A battery pack information collection system based on terminal control

Abstract

The present invention discloses a battery pack information acquisition system based on terminal control; the system comprises a main control module, the main control module is electrically connected to a data processing module, the data processing module is electrically connected to a BMS management system and a communication module, the BMS management system is electrically connected to a battery module, the main control module is electrically connected to an electric power device, and the communication module is communicatively connected to a remote terminal module. The present invention manages and controls the battery module through the BMS management system, and then calculates and processes the data information through the data processing module, calculates and processes the power supply mode of the battery module through a greedy algorithm to achieve a balanced and stable power supply mode, and evaluates the power supply mode through a neural network algorithm to prevent calculation errors. Finally, when errors occur in the data information, the data information is corrected and eliminated to improve the accuracy and validity of the data.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery information collection, and in particular relates to a battery pack information collection system based on terminal control. Background Art

[0002] 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.

[0003] Fuel cells are specifically used in fuel cell electric vehicles, including alkaline fuel cells, phosphoric acid fuel cells, molten carbonate fuel cells, solid oxide fuel cells, proton exchange membrane fuel cells, and direct methanol fuel cells. When electric vehicles are in use, the batteries need to be managed and data collected and processed. Generally, the BMS management system is used for battery management, and data information is transmitted through data collection to achieve battery control and adjustment. However, there are still various problems with various battery management and collection on the market.

[0004] For example, a new energy safety early warning management system and method based on 5GNB-IOT technology disclosed in announcement number CN115144756A, although it realizes the use of a server to establish a big data model to compare real-time data, judge and warn of possible dangerous situations in advance, so that users can manage safety and reduce the possibility of safety accidents, but it does not solve the problems existing in the existing battery information collection of effective processing of data information, maintaining the security and accuracy of battery information, and the management of battery information, and it does not realize remote control, which is easy to cause accidents. For this reason, we propose a battery pack information collection system based on terminal control. Summary of the invention

[0005] The purpose of the present invention is to provide a battery pack information collection system based on terminal control to solve the problems raised in the above background technology.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a battery pack information acquisition system based on terminal control, comprising a main control module, the main control module is electrically connected to a data processing module, the data processing module is electrically connected to a BMS management system and a communication module, the BMS management system is electrically connected to a battery module, the main control module is electrically connected to an electric power device, the main control module is electrically connected to an auxiliary module and a storage module, the communication module is communicatively connected to a remote terminal module, the BMS management system is used to detect and control each battery cell in the battery module, and a single precise control is achieved through a distributed mode, the remote terminal module realizes remote control and adjustment of the system, and cooperates with the main control module to realize precise control and adjustment of the power supply process of the battery module, the electric power device is used to realize power output, the communication module adopts wireless communication, and the wireless communication includes a Bluetooth module and a 5G module, the 5G module is used to upload data information to the remote terminal module, the Bluetooth module is used to realize in-vehicle information transmission and mobile device reception, and the 5G module is connected to the remote terminal module through a Server server;

[0007] The data processing module is used to realize the calculation and processing of the transmitted and received data information, and improve the accuracy and security of the data information. The data processing module includes a data information receiving unit, a data information preprocessing unit, a data information filtering unit, a data information conversion unit, a data information gain unit, a data information calculation unit and a data information correction unit. The data information receiving unit is used to realize the acquisition and reception of the transmitted and detected data information. The data information preprocessing unit is used to realize the identification and analysis of the data information, and the analysis mainly uses association analysis, classification clustering and deep learning technology to realize the classification and analysis of data. The data information filtering unit is used to realize the filtering of the data information, and the data information filtering unit includes a low-pass filter. The invention relates to a method for transmitting the power of a battery to a plurality of cells of a battery. The method comprises: a filter and an FIR filter, wherein the data information conversion unit is used to convert the format of the data information so as to unify the format of the data information, the data information gain unit is used to effectively amplify the data information and improve the transmission capacity of the data information, the algorithm adopted by the data information calculation unit is a greedy algorithm, and the calculation of the greedy algorithm is used to effectively calculate the data, calculate and process the structures of various data information, judge the power supply scheme of the battery, and evaluate and process the power supply scheme of the battery through a neural network algorithm, realize feedback control of the power supply scheme of the battery, and improve safety, and the data information correction unit is used to detect dirty data in the data and improve the quality of the data through data screening and data repair.

[0008] Preferably, the BMS management system includes a plurality of CSC slave control units, the battery module includes a plurality of battery cells, each of the CSC slave control units is electrically connected to each of the battery cells, and the CSC slave control unit includes a detection unit, and the detection unit is electrically connected to each of the battery cells.

[0009] Preferably, the CSC slave control unit includes a high-voltage management unit responsible for monitoring the total voltage of the battery cell, the total bus voltage, and the insulation resistance status, and the bus current is collected by a Hall sensor or a shunt, and the BMU performs battery system BSE evaluation, electrical system status detection, contactor management, thermal management, operation management, charging management, diagnostic management, and management of internal and external communication networks.

[0010] Preferably, the detection unit includes measurement function, protection function, power supply design, single cell balancing, fault alarm, relay control, battery algorithm, and safety detection;

[0011] The measurement functions include temperature detection, voltage detection and current detection. The temperature detection includes temperature detection and cooling system of each battery cell. The cooling system adopts embedded heat exchanger to realize cooling and heating of the battery cell. The voltage detection includes battery cell voltage detection and battery module voltage detection.

[0012] The protection functions include sampling line protection and single-cell protection. The sampling line protection includes short circuit and leakage. The single-cell protection includes overvoltage protection, undervoltage protection and overtemperature protection.

[0013] The power supply design includes battery module power, battery cell power and 12V power. The battery cell power includes working current and static current.

[0014] The monomer balancing includes active balancing, passive balancing and diagnosis;

[0015] The relay control includes a pre-charge relay, a positive and negative relay and a diagnosis;

[0016] The battery algorithm includes battery state determination and limit. The battery state obtains the available charge and discharge power of the current battery by looking up the table of temperature and SOC. SOH mainly represents the health state of the current battery, and also includes temperature, voltage, maximum discharge current and maximum charge current.

[0017] The safety detection includes insulation detection, interlocking and cover opening detection.

[0018] Preferably, the main control module is electrically connected to an auxiliary module, and the auxiliary module includes a display, control buttons, a clock crystal oscillator circuit, a reset circuit, an alarm, CAN bus and RS485 communication, the CAN bus and the RS485 communication are used to realize effective transmission of data information, the display and the control buttons are used to display data information and control the system, as well as query data information, the clock crystal oscillator circuit is used to transmit control waveforms, the reset circuit is used to restart the system when a fault occurs, and the alarm is used to perform sound and light alarm processing when a system fault occurs or the data is abnormal.

[0019] Preferably, the battery module is electrically connected to a voltage stabilizing and step-down module, and the voltage stabilizing and step-down module is electrically connected to the main control module. The voltage stabilizing and step-down module is used to stabilize and reduce the voltage when the battery module supplies power to the main control module to maintain the stability of the power supply performance, and also includes a surge protection circuit and a lightning protection circuit to prevent the battery module from having excessive voltage shock at the moment of power supply, and to prevent system damage caused by lightning strikes.

[0020] Preferably, the main control module is electrically connected to a storage module, and the storage module includes a ROM memory for storing a program body for system operation, a RAM memory for storing an operation log, and a cache for caching data information. The storage method adopted by the storage module is a first-in-first-out and last-in-last-out arrangement mode, and the first-in-first-out data information is first stored in the cache, so that the data information can be quickly stored, thereby improving storage efficiency.

[0021] Preferably, the battery module is electrically connected to a boost module, the boost module is used to increase the supply voltage, the boost module is electrically connected to a relay module, the relay module is used to control the on and off of the power supply, and the relay module is electrically connected to the electric power equipment to realize power supply operation of the electric power equipment.

[0022] Preferably, the low-pass filter adopts a second-order IIR low-pass filter, and the calculation formula of the second-order IIR low-pass filter is as follows:

[0023]

[0024] y(n) is the output data, x n is the input data, a and b are the coefficients of the filter, n is the number of filtering times, k=0 is the data information processed this time, k=1 is the data information processed next time, and nk is the position of the data information;

[0025] The FIR filter uses a finite length unit impulse response filter. The definition of an M-order FIR filter is as follows:

[0026] The relationship between the FIR output of length M and the input time series z(n) is given by a finite convolution sum:

[0027]

[0028] The above expression is an M-1 order FIR filter, which has M taps, and therefore consists of M multipliers and M-1 accumulators. Each tap requires a multiplier accumulator unit that consumes logic resources.

[0029] Where z(n) is the input signal, h(j) is the FIR filter coefficient, and v(n) is the filtered signal.

[0030] Preferably, the AI ​​learning algorithm used by the neural network algorithm is:

[0031] The input neuron information and the corresponding weight matrix W are determined by T X t , X is a vector, W is a weight matrix, and W is used to transform X into another vector;

[0032] The information transmitted from the hidden layer neurons at the previous moment to the neurons at the current moment has a value of S t-1 And the corresponding weight matrix U is determined, U T S t-1 , S t-1 is a vector, U is a weight matrix, and S is transformed by U t-1 Convert to another vector;

[0033] Mainly the neuron S at the current moment t , integrate the above input information from the input neuron and the information transmitted from the hidden layer neurons at the previous moment to the neurons at the current moment, activate and generate the output of the hidden layer neurons at the current moment, and the integration process is vector addition: W T X t +U T S t-1 ;

[0034] Assuming the activation function is f, the value of the neuron at the current moment is generated after activation: S t =f(W T X t +U T S t-1 );

[0035] Information transfer mainly transfers the value of the hidden layer neuron at the current moment to the output neuron at the current moment:

[0036] O t =g(V T S t );

[0037] The forward formula is as follows:

[0038] S t =f(W T X t +U T S t-1 ),O t =g(V T S t )=g(V T f(W T X t +U T S t-1 ));

[0039] In the entire neural network, there are three weight matrices in total. The first matrix is ​​W. The dimension of the matrix is ​​(N, K), where N represents the vector dimension of the hidden layer neuron values ​​and K represents the dimension of the vector of the input neural unit. The second weight matrix is ​​V, and the dimension of the matrix is ​​(L, N), where L represents the vector dimension of the neurons in the output layer. The third is the weight matrix U, and the dimension of the matrix is ​​(N, N).

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] When the present invention is in use, the battery module is managed and controlled through the BMS management system, and then the data information is calculated and processed through the data processing module, and the data information is received, pre-processed, filtered, converted, gained, calculated and corrected. In particular, the data information is filtered through multi-stage filtering to achieve the accuracy of the data information, and the data information is formatted and unified to facilitate subsequent processing of the data information. The power supply mode of the battery module is calculated and processed through the greedy algorithm to achieve a balanced and stable power supply mode, and the power supply mode is evaluated through the neural network algorithm to prevent calculation errors and effectively perform feedback adjustment. Finally, when errors occur in the data information, the data information is corrected and eliminated to improve the accuracy and effectiveness of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0043] 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.

[0044] See also Figure 1 The present invention provides a technical solution: a battery pack information acquisition system based on terminal control, comprising a main control module, the main control module is electrically connected to a data processing module, the data processing module is electrically connected to a BMS management system and a communication module, the BMS management system is electrically connected to a battery module, the main control module is electrically connected to an electric power device, the main control module is electrically connected to an auxiliary module and a storage module, the communication module is communicatively connected to a remote terminal module, the BMS management system is used to detect and control each battery cell in the battery module, and a single precise control is achieved through a distributed mode, the remote terminal module realizes remote control and adjustment of the system, and cooperates with the main control module to realize precise control and adjustment of the power supply process of the battery module, the electric power device is used to realize power output, the communication module adopts wireless communication, and the wireless communication includes a Bluetooth module and a 5G module, the 5G module is used to upload data information to the remote terminal module, the Bluetooth module is used to realize in-vehicle information transmission and mobile device reception, and the 5G module is connected to the remote terminal module through a Server server;

[0045] The data processing module is used to realize the calculation and processing of the transmitted and received data information, and improve the accuracy and security of the data information. The data processing module includes a data information receiving unit, a data information preprocessing unit, a data information filtering unit, a data information conversion unit, a data information gain unit, a data information calculation unit and a data information correction unit. The data information receiving unit is used to realize the acquisition and reception of the transmitted and detected data information. The data information preprocessing unit is used to realize the identification and analysis of the data information, and the analysis mainly uses association analysis, classification clustering and deep learning technology to realize the classification and analysis of data. The data information filtering unit is used to realize the filtering of the data information, and the data information filtering unit includes a low-pass filter. The invention relates to a method for transmitting the power of a battery to a plurality of cells of a battery. The method comprises: a filter and an FIR filter, wherein the data information conversion unit is used to convert the format of the data information so as to unify the format of the data information, the data information gain unit is used to effectively amplify the data information and improve the transmission capacity of the data information, the algorithm adopted by the data information calculation unit is a greedy algorithm, and the calculation of the greedy algorithm is used to effectively calculate the data, calculate and process the structures of various data information, judge the power supply scheme of the battery, and evaluate and process the power supply scheme of the battery through a neural network algorithm, realize feedback control of the power supply scheme of the battery, and improve safety, and the data information correction unit is used to detect dirty data in the data and improve the quality of the data through data screening and data repair.

[0046] In order to achieve precise control and regulation of each battery cell and realize distributed control, in the present embodiment, preferably, the BMS management system includes a plurality of CSC slave control units, the battery module includes a plurality of battery cells, each of the CSC slave control units is electrically connected to each of the battery cells, and the CSC slave control unit includes a detection unit, and the detection unit is electrically connected to each of the battery cells.

[0047] In order to achieve single precise control of the battery and effective management of the battery cells, in this embodiment, preferably, the CSC slave control unit includes a high-voltage management unit responsible for monitoring the total voltage, bus total voltage, and insulation resistance status of the battery cells, and the bus current is collected by a Hall sensor or a shunt, and the BMU performs battery system BSE evaluation, electrical system status detection, contactor management, thermal management, operation management, charging management, diagnostic management, and management of internal and external communication networks.

[0048] In order to achieve effective detection and management of the battery cells, in this embodiment, preferably, the detection unit includes measurement function, protection function, power supply design, single cell balancing, fault alarm, relay control, battery algorithm, and safety detection;

[0049] The measurement functions include temperature detection, voltage detection and current detection. The temperature detection includes temperature detection and cooling system of each battery cell. The cooling system adopts embedded heat exchanger to realize cooling and heating of the battery cell. The voltage detection includes battery cell voltage detection and battery module voltage detection.

[0050] The protection functions include sampling line protection and single-cell protection. The sampling line protection includes short circuit and leakage. The single-cell protection includes overvoltage protection, undervoltage protection and overtemperature protection.

[0051] The power supply design includes battery module power, battery cell power and 12V power. The battery cell power includes working current and static current.

[0052] The monomer balancing includes active balancing, passive balancing and diagnosis;

[0053] The relay control includes a pre-charge relay, a positive and negative relay and a diagnosis;

[0054] The battery algorithm includes battery state determination and limit. The battery state obtains the available charge and discharge power of the current battery by looking up the table of temperature and SOC. SOH mainly represents the health state of the current battery, and also includes temperature, voltage, maximum discharge current and maximum charge current.

[0055] The safety detection includes insulation detection, interlocking and cover opening detection.

[0056] In order to realize effective auxiliary operation of the system and improve the convenience of operation, in the present embodiment, preferably, the main control module is electrically connected with an auxiliary module, and the auxiliary module includes a display, control buttons, a clock crystal oscillator circuit, a reset circuit, an alarm, a CAN bus and RS485 communication. The CAN bus and the RS485 communication are used to realize effective transmission of data information, the display and the control buttons are used to display data information and control the system, as well as query data information, the clock crystal oscillator circuit is used to transmit control waveforms, the reset circuit is used to restart the system when a fault occurs, and the alarm is used to perform sound and light alarm processing when a system fault occurs or the data is abnormal.

[0057] In order to achieve stable power supply to the main control module and maintain the stability of power supply, in this embodiment, preferably, the battery module is electrically connected to a voltage stabilizing and step-down module, and the voltage stabilizing and step-down module is electrically connected to the main control module. The voltage stabilizing and step-down module is used to stabilize and reduce the voltage when the battery module supplies power to the main control module to maintain the stability of power supply performance, and also includes a surge protection circuit and a lightning protection circuit to prevent the battery module from having excessive voltage shock at the moment of power supply, and to prevent lightning strikes from causing system damage.

[0058] In order to store data information and improve data information efficiency, in the present embodiment, preferably, a storage module is electrically connected to the main control module, and the storage module includes a ROM memory for storing a program body for system operation, a RAM memory for storing an operation log, and a cache for caching data information. The storage method adopted by the storage module is a first-in-first-out and last-in-last-out arrangement mode, and the first-in-first-out data information is first stored in the cache, so that the data information can be quickly stored, thereby improving storage efficiency.

[0059] In order to realize effective power supply operation of the electric power equipment, in the present embodiment, preferably, the battery module is electrically connected with a boost module, the boost module is used to realize increasing the power supply voltage, the boost module is electrically connected with a relay module, the relay module is used to realize controlling the power supply on and off, the relay module is electrically connected to the electric power equipment, and realizes power supply operation of the electric power equipment.

[0060] In order to achieve effective filtering of data information, in this embodiment, preferably, the low-pass filter adopts a second-order IIR low-pass filter, and the calculation formula of the second-order IIR low-pass filter is as follows:

[0061]

[0062] y(n) is the output data, x n is the input data, a and b are the coefficients of the filter, n is the number of filtering times, k=0 is the data information processed this time, k=1 is the data information processed next time, and nk is the position of the data information;

[0063] The FIR filter uses a finite length unit impulse response filter. The definition of an M-order FIR filter is as follows:

[0064] The relationship between the FIR output of length M and the input time series z(n) is given by a finite convolution sum:

[0065]

[0066] The above expression is an M-1 order FIR filter, which has M taps, and therefore consists of M multipliers and M-1 accumulators. Each tap requires a multiplier accumulator unit that consumes logic resources.

[0067] Where z(n) is the input signal, h(j) is the FIR filter coefficient, and v(n) is the filtered signal.

[0068] In order to implement the neural network algorithm processing, in this embodiment, preferably, the neural network algorithm adopts an AI learning algorithm:

[0069] The input neuron information and the corresponding weight matrix W are determined by T X t , X is a vector, W is a weight matrix, and W is used to transform X into another vector;

[0070] The information transmitted from the hidden layer neurons at the previous moment to the neurons at the current moment has a value of S t-1 And the corresponding weight matrix U is determined, U T S t-1 , S t-1 is a vector, U is a weight matrix, and S is transformed by U t-1 Convert to another vector;

[0071] Mainly the neuron S at the current moment t , integrate the above input information from the input neuron and the information transmitted from the hidden layer neurons at the previous moment to the neurons at the current moment, activate and generate the output of the hidden layer neurons at the current moment, and the integration process is vector addition: W T X t +U T S t-1 ;

[0072] Assuming the activation function is f, the value of the neuron at the current moment is generated after activation: S t =f(W T X t +U T S t-1 );

[0073] Information transfer mainly transfers the value of the hidden layer neuron at the current moment to the output neuron at the current moment:

[0074] O t =g(V T S t );

[0075] The forward formula is as follows:

[0076] S t =f(W T X t +U T S t-1 ),O t =g(V T S t )=g(V T f(W T X t +U T S t-1 ));

[0077] In the entire neural network, there are three weight matrices in total. The first matrix is ​​W. The dimension of the matrix is ​​(N, K), where N represents the vector dimension of the hidden layer neuron values ​​and K represents the dimension of the vector of the input neural unit. The second weight matrix is ​​V, and the dimension of the matrix is ​​(L, N), where L represents the vector dimension of the neurons in the output layer. The third is the weight matrix U, and the dimension of the matrix is ​​(N, N).

[0078] The working principle and use process of the present invention are as follows: when in use, each battery cell in the battery module is detected and managed through the BMS management system, and the data information of the BMS management system is transmitted through the data processing module, and the data information is calculated and processed through the data processing module. The data processing module includes a data information receiving unit, a data information preprocessing unit, a data information filtering unit, a data information conversion unit, a data information gain unit, a data information calculation unit and a data information correction unit. The data information receiving unit is used to obtain and receive the transmitted and detected data information. The data information preprocessing unit is used to identify and analyze the data information, and the analysis mainly uses association analysis, classification clustering and deep learning technology to realize data classification and analysis processing. The data information filtering unit is used to filter the data information. The data information filtering unit includes a low-pass filter and a FIR filter. The data information conversion unit is used to convert the format of the data information so that the format of the data information is unified. The data information gain unit is used to effectively amplify the data information and improve the transmission capacity of the data information. The algorithm adopted by the information calculation unit is a greedy algorithm. Through the calculation of the greedy algorithm, effective calculation of data is realized, and the structure of various data information is calculated and processed, and the power supply scheme of the battery is determined. The power supply scheme of the battery is evaluated and processed through the neural network algorithm, and feedback control of the power supply scheme of the battery is realized to improve safety. The data information correction unit is used to detect dirty data in the data, improve the quality of the data through data screening and data repair, and then transmit the data information to the main control module to realize control and adjustment of the battery system and management of data information. When in use, the battery system is operated and controlled through the auxiliary module, and the battery module is remotely controlled and adjusted through the communication module and the remote terminal module to improve the safety of the battery module. Then the main control module realizes control so that the battery module can power the electrical equipment through the boost module and the relay module to realize operation. The operation of the main control module is also the power supply operation of the battery module through the voltage stabilizing and bucking module. The data information is stored through the storage module and classified storage to prevent confusion of the data information and improve the storage and extraction rate of the data information.

[0079] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A battery pack information collection system based on terminal control, including a main control module, characterized in that: The main control module is electrically connected to a data processing module, the data processing module is electrically connected to a BMS management system and a communication module, the BMS management system is electrically connected to a battery module, the main control module is electrically connected to an electric power device, the main control module is electrically connected to an auxiliary module and a storage module, the communication module is communicatively connected to a remote terminal module, the BMS management system is used to detect and control each battery cell in the battery module, and to achieve single precise control through a distributed mode, the remote terminal module realizes remote control and adjustment of the system, and cooperates with the main control module to achieve precise control and adjustment of the power supply process of the battery module, the electric power device is used to achieve power output, the communication module adopts wireless communication, and the wireless communication includes a Bluetooth module and a 5G module, the 5G module is used to upload data information to the remote terminal module, the Bluetooth module is used to realize in-vehicle information transmission and mobile device reception, and the 5G module is connected to the remote terminal module through the Server server; The data processing module is used to realize the calculation and processing of the transmitted and received data information, and improve the accuracy and security of the data information. The data processing module includes a data information receiving unit, a data information preprocessing unit, a data information filtering unit, a data information conversion unit, a data information gain unit, a data information calculation unit and a data information correction unit. The data information receiving unit is used to realize the acquisition and reception of the transmitted and detected data information. The data information preprocessing unit is used to realize the identification and analysis of the data information, and the analysis mainly uses association analysis, classification clustering and deep learning technology to realize the classification and analysis of data. The data information filtering unit is used to realize the filtering of the data information, and the data information filtering unit includes a low-pass filter. The invention relates to a method for transmitting the power of a battery to a plurality of cells of a battery. The method comprises: a filter and an FIR filter, wherein the data information conversion unit is used to convert the format of the data information so as to unify the format of the data information, the data information gain unit is used to effectively amplify the data information and improve the transmission capacity of the data information, the algorithm adopted by the data information calculation unit is a greedy algorithm, and the calculation of the greedy algorithm is used to effectively calculate the data, calculate and process the structures of various data information, judge the power supply scheme of the battery, and evaluate and process the power supply scheme of the battery through a neural network algorithm, realize feedback control of the power supply scheme of the battery, and improve safety, and the data information correction unit is used to detect dirty data in the data and improve the quality of the data through data screening and data repair.

2. The battery pack information collection system based on terminal control according to claim 1, characterized in that: The BMS management system includes a plurality of CSC slave control units, the battery module includes a plurality of battery cells, each of the CSC slave control units is electrically connected to each of the battery cells, and the CSC slave control units include detection units, which are electrically connected to each of the battery cells.

3. The battery pack information collection system based on terminal control according to claim 2 is characterized in that: The CSC slave control unit includes a high-voltage management unit that is responsible for monitoring the total voltage of the battery cell, the total bus voltage, and the insulation resistance status, and the bus current is collected by a Hall sensor or a shunt. The BMU performs battery system BSE evaluation, electrical system status detection, contactor management, thermal management, operation management, charging management, diagnostic management, and management of internal and external communication networks.

4. The battery pack information collection system based on terminal control according to claim 2 is characterized in that: The detection unit includes measurement function, protection function, power supply design, single cell balancing, fault alarm, relay control, battery algorithm, and safety detection; The measurement functions include temperature detection, voltage detection and current detection. The temperature detection includes temperature detection and cooling system of each battery cell. The cooling system adopts embedded heat exchanger to realize cooling and heating of the battery cell. The voltage detection includes battery cell voltage detection and battery module voltage detection. The protection functions include sampling line protection and single-cell protection. The sampling line protection includes short circuit and leakage. The single-cell protection includes overvoltage protection, undervoltage protection and overtemperature protection. The power supply design includes battery module power, battery cell power and 12V power. The battery cell power includes working current and static current. The monomer balancing includes active balancing, passive balancing and diagnosis; The relay control includes a pre-charge relay, a positive and negative relay and a diagnosis; The battery algorithm includes battery state determination and limit. The battery state obtains the available charge and discharge power of the current battery by looking up the table of temperature and SOC. SOH mainly represents the health state of the current battery, and also includes temperature, voltage, maximum discharge current and maximum charge current. The safety detection includes insulation detection, interlocking and cover opening detection.

5. The battery pack information collection system based on terminal control according to claim 1, characterized in that: The main control module is electrically connected to an auxiliary module, which includes a display, control buttons, a clock crystal oscillator circuit, a reset circuit, an alarm, a CAN bus and RS485 communication. The CAN bus and the RS485 communication are used to realize effective transmission of data information. The display and the control buttons are used to display data information and control the system, as well as to query data information. The clock crystal oscillator circuit is used to transmit control waveforms. The reset circuit is used to restart the system when a fault occurs. The alarm is used to perform sound and light alarm processing when a fault occurs in the system or the data is abnormal.

6. The battery pack information collection system based on terminal control according to claim 1, characterized in that: The battery module is electrically connected to a voltage stabilizing and step-down module, which is electrically connected to the main control module. The voltage stabilizing and step-down module is used to stabilize and reduce the voltage when the battery module supplies power to the main control module to maintain the stability of the power supply performance. It also includes a surge protection circuit and a lightning protection circuit to prevent the battery module from having excessive voltage shock at the moment of power supply and to prevent system damage caused by lightning strikes.

7. The battery pack information collection system based on terminal control according to claim 1, characterized in that: The main control module is electrically connected to a storage module, which includes a ROM memory for storing a program body for system operation, a RAM memory for storing an operation log, and a buffer for caching data information. The storage module adopts a first-in-first-out and last-in-last-out arrangement mode, and the first-in-first-out data information is first stored in the buffer, so that the data information can be quickly stored, thereby improving storage efficiency.

8. The battery pack information collection system based on terminal control according to claim 1, characterized in that: The battery module is electrically connected to a boost module, which is used to increase the power supply voltage. The boost module is electrically connected to a relay module, which is used to control the on and off of the power supply. The relay module is electrically connected to the electric power equipment to power the electric power equipment.

9. The battery pack information collection system based on terminal control according to claim 1, characterized in that: The low-pass filter adopts a second-order IIR low-pass filter, and the calculation formula of the second-order IIR low-pass filter is as follows: y(n) is the output data, x n is the input data, a and b are the coefficients of the filter, n is the number of filtering times, k=0 is the data information processed this time, k=1 is the data information processed next time, and nk is the position of the data information; The FIR filter uses a finite length unit impulse response filter. The definition of an M-order FIR filter is as follows: The relationship between the FIR output of length M and the input time series z(n) is given by a finite convolution sum: The above expression is an M-1 order FIR filter, which has M taps, and therefore consists of M multipliers and M-1 accumulators. Each tap requires a multiplier accumulator unit that consumes logic resources. Where z(n) is the input signal, h(j) is the FIR filter coefficient, and v(n) is the filtered signal.

10. The battery pack information collection system based on terminal control according to claim 1, characterized in that: The AI ​​learning algorithm used by the neural network algorithm is: The input neuron information and the corresponding weight matrix W are determined, W T X t , X is a vector, W is a weight matrix, and W is used to transform X into another vector; The information transmitted from the hidden layer neurons at the previous moment to the neurons at the current moment has a value of S t-1 And the corresponding weight matrix U is determined, U T S t-1 , S t-1 is a vector, U is a weight matrix, and S is transformed by U t-1 Convert to another vector; Mainly the neuron S at the current moment t , integrates the input information from the input neuron and the information transmitted from the hidden layer neurons at the previous moment to the neurons at the current moment, and activates the output of the hidden layer neurons at the current moment. The integration process is vector addition: W T X t +U T S t-1 ; Assuming the activation function is f, the value of the neuron at the current moment is generated after activation: S t =f(W T X t +U T S t-1 ); Information transfer mainly transfers the value of the hidden layer neuron at the current moment to the output neuron at the current moment: O t =g(V T S t ); The forward formula is as follows: S t =f(W T X t +U T S t-1 ),O t =g(V T S t )=g(V T f(W T X t +U T S t-1 )); In the entire neural network, there are three weight matrices in total. The first matrix is ​​W. The dimension of the matrix is ​​(N, K), where N represents the vector dimension of the hidden layer neuron values ​​and K represents the dimension of the vector of the input neural unit. The second weight matrix is ​​V, and the dimension of the matrix is ​​(L, N), where L represents the vector dimension of the neurons in the output layer. The third is the weight matrix U, and the dimension of the matrix is ​​(N, N).

Images