequency charging data within a specific time period;

Taking the second time series as model input and the second time series as model output, performing model training, and constructing a second BP neural network model;

The first BP neural network model and the second BP neural network model are assigned a first weight and a second weight respectively to construct a BP neural network model, and the BP neural network model is used to predict the battery health status according to the current high-frequency charging data and battery operation data.

Preferably, the expression of the first original data sequence or the second original data sequence is:

X ⁽⁰⁾ = {x ⁽⁰⁾ (1), x ⁽⁰⁾ (2),..., x ⁽⁰⁾ (n)}

Wherein, X ⁽⁰⁾ represents the original data sequence, and x ⁽⁰⁾ (n) represents the nth data in the original data sequence.

Preferably, in the process of generating the first data sequence or the second data sequence, the first-order accumulation process is:

Preferably, the expression of the first data sequence or the second data sequence is:

X ⁽¹⁾ = {x ⁽¹⁾ (1), x ⁽¹⁾ (2), ..., x ⁽¹⁾ (n)}.

Preferably, in the process of constructing the BP neural network model, the BP neural network model includes an input layer, a hidden layer, and an output layer;

The hidden nodes of the hidden layer are calculated according to the formula Calculated and determined, m is the number of input neurons, p is the number of output neurons, and q is a constant between 1 and 10.

Preferably, in the process of constructing the first BP neural network model or the second BP neural network model, the equation expression of the first BP neural network model or the second BP neural network model is:

A battery health status diagnosis system based on BP neural network, comprising:

A first data module is used to collect the battery life cycle operation data of the electric vehicle and construct a first original data sequence;

A first data processing module, used for performing first-order accumulation on the first original data sequence to generate a first data sequence, wherein the first data sequence includes a first time series and a second time series, and the first time series and the second time series are used to represent a first data set within a specific time period of the entire life cycle of the battery;

A first data analysis module is used to use the first time series as a model input and the second time series as a model output, perform model training, and construct a first BP neural network model;

A second data acquisition module is used to collect high-frequency charging data of the charging pile and construct a second original data sequence;

A second data processing module, used for performing accumulation on the second original data sequence to generate a second data sequence, wherein the second data sequence includes a third time series and a fourth time series, and the third time series and the fourth time series are used to represent a second data set of high-frequency charging data within a specific time period;

The second data analysis module uses the second time series as a model input and the second time series as a model output to perform model training and construct a second BP neural network model;

The state prediction module is used to assign a first weight and a second weight to the first BP neural network model and the second BP neural network model respectively, and construct a BP neural network model. The BP neural network model is used to predict the battery health status according to the current high-frequency charging data and battery operation data.

Preferably, the battery health status diagnosis system further includes:

A data storage module, used for storing the first data set, the second data set and other system data;

Communication module, used for data exchange of battery health status diagnosis system;

Display module, used to display system data and battery health status;

A positioning module is used to locate the charging pile and the electric vehicle, and obtain the location information of the charging pile and the electric vehicle respectively;

The blockchain module is used to upload system data to the alliance chain and store system data in the private chain.

Preferably, the battery health state diagnosis system further includes a computer program, which is applied to the battery health state diagnosis system and is used to implement the battery health state diagnosis method.

Preferably, the battery health status diagnostic system is applied in a battery health status diagnostic device, which includes a Beidou positioning device, a voltage sensor, a current sensor, a temperature sensor, an ambient temperature sensor, a 5G communication antenna, a memory, and a chip; the battery health status diagnostic device is respectively arranged in a charging pile and an electric vehicle, and is used for the charging pile to identify and locate the electric vehicle, and after data collection, the collected data is transmitted to a background server or a cloud server for data processing.

The present invention discloses the following technical effects:

The method and system proposed in the present invention collect charging pile data and battery life data to generate a BP neural network model. After the model integrates the charging data, it can predict the entire life cycle of the battery and the prediction is accurate, providing new technical insights for the life cycle prediction of electric vehicle batteries and proposing new technical ideas for battery health prediction.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a flow chart of the method of the present invention.

Detailed ways

In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

As shown in FIG1 , the present invention provides a battery health status diagnosis method based on BP neural network, which is characterized by comprising the following steps:

Collect the battery operation data of electric vehicles throughout their life cycle and construct the first original data sequence;

Performing first-order accumulation on the first original data sequence to generate a first data sequence, wherein the first data sequence includes a first time series and a second time series, and the first time series and the second time series are used to represent a first data set within a specific time period of the entire life cycle of the battery;

The first time series is used as the model input, and the second time series is used as the model output, and the model training is performed to construct a first BP neural network model;

Collect high-frequency charging data of the charging pile and construct a second original data sequence;

Performing accumulation on the second original data sequence to generate a second data sequence, wherein the second data sequence includes a third time series and a fourth time series, and the third time series and the fourth time series are used to represent a second data set of high-frequency charging data within a specific time period;

Taking the second time series as model input and the second time series as model output, performing model training, and constructing a second BP neural network model;

The first BP neural network model and the second BP neural network model are assigned a first weight and a second weight respectively to construct a BP neural network model, and the BP neural network model is used to predict the battery health status according to the current high-frequency charging data and battery operation data.

Further preferably, the expression of the first original data sequence or the second original data sequence is:

X ⁽⁰⁾ = {x ⁽⁰⁾ (1), x ⁽⁰⁾ (2),..., x ⁽⁰⁾ (n)}

Wherein, X ⁽⁰⁾ represents the original data sequence, and x ⁽⁰⁾ (n) represents the nth data in the original data sequence.

Further preferably, in the process of generating the first data sequence or the second data sequence, the first-order accumulation process is:

Further preferably, the expression of the first data sequence or the second data sequence is:

X ⁽¹⁾ = {x ⁽¹⁾ (1), x ⁽¹⁾ (2), ..., x ⁽¹⁾ (n)}.

Further preferably, in the process of constructing the BP neural network model, the BP neural network model includes an input layer, a hidden layer, and an output layer;

The hidden nodes of the hidden layer are calculated according to the formula Calculated and determined, m is the number of input neurons, p is the number of output neurons, and q is a constant between 1 and 10.

Further preferably, in the process of constructing the first BP neural network model or the second BP neural network model, the equation expression of the first BP neural network model or the second BP neural network model is:

A battery health status diagnosis system based on BP neural network, comprising:

A first data module is used to collect the battery life cycle operation data of the electric vehicle and construct a first original data sequence;

A first data processing module, used for performing first-order accumulation on the first original data sequence to generate a first data sequence, wherein the first data sequence includes a first time series and a second time series, and the first time series and the second time series are used to represent a first data set within a specific time period of the entire life cycle of the battery;

A first data analysis module is used to use the first time series as a model input and the second time series as a model output, perform model training, and construct a first BP neural network model;

A second data acquisition module is used to collect high-frequency charging data of the charging pile and construct a second original data sequence;

A second data processing module, used for performing accumulation on the second original data sequence to generate a second data sequence, wherein the second data sequence includes a third time series and a fourth time series, and the third time series and the fourth time series are used to represent a second data set of high-frequency charging data within a specific time period;

The second data analysis module uses the second time series as a model input and the second time series as a model output to perform model training and construct a second BP neural network model;

The state prediction module is used to assign a first weight and a second weight to the first BP neural network model and the second BP neural network model respectively, and construct a BP neural network model. The BP neural network model is used to predict the battery health status according to the current high-frequency charging data and battery operation data.

Further preferably, the battery health status diagnosis system further includes:

A data storage module, used for storing the first data set, the second data set and other system data;

Communication module, used for data exchange of battery health status diagnosis system;

Display module, used to display system data and battery health status;

A positioning module is used to locate the charging pile and the electric vehicle, and obtain the location information of the charging pile and the electric vehicle respectively;

The blockchain module is used to upload system data to the alliance chain and store system data in the private chain.

Further preferably, the battery health status diagnosis system also includes a computer program, which is applied to the battery health status diagnosis system and is used to implement the battery health status diagnosis method.

Further preferably, the battery health status diagnostic system is applied in a battery health status diagnostic device, which includes a Beidou positioning device, a voltage sensor, a current sensor, a temperature sensor, an ambient temperature sensor, a 5G communication antenna, a memory, and a chip; the battery health status diagnostic device is respectively arranged in a charging pile and an electric vehicle, and is used for the charging pile to identify and locate the electric vehicle, and after data collection, the collected data is transmitted to a background server or a cloud server for data processing.

Embodiment 1: Establishing an unequal weight grey BP neural network combination model;

(1) Establishing the original grey prediction model

Create the original data sequence:

X ⁽⁰⁾ = {x ⁽⁰⁾ (1), x ⁽⁰⁾ (2),..., x ⁽⁰⁾ (n)} (1)

According to the following formula (2)

Perform first-order accumulation on the original data sequence X ⁽⁰⁾ to generate a 1-AGO sequence:

X ⁽¹⁾ ={x ⁽¹⁾ (1),x ⁽¹⁾ (2),...,x ⁽¹⁾ (n)} (3)

(2) Unequal weight optimization of original grey prediction model

The original grey prediction model only performs equal weight accumulation of the original sequence, and does not consider the impact of time factors on the prediction results. In actual situations, the closer the time series is to the prediction, the greater the amount of information it contains, the more it can reflect the trend of future development, and the greater the weight assigned. Therefore, the hierarchical analysis method is used to further optimize the original grey prediction model, and experts are invited to use the Delphi method to compare and evaluate each factor pairwise, and determine the weight of the recent time series as λ1 and the weight of the long-term as λ2. The original grey prediction model is optimized to unequal weights:

Then generate the unequal weight 1-AGO sequence model:

X′ ⁽¹⁾ ={x′ ⁽¹⁾ (1),x′ ⁽¹⁾ (2),...,x′ ⁽¹⁾ (n)} (5)

BP neural network design

Establish a three-layer network with input layer, hidden layer, and output layer:

① In the unequal-weight 1-AGO sequence model, the time series values {x′ ⁽¹⁾ (1), x′ ⁽¹⁾ (2), ..., x′ ⁽¹⁾ (m)} (m < n) are selected as the input layer of the BP neural network;

②Use x′ ⁽¹⁾ (m+1) as the output layer of the BP neural network;

③The hidden layer nodes can be calculated according to the formula Calculate and determine, m is the number of input neurons, p is the number of output neurons, and q is a constant between 1 and 10;

④ Use the trained BP neural network to make predictions, and use cumulative reduction to restore the prediction sequence to get the predicted value for the future.

There are many types of chemical batteries with different performances. The indicators commonly used to characterize their performance are: electrical properties, mechanical properties, storage performance, etc., and sometimes also include performance and economic cost. We mainly introduce its electrical properties and storage performance. Electrical properties include: electromotive force, rated voltage, open circuit voltage, operating voltage, termination voltage, charging voltage, internal resistance, capacity, specific energy and specific power, storage performance and self-discharge, life, etc. Storage performance mainly depends on the self-discharge of the battery.

Electromotive force

The electromotive force of a battery, also known as the standard voltage or theoretical voltage of the battery, is the potential difference between the positive and negative poles when the battery is disconnected.

Rated voltage

Rated voltage (or nominal voltage) refers to the recognized standard voltage when the battery of this electrochemical system is working.

Open circuit voltage

The open circuit voltage of a battery is the battery voltage under no-load conditions. The open circuit voltage is not equal to the electromotive force of the battery. It must be pointed out that the electromotive force of the battery is calculated from the thermodynamic function, while the open circuit voltage of the battery is actually measured.

Operating Voltage

Refers to the actual discharge voltage of the battery under a certain load, usually referring to a voltage range.

⑸Termination voltage

It refers to the voltage value at the end of discharge, which varies depending on the load and usage requirements.

Charging voltage

Refers to the voltage of the external circuit DC voltage charging the battery. The general charging voltage is greater than the open circuit voltage of the battery, usually within a certain range.

Internal resistance

The internal resistance of the battery includes: the resistance of the positive and negative plates, the resistance of the electrolyte, the resistance of the separator and the resistance of the connector, etc.

Positive and negative resistance

The commonly used positive and negative plates of lead-acid batteries are paste-coated, consisting of a lead-antimony alloy or lead-calcium alloy grid frame and an active material. Therefore, the plate resistance is also composed of the grid resistance and the active material resistance. The grid is in the inner layer of the active material and will not undergo chemical changes during charging and discharging, so its resistance is the inherent resistance of the grid. The resistance of the active material changes with the different charging and discharging states of the battery.

When the battery is discharged, the active material of the plate is converted into lead sulfate (PbSO4). The higher the lead sulfate content, the greater its resistance. When the battery is charged, the lead sulfate is reduced to lead (Pb). The lower the lead sulfate content, the lower its resistance.

Electrolyte resistance

The resistance of the electrolyte varies depending on its concentration. Once a certain concentration is selected within the specified concentration range, the electrolyte resistance will change with the degree of charge and discharge. When the battery is charged, the electrolyte concentration increases while the plate active material is reduced, and its resistance decreases; when the battery is discharged, the electrolyte concentration decreases while the plate active material is sulfated, and its resistance increases.

Separator resistance

The resistance of the separator varies depending on its porosity. The resistance of the separator of a new battery tends to be fixed, but as the battery runs longer, its resistance increases. This is because some lead slag and other deposits are deposited on the separator during the operation of the battery, which reduces the porosity of the separator and increases the resistance.

Connector resistance

The connector includes the inherent resistance of metals such as connecting bars when single cells are connected in series, the connection resistance between battery plates, and the metal resistance of the connector that forms the electrode group of positive and negative plates. If the welding and connection contact are good, the connector resistance can be regarded as a fixed resistance.

The internal resistance of each battery is the sum of the resistances of the above objects. The relationship between the battery internal resistance R and the electromotive force, terminal voltage and discharge current is: Rs = (E-Uf) ÷ If

The internal resistance of the battery will gradually increase during the discharge process, and gradually decrease during the charging process. Therefore, during the charging and discharging process of the battery, the terminal voltage will also change due to the change of its internal resistance. Therefore, the terminal voltage is lower than the electromotive force of the battery during discharge, and higher than the electromotive force of the battery during charging.

capacity

The capacity of a battery is measured in coulombs (C) or ampere-hours (Ah). There are three special terms that characterize battery capacity characteristics:

a. Theoretical capacity. Refers to the amount of electricity calculated based on the number of electrochemical equivalents of active substances participating in the electrochemical reaction. Generally, theoretically, 1 electrochemical equivalent of substance will release 1 Faraday of electricity, that is, 96500C or 26.8Ah (the amount of 1 electrochemical equivalent of substance is equal to the atomic weight or molecular weight of the active substance divided by the number of electrons in the reaction).

b. Rated capacity: refers to the minimum amount of electricity that should be discharged by the battery under specified discharge conditions, which is stipulated or guaranteed when the battery is designed and produced.

c. Actual capacity. It refers to the amount of electricity that the battery can discharge before the termination voltage under certain discharge conditions, that is, under certain discharge current and temperature.

The actual capacity of a battery is usually 10% to 20% greater than its rated capacity.

The capacity of a battery is related to the quantity and activity of active materials on the positive and negative electrodes, as well as the structure and manufacturing process of the battery and the discharge conditions (current and temperature) of the battery.

The comprehensive index of factors affecting battery capacity is the utilization rate of active materials. In other words, the more fully the active materials are utilized, the higher the capacity of the battery.

The utilization rate of active substances can be defined as:

Utilization rate = (battery actual capacity/battery theoretical capacity) × 100%

Or, utilization rate = (theoretical amount of active substance/actual amount of active substance) × 100%.

Specific Energy

The output energy of a battery refers to the electrical work that the battery can produce under certain discharge conditions. It is equal to the product of the battery's discharge capacity and the battery's average operating voltage. Its unit is usually expressed in watt-hours (Wh).

There are two types of battery specific energy. One is called weight specific energy, expressed in watt-hours/kilogram (Wh/kg); the other is called volume specific energy, expressed in watt-hours/liter (Wh/L). The physical meaning of specific energy is the effective electrical energy of the battery per unit weight or unit volume. It is an important indicator for comparing the performance of batteries.

Specific power

The power of a battery refers to the energy that the battery can output per unit time under certain discharge conditions. The unit is watt (W) or kilowatt (kW). The power per unit weight or per unit volume of a battery is called the specific power of the battery, and its unit is watt/kilogram (W/kg) or watt/liter (W/L). If the specific power of a battery is large, it means that more energy is given per unit weight or per unit volume per unit time, which means that the battery can be discharged with a larger current. Therefore, the specific power of a battery is also one of the important indicators for evaluating the performance of a battery.

Storage performance

After a certain period of dry storage (without electrolyte) or wet storage (with electrolyte), the capacity of the battery will decrease automatically. This phenomenon is called self-discharge. The so-called "storage performance" refers to the self-discharge of the battery after being stored for a certain period of time under certain conditions (such as temperature and humidity) when the battery is open-circuited.

Although the battery does not release electrical energy during storage, there is always self-discharge inside the battery. Even if it is stored dry, due to poor sealing, water, air, carbon dioxide and other substances will enter, causing some of the positive and negative active materials in a thermodynamically unstable state to form a micro-battery corrosion mechanism, and undergo redox reactions and be consumed in vain. This is even more true if it is stored wet. Active materials in electrolytes for a long time are also unstable. Most of the negative active materials are active metals, and anode self-dissolution will occur. In acidic solutions, negative metals are unstable, and they are not very stable in alkaline and neutral solutions.

Self-discharge

The size of battery self-discharge is generally expressed as the percentage of capacity reduction per unit time, that is:

Self-discharge = (Co-Ct/Cot) × 100%

Where: Co - battery capacity before storage, Ah;

Ct - battery capacity after storage, Ah;

t – storage time, expressed in days, weeks, months or years.

The size of self-discharge can also be expressed by the number of days when the battery is stored to a certain specified capacity, which is called storage life. There are two types of storage life, namely dry storage life and wet storage life. The storage life of batteries that are added with electrolyte only when in use is also customarily called dry storage life. Dry storage life can be very long. The storage life of batteries that have electrolyte added before leaving the factory is customarily called wet storage life (or wet charge life). Self-discharge is serious during wet storage and the life is short. For example, the dry storage life of silver-zinc batteries can reach 5 to 8 years, but its wet storage life is usually only a few months.

The measures to reduce the self-discharge in the battery are generally to use raw materials with higher purity, or to pre-treat the raw materials to remove harmful impurities. Metals with higher hydrogen overpotential, such as Ag, Cd, etc., can also be added to the negative electrode metal grid, and corrosion inhibitors can also be added to the solution, all of which aim to inhibit the precipitation of hydrogen and reduce the occurrence of self-discharge reactions.

It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or perform equivalent replacements on some of the technical features thereof; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. They should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A battery health status diagnosis method based on BP neural network, characterized by comprising the following steps: Collect the battery operation data of electric vehicles throughout their life cycle and construct the first original data sequence; Performing first-order accumulation on the first original data sequence to generate a first data sequence, wherein the first data sequence includes a first time series and a second time series, and the first time series and the second time series are used to represent a first data set within a specific time period of the entire life cycle of the battery; Using the first time series as model input and the second time series as model output, performing model training, and constructing a first BP neural network model; Collect high-frequency charging data of the charging pile and construct a second original data sequence; Performing first-order accumulation on the second original data sequence to generate a second data sequence, wherein the second data sequence includes a third time series and a fourth time series, and the third time series and the fourth time series are used to represent a second data set of the high-frequency charging data within the specific time period; Taking the second time series as model input and the second time series as model output, performing model training, and constructing a second BP neural network model; The first BP neural network model and the second BP neural network model are assigned a first weight and a second weight respectively to construct a BP neural network model, wherein the BP neural network model is used to predict the battery health status according to the current high-frequency charging data and battery operation data. 2. The battery health status diagnosis method based on BP neural network according to claim 1, characterized in that: The expression of the first original data sequence or the second original data sequence is: X ⁽⁰⁾ = {x ⁽⁰⁾ (1), x ⁽⁰⁾ (2),..., x ⁽⁰⁾ (n)} Wherein, X ⁽⁰⁾ represents the original data sequence, and x ⁽⁰⁾ (n) represents the nth data in the original data sequence. 3. The battery health status diagnosis method based on BP neural network according to claim 2 is characterized in that: In the process of generating the first data sequence or the second data sequence, the first-order accumulation process is: 4. The battery health status diagnosis method based on BP neural network according to claim 3 is characterized by: The expression of the first data sequence or the second data sequence is: X ⁽¹⁾ = {x ⁽¹⁾ (1), x ⁽¹⁾ (2), .., x ⁽¹⁾ (n)}. 5. The battery health status diagnosis method based on BP neural network according to claim 4 is characterized in that: In the process of constructing the BP neural network model, the BP neural network model includes an input layer, a hidden layer, and an output layer; The hidden layer nodes of the hidden layer are calculated according to the formula Calculated and determined, m is the number of input neurons, p is the number of output neurons, and q is a constant between 1 and 10. 6. The battery health status diagnosis method based on BP neural network according to claim 5, characterized in that: In the process of constructing the first BP neural network model or the second BP neural network model, the equation expression of the first BP neural network model or the second BP neural network model is: 7. A battery health status diagnosis system based on BP neural network, characterized by comprising: A first data module is used to collect the battery life cycle operation data of the electric vehicle and construct a first original data sequence; A first data processing module, configured to perform first-order accumulation on the first original data sequence to generate a first data sequence, wherein the first data sequence includes a first time series and a second time series, and the first time series and the second time series are used to represent a first data set within a specific time period of the entire life cycle of the battery; A first data analysis module, used to use the first time series as a model input and the second time series as a model output, perform model training, and construct a first BP neural network model; A second data acquisition module is used to collect high-frequency charging data of the charging pile and construct a second original data sequence; A second data processing module, configured to perform first-order accumulation on the second original data sequence to generate a second data sequence, wherein the second data sequence includes a third time series and a fourth time series, and the third time series and the fourth time series are used to represent a second data set of the high-frequency charging data within the specific time period; A second data analysis module, taking the second time series as a model input, taking the second time series as a model output, performing model training, and constructing a second BP neural network model; The state prediction module is used to assign a first weight and a second weight to the first BP neural network model and the second BP neural network model respectively, and construct a BP neural network model, wherein the BP neural network model is used to predict the battery health status according to the current high-frequency charging data and battery operation data. 8. The battery health status diagnosis system based on BP neural network according to claim 7, characterized in that: The battery health status diagnosis system also includes: A data storage module, used for storing the first data set, the second data set and other system data; A communication module, used for data interaction of the battery health status diagnosis system; A display module, used to display system data and the battery health status; A positioning module, used to locate the charging pile and the electric car, and obtain the location information of the charging pile and the electric car respectively; The blockchain module is used to upload the system data to the alliance chain and store the system data to the private chain. 9. The battery health status diagnosis system based on BP neural network according to claim 8, characterized in that: The battery health status diagnosis system also includes a computer program, which is applied to the battery health status diagnosis system and is used to implement the battery health status diagnosis method described in any one of claims 1-6. 10. The battery health status diagnosis system based on BP neural network according to claim 9, characterized in that: The battery health status diagnostic system is applied in a battery health status diagnostic device, which includes a Beidou positioning device, a voltage sensor, a current sensor, a temperature sensor, an ambient temperature sensor, a 5G communication antenna, a memory, and a chip; the battery health status diagnostic device is respectively arranged in a charging pile and an electric vehicle, and is used for the charging pile to identify and locate the electric vehicle, and after data collection, the collected data is transmitted to a background server or a cloud server for data processing.