A multi-source data acquisition method and device applied to an energy storage battery PACK pack

Abstract

The application provides a multi-source data acquisition method and device applied to an energy storage battery PACK package, and relates to the field of battery management systems. The method comprises the following steps: acquiring physical signal parameter data of the energy storage battery PACK package, and classifying the physical signal parameter data according to different heterogeneous data interfaces corresponding to the physical signal parameter data; acquiring first data and second data in the classified physical signal parameter data; constructing system interaction characteristics between internal structure units of the energy storage battery PACK package through the first data; constructing external collaborative characteristics between the energy storage battery PACK package and external connection equipment through the second data; inputting the system interaction characteristics and the external collaborative characteristics into a multi-source feature analysis model, and outputting multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model. The application solves the problem that it is difficult to cope with the actual demand of multi-source information fusion and control closed-loop cooperation in a complex application scenario, thereby causing low acquisition accuracy of related parameter data of the energy storage battery PACK package.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of battery management systems, in particular to a multi-source data acquisition method and device applied to an energy storage battery PACK package. BACKGROUND

[0002] In recent years, with the increasing proportion of renewable energy and the increasing demand for flexible regulation of power systems, the intelligent sensing and dynamic response capability of energy storage battery PACK packages as the core energy unit in industrial and commercial energy storage, electric transportation and distributed energy systems has gradually become the focus of research and engineering implementation.

[0003] However, in the traditional technical solution, the data acquisition and state analysis of the energy storage battery PACK package are mostly based on single data stream for independent modeling, lacking the ability to jointly model the coupling relationship between internal structural units and the collaborative relationship between external control systems. That is, the traditional solution cannot fit the dynamic evolution relationship between the multi-physical domain parameters inside the energy storage battery PACK package and the control logic consistency mapping relationship between the energy storage battery PACK package and the external energy control system, so it is difficult to meet the actual needs of multi-source information fusion and control closed-loop collaboration in complex application scenarios, resulting in low accuracy of obtaining related parameter data of the energy storage battery PACK package.

[0004] Therefore, there is an urgent need for a multi-source data acquisition method and device applied to an energy storage battery PACK package. SUMMARY

[0005] The present application provides a multi-source data acquisition method and device applied to an energy storage battery PACK package, which solves the problem that the traditional data acquisition method is difficult to meet the actual needs of multi-source information fusion and control closed-loop collaboration in complex application scenarios, resulting in low accuracy of obtaining related parameter data of the energy storage battery PACK package.

[0006] In a first aspect of the present application, a multi-source data acquisition method applied to an energy storage battery PACK package is provided, the method comprising: acquiring physical signal parameter data of the energy storage battery PACK package, and classifying the physical signal parameter data according to different heterogeneous data interfaces corresponding to different physical signal parameter data; acquiring first data and second data in the classified physical signal parameter data, the first data being internal data in the energy storage battery PACK package, and the second data being external data of the energy storage battery PACK package; constructing system-to-system interaction features between internal structural units of the energy storage battery PACK package through the first data; constructing external collaborative features between the energy storage battery PACK package and external connected devices through the second data; inputting the system-to-system interaction features and the external collaborative features into a multi-source feature analysis model, and outputting multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model.

[0007] Optionally, the physical signal parameter data of the energy storage battery PACK package is acquired, and the physical signal parameter data is classified according to different heterogeneous data interfaces corresponding to different physical signal parameter data, specifically including: acquiring the physical signal parameter data of the energy storage battery PACK package, the physical signal parameter data including voltage data, temperature data and current data; classifying the physical signal parameter data according to different heterogeneous data interfaces corresponding to different physical signal parameter data, the heterogeneous data interfaces including an analog signal interface, a digital quantity acquisition interface and a pulse signal acquisition interface.

[0008] Optionally, the system interaction features between the internal structure units of the energy storage battery PACK package are constructed through the first data, specifically including: based on the cell monomer voltage data, the cell monomer temperature data and the cell module current data in the first data, the internal electrical state coupling relationship of the cell module is established, and the voltage consistency feature, the temperature balance feature and the current shunt feature are constructed according to the electrical state coupling relationship; based on the output power change rate and the power difference of the cell module, the virtual inductance parameter is dynamically adjusted to construct the adaptive adjustment feature between the virtual inductance and the power dynamic response; based on the module insulation state data in the first data and the electrical state coupling relationship, the insulation integrity correlation feature between modules is constructed; based on the cooling liquid flow rate data, the cooling liquid pressure data and the electrical state coupling relationship in the first data, the heat exchange coupling feature is constructed; the voltage consistency feature, the adaptive adjustment feature, the temperature balance feature, the current shunt feature, the insulation integrity correlation feature and the heat exchange coupling feature are taken as the system interaction features.

[0009] Optionally, based on the output power change rate and the power difference of the cell module, the virtual inductance parameter is dynamically adjusted to construct the adaptive adjustment feature between the virtual inductance and the power dynamic response, specifically including:

[0010]

[0011] Wherein, ΔL is the virtual inductance coarse adjustment increment, k1 is the power change rate adjustment coefficient, k2 is the power difference adjustment coefficient, is the output power change rate, (P ref -P) is the power difference between the power instruction and the actual output power;

[0012] L fine (t)=L fine (t-1)+α·ΔL;

[0013] Wherein, L fine (t) is the virtual inductance fine adjustment value of the current sampling period, L fine (t-1) is the virtual inductance fine adjustment value of the last sampling period, and α is the fine adjustment step length coefficient;

[0014] Lreturn = L init + β · (L fine (t) - L init );

[0015] wherein, L return is the virtual inductance after regression initial value, L init is the initial set value of the virtual inductance, and β is a regression adjustment coefficient;

[0016] L final = L base + ΔL + L fine ;

[0017] wherein, L base is the basic virtual inductance value, and L final is the virtual inductance parameter.

[0018] Optionally, the external coordination features between the energy storage battery PACK package and the external connection equipment are constructed through the second data, and specifically include: establishing an electric energy interaction relationship based on the charge and discharge power instruction data in the second data, and constructing a power adaptation feature according to the electric energy interaction relationship; establishing a power grid synchronization relationship based on the power grid connection state data and the high-voltage connection system bus voltage data in the second data, and constructing a grid consistency feature according to the power grid synchronization relationship; establishing a thermal management cooperation relationship based on the environmental temperature data, the cooling liquid flow rate data and the cooling liquid pressure data in the second data, and constructing a thermal load response feature according to the thermal management cooperation relationship; establishing a communication synchronization relationship based on the communication link state and the energy management platform control instruction data in the second data, and constructing an instruction interaction consistency feature according to the communication synchronization relationship; the power adaptation feature, the grid consistency feature, the thermal load response feature and the instruction interaction consistency feature are taken as the external coordination features.

[0019] Optionally, the inter-system interaction features and the external coordination features are input into a multi-source feature analysis model, and multi-source data corresponding to the energy storage battery PACK package is output based on the multi-source feature analysis model, and specifically includes: performing feature normalization processing on the inter-system interaction features and the external coordination features by the multi-source feature analysis model; based on the result of the feature normalization processing, performing multi-source feature fusion processing, and mapping multi-dimensional features representing physical states, control logic and cooperation relationships to a unified feature space; in the unified feature space, the trend of the features is modeled in time sequence by the multi-source feature analysis model; according to the multi-source feature fusion processing result and the time sequence modeling result, state classification and dynamic prediction reasoning are performed, and the multi-source data is output by the multi-source feature analysis model.

[0020] Optionally, after inputting the inter-system interaction feature and the external coordination feature into the multi-source feature analysis model and outputting the multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model, the method further comprises: performing multi-source data comprehensive analysis on the energy storage battery PACK package by a preset method according to the multi-source data, and the multi-source data comprehensive analysis includes health state analysis, residual service life prediction analysis, and charging and discharging strategy dynamic adjustment analysis.

[0021] In a second aspect of the present application, a multi-source data acquisition device applied to an energy storage battery PACK package is provided, the device comprising an acquisition module and a processing module, wherein,

[0022] The acquisition module is configured to acquire physical signal parameter data of the energy storage battery PACK package, and classify the physical signal parameter data according to different heterogeneous data interfaces corresponding to different physical signal parameter data; and acquire first data and second data in the classified physical signal parameter data, wherein the first data is internal data in the energy storage battery PACK package, and the second data is external data of the energy storage battery PACK package.

[0023] The processing module is configured to construct an inter-system interaction feature between internal structure units of the energy storage battery PACK package by using the first data; construct an external coordination feature between the energy storage battery PACK package and an external connection device by using the second data; input the inter-system interaction feature and the external coordination feature into a multi-source feature analysis model, and output multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model.

[0024] In a third aspect of the present application, an electronic device is provided, comprising a processor, a memory, a user interface and a network interface, the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to enable the electronic device to perform the method of any one of the above aspects.

[0025] In a fourth aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to perform the method of any one of the above aspects.

[0026] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0027] 1、Obtain the physical signal parameter data of the energy storage battery PACK package, and classify the physical signal parameter data according to the heterogeneous data interfaces corresponding to different physical signal parameter data; obtain first data and second data in the classified physical signal parameter data; construct the inter-system interaction characteristics between the internal structure units of the energy storage battery PACK package through the first data; construct the external collaboration characteristics between the energy storage battery PACK package and the external connection equipment through the second data; input the inter-system interaction characteristics and the external collaboration characteristics into the multi-source feature analysis model, and output the multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model, thereby realizing the structured acquisition, feature modeling and time sequence analysis of the multi-source heterogeneous data of the energy storage battery PACK package, and further systematically solving the problem of low parameter data acquisition accuracy caused by the difficulty of multi-source information fusion and control closed-loop collaboration in complex application scenarios in the traditional scheme.

[0028] 2、By classifying the physical signal parameter data according to the heterogeneous data interfaces corresponding to different physical signal parameter data, the structured management of the physical parameters of multiple types, multiple sources and multiple sampling characteristics in the energy storage battery PACK package can be realized, so that different physical quantities complete interface adaptation, channel identification and function differentiation at the collection layer, thereby effectively improving the analyzability and collection consistency of subsequent multi-source data fusion.

[0029] 3、The multi-source feature analysis model performs feature normalization processing on the inter-system interaction characteristics and the external collaboration characteristics; based on the results of the feature normalization processing, multi-source feature fusion processing is performed, and multi-dimensional features representing physical states, control logic and collaboration relationships are mapped to a unified feature space; in the unified feature space, the multi-source feature analysis model performs time sequence modeling on the feature change trend; according to the multi-source feature fusion processing results and the time sequence modeling results, state classification and dynamic prediction reasoning are performed, and the multi-source data is output through the multi-source feature analysis model, thereby realizing deep perception and structural reconstruction of the running state of the energy storage battery PACK package, so that the correlation between various physical quantities, the state evolution path and the response mechanism can be uniformly expressed and dynamically tracked, and the prediction accuracy of the system under high-frequency disturbance, control change and complex working conditions is significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 is a flowchart of a multi-source data acquisition method applied to an energy storage battery PACK package provided by an embodiment of the present application;

[0031] Figure 2 is a module schematic diagram of a multi-source data acquisition device applied to an energy storage battery PACK package provided by an embodiment of the present application;

[0032] Figure 3Fig. 1 is a structural schematic diagram of an electronic device provided by an embodiment of the present application.

[0033] Marker: 21, acquisition module; 22, processing module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0034] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in conjunction with the drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all.

[0035] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to be limiting to the present application. As used in the specification, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "and / or" used in the present application, means and includes any or all possible combinations of one or more listed items.

[0036] Hereinafter, the terms "first" and "second" are only for the purpose of description, and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0037] In order for those skilled in the art to better understand the technical solutions of the present application, the present application will be further described in conjunction with the drawings.

[0038] Please refer to Figure 1 Fig. 1 is a structural schematic diagram of an electronic device provided by an embodiment of the present application.

[0039] Step S101, acquiring physical signal parameter data of the energy storage battery PACK package, and classifying the physical signal parameter data according to different heterogeneous data interfaces corresponding to different physical signal parameter data.

[0040] Specifically, in various practical application scenarios, the acquisition requirements and classification methods of physical signal parameter data are significantly different, and need to be adaptively designed according to the running targets, perception depth and collection response speed in different working conditions. For example, in the conventional industrial and commercial energy storage running scene, the energy storage battery PACK package is usually in a long-time steady-state running state in the application of day-night load adjustment, peak clipping and valley filling, and photovoltaic storage cooperation. The data collection target focuses on power balance, cell consistency and thermal management stability. In such a scenario, the low-frequency variation quantities such as cell monomer voltage, cell module temperature, current, inter-cell voltage difference and cooling liquid temperature difference are preferentially collected. The classification method is divided according to the physical type, such as analog signal type (voltage, current, temperature), switching value type (relay state, contactor position) and system instruction type (EMS issued control parameters). The heterogeneous interfaces mainly include analog quantity ADC interface, digital quantity GPIO interface and CAN communication protocol interface; in the electric vehicle high-rate charging scene, the PACK package needs to support short-time high-power fast response. At this time, the system pays attention to the high-frequency dynamic signal change trend and the rapid identification of the state close to the limit working condition boundary. In such a scenario, key parameters such as dynamic current, voltage fluctuation rate, voltage equalization deviation rate, wire heating rate and thermal management response delay time need to be collected under high sampling frequency. When classifying, the classification is divided according to the response characteristics, including high-speed real-time signal type (such as voltage peak, current surge), thermal delay response type (such as temperature rise rate, cooling rate) and dynamic electrical load type. The heterogeneous interfaces mainly include high-speed sampling ADC, FPGA bus interface, SPI / I2C type on-chip high-speed collection interface; in the remote operation and maintenance and fault diagnosis scene of the energy storage system, the data collection target is biased towards fault precursor feature extraction and historical trajectory reconstruction, and attention is paid to the structure, time sequence integrity and remote synchronization capability of the data. In such a scenario, the collection content covers the timestamp sequence of various running data (such as temperature curve, pressure difference evolution trajectory, current deviation trend), alarm triggering event stream, communication status code, etc. The classification is divided according to the data use and interaction mode, including historical state type (for trajectory playback), abnormal event type (for fault positioning), remote transmission type (for cloud analysis), and the interfaces mainly include Ethernet interface, 4G / 5G Internet of Things module, Modbus-TCP or MQTT protocol interface of edge gateway switching.

[0041] In a possible implementation, the step S101 further includes: acquiring physical signal parameter data of the energy storage battery PACK package, the physical signal parameter data including voltage data, temperature data and current data; and classifying the physical signal parameter data according to heterogeneous data interfaces corresponding to different physical signal parameter data, the heterogeneous data interfaces including an analog signal interface, a digital quantity collection interface and a pulse signal collection interface.

[0042] Specifically, the physical signal parameter data includes voltage data, temperature data, and current data, wherein the voltage data includes cell monomer voltage, module end voltage, and busbar total voltage, which are used to reflect the potential state of each level of electrical unit in the energy storage battery PACK package, have a large change range and high precision requirements, and are usually sampled through a high-resolution ADC module connected through an analog signal interface; the temperature data includes cell temperature, module shell temperature, cooling liquid temperature, and environmental temperature, which are used to monitor thermal imbalance, overheating risk, and thermal management response effect, and are also sampled through an analog signal interface, and some high-reliability systems can be configured with a thermocouple or thermistor network for parallel collection; the current data includes charging and discharging main loop current, module current, and balancing current, wherein the main loop current and the module current usually use a Hall sensor, a shunt, etc. to form a continuous analog signal, which is input through an analog interface; and the balancing current control or relay state detection usually acquires a switching state signal through a digital quantity collection interface, which is used to judge whether the balancing circuit or the protection circuit is closed.

[0043] In addition, for the pulse signal collection interface, it is mainly used to acquire event data or periodic count information triggered by external devices or battery management systems, such as frequency signals output by a cooling liquid flow rate sensor, pulse type pressure sensor count signals, or module wake-up signals, etc. Such signals have clear rising edge or falling edge trigger characteristics, and need to be identified by a pulse capture module or an FPGA interface.

[0044] Through the mapping relationship of the above physical quantities and interface types, the physical signal parameter data can be classified into: one type is continuous analog input data, which is suitable for acquiring continuous state quantities such as voltage, temperature, and large current signals; one type is discrete digital signal, which is suitable for system state detection and action confirmation; another type is high-precision pulse signal, which is suitable for timing and capturing of periodic dynamic data or edge events. Each type of signal is bound to the corresponding data interface type, and is sampled and data collected synchronously through a unified data collection framework, thereby constructing a collection system structure suitable for multi-dimensional sensing of the running state of the energy storage battery PACK package.

[0045] In step S102, first data and second data in the classified physical signal parameter data are acquired.

[0046] Specifically, the first data is internal data in the energy storage battery PACK package, which refers to original operating parameters generated or directly related by each internal structural unit of the energy storage battery PACK package, reflecting the state evolution process of the cell module, battery management system, thermal management system, and high and low voltage connection system; the second data is external data of the energy storage battery PACK package, which refers to control instructions, environmental feedback signals or interface state information transmitted by external devices or upper control systems connected to the PACK package during the operation of the PACK package, reflecting the cooperative relationship and response mechanism between the PACK package and the external operating environment. For example, in a typical photovoltaic storage and charging integrated scene, the first data includes but is not limited to cell voltage, cell temperature, cell module current, module insulation state, equalization circuit operating state, cooling liquid flow rate, pressure, and main loop current, etc. These data are collected by voltage acquisition modules, thermal elements, Hall current sensors, pressure transmitters, insulation detection units, etc. deployed inside the PACK package, reflecting the health status, thermal stability and load response capability of the energy storage battery PACK package; and the second data includes the charge and discharge power instructions issued by the external EMS system, remote switching control commands, grid connection state, power quality monitoring parameters, environmental temperature and humidity, external cooling system working state and communication link feedback state, etc. These data are injected into the PACK package control system through CAN communication, 485 protocol, Modbus TCP / IP interface or IoT remote channel, etc. for guiding or regulating the internal operation behavior.

[0047] Further, to ensure that the functional roles of data in the system can be accurately identified and support modeling processing, the first data and the second data will be respectively bound to corresponding structure source labels and control attribution labels in the system, for example, voltage, current, temperature, etc. are labeled as "from module A / B / C" "associated with electrical branch X" etc., and external control instructions are labeled as "EMS source instruction" "environmental interface feedback" etc. In this way, the data source attributes, action links and logical directions are clearly defined, providing a basis for subsequent system internal and external coupling modeling and multi-source analysis.

[0048] Step S103, constructing the inter-system interaction characteristics between the internal structural units of the energy storage battery PACK package through the first data.

[0049] Specifically, based on the cell voltage, temperature, current, insulation state and thermal management parameters in the first data, the operating correlation between each structural unit (such as cell module, battery management system, high voltage connection unit, thermal management subsystem) in the energy storage battery PACK package is identified, and the feature information describing the physical coupling, control linkage and function feedback between each structural unit is extracted by analyzing the change trend, response time sequence and state dependence between different physical quantities.

[0050] In a possible implementation, step S103 further includes: based on the cell monomer voltage data, the cell monomer temperature data, and the cell module current data in the first data, establishing an electrical state coupling relationship inside the cell module, and constructing a voltage consistency feature, a temperature balance feature, and a current shunt feature according to the electrical state coupling relationship; based on the output power change rate and the power difference of the cell module, dynamically adjusting the virtual inductance parameter to construct an adaptive adjustment feature between the virtual inductance and the power dynamic response; based on the module insulation state data in the first data and the electrical state coupling relationship, constructing an insulation integrity correlation feature between modules; based on the cooling liquid flow rate data, the cooling liquid pressure data, and the electrical state coupling relationship in the first data, constructing a heat exchange coupling feature; and taking the voltage consistency feature, the adaptive adjustment feature, the temperature balance feature, the current shunt feature, the insulation integrity correlation feature, and the heat exchange coupling feature as the inter-system interaction feature.

[0051] Specifically, inside the energy storage battery PACK package, the cell monomer voltage, temperature, and module current form a typical thermal-electric coupling relationship at the physical level. By statistically analyzing the voltage data of all cells in each module at the same time, the voltage range, standard deviation, or maximum deviation can be calculated to quantify the voltage consistency of the cells in the module, thereby forming a voltage consistency feature, which can be used to identify problems such as single cell performance degradation, uneven charging and discharging, or equalization control failure. At the same time, by comparing the uniformity of the spatial distribution of the cell temperature inside the module and its dynamic change gradient, a temperature balance feature can be extracted to reflect the temperature control effect and thermal field stability of the thermal management in the single module dimension. In addition, by combining the total current of the module and the estimated current shared by each cell, the load distribution ratio of each branch can be derived through the series-parallel topology structure to extract a current shunt feature, which is used to reflect the balance degree of the load distribution between the cells, and further identify potential problems such as connection impedance difference and cell internal resistance deviation.

[0052] During the load disturbance, control strategy switching, or external system response process of the cell module, the output power often suddenly changes or the change trend is discontinuous. By calculating the change rate of the module output power in a unit of time and the difference between the current actual output power and the target reference power, the control amount of the corresponding virtual inductance can be dynamically adjusted. The specific calculation method is as follows:

[0053]

[0054] where ΔL is the virtual inductance coarse adjustment increment, k1 is the power change rate adjustment coefficient, k2 is the power difference adjustment coefficient, is the output power change rate, (P ref -P) is the power difference between the power instruction and the actual output power.

[0055] L fine(t) = L fine (t-1) + a*AL

[0056] wherein, L fine (t) is the virtual inductance fine-tuning value of the current sampling period, L fine (t-1) is the virtual inductance fine-tuning value of the last sampling period, and a is a fine-tuning step coefficient.

[0057] L return = L init + b*(L fine (t) - L init );

[0058] wherein, L return is the virtual inductance after regression initial value, L init is the initial virtual inductance setting value, and b is a regression adjustment coefficient.

[0059] L final = L base + AL + L fine ;

[0060] wherein, L base is the basic virtual inductance value, and L final is the virtual inductance parameter. The change of the virtual inductance affects the voltage and current regulation rate of the module and the amplitude stability, so a power feedback regulation formula is introduced, the power difference and the change rate are weighted and superimposed through a proportional coefficient to generate an inductance correction amount, and the continuity and long-term stability are controlled by combining the fine-tuning and regression mechanism. Finally, the adaptive adjustment characteristics constructed not only reflect the response ability of the module to the dynamic change of the load, but also embody the flexible adjustment performance of the control strategy, which has a significant influence on the steady-state recovery speed and control accuracy after power disturbance

[0061] In a multi-module high-voltage system, the insulation resistance and leakage current state between modules directly affect the safety of system operation. By collecting the insulation state value (such as insulation resistance value, insulation alarm state bit) of each module relative to the shell or negative bus, and combining the module voltage, current and thermal state, the insulation stability evolution law in the electrical load change process is analyzed. For example, if the insulation resistance of a module decreases significantly at high temperature or high current output, it indicates that the module has a trend of electric field stress concentration or material degradation. By comparing the insulation state curves of multiple modules with their electrical state responses, the insulation integrity similarity, synergy and relative offset between modules are constructed, and finally the insulation integrity correlation features are extracted to reflect the insulation balance and local insulation risk points of the system at different operating stages.

[0062] The thermal management system realizes the rapid transfer and balance of the module thermal load by adjusting the flow rate and pressure of the cooling liquid. In this step, first, the time series data of the flow rate and pressure are obtained through the cooling liquid sensor, and the dynamic model between the heat power generation and the heat transfer system response is established by combining the module temperature gradient, the cell power consumption and the current data. By analyzing the flow rate change trend corresponding to the unit temperature rise, the change range of the heat exchange efficiency under different pressure conditions, the matching degree between the dynamic response capability of the thermal management system and the actual temperature control capability is identified. Further, by comparing the hysteresis, linearity and saturation characteristics of the module thermal load change and the cooling liquid flow adjustment, the heat exchange coupling characteristics can be constructed, which are used to represent the accuracy, adjustment boundary and mismatch risk of the thermal management response, and provide input basis for thermal runaway risk prediction and liquid cooling strategy optimization.

[0063] In step S104, an external coordination feature between the energy storage battery PACK package and the external connection device is constructed through the second data.

[0064] Specifically, the interaction law between the energy storage battery PACK package and the external system during operation is identified, the control instruction, the communication state, the power grid information and the environmental condition reflected in the second data are analyzed, the linkage relationship between the external energy system, the power interface, the communication link and the thermal management unit and the PACK package is established, the key feature parameters reflecting the coordinated control, energy consistency and communication synchronization are extracted, and the data expression form representing the external coordination capability is taken as the data expression form.

[0065] In one possible implementation, step S104 further includes: establishing an electric energy interaction relationship based on the charge and discharge power instruction data in the second data, and constructing a power adaptation feature according to the electric energy interaction relationship; establishing a power grid synchronization relationship based on the power grid connection state data and the high-voltage connection system bus voltage data in the second data, and constructing a grid consistency feature according to the power grid synchronization relationship; establishing a thermal management cooperation relationship based on the environmental temperature data, the cooling liquid flow rate data and the cooling liquid pressure data in the second data, and constructing a thermal load response feature according to the thermal management cooperation relationship; establishing a communication synchronization relationship based on the communication link state and the energy management platform control instruction data in the second data, and constructing an instruction interaction consistency feature according to the communication synchronization relationship; taking the power adaptation feature, the grid consistency feature, the thermal load response feature and the instruction interaction consistency feature as the external coordination feature.

[0066] Specifically, by acquiring the charge-discharge power instruction issued by the energy management system (EMS) or the charging pile controller, and comparing and analyzing it with the actual output power or module current data of the PACK package, it is evaluated whether the system can quickly, accurately and stably respond to the control target. If the deviation between the instruction power and the output power is small and the adjustment rate matches, it means that the energy interaction mechanism is good. The extracted power adaptation features include response delay time, power tracking error, adjustment slope, etc., to reflect the compliance and precision control capability of the PACK package to external power scheduling.

[0067] The grid connection state represents whether the PACK package is in grid-connected or island operation state, and the high-voltage connection system bus voltage reflects the actual voltage amplitude and frequency of the grid-connected interface. By analyzing the state evolution during grid switching, disturbance or recovery, the consistency between the grid-connected voltage fluctuation and the control instruction can be identified, and the grid-connected consistency feature can be constructed to judge the synchronization control capability and voltage coordination performance of the energy storage system under grid-side dynamic disturbance, and to improve the grid-connected stability and compatibility.

[0068] By analyzing the correspondence between external environmental temperature changes and cooling system parameters, it is determined whether the external thermal management unit (such as a cooling pump, cooling plate, heat exchanger) can adjust the operating state in a timely manner according to the external thermal load. If the system can quickly increase the flow rate or pressure to maintain the module temperature stable under high environmental temperature, it means that the thermal coordination mechanism is effective. The thermal load response features include cooling response time, thermal conduction lag rate, adjustment range, etc., reflecting the dynamic coordination capability between the system and the external temperature control resources.

[0069] The time delay, consistency and error rate between the control signal and the state feedback are evaluated, and the instruction interaction consistency feature is extracted by cross analyzing the link state (such as signal strength, connection stability, transmission period) and the instruction transmission state (such as control instruction issuing frequency, response confirmation frame reception rate), which is used to evaluate the stability, communication timeliness and anti-interference capability of the control closed loop between the PACK package and the upper management system, and is a key supporting index for realizing remote scheduling and distributed control.

[0070] In step S105, the inter-system interaction features and the external coordination features are input into a multi-source feature analysis model, and multi-source data corresponding to the energy storage battery PACK package is output based on the multi-source feature analysis model.

[0071] Specifically, by constructing a unified feature processing framework, the internal structure response features and external coordination interaction features of the energy storage battery PACK package extracted in the previous steps are normalized, fused, modeled and dynamically evolved, so that the multi-dimensional heterogeneous data is structure-consistent and time-series logic-reconstructed in the unified model. Finally, structured, multi-dimensional and time-series related multi-source data is output, which can be used for subsequent state estimation, prediction reasoning and energy optimization decision-making.

[0072] In a possible implementation, step S105 further includes: performing feature normalization processing on the inter-system interaction features and the external coordination features by the multi-source feature analysis model; performing multi-source feature fusion processing based on the results of the feature normalization processing, and mapping the multi-dimensional features representing the physical state, the control logic, and the coordination relationship to a unified feature space; in the unified feature space, performing time series modeling on the feature change trend by the multi-source feature analysis model; and performing state classification and dynamic prediction reasoning according to the results of the multi-source feature fusion processing and the time series modeling results, and outputting the multi-source data by the multi-source feature analysis model.

[0073] Specifically, for the inter-system interaction features (such as voltage consistency features, temperature balancing features, virtual inductance adjustment features, etc.) constructed in step S103 and the external coordination features (such as power adaptation features, grid-connected consistency features, thermal load response features, and instruction interaction consistency features) constructed in step S104, since their data dimensions, numerical distributions, and sampling frequencies are different, normalization processing is required. The normalization processing includes using methods such as range scaling, Z-score standardization, or wavelet decomposition boundary adjustment on each feature value to map all features to a comparable numerical space, and eliminate the inconsistency of physical quantities at the numerical level. After the normalization processing is completed, a feature fusion algorithm (such as feature embedding mapping, coordination feature tensor construction, or multi-dimensional aggregation based on an attention mechanism) is used to jointly map the multi-dimensional features representing electrical state, thermal management response, communication interaction, and control synchronization to a unified feature space. This space serves as the basic structure for system state description, maintaining the functional independence of each feature in the spatial dimension, and having the ability to model dynamic interactions between features in the time dimension. Under the unified feature space, a time series modeling mechanism is introduced to model the trend of feature evolution over time. This modeling can be implemented based on a recurrent neural network (RNN), a gated recurrent unit (GRU), a long short-term memory network (LSTM), or an attention-based time graph neural network, to extract the response lag, prediction trajectory, and joint evolution path of each feature at different operating stages. For example, after a certain load disturbance, it is analyzed whether the temperature balancing degradation and the communication lag constitute a potential safety risk linkage. In combination with the feature fusion results and the time series modeling output, further system state classification and prediction tasks are performed. State classification is used to identify the current operating interval (such as normal, sub-health, fault warning, abnormal offline, etc.) of the energy storage battery PACK package, while dynamic prediction reasoning is directed to target parameters such as output power, temperature distribution, and voltage balancing, to construct a prediction trajectory in a future time window and provide a quantitative inference of future operating trends.

[0074] In a possible implementation, step S105 further includes: performing multi-source data comprehensive analysis on the energy storage battery PACK package by a preset method according to the multi-source data, and the multi-source data comprehensive analysis includes health state analysis, residual service life prediction analysis, and charging and discharging strategy dynamic adjustment analysis.

[0075] Specifically, the health state analysis includes: identifying performance stability of each module inside the energy storage battery PACK package at different operating stages based on voltage consistency features, temperature balancing features, and current shunt features in the multi-source data, quantifying health evaluation scores of each module in combination with historical operating trajectories and current state offset amounts, and constructing a module health level mapping matrix for identifying local abnormal units, equalization failure trends, and early signs of thermal runaway.

[0076] The residual service life prediction analysis includes: constructing a degradation path evolution model by a life degradation modeling algorithm based on dynamic features such as cell temperature rise rate, internal resistance drift trend, equalization load change, and cooling response lag in the multi-source data, estimating future capacity retention rate and performance degradation rate of the cell module in combination with historical degradation curves and current parameter incremental changes, outputting residual service cycle prediction values and failure confidence intervals corresponding to each module, and realizing individualized modeling and system-level aggregated evaluation of life prediction.

[0077] The charging and discharging strategy dynamic adjustment analysis includes: dynamically calculating optimal charging and discharging power distribution, switching time, and load response path by a control optimization algorithm in combination with current load conditions, electricity price signals, power grid states, and operating history based on power adaptation features, grid-connected consistency features, thermal load response features, and control instruction interaction consistency features, and adjusting state-of-charge management strategies, equalization strategies, and power buffer strategies in real time to realize adaptive charging and discharging scheduling control under the dual goals of economy and life.

[0078] By adopting the above method, the physical signal parameter data of the energy storage battery PACK package is acquired, and the physical signal parameter data is classified according to different heterogeneous data interfaces corresponding to different physical signal parameter data; first data and second data in the classified physical signal parameter data are acquired; system-to-system interaction features between internal structure units of the energy storage battery PACK package are constructed through the first data; external coordination features between the energy storage battery PACK package and external connection devices are constructed through the second data; the system-to-system interaction features and the external coordination features are input into a multi-source feature analysis model, and multi-source data corresponding to the energy storage battery PACK package is output based on the multi-source feature analysis model, so that structured acquisition, feature modeling, and time sequence analysis of multi-source heterogeneous data of the energy storage battery PACK package are realized, and the problem of low parameter data acquisition accuracy caused by the fact that the traditional scheme is difficult to cope with multi-source information fusion and control closed-loop coordination in complex application scenarios is systematically solved.

[0079] Referring to Figure 2 Fig. 1 shows a module schematic diagram of a multi-source data acquisition device applied to an energy storage battery PACK package according to an embodiment of the present application, the device comprising an acquisition module 21 and a processing module 22, wherein

[0080] The acquisition module 21 is configured to acquire physical signal parameter data of the energy storage battery PACK package, and classify the physical signal parameter data according to different heterogeneous data interfaces corresponding to different physical signal parameter data; acquire first data and second data in the classified physical signal parameter data, the first data being internal data in the energy storage battery PACK package, and the second data being external data of the energy storage battery PACK package.

[0081] The processing module 22 is configured to construct system interaction features between internal structure units of the energy storage battery PACK package through the first data, construct external collaborative features between the energy storage battery PACK package and external connection equipment through the second data, input the system interaction features and the external collaborative features into a multi-source feature analysis model, and output multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model.

[0082] In a possible implementation, the acquisition module 21 is configured to acquire physical signal parameter data of the energy storage battery PACK package, and classify the physical signal parameter data according to different heterogeneous data interfaces corresponding to different physical signal parameter data, specifically comprising: acquiring physical signal parameter data of the energy storage battery PACK package, the physical signal parameter data comprising voltage data, temperature data and current data; and classifying the physical signal parameter data according to different heterogeneous data interfaces corresponding to different physical signal parameter data, the heterogeneous data interfaces comprising an analog signal interface, a digital quantity acquisition interface and a pulse signal acquisition interface.

[0083] In one possible implementation, the processing module 22 is used to construct inter-system interaction characteristics between internal structural units of the energy storage battery PACK using the first data. Specifically, this includes: establishing an internal electrical state coupling relationship of the cell module based on the cell individual voltage data, cell individual temperature data, and cell module current data in the first data, and constructing voltage consistency characteristics, temperature equalization characteristics, and current shunting characteristics based on the electrical state coupling relationship; dynamically adjusting virtual inductance parameters based on the output power change rate and power difference of the cell module to construct an adaptive adjustment characteristic between virtual inductance and power dynamic response; constructing inter-module insulation integrity correlation characteristics based on the module insulation state data and electrical state coupling relationship in the first data; constructing heat exchange coupling characteristics based on coolant flow rate data, coolant pressure data, and electrical state coupling relationship in the first data; and using the voltage consistency characteristics, adaptive adjustment characteristics, temperature equalization characteristics, current shunting characteristics, insulation integrity correlation characteristics, and heat exchange coupling characteristics as inter-system interaction characteristics.

[0084] In one possible implementation, the processing module 22 is used to dynamically adjust the virtual inductance parameters based on the output power change rate and power difference of the battery cell module, so as to construct an adaptive adjustment feature between the virtual inductance and the dynamic power response, specifically including:

[0085]

[0086] Where ΔL is the coarse adjustment increment of the virtual inductance, k1 is the power change rate adjustment coefficient, and k2 is the power difference adjustment coefficient. The output power change rate, (P) ref -P) represents the power difference between the power command and the actual output power;

[0087] L fine (t)=L fine (t-1)+α·ΔL;

[0088] Among them, L fine (t) represents the virtual inductance fine-tuning value for the current sampling period, L fine (t-1) is the virtual inductance fine-tuning value of the previous sampling period, and α is the fine-tuning step size coefficient;

[0089] L return =L init +β·(L fine (t)-L init );

[0090] Among them, L return For the virtual inductance after reverting to the initial value, L init β is the initial setting value for the virtual inductance, and β is the regression adjustment coefficient;

[0091] L final = L base + ΔL + L fine ;

[0092] wherein, L base is a basic virtual inductance value, L final is the virtual inductance parameter.

[0093] In a possible implementation, the processing module 22 is configured to construct, by using the second data, external coordination features between the energy storage battery PACK package and external connection devices, specifically including: establishing an electric energy interaction relationship based on the charge and discharge power instruction data in the second data, and constructing a power adaptation feature according to the electric energy interaction relationship; establishing a power grid synchronization relationship based on the power grid connection state data and the high-voltage connection system bus voltage data in the second data, and constructing a grid consistency feature according to the power grid synchronization relationship; establishing a thermal management cooperation relationship based on the environmental temperature data, the cooling liquid flow rate data and the cooling liquid pressure data in the second data, and constructing a thermal load response feature according to the thermal management cooperation relationship; establishing a communication synchronization relationship based on the communication link state and the energy management platform control instruction data in the second data, and constructing an instruction interaction consistency feature according to the communication synchronization relationship; and taking the power adaptation feature, the grid consistency feature, the thermal load response feature and the instruction interaction consistency feature as the external coordination features.

[0094] In a possible implementation, the processing module 22 is configured to input the inter-system interaction features and the external coordination features into a multi-source feature analysis model, and output multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model, specifically including: performing feature normalization processing on the inter-system interaction features and the external coordination features by using the multi-source feature analysis model; performing multi-source feature fusion processing based on a result of the feature normalization processing, and mapping multi-dimensional features representing physical states, control logics and cooperation relationships to a unified feature space; performing time series modeling on feature change trends in the unified feature space by using the multi-source feature analysis model; performing state classification and dynamic prediction reasoning according to a result of the multi-source feature fusion processing and a result of the time series modeling, and outputting the multi-source data by using the multi-source feature analysis model.

[0095] In a possible implementation, after the processing module 22 inputs the inter-system interaction features and the external coordination features into the multi-source feature analysis model, and outputs the multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model, the method further includes: performing multi-source data comprehensive analysis on the energy storage battery PACK package by using a preset method according to the multi-source data, and the multi-source data comprehensive analysis includes health state analysis, remaining useful life prediction analysis and charge and discharge strategy dynamic adjustment analysis.

[0096] It should be noted that the apparatus provided in the above examples is only used as an example for the division of the above functional modules in realizing the functions thereof, and in actual applications, the above functions can be completed by different functional modules according to the needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the apparatus and method embodiments provided in the above examples belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0097] The present application also provides an electronic device. Referring to Figure 3 , Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. The electronic device can include at least one processor 301, at least one communication bus 302, a user interface 303, at least one network interface 304, and a memory 305.

[0098] The communication bus 302 is used to realize the connection and communication between the components.

[0099] The user interface 303 can include a display screen (Display), a camera (Camera), and optionally a standard wired interface, a wireless interface.

[0100] The network interface 304 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0101] The processor 301 can include one or more processing cores. The processor 301 connects various parts within the server through various interfaces and lines, performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Alternatively, the processor 301 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 301 can integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes operating systems, user interfaces, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be realized by a separate chip.

[0102] The memory 305 can include a random access memory (RAM) and can also include a read-only memory (ROM). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 305 can also be at least one storage device located away from the aforementioned processor 301. Referring to Figure 3 The memory 305 as a computer storage medium can include an operating system, a network communication module, a user interface module, and a multi-source data acquisition application applied to the energy storage battery PACK package.

[0103] In Figure 3In the electronic device shown, the user interface 303 is mainly used to provide an interface for the user to input, and obtain data input by the user; and the processor 301 can be used to call the multi-source data collection application stored in the memory 305 and applied to the energy storage battery PACK package, and when executed by one or more processors 301, the electronic device is caused to perform the method described in one or more of the above embodiments. It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0104] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device is caused to perform the method described in one or more of the above embodiments.

[0105] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0106] In the several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other manners. For example, the division of the units is merely a logical function division, and there can be another division manner in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical or other forms.

[0107] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0108] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of software functional units.

[0109] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned memory includes: a U disk, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0110] The above is only exemplary embodiments of the present application, and cannot limit the scope of the present application. That is, any equivalent changes and modifications made in accordance with the teachings of the present application are still within the scope of the present application.

[0111] The present application is intended to cover any variations, uses or adaptive changes of the present application, which follow the general principles of the present application and include common knowledge or conventional technical means in the technical field not disclosed in the present application.

Claims

1. A multi-source data acquisition method applied to an energy storage battery PACK package, characterized in that, The method comprises: acquiring physical signal parameter data of an energy storage battery PACK package, and classifying the physical signal parameter data according to different heterogeneous data interfaces corresponding to the physical signal parameter data; acquiring first data and second data in the classified physical signal parameter data, the first data being internal data in the energy storage battery PACK package, and the second data being external data of the energy storage battery PACK package; constructing, through the first data, system interaction features between internal structure units of the energy storage battery PACK package, specifically comprising: based on cell monomer voltage data, cell monomer temperature data and cell module current data in the first data, establishing an electrical state coupling relationship in a cell module, and constructing voltage consistency features, temperature balancing features and current shunt features according to the electrical state coupling relationship; based on the output power change rate and the power difference of the cell module, dynamically adjusting the virtual inductance parameter to construct an adaptive adjustment feature between the virtual inductance and the power dynamic response; based on the module insulation state data in the first data and the electrical state coupling relationship, constructing an insulation integrity correlation feature between modules; based on the cooling liquid flow rate data, the cooling liquid pressure data in the first data and the electrical state coupling relationship, constructing a heat exchange coupling feature; the voltage consistency features, the adaptive adjustment features, the temperature balancing features, the current shunt features, the insulation integrity correlation features and the heat exchange coupling features are taken as the system interaction features; the adaptive adjustment feature between the virtual inductance and the power dynamic response is constructed by dynamically adjusting the virtual inductance parameter based on the output power change rate and the power difference of the cell module, specifically comprising: ； wherein, is a virtual inductance coarse adjustment increment, is a power variation rate adjustment coefficient, is a power difference adjustment coefficient, is the output power variation rate, is the power difference between the power command and the actual output power; ； wherein, is a virtual inductance fine tuning value for the current sampling period, is the virtual inductance fine tuning value for the previous sampling period, is a fine tuning step size coefficient; ； wherein, Lvirt is the virtual inductance after regression, L0 is the initial value of the virtual inductance, K is the regression adjustment coefficient; ； wherein, is a base virtual inductance value, is the virtual inductance parameter; constructing, through the second data, external coordination features between the energy storage battery PACK package and external connection equipment; inputting the system interaction features and the external coordination features into a multi-source feature analysis model, and outputting multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model; inputting the system interaction features and the external coordination features into a multi-source feature analysis model, and outputting multi-source data corresponding to the energy storage battery PACK package based on the multi-source feature analysis model, specifically comprising: performing feature normalization processing on the system interaction features and the external coordination features through the multi-source feature analysis model; based on the result of the feature normalization processing, performing multi-source feature fusion processing, and mapping multi-dimensional features representing physical states, control logic and cooperation relationships to a unified feature space; in the unified feature space, modeling the feature change trend through the multi-source feature analysis model; according to the multi-source feature fusion processing result and the time series modeling result, performing state classification and dynamic prediction reasoning, and outputting the multi-source data through the multi-source feature analysis model.

2. The method of claim 1, wherein, The physical signal parameter data of the energy storage battery PACK package is acquired, and the physical signal parameter data is classified according to different heterogeneous data interfaces corresponding to the physical signal parameter data, and specifically includes: Acquiring the physical signal parameter data of the energy storage battery PACK package, the physical signal parameter data including voltage data, temperature data and current data; Classifying the physical signal parameter data according to different heterogeneous data interfaces corresponding to the physical signal parameter data, the heterogeneous data interfaces including analog signal interfaces, digital quantity acquisition interfaces and pulse signal acquisition interfaces.

3. The method of claim 1, wherein, The external collaborative features between the energy storage battery PACK package and external connection equipment are constructed through the second data, and specifically includes: Based on the charge-discharge power instruction data in the second data, an electric energy interaction relationship is established, and a power adaptation feature is constructed according to the electric energy interaction relationship; Based on the grid connection state data and high-voltage connection system busbar voltage data in the second data, a grid synchronization relationship is established, and a grid consistency feature is constructed according to the grid synchronization relationship; Based on the environmental temperature data, cooling liquid flow rate data and cooling liquid pressure data in the second data, a thermal management collaboration relationship is established, and a thermal load response feature is constructed according to the thermal management collaboration relationship; Based on the communication link state and energy management platform control instruction data in the second data, a communication synchronization relationship is established, and an instruction interaction consistency feature is constructed according to the communication synchronization relationship; The power adaptation feature, the grid consistency feature, the thermal load response feature and the instruction interaction consistency feature are taken as the external collaborative features.

4. The method of claim 1, wherein, After the system interaction features and the external collaborative features are input into the multi-source feature analysis model, and the multi-source data corresponding to the energy storage battery PACK package is output based on the multi-source feature analysis model, the method further includes: According to the multi-source data, the energy storage battery PACK package is subjected to multi-source data comprehensive analysis through a preset method, the multi-source data comprehensive analysis including health state analysis, remaining useful life prediction analysis and charge-discharge strategy dynamic adjustment analysis.

5. A multi-source data acquisition device applied to an energy storage battery PACK package, characterized in that, The device includes an acquisition module and a processing module, wherein, The acquisition module is used for acquiring the physical signal parameter data of the energy storage battery PACK package, and classifying the physical signal parameter data according to different heterogeneous data interfaces corresponding to the physical signal parameter data; acquiring first data and second data in the classified physical signal parameter data, the first data being internal data in the energy storage battery PACK package, and the second data being external data of the energy storage battery PACK package; The processing module is configured to construct, by using the first data, system interaction features between internal structure units of the energy storage battery PACK package, specifically including: establishing an electrical state coupling relationship of a battery module based on battery monomer voltage data, battery monomer temperature data, and battery module current data in the first data, and constructing voltage consistency features, temperature balancing features, and current shunt features according to the electrical state coupling relationship; dynamically adjusting a virtual inductance parameter based on an output power change rate and a power difference of the battery module, to construct an adaptive adjustment feature between the virtual inductance and a power dynamic response; constructing a module insulation integrity correlation feature based on module insulation state data in the first data and the electrical state coupling relationship; constructing a heat exchange coupling feature based on cooling liquid flow rate data, cooling liquid pressure data in the first data, and the electrical state coupling relationship; and taking the voltage consistency features, the adaptive adjustment feature, the temperature balancing features, the current shunt features, the insulation integrity correlation feature, and the heat exchange coupling feature as the system interaction features. ； wherein, is a virtual inductance coarse adjustment increment, is a power variation rate adjustment coefficient, is a power difference adjustment coefficient, is the output power variation rate, is the power difference between the power command and the actual output power; ； wherein, is a virtual inductance fine tuning value for the current sampling period, is the virtual inductance fine tuning value for the previous sampling period, is a fine tuning step size coefficient; ； wherein, Lvirt is the virtual inductance after regression, Lvirt0 is the initial value of the virtual inductance, K is the regression adjustment coefficient; ； wherein, is a base virtual inductance value, is the virtual inductance parameter; The second data is used to construct external coordination features between the energy storage battery PACK package and external connection devices; the system interaction features and the external coordination features are input into a multi-source feature analysis model, and multi-source data corresponding to the energy storage battery PACK package is output based on the multi-source feature analysis model; the system interaction features and the external coordination features are input into a multi-source feature analysis model, and multi-source data corresponding to the energy storage battery PACK package is output based on the multi-source feature analysis model, specifically including: performing feature normalization processing on the system interaction features and the external coordination features by using the multi-source feature analysis model; performing multi-source feature fusion processing based on a result of the feature normalization processing, and mapping multi-dimensional features representing physical states, control logics, and cooperation relationships to a unified feature space; performing time series modeling on feature change trends in the unified feature space by using the multi-source feature analysis model; performing state classification and dynamic prediction reasoning according to a result of the multi-source feature fusion processing and a result of the time series modeling, and outputting the multi-source data by using the multi-source feature analysis model.

6. An electronic device, comprising: The electronic device includes a processor, a communication bus, a user interface, a network interface, and a memory, the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to enable the electronic device to perform the method of any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions, when the instructions are executed, to perform the method of any one of claims 1 to 4.

Images