Intelligent diagnosis and automatic equalization device based on energy storage power station and processing method

Abstract

The invention relates to the technical field of energy storage power station cell charging and discharging, in particular to an intelligent diagnosis and automatic equalization device based on an energy storage power station and a processing method. The device comprises a first micro-control unit, a cell data acquisition unit, a charging power supply, a channel selection unit, a CAN driver and a USB interface. One ends of the cell data acquisition unit, the charging power supply and the channel selection unit are respectively in communication connection with the first micro-control unit, the other end of the charging power supply is in communication connection with the channel selection unit, and the other ends of the cell data acquisition unit and the channel selection unit are in communication connection with the charging harness; one end of the CAN driver and one end of the USB interface are respectively in communication connection with the first micro-control unit, the other end of the CAN driver is in communication connection with a high-voltage box debugging port, and the other end of the USB interface is in communication connection with mobile equipment. The battery cell consistency can be optimized, the schedulable interval can be expanded, the fault processing flow can be simplified, the operation safety can be improved, and the operation and maintenance threshold can be reduced.

Description

Technical Field

[0001] This application relates to the field of cell charging and discharging technology for energy storage power stations, and in particular to a device and processing method for intelligent diagnosis and automatic balancing based on energy storage power stations. Background Technology

[0002] In practical applications of centralized energy storage power stations, their inherent defects and specific physical architecture make it difficult to maintain consistent internal impedance. This issue leads to a gradual increase in the performance differences among individual cells after long-term operation, resulting in a significant "weakest link" effect. The overall system performance is limited by the worst-performing cell, making it prone to prematurely triggering charge / discharge protection and exhibiting "high charge, low discharge" phenomena. Specifically, during charging, to avoid overcharging the weakest cell, the system must control the charging process according to its maximum full charge limit, failing to fully utilize the capacity of the high-performing cells. During discharging, the weakest cell reaches its discharge limit first, causing the system to stop discharging prematurely, leaving the remaining energy of the high-performing cells unreleased. Ultimately, this continuously narrows the dispatchable range of the power station, resulting in lower-than-expected actual operational benefits. Furthermore, centralized energy storage power stations employ a multi-cluster parallel structure, making fault location difficult. Fault maintenance relies on on-site handling by professional personnel from the manufacturer, typically resulting in long recovery times and a high probability of system outages. When the "weakest link" effect becomes apparent, it is necessary to replenish the power of the weakest battery cells. This process carries safety risks, and improper operation can easily expand the scope of the fault. It cannot be carried out by non-professionals, which further affects the stability and economy of the power plant operation.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main objective of this application is to propose a device and processing method for intelligent diagnosis and automatic balancing of energy storage power stations, which can optimize cell consistency, broaden the dispatchable range, simplify fault handling procedures, improve operational safety, and lower the operation and maintenance threshold.

[0005] To achieve the above objectives, one aspect of this application proposes a device for intelligent diagnosis and automatic balancing based on an energy storage power station, comprising: a first microcontroller unit, a cell data acquisition unit, a power supply, a channel selection unit, a CAN driver, and a USB interface; One end of the cell data acquisition unit, the power supply, and the channel selection unit are respectively communicatively connected to the first microcontroller unit; the other end of the power supply is communicatively connected to the channel selection unit; and the other ends of the cell data acquisition unit and the channel selection unit are communicatively connected to the power supply harness. One end of the CAN driver and one end of the USB interface are respectively connected to the first microcontroller unit, the other end of the CAN driver is connected to the high-voltage box debugging port, and the other end of the USB interface is connected to the mobile device.

[0006] In some embodiments, the battery cell data acquisition unit includes a CAN driver chip, an isolation module, and a protection module; The CAN driver chip is used to realize the CAN communication interaction between the battery cell data and the first microcontroller unit; The isolation module is a CAN transceiver isolator with isolation function. The isolation module is connected between the CAN transceiver chip and the protection module. The isolation module is used to achieve electrical isolation of communication signals. The protection module includes a transient suppression diode array and a common-mode inductor. The protection module is used to protect CAN communication signals from overvoltage, overcurrent and common-mode interference. The first microcontroller unit reads the cell's status parameters from the registers via the IIC serial communication interface or the SPI serial communication interface.

[0007] In some embodiments, the cell data acquisition unit includes an analog front-end circuit; The analog front-end circuit uses a multi-channel sampling architecture, with each sampling channel equipped with filtering and voltage regulation components.

[0008] In some embodiments, the channel selection unit includes multiple sets of optocoupler relay modules and a second microcontroller unit; The optocoupler relay module is constructed using an optocoupler relay, and the optocoupler relay module is used to control the connection and disconnection between the battery cell and the charging circuit; The second microcontroller unit is connected to the optocoupler relay module via a GPIO interface. The DO output port of the second microcontroller unit outputs a corresponding high-level signal based on the cell status calculation result. The high-level signal is used to drive the optocoupler relay to operate.

[0009] In some embodiments, the optocoupler relay module adopts a parallel architecture of multiple sets of optocoupler relays, with each set of optocoupler relays corresponding to the power supply channel control of one battery cell. In some embodiments, the power supply includes an input rectifier circuit, an isolation transformer, a control chip, and an output regulation circuit; The input rectifier circuit rectifies the input voltage; the isolation transformer provides electrical isolation between the input and output; the control chip controls the operating state of the switching power supply and adjusts the output voltage and current; the output adjustment circuit adjusts the output current based on data sent by the MCU.

[0010] In some embodiments, the input rectifier circuit includes a filter capacitor and a rectifier diode; The isolation transformer is equipped with protection elements on its primary and secondary sides, and voltage and current sampling circuits are provided at its output terminals.

[0011] To achieve the above objectives, another aspect of this application proposes a processing method for intelligent diagnosis and automatic balancing of energy storage power stations, the method comprising the following steps: Confirm that the aforementioned intelligent diagnostic and automatic balancing device based on the energy storage power station is connected to and activated by the energy storage power station and the mobile device, respectively. The cell status parameters of the energy storage power station are obtained through the cell data acquisition unit. The acquired cell state parameters are preprocessed; The preprocessed cell status parameters are input into the intelligent diagnostic parameter model to obtain operational status fault information; The operational status fault information is transmitted to the mobile device for real-time display.

[0012] In some embodiments, inputting the preprocessed cell status parameters into an intelligent diagnostic parameter model to obtain operational status fault information includes the following steps: Local features of the preprocessed cell state parameters are extracted using a convolutional neural network model to obtain key features of the cell's local operating state. The key features of the extracted local operating state are modeled globally using the self-attention mechanism of the converter model to obtain the state parameter association features of the battery cell. The key features of the local operating state and the associated features of the state parameters are weighted and fused to obtain the comprehensive operating state features of the battery cell. The classifier determines the fault category of the comprehensive operating status characteristics of the battery cell to obtain operating status fault information.

[0013] In some embodiments, transmitting the operational status fault information to the mobile device for real-time display includes the following steps: The operating status fault information is transmitted to the mobile device for real-time display via the USB interface; The operational status fault information includes fault information, fault reasoning, component information, maintenance contact information, and handling methods.

[0014] The embodiments of this application include at least the following beneficial effects: This application provides a device and processing method for intelligent diagnosis and automatic balancing based on energy storage power stations. This solution integrates a power supply, a channel selection unit, a cell data acquisition unit, a CAN driver, and a USB interface through a first microcontroller unit. On the one hand, the cell data acquisition unit accurately monitors the cell status, and combined with the intelligent switching of the channel selection unit, it can selectively replenish power to the weakest cells, effectively alleviating the bottleneck effect, expanding the dispatchable range of the energy storage power station, and improving actual benefits. On the other hand, the connection between the CAN driver and the high-voltage box debugging port, as well as the centralized control of the first microcontroller unit, simplifies the fault location and operation and maintenance process, reduces the probability of outages, and the automation and intelligence of the power replenishment operation also avoids the safety risks of manual power replenishment, improving the overall stability and safety of operation, and providing strong support for the efficient and reliable operation of centralized energy storage power stations. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the high-charge and low-discharge operation of battery cells in an energy storage power station. Figure 2 This is a schematic diagram of the structure of the intelligent diagnostic and automatic balancing device based on an energy storage power station provided in the embodiments of this application; Figure 3 This is a schematic diagram of the system integration structure of the battery cell data acquisition unit; Figure 4 This is a schematic diagram of the analog front-end and core processing circuit of the battery cell data acquisition unit; Figure 5 This is a schematic diagram of the IIC communication isolation circuit of the battery cell data acquisition unit; Figure 6 This is a diagram of the cell connection interface for the cell data acquisition unit; Figure 7 This is a schematic diagram of the first multi-channel optocoupler relay control circuit; Figure 8 This is a schematic diagram of the second multi-channel optocoupler relay control circuit; Figure 9 This is a circuit diagram of the power supply. Figure 10 This application provides another embodiment of a flowchart of a processing method for intelligent diagnosis and automatic balancing based on energy storage power stations. Figure 11 This is a schematic diagram displayed on a mobile device. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0017] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0018] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0021] BMS: Battery Management System, used to monitor battery status, control charging and discharging, and ensure battery safety and lifespan.

[0022] SOC: State of charge, which is the percentage of remaining charge relative to the total capacity, is a key parameter for battery management.

[0023] CNN: Convolutional Neural Network, which extracts local features through convolution operations.

[0024] Transformer: A model based on self-attention mechanism, which excels at capturing long-distance dependencies.

[0025] IIC / SPI: Two serial communication protocols. IIC is a two-wire, multi-master / slave protocol, while SPI is a four-wire, high-speed synchronous protocol used for data transmission between devices, such as battery cell data acquisition.

[0026] PACK: A battery pack is a complete battery unit consisting of multiple battery cells, protection circuits, etc.

[0027] COMP terminal: Comparator output terminal, used to compare two voltage signals and output logic level.

[0028] CAN transceiver isolator: Provides electrical isolation for CAN bus signals to prevent interference.

[0029] CANH: The high-level line of the CAN bus, which, together with CANL (low-level line), forms a differential signal pair to achieve interference-resistant CAN communication.

[0030] CANL: The low-level line of the CAN bus, used in conjunction with CANH to transmit differential signals and ensure the stability of CAN communication.

[0031] In related technologies, such as Figure 1 As shown, Figure 1 This is a schematic diagram of the high-charge and low-discharge behavior of battery cells in an energy storage power station. Due to the inherent defects and physical architecture of centralized energy storage power stations, impedance inconsistencies lead to increased differences in battery cell performance over long-term operation. When multiple clusters are connected in parallel on the DC side, the "weakest link" effect inevitably occurs, limiting the system's lifespan to the worst-performing cell. This prematurely triggers protection, resulting in high-charge and low-discharge behavior, narrowing the dispatchable range, exacerbating internal resistance differences over long periods, and causing circulating current losses. This can result in a system charge / discharge capacity loss of 15%-20% or more, leading to unsatisfactory actual returns. For example, during charging, to prevent the cell with the highest capacity from overcharging, the entire system can only charge to the maximum capacity of that cell, meaning the full capacity of other high-quality cells remains unused—appearing fully charged but actually not fully charged. During discharging, the cell with the lowest capacity discharges first, and the system stops discharging prematurely. The remaining high-quality cells still have a significant amount of undischarged capacity, ultimately resulting in lower-than-expected charging and discharging. Premature protection triggering occurs when a weak cell in the energy storage system has low capacity and rapid degradation. This weak cell charges first and discharges first. When the system detects that this weak cell has reached its charge / discharge limit, it triggers overall protection to prevent damage, causing the entire system to prematurely stop charging / discharging. Maintenance for this fault requires on-site handling by the manufacturer. The multi-cluster parallel structure makes fault location difficult, with an average recovery time of at least 48 hours, resulting in a high probability of system downtime. When the weakest link in the circuit occurs, the weakest cell needs to be recharged, a dangerous operation that can easily exacerbate the fault; it is not suitable for non-professionals.

[0032] In view of this, this application provides a device and processing method for intelligent diagnosis and automatic balancing of energy storage power stations, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of the intelligent diagnostic and automatic balancing device for energy storage power stations provided in this application embodiment. The solution uses a first microcontroller unit as the core control unit, receiving power replenishment parameter commands via an SPI stream setting module and connecting to a cell data acquisition unit via an IIC / SPI interface to obtain real-time cell status information. The output of the cell data acquisition unit is associated with a channel selection unit. The first microcontroller unit includes a 32-bit MCU, which controls the channel selection unit to switch power replenishment channels. The power replenishment power supply is connected to the power replenishment cable harness via the channel selection unit, achieving precise power replenishment of designated cells. Furthermore, the 32-bit MCU is also connected to the high-voltage box debugging port via a CAN driver to complete the high-voltage box debugging interaction. Through the linkage between the cell data acquisition unit and the channel selection unit, weak cells can be accurately identified and targeted for power replenishment, effectively alleviating the bottleneck effect, widening the dispatchable range, and improving the actual benefits of the energy storage power station. The centralized control of the first microcontroller unit simplifies fault location and maintenance processes, reduces the probability of system downtime, and the automated power replenishment operation avoids the safety risks of manual operation, improving the stability and safety of system operation and providing strong support for the efficient operation and maintenance of centralized energy storage power stations.

[0033] In some embodiments, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the system integration of the battery cell data acquisition unit. The CAN_RX and CAN_TX interfaces receive external data signals, which are then filtered by capacitor C8 and input to the RXD and TXD pins of the CAN transceiver chip U2 (ISD1050). U2's VCC1 is powered by VCC_3V3, and VCC2 and GND2 are connected to the VISO_5V0 power supply with capacitor C7 for filtering. U2's CANH and CANL pins are connected to isolator A1 (ACT45B-110-2P-TL003) for electrical isolation. After passing through a protection circuit composed of transient suppression diodes D5, D6, and D7, resistors R27, R31, and R34, and a common-mode inductor R28, the signals are finally connected to the CAN_H and CAN_L terminals of interface J1 (KF2EDGR-3.5-2P). The CAN protocol is used to exchange cell data through a CAN transceiver chip. The isolation module ensures electrical isolation of signal transmission and prevents external interference from entering. The protection module effectively suppresses surge and common-mode interference. The multi-stage design enables the cell data acquisition unit to transmit various parameters of the cell stably and reliably in complex electromagnetic environments, providing hardware support for accurate monitoring of cell status in energy storage power stations.

[0034] Figure 3The core of this battery cell data acquisition unit comprises a CAN driver chip, an isolation module, and a protection module. These modules are connected in an orderly manner through specific links to form a complete acquisition and communication architecture. The CAN driver chip, as the core communication device, is responsible for the CAN protocol interaction between the battery cell data and the external control unit. Its CANH and CANL pins interface with the protection module after passing through the isolation module. The isolation module uses a CAN transceiver isolator with isolation function, connected between the CAN driver chip and the protection module, which can achieve electrical isolation of communication signals and prevent external circuit interference from entering the acquisition circuit. The protection module consists of transient suppression diodes and common-mode inductors, specifically designed to provide overvoltage and overcurrent protection and common-mode interference filtering for CAN communication signals. Finally, it connects to the battery cell through the interface of the external battery cell data acquisition unit. This circuit, through the combination of isolation design and anti-interference protection, effectively improves the stability and security of the battery cell data acquisition unit, ensuring reliable transmission of various battery cell parameters in complex electromagnetic environments.

[0035] The core of the telecommunications data acquisition unit consists of a CAN driver chip, a CAN transceiver isolator, a transient voltage suppression diode array, and a common-mode inductor, along with power supply filtering and signal processing components. The CAN driver chip is specifically responsible for processing CAN protocol parsing and transmission of battery cell data. Its power supply-side filter capacitor effectively suppresses power supply noise, ensuring stable chip operation. The CAN transceiver isolator provides electrical isolation between the CAN driver chip and external circuits, blocking interference transmission paths at the hardware level. The dual protection circuit composed of the transient voltage suppression diode array and the common-mode inductor can specifically filter surge voltages and common-mode interference signals from the CAN bus. These components are connected in series to form a complete data acquisition link, capable of accurately reading various parameters such as battery voltage, capacity, and health status, and possessing strong anti-interference and damage-resistant characteristics.

[0036] In the battery cell data acquisition unit, such as Figure 4 , Figure 5 and Figure 6 As shown, Figure 4 This is a schematic diagram of the analog front-end and core processing circuit of the battery cell data acquisition unit; Figure 5 This is a schematic diagram of the IIC communication isolation circuit of the battery cell data acquisition unit; Figure 6 This is a diagram of the cell connection interface for the cell data acquisition unit. Figure 4In the circuit, a multi-channel sampling circuit, composed of capacitors, resistors, and sampling interfaces, is connected to multiple battery cells to sample parameters such as cell voltage and current in parallel. The sampled signals are transmitted to the core data acquisition and processing chip, where they are integrated and initially processed before being connected to the MCU (Microcontroller Unit) for further data processing and external communication. Multi-channel parallel sampling improves the efficiency and accuracy of battery cell data acquisition, while the collaborative work of the core chip and the MCU ensures timely data processing, providing hardware support for accurate monitoring of battery cell status in energy storage power stations. Figure 5 In the circuit, the NSI8100N isolation chip serves as the core. One side connects to external devices via the A-IIC_SDA and A-IIC_SCL interfaces, while the other side connects to the MCU via the IIC1_SDA and IIC1_SCL interfaces. The circuit also includes power supply filter capacitors (such as C41 and C1), pull-up resistors (such as R05, R06, R2, and R3), and current-limiting resistors (such as R03, R6, and R7), achieving electrical isolation and stable transmission of communication signals. This isolation design blocks external electromagnetic interference from affecting the communication link, ensuring the reliability of data transmission between the battery cells. Figure 6 The interface has multiple pins corresponding to the positive and negative terminals and sampling points of different battery cells. These pins enable the physical connection between multiple battery cells and the data acquisition unit, establishing a sampling link for parameters such as battery cell voltage and current. The standardized pin layout and clear cell correspondence ensure the convenience and accuracy of connecting the battery cells to the acquisition unit.

[0037] The analog front-end circuit is responsible for raw sampling of parameters such as voltage and current of multiple battery cells. The core data acquisition and processing chip is connected to the analog front-end circuit to integrate and perform preliminary processing on the multi-channel sampled signals. The communication isolation circuit communicates with the core data acquisition and processing chip to complete further data processing and storage, and to achieve information exchange with external systems. The analog front-end circuit adopts a multi-channel independent sampling architecture, with each channel equipped with filtering and voltage regulation components, enabling parallel sampling of at least 8 battery cells simultaneously, significantly improving the parallelism and data accuracy of the acquisition. The communication isolation circuit is connected to the first microcontroller unit through a dedicated communication interface, enabling real-time transmission of multi-dimensional parameters of the battery cells. The accompanying power management and anti-interference circuits ensure the stability of data transmission in complex electromagnetic environments. After the channel selection unit determines the short-board battery cell that needs to be recharged, it is connected to the recharge power supply circuit, and the power of the recharge power supply is controlled by the MCU.

[0038] In some embodiments, the channel selection unit, such as Figure 7 and Figure 8 As shown, Figure 7 This is a schematic diagram of the first multi-channel optocoupler relay control circuit; Figure 8 This is a schematic diagram of the second multi-channel optocoupler relay control circuit. Figure 7 and Figure 8 The system is built around multiple sets of optocoupler relays. The control terminal of each optocoupler relay is connected one-to-one to the GPIO interface of the MCU via a current-limiting resistor, forming an independent control signal link. The input terminals of the optocoupler relays correspond to the cell circuit nodes of the energy storage power station, with each input terminal associated with only one cell, achieving independent channel control for each cell. The output terminals of all optocoupler relays converge in parallel to a unified supplementary power supply circuit interface, and each output terminal is equipped with a reverse protection diode. Simultaneously, the power supply terminals of the optocoupler relays are connected to the system power supply circuit via filter capacitors, and the control terminals also have freewheeling components connected in parallel, forming a unified "MCU control signal" system. Current limiting driver Optocoupler relay The system features a complete connection architecture for the "cell / recharge circuit," with multiple optocoupler relays arranged symmetrically in parallel. First, a high-level output via the corresponding GPIO interface precisely drives the target optocoupler relay to conduct, connecting only the cell requiring recharge to the recharge circuit and avoiding ineffective or erroneous recharge. Second, the isolated connection design of the optocoupler relays, combined with current-limiting and freewheeling components on the control side and a reverse protection diode on the output side, ensures stable switching under high-current recharge scenarios by utilizing the large contact current and arc-free characteristics of the optocoupler relays, while also preventing electrical interference between the cell circuit and the control circuit.

[0039] The channel selection unit comprises multiple optocoupler relay modules and a second microcontroller unit. The optocoupler relay modules, centered around optocoupler relays, utilize a parallel architecture with multiple groups of relays, each corresponding to the charging channel control of one battery cell. Thanks to their large contact current and arc-free operation, they function stably under high-current charging scenarios. The second microcontroller unit connects to the optocoupler relay modules via a GPIO interface. Its DO output port calculates the battery cell status from the host computer and outputs a corresponding high-level signal to drive the optocoupler relays, thus precisely connecting the short-circuited battery cell requiring charging to the charging circuit. Through the electrical isolation and stable switching capabilities of the optocoupler relays, combined with the intelligent control logic of the second microcontroller unit, precise charging of the battery cells in the energy storage power station is achieved, ensuring the safety and reliability of the charging operation.

[0040] In some embodiments, such as Figure 9 As shown, Figure 9This is a circuit diagram of a power supply. The diagram shows an isolated switching power supply design. The input EA+ and EA- are processed by a rectifier and filter circuit consisting of diode D1 and capacitor C4, and then connected to the primary winding (pins 5 and 6) of transformer T1 to achieve initial rectification and filtering of the input power. The secondary windings of transformer T1 (pins 1 and 2 and pins 3 and 4) are connected to different circuit branches. The output from pin 1 is powered by a circuit consisting of resistor R5, capacitor C2, resistor R4, and diode D3, as well as filtering by capacitor C3, supplying power to the VDD terminal (pin 1) of the power control chip U1. Simultaneously, pin 2 is connected to the current detection terminal (pins 5 and 6) of U1 via diode D2 and resistor R8 to sample the secondary current. Pin 3 is connected to the feedback terminal (pin 3) of U1 via resistors R9 and R12, forming a voltage feedback loop with capacitor C6 to stabilize the output voltage. The compensation terminal (pin 2) of U1 is connected to capacitor C5, and the COMP terminal (pin 4) is connected to resistors R10 (5R) and R11 (5R), jointly achieving loop compensation and output regulation of the power supply. In addition, the circuit also includes a feedback control branch consisting of optocoupler P1 and resistors R13, R14, and R15. The input of P1 is connected to P24V, and the output is PWR-CHIA signal after being divided by resistors. This enables the MCU to control the power supply and adjust the output current according to the cell status, thereby providing accurate and safe power supply support for the short-board cells of the energy storage power station.

[0041] The power supply employs an isolated switching power supply design, including an input rectifier and filter circuit, an isolation transformer, a control chip, and an output regulation circuit. The input EA+ and EA- are rectified and filtered by diode D1 and capacitor C4 before being connected to the primary winding of transformer T1, providing a stable DC input for subsequent energy transmission. The secondary winding of the transformer achieves electrical isolation between the input and output. One secondary output path supplies power to the VDD terminal of U1 via resistors, capacitors, and diodes; the other path uses diode D2 and resistor R8 to sample the secondary current and connects to the current detection terminal of U1. Simultaneously, a voltage feedback loop composed of resistors and capacitors connects to the feedback terminal of U1. This, along with the compensation circuit of U1 and external components at the COMP terminal, achieves power loop compensation and output regulation, ultimately outputting stable power. The power control chip U1 uses the NE8311AS7G, which features voltage feedback (FB) and current detection (CS) functions. Connected to the feedback branch composed of optocoupler P1 and resistors via the output regulation circuit, it can receive current adjustment commands from the MCU, achieving precise adjustment of the power supply current to meet the power supply needs of different battery cells. The input rectifier circuit is equipped with a filter capacitor C4 and a rectifier diode D1. The primary and secondary sides of the isolation transformer T1 are respectively equipped with protection and sampling elements. The output terminal is equipped with a voltage sampling and current sampling circuit composed of resistors and capacitors, and has a feedback control branch composed of optocoupler P1 to ensure stable operation of the power supply under high current and isolation conditions.

[0042] To achieve the above objectives, another aspect of this application proposes a processing method for intelligent diagnosis and automatic balancing of energy storage power stations, such as... Figure 10 As shown, Figure 10 This is an optional flowchart of a processing method for intelligent diagnosis and automatic balancing based on energy storage power stations provided in an embodiment of this application. Figure 10 The method may include, but is not limited to, steps S110 to S150.

[0043] Step S110: Confirm that the aforementioned intelligent diagnostic and automatic balancing devices based on the energy storage power station are connected to and turned on by the energy storage power station and the mobile device, respectively. Step S120: Obtain the cell status parameters of the energy storage power station through the cell data acquisition unit; Step S130: Preprocess the acquired cell state parameters; Step S140: Input the preprocessed cell status parameters into the intelligent diagnostic parameter model to obtain the operating status fault information; Step S150: The operating status fault information is transmitted to the mobile device for real-time display.

[0044] In steps S110-S130, after the intelligent diagnostic and automatic balancing device based on the energy storage power station is connected to and activated by both the energy storage power station and the mobile device, it communicates with the cells in the energy storage power station through the network communication interface of the cell data acquisition unit to obtain cell status parameters. These parameters include key information such as battery-related voltages, total battery stack voltage, current charging / discharging current, cell voltage, cell temperature, accumulated charge, and accumulated discharge charge, and are then stored in the system's internal database. Since the voltage (V), current (I), and temperature (T) parameters collected from the cells may contain abnormal data, the abnormal data detection uses a 3-standard-deviation method, with data within -3 and +3 standard deviations. Values ​​outside the range are considered outliers and are replaced by the average value. If there are missing values, they are filled directly using the average value. In addition, due to the inconsistency of unit dimensions, normalization is performed to eliminate the influence of unit dimensions, thereby accelerating the convergence speed of the neural network and improving the accuracy of the algorithm.

[0045] In step S140, local features are extracted from the preprocessed cell state parameters using a convolutional neural network model to obtain key features of the cell's local operating state; global dependency modeling is performed on the extracted key features of the local operating state using the self-attention mechanism of the converter model to obtain the state parameter association features of the cell; the key features of the local operating state and the state parameter association features are weighted and fused to obtain the comprehensive operating state features of the cell; and the comprehensive operating state features of the cell are used by a classifier to determine the fault category to obtain the operating state fault information.

[0046] Specifically, the intelligent diagnostic parameter model includes a CNN+Transformer hybrid model, which combines a convolutional neural network model and a transformer model. This hybrid model extracts multi-dimensional features and performs global correlation analysis on the pre-processed cell state parameters, resulting in a dynamic feature map of the cell's operating status. This map covers core information such as parameter fluctuation patterns under normal charging and discharging conditions, early characteristic signals of potential anomalies, and performance degradation trends under different operating conditions. In subsequent steps, this dynamic feature map will be matched and compared with a pre-set cell health status benchmark model and a fault feature database. The model's built-in classification decision module will then determine the status and classify faults, ultimately yielding the cell's specific operating status, such as normal operation, performance degradation, or decreased charging efficiency, as well as precise fault information, such as the risk of overcharging in localized cells, discharge faults caused by abnormally increased internal resistance, and safety hazards caused by temperature runaway. This provides direct data support for fault early warning and operation and maintenance decisions in energy storage power station cell systems.

[0047] The CNN+Transformer model was trained using two NVIDIA RTX 3090 GPUs to build a deep learning environment. The training loss function was MSELoss, and the optimizer was Adam adaptive moment estimation. The model converged after 500 iterations, and the optimal model parameter file was saved. During use, the acquired time series data were correlated. Voltage (V), current (I), temperature (T), and SOC values ​​were grouped in chronological order at 200 sampling points intervals. Each sample contained data on key parameters such as voltage, current, and temperature from 200 sampling points. The n sample sets were divided into training and test datasets at an 80%:20% ratio. One-dimensional CNN convolutional neural network feature information (voltage, current, and temperature) was used, with positional encoding embedded at the corresponding time series positions, and input into the Transformer model to capture relevant battery operating states and fault information.

[0048] In step S150, the results captured by the Transformer model library are stored in an internal database, which is also shared with the human-computer interaction interface. Running status and fault information are transmitted to a mobile device via a USB interface for real-time display, with a refresh time of 1 second. Figure 11As shown, the operational status fault information includes fault information, fault reasoning, component information, maintenance contact information, and handling methods. After the user plugs and unplugs the wiring harness of the short-board battery cell into the acquisition wiring harness, the system can automatically identify the location of the short-board battery cell based on the read battery cell status parameters, select the corresponding channel, calculate the current value that needs to be replenished based on the current value, and automatically start replenishment. When replenishment is completed, it automatically shuts down and prompts "Replenishment complete. Please plug and unplug the wiring harness back into the BMS acquisition unit. The system will re-detect."

[0049] In some embodiments, during the intelligent diagnosis and automatic power balancing process of the energy storage power station, the cell data acquisition unit is first connected to the battery system consisting of multiple PACKs (battery packs) and a high-voltage box through the acquisition harness to comprehensively collect the cell status parameters of each PACK and the operating data of the high-voltage box. The intelligent diagnostic and automatic balancing device for energy storage power stations integrates various functional circuits, such as the corresponding circuit of the cell data acquisition unit, the circuit of the channel selection unit, and the circuit of the replenishment power supply. The cell data acquisition unit acquires detailed data of the cells through interfaces such as IIC / SPI. Under the control of a 32-bit MCU and combined with the calculation results of the host computer, the channel selection circuit connects the short-board cells that need replenishment to the replenishment power supply harness circuit, thereby achieving precise replenishment of the cells to balance the power. At the same time, the cell data acquisition unit also uses a hybrid model based on CNN+Transformer to perform multi-dimensional feature extraction and global correlation analysis on the preprocessed cell state parameters to obtain a dynamic feature map of the cell operating status. This map is then matched with a preset benchmark model and fault database to complete the intelligent diagnosis of the cell system of the energy storage power station, identifying fault information such as overcharging, abnormal internal resistance, and temperature runaway, ultimately ensuring the stable and efficient operation of the energy storage power station system.

[0050] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0051] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0052] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0053] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0054] It should be understood that the data used in this way can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than those illustrated or described herein. Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or apparatus.

[0055] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0056] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0057] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0058] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0059] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0060] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A device for intelligent diagnosis and automatic balancing based on energy storage power stations, characterized in that, include: The system includes a first microcontroller unit, a battery cell data acquisition unit, a power supply, a channel selection unit, a CAN driver, and a USB interface. One end of the cell data acquisition unit, the power supply, and the channel selection unit are respectively communicatively connected to the first microcontroller unit; the other end of the power supply is communicatively connected to the channel selection unit; and the other ends of the cell data acquisition unit and the channel selection unit are communicatively connected to the power supply harness. One end of the CAN driver and one end of the USB interface are respectively connected to the first microcontroller unit, the other end of the CAN driver is connected to the high-voltage box debugging port, and the other end of the USB interface is connected to the mobile device.

2. The device for intelligent diagnosis and automatic balancing based on energy storage power stations according to claim 1, characterized in that, The battery cell data acquisition unit includes a CAN driver chip, an isolation module, and a protection module; The CAN driver chip is used to realize the CAN communication interaction between the battery cell data and the first microcontroller unit; The isolation module is a CAN transceiver isolator with isolation function. The isolation module is connected between the CAN transceiver chip and the protection module. The isolation module is used to achieve electrical isolation of communication signals. The protection module includes a transient suppression diode array and a common-mode inductor, and is used to protect CAN communication signals from overvoltage, overcurrent and common-mode interference.

3. The device for intelligent diagnosis and automatic balancing based on energy storage power stations according to claim 2, characterized in that, The battery cell data acquisition unit includes an analog front-end circuit; The analog front-end circuit uses a multi-channel sampling architecture, with each sampling channel equipped with filtering and voltage regulation components.

4. The device for intelligent diagnosis and automatic balancing based on energy storage power stations according to claim 1, characterized in that, The channel selection unit includes multiple sets of optocoupler relay modules and a second microcontroller unit. The optocoupler relay module is constructed using an optocoupler relay, and the optocoupler relay module is used to control the connection and disconnection between the battery cell and the charging circuit; The second microcontroller unit is connected to the optocoupler relay module via a GPIO interface. The DO output port of the second microcontroller unit outputs a corresponding high-level signal based on the cell status calculation result. The high-level signal is used to drive the optocoupler relay to operate.

5. The device for intelligent diagnosis and automatic balancing based on energy storage power stations according to claim 4, characterized in that, The optocoupler relay module adopts a parallel architecture of multiple optocoupler relays, with each group of optocoupler relays corresponding to the power supply channel control of one battery cell.

6. The device for intelligent diagnosis and automatic balancing based on energy storage power stations according to claim 1, characterized in that, The power supply includes an input rectifier circuit, an isolation transformer, a control chip, and an output regulation circuit; The input rectifier circuit rectifies the input voltage; The isolation transformer is used for electrical isolation between input and output; the control chip is used to control the working state of the switching power supply and adjust the output voltage and current; the output adjustment circuit can adjust the output current according to the data sent by the MCU.

7. The device for intelligent diagnosis and automatic balancing based on energy storage power stations according to claim 6, characterized in that, The input rectifier circuit is equipped with a filter capacitor and a rectifier diode; The isolation transformer is equipped with protection elements on its primary and secondary sides, and voltage and current sampling circuits are provided at its output terminals.

8. A method for intelligent diagnosis and automatic balancing based on energy storage power stations, characterized in that, The method includes the following steps: The device for intelligent diagnosis and automatic balancing based on an energy storage power station as described in any one of claims 1-7 is confirmed to be connected to and activated by the energy storage power station and the mobile device, respectively. The cell status parameters of the energy storage power station are obtained through the cell data acquisition unit. The acquired cell state parameters are preprocessed; The preprocessed cell status parameters are input into the intelligent diagnostic parameter model to obtain operational status fault information; The operational status fault information is transmitted to the mobile device for real-time display.

9. The intelligent diagnosis and automatic balancing method based on an energy storage power station according to claim 8, characterized in that, The process of inputting the preprocessed cell status parameters into the intelligent diagnostic parameter model to obtain operational status fault information includes the following steps: Local features of the preprocessed cell state parameters are extracted using a convolutional neural network model to obtain key features of the cell's local operating state. The key features of the extracted local operating state are modeled globally using the self-attention mechanism of the converter model to obtain the state parameter association features of the battery cell. The key features of the local operating state and the associated features of the state parameters are weighted and fused to obtain the comprehensive operating state features of the battery cell. The classifier determines the fault category of the comprehensive operating status characteristics of the battery cell to obtain operating status fault information.

10. The intelligent diagnosis and automatic balancing processing method based on energy storage power stations according to claim 8, characterized in that, The step of transmitting the operational status fault information to the mobile device for real-time display includes the following steps: The operating status fault information is transmitted to the mobile device for real-time display via the USB interface; The operational status fault information includes fault information, fault reasoning, component information, maintenance contact information, and handling methods.

Images