Energy storage system operation and maintenance work order generation method and system based on multi-dimensional consistency of battery cell

Abstract

The application relates to an energy storage system operation and maintenance work order generation method and system based on multi-dimensional consistency of battery cells, wherein the method comprises obtaining multi-dimensional operation data of each battery cell of the energy storage system, and constructing a three-dimensional feature model; based on the three-dimensional feature model, discrete drift features of the battery cells in the time dimension and aggregation features of the battery cells in the space dimension are extracted respectively, and a space-time feature set is generated; the space-time feature set is classified and identified through a preset root cause determination rule, and a degradation root cause category of the battery cells is obtained; a hierarchical regulation instruction is generated according to the degradation root cause category, and regulated battery cell state feedback data is obtained; when the battery cell state feedback data represents ineffective regulation, and the corresponding degradation root cause category is irreversible aging, the spatial position information and historical state data of the corresponding degraded battery cell are extracted, an operation and maintenance work order is generated and pushed. The application solves the problem of how to automatically generate an operation and maintenance work order that fuses space-time features and accurately identifies a degradation root cause in the related art.

Description

Technical Field

[0001] This application relates to the technical field of energy storage systems, and in particular to a method and system for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells. Background Technology

[0002] The existing methods for generating operation and maintenance work orders for energy storage systems mainly involve collecting electrical parameters such as cell voltage and temperature, judging the battery consistency status based on parameter thresholds, and combining abnormal alarm information to carry out operation and maintenance reminders and issue work orders.

[0003] However, the existing maintenance work order generation methods mentioned above have several shortcomings. First, the equalization triggering mechanism is mostly based on voltage or SOC threshold at a single moment, making it difficult to distinguish between occasional sensor errors, contact resistance fluctuations, and irreversible cell aging, easily leading to ineffective equalization and wasted energy. Second, it lacks consideration of the physical spatial location of the cells within the container, making it difficult to identify temperature field inconsistencies caused by spatial factors such as heat dissipation dead zones and air conditioning vents, and their impact on the aging rate. Third, when consistency is abnormal, maintenance personnel can only locate the issue at the battery cluster level, making it difficult to accurately determine the physical coordinates of the degraded cells. On-site troubleshooting relies on manual measurement one by one, often employing a whole-cluster replacement strategy, resulting in resource waste.

[0004] Currently, there is an urgent need for a technical solution that can integrate spatiotemporal characteristics, accurately identify the root causes of cell degradation, and automatically generate maintenance work orders. Summary of the Invention

[0005] This application provides a method and system for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells, so as to at least solve the problem in related technologies of how to automatically generate operation and maintenance work orders that integrate spatiotemporal features and accurately identify the root causes of degradation.

[0006] In a first aspect, embodiments of this application provide a method for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells, the method comprising: Acquire multi-dimensional operational data of each cell in the energy storage system, and construct a three-dimensional feature model based on the multi-dimensional operational data; Based on the three-dimensional feature model, the discrete drift features of the battery cell in the time dimension and the clustering features in the spatial dimension are extracted respectively to generate a spatiotemporal feature set; The spatiotemporal feature set is classified and identified by a preset root cause determination rule to obtain the category of the root cause of the cell's degradation. Based on the aforementioned root cause of degradation, a graded control instruction is generated, and the graded control instruction is executed to obtain the cell status feedback data after control. When the cell status feedback data indicates that the regulation is ineffective and the corresponding root cause of degradation is irreversible aging, the spatial location information and historical status data of the corresponding degraded cell are extracted, and a maintenance work order is generated and pushed.

[0007] In one embodiment, acquiring multi-dimensional operational data of each cell in the energy storage system and constructing a three-dimensional feature model based on the multi-dimensional operational data includes: Real-time acquisition of multidimensional operation raw data of each cell at multiple times and the physical spatial coordinates of each cell within the battery cluster, and denoising and normalization processing of the multidimensional operation raw data to obtain standardized feature vectors; Based on the standardized feature vector and the physical space coordinates, the time series is mapped to the X-axis coordinates, the standardized feature vector is mapped to the Y-axis coordinates, and the physical space coordinates are mapped to the Z-axis spatial hierarchy index, thus establishing the mapping relationship of the battery cell in the three-dimensional coordinate system. Based on the mapping relationship, the spatial hierarchy index of the X-axis coordinate, Y-axis coordinate and Z-axis corresponding to the battery cell is fused and rendered in a three-dimensional coordinate system to generate a three-dimensional feature model representing time, value and spatial relationship.

[0008] In one embodiment, the step of extracting the discrete drift features of the battery cell in the time dimension and the clustering features in the spatial dimension based on the three-dimensional feature model to generate a spatiotemporal feature set includes: Within a preset sliding time window, the variance of the battery cell is calculated, and the variance change is calculated based on the variance of adjacent periods. The variance change is linearly fitted, and the slope of the fitted line is determined as the dispersion drift rate in the time dimension. A spatial weight matrix is ​​constructed based on the physical spatial coordinates of the battery cell. The spatial lag value of the target operating parameters of the battery cell is calculated based on the spatial weight matrix. The aggregation feature index of the spatial dimension is calculated based on the global average value of the target operating parameters of the battery cell. The dispersion drift rate corresponding to the battery cell is associated and combined with the aggregation feature index to generate a spatiotemporal feature set including time and space dimensions.

[0009] In one embodiment, the step of constructing a spatial weight matrix based on the physical spatial coordinates of the battery cell, calculating the spatial lag value of the target operating parameters of the battery cell based on the spatial weight matrix, and calculating the spatial dimension aggregation feature index based on the global average value of the target operating parameters of the battery cell includes: A spatial weight matrix is ​​constructed based on the comparison result of the Euclidean distance between the two battery cells and a preset distance threshold. When the Euclidean distance is less than the preset distance threshold, the corresponding weight matrix element takes a value of 1, otherwise it takes a value of 0. The weighted average of the target operating parameters of the battery cell is calculated based on the spatial weight matrix and used as the spatial lag value of the corresponding battery cell. Based on the target operating parameter values ​​of the battery cell, the spatial lag value, the global average value, and the spatial weight matrix, the clustering characteristic index is calculated through spatial autocorrelation analysis.

[0010] In one embodiment, the step of classifying and identifying the spatiotemporal feature set using a preset root cause determination rule to obtain the category of the cell's degradation root cause includes: Based on the preset discreteness drift rate judgment threshold and clustering characteristic index judgment threshold, the feature and root cause judgment matrix of the battery cell is constructed, and the degradation root cause classification judgment benchmark of the battery cell is generated. Based on the degradation root cause classification criteria, the dispersion drift rate of the spatiotemporal feature set is determined with the dispersion drift rate determination threshold, and the aggregation feature index of the spatiotemporal feature set is determined with the aggregation feature index determination threshold to obtain the degradation root cause category of the battery cell. The degradation root cause category includes transient interference, environmental thermodynamic inconsistency, and irreversible aging.

[0011] In one embodiment, the step of generating a graded control instruction based on the type of degradation root cause, executing the graded control instruction, and obtaining the controlled cell state feedback data includes: If the root cause of the degradation is transient interference, then generate instructions to shield the passive equalization trigger signal, as well as data filtering and sensor self-test instructions. If the root cause of the degradation is environmental thermodynamic inconsistency, then the coordinates of the abnormal aggregation area are calculated based on the aggregation characteristics, and a thermal management linkage adjustment command for the coordinates of the area is generated. If the root cause of degradation is irreversible aging, then the dispersion drift feature is compared with the preset aging classification threshold. If it is in the mild aging range, a passive balancing instruction is generated. If it is in the severe aging range, an active balancing instruction is generated. When the active balancing cannot converge, a charge-discharge curve reconstruction instruction is generated. Each instruction is sent to the corresponding execution unit, which performs the corresponding control operation and collects the status data of each cell after control as cell status feedback data.

[0012] In one embodiment, when the cell status feedback data indicates that regulation is ineffective and the corresponding root cause of degradation is irreversible aging, the spatial location information and historical status data of the corresponding degraded cell are extracted, and a maintenance work order is generated and pushed, including: The deterioration root cause category of the battery cell and the battery cell status feedback data after adjustment are obtained. It is determined whether there is a battery cell whose deterioration root cause type is irreversible aging and whose dispersion drift characteristics have not converged to the dispersion drift rate threshold after a preset number of charge and discharge cycles. If so, the battery cell is marked as a deteriorated battery cell and the operation and maintenance process is triggered. In response to receiving the instructions of the operation and maintenance process, the physical space coordinates and unique device code of the degraded battery cell are extracted from the extreme value data table, and the historical scatter drift curve, current internal resistance estimate and current capacity estimate of the degraded battery cell are obtained at the same time. Based on the physical space coordinates, the unique device code, the historical scatter drift curve, the current internal resistance estimate, and the current capacity estimate, a structured maintenance work order is generated. The work order includes the three-dimensional spatial location of the degraded cell, the historical scatter drift curve, the current internal resistance and capacity estimate, and the suggested disposal plan. The structured operation and maintenance work order is pushed to the mobile terminal of the operation and maintenance personnel, and the location of the degraded battery cell corresponding to the physical space coordinates is displayed in the three-dimensional digital twin visualization platform of the energy storage system.

[0013] Secondly, embodiments of this application provide a system for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells. This system is used to execute the aforementioned method and includes a module for constructing a three-dimensional feature model, a module for generating a spatiotemporal feature set, a module for classifying degradation root causes, a feedback data module, and a module for generating operation and maintenance work orders. The module for constructing a three-dimensional feature model is used to acquire multi-dimensional operating data of each cell in the energy storage system and construct a three-dimensional feature model based on the multi-dimensional operating data. The module for generating a spatiotemporal feature set is used to extract the discrete drift features of the battery cell in the time dimension and the clustering features in the spatial dimension based on the three-dimensional feature model and using a preset time window, respectively, to generate a spatiotemporal feature set. The degradation root cause category module is used to classify and identify the spatiotemporal feature set according to a preset root cause determination rule to obtain the degradation root cause category of the battery cell. The feedback data module is used to generate graded control instructions based on the type of deterioration root cause, execute the graded control instructions, and obtain the cell status feedback data after control. The module for generating maintenance work orders is used to extract the spatial location information and historical status data of the corresponding deteriorated battery cell when the cell status feedback data indicates that the control is ineffective and the corresponding root cause of degradation is irreversible aging, and then generate and push a maintenance work order.

[0014] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells as described in the first aspect above.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells as described in the first aspect above.

[0016] The method and system for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells provided in this application embodiment have at least the following technical effects.

[0017] By constructing a three-dimensional feature model that integrates multi-dimensional operational data and spatial location information, this approach overcomes the limitations of traditional methods that rely solely on time-series electrical numerical values ​​for analysis. Based on this three-dimensional feature model, it simultaneously extracts temporal dimension dispersion drift features and spatial dimension clustering features to generate a spatiotemporal feature set. This allows for the simultaneous quantification of the temporal evolution trend and spatial distribution pattern of cell parameters, enabling joint spatiotemporal assessment of consistency status. By classifying and identifying the spatiotemporal feature set using preset root cause determination rules, it can accurately distinguish between three types of degradation root causes: transient interference, environmental thermodynamic inconsistencies, and irreversible cell aging, effectively... This approach avoids misjudgments caused by single threshold determinations and reduces energy loss due to ineffective balancing. It generates tiered control commands based on different root causes of degradation and executes adaptive controls, breaking down control silos across multiple systems and specifically eliminating inconsistencies caused by different factors, thus improving control accuracy. Finally, based on the cell status feedback data after control, it generates and pushes precise single-cell-level maintenance work orders when control is ineffective and the root cause of degradation is irreversible aging. This significantly improves maintenance and troubleshooting efficiency, avoids resource waste caused by blindly replacing entire clusters, and forms a complete technical closed loop from status analysis and collaborative control to precise maintenance. It addresses the challenge of automatically generating maintenance work orders that integrate spatiotemporal features and accurately identify root causes of degradation in related technologies.

[0018] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1This is a flowchart illustrating a method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells, according to an exemplary embodiment. Figure 2 This is a structural block diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0021] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0022] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0023] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0024] In this document, it should be understood that the terms used may be technical means used to implement part of the present invention or other summary technical terms. For example, the terms may include: Cell multidimensional consistency: refers to the degree of balanced matching of each individual cell in the energy storage system in terms of multidimensional operating attributes. It includes the static numerical consistency of electrical and thermodynamic parameters such as voltage, internal resistance, temperature, and charge and discharge status, as well as the consistency of the temporal evolution trend of parameters in continuous charge and discharge cycles, and the spatial distribution consistency of cell parameters in the physical spatial layout of the battery cluster. It is the core evaluation dimension for comprehensively measuring the differences in cell status and degradation trends.

[0025] Degradation root cause category: refers to the cause type of abnormal phenomenon of cell consistency, based on the threshold matching rule of spatiotemporal characteristic parameters. In this application, it is specifically divided into three categories: transient interference, environmental thermodynamic inconsistency, and irreversible aging. Different categories correspond to different abnormality recoverability and mechanism of action, which are used to match the corresponding collaborative control strategy and operation and maintenance disposal method. It is the classification basis for realizing hierarchical precise control and operation and maintenance scheduling.

[0026] Firstly, embodiments of this application provide a method for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells. Figure 1 This is a flowchart of a method for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells, such as... Figure 1As shown, the method includes: Step S101: Obtain multi-dimensional operating data of each cell in the energy storage system, and construct a three-dimensional feature model based on the multi-dimensional operating data.

[0027] Step S102: Based on the three-dimensional feature model, extract the discrete drift features of the battery cell in the time dimension and the clustering features in the spatial dimension to generate a spatiotemporal feature set.

[0028] Step S103: Classify and identify the spatiotemporal feature set according to the preset root cause determination rules to obtain the root cause category of cell degradation.

[0029] Step S104: Generate graded control instructions based on the type of deterioration root cause, execute the graded control instructions, and obtain the cell status feedback data after control.

[0030] Step S105: When the cell status feedback data indicates that the regulation is ineffective and the corresponding root cause of degradation is irreversible aging, extract the spatial location information and historical status data of the corresponding degraded cell, generate and push the maintenance work order.

[0031] In summary, this application provides a method for generating operation and maintenance work orders for energy storage systems based on multi-dimensional cell consistency. By constructing a three-dimensional feature model that integrates multi-dimensional operational data and spatial location information, it overcomes the limitations of traditional solutions that rely solely on time-series electrical values ​​for analysis. Based on this three-dimensional feature model, it simultaneously extracts time-dimensional dispersion drift features and spatial-dimensional clustering features to generate a spatiotemporal feature set. This allows for the simultaneous quantification of the time-series evolution trend and spatial distribution pattern of cell parameters, achieving a spatiotemporal joint assessment of consistency status. By classifying and identifying the spatiotemporal feature set using preset root cause determination rules, it can accurately distinguish transient interference and environmental thermodynamic inconsistencies. This approach addresses three root causes of irreversible cell aging, effectively avoiding misjudgments caused by single-threshold determinations and reducing energy loss due to ineffective balancing. It generates tiered control commands based on different root cause categories and executes adaptive controls, breaking down control silos across multiple systems and specifically eliminating consistency anomalies caused by different factors, thus improving control accuracy. Finally, based on the cell status feedback data after control, it generates and pushes precise single-unit-level maintenance work orders when control is ineffective and the root cause is irreversible aging. This significantly improves maintenance and troubleshooting efficiency, avoids resource waste caused by blindly replacing entire clusters, and forms a complete technical closed loop from status analysis and collaborative control to precise maintenance. It solves the problem of how to automatically generate maintenance work orders that integrate spatiotemporal features and accurately identify root causes of degradation in related technologies.

[0032] In one embodiment, step S101 involves acquiring multi-dimensional operational data of each cell in the energy storage system and constructing a three-dimensional feature model based on the multi-dimensional operational data. Specifically, this includes the following steps: Step S1011: Collect the multi-dimensional operation raw data of each cell at multiple times in real time and the physical spatial coordinates of each cell in the battery cluster, and perform noise reduction and normalization processing on the multi-dimensional operation raw data to obtain a standardized feature vector. Optionally, data acquisition and preprocessing: Real-time acquisition of multi-dimensional operational raw data of the i-th cell in the energy storage power station at time t, including voltage Vi(t), temperature Ti(t), internal resistance Ri(t), and charging / discharging current Ii(t). Simultaneously, the physical spatial coordinates Pi(x,y,z) of the cell within the battery cluster / container (e.g., layer number, column number, row number) are acquired. The raw data is then denoised and normalized to obtain a standardized feature vector Di(t).

[0033] Step S1012: Based on the standardized feature vector and physical space coordinates, the time series is mapped to the X-axis coordinate, the standardized feature vector is mapped to the Y-axis coordinate, and the physical space coordinates are mapped to the spatial hierarchy index of the Z-axis, thus establishing the mapping relationship of the battery cell in the three-dimensional coordinate system. Optionally, spatial topology mapping: mapping physical spatial coordinates Pi(x,y,z) to the spatial hierarchy index Zi of the Z-axis; mapping the time series t to the X-axis; and mapping the normalized eigenvector Di(t) to the electrical / thermodynamic values ​​of the Y-axis. This establishes the mapping relationship of the battery cell in the three-dimensional coordinate system.

[0034] Step S1013: Based on the mapping relationship, the spatial hierarchy index of the X-axis coordinate, Y-axis coordinate and Z-axis corresponding to the battery cell is fused and rendered in the three-dimensional coordinate system to generate a three-dimensional feature model representing time, value and spatial relationship.

[0035] Optionally, a three-dimensional feature model (three-dimensional scatter cloud model) is generated: the data of the above three dimensions are fused and rendered in a three-dimensional coordinate system to generate a three-dimensional scatter cloud model S(X,Y,Z) containing a large number of data points, so as to realize the visualization and structured expression of the running data in the "time-numerical-space" dimension.

[0036] Steps S1011-S1013 construct a three-dimensional feature model that integrates multi-dimensional operational data and spatial location information, overcoming the limitations of traditional solutions that rely solely on time-series electrical values ​​for analysis. This model can capture the evolutionary patterns of cell consistency from both spatiotemporal dimensions, thereby accurately identifying different root causes such as transient interference, environmental thermodynamic inconsistencies, and irreversible aging.

[0037] In one embodiment, step S102 involves extracting the discrete drift features of the battery cell in the time dimension and the clustering features in the spatial dimension based on a three-dimensional feature model, thereby generating a spatiotemporal feature set. Specifically, this includes the following steps: Step S1021: Within a preset sliding time window, calculate the variance of the battery cell, calculate the variance change based on the variance of adjacent periods, perform linear fitting on the variance change, and determine the slope of the fitted line as the dispersion drift rate of the time dimension.

[0038] Optionally, the time dimension - dispersion drift rate (ΔD) t Calculation of ) It is used to characterize the variance change rate and aging acceleration trend of specific cell values ​​in continuous cycling.

[0039] First, within the sliding window N, calculate the variance of a specific parameter (such as voltage) for the i-th cell. , where k is the cycle number.

[0040] Secondly, calculate the variance change between adjacent cycle periods. .

[0041] Finally, a linear fit was performed on the variance change within the window, and the slope of the fitted line was extracted as the dispersion drift rate ΔD. t If ΔD t A value greater than 0 and a relatively large value indicates that the dispersion of the cell parameters is accelerating and that there is an aging trend.

[0042] Step S1022: Construct a spatial weight matrix based on the physical spatial coordinates of the battery cell; calculate the spatial lag value of the target operating parameters of the battery cell based on the spatial weight matrix; and calculate the spatial dimension aggregation characteristic index based on the global average value of the target operating parameters of the battery cell. Specifically, this includes: A spatial weight matrix is ​​constructed based on the comparison result of the Euclidean distance between the two battery cells and a preset distance threshold. When the Euclidean distance is less than the preset distance threshold, the corresponding weight matrix element takes a value of 1, otherwise it takes a value of 0. The weighted average of the target operating parameters of the battery cell is calculated based on the spatial weight matrix and used as the spatial lag value of the corresponding battery cell. Based on the target operating parameter values, spatial lag values, global average values, and spatial weight matrix of the battery cell, the clustering characteristic index is calculated through spatial autocorrelation analysis.

[0043] Step S1023: Associate and combine the dispersion drift rate and aggregation characteristic index corresponding to the battery cell to generate a spatiotemporal feature set including time and space dimensions.

[0044] Optionally, by combining the physical coordinates of the battery cells and using spatial autocorrelation analysis (such as the global Moran's I index), the degree of clustering of outlier values ​​in the physical space can be calculated.

[0045] First, define the spatial weight matrix W. If cell i and cell j are physically adjacent (e.g., the Euclidean distance is less than a set threshold), then W... ij =1, otherwise W ij =0.

[0046] Secondly, calculate the spatial lag value of a specific parameter (such as temperature or voltage deviation), which is the weighted average of that parameter between adjacent cells.

[0047] Finally, using the formula Calculate the clustering characteristic index C s (where x) i Here are the parameter values ​​for cell i. (This is the global average). C s The higher the value (approaching 1), the more significant the clustering of abnormal values ​​in physical space (e.g., concentrated in heat dissipation dead zones); if it approaches 0, it shows a random discrete distribution.

[0048] Steps S1021-S1023 calculate the variance and its changes in adjacent cycles within a sliding time window, and obtain the dispersion drift rate by linear fitting the changes. This can accurately capture the aging trend of cell parameters continuously increasing with the cycle period, and effectively distinguish between occasional measurement errors and irreversible capacity decay. At the same time, a weight matrix is ​​constructed using physical spatial coordinates, and the spatial lag value and global average deviation are calculated to obtain the aggregation characteristic index. This can accurately identify the degree of aggregation of abnormal values ​​in areas such as heat dissipation dead corners or air conditioning vents, solving the problem of thermodynamic inconsistency misjudgment caused by ignoring spatial location in traditional methods. It avoids ineffective equalization and energy waste triggered by a single threshold, and improves the accuracy of consistency degradation judgment and the effectiveness of equalization control.

[0049] In one embodiment, step S103 involves classifying and identifying the spatiotemporal feature set using preset root cause determination rules to obtain the root cause category of the battery cell's degradation. Specifically, this includes the following steps: Step S1031: Based on the preset discrete drift rate judgment threshold and clustering characteristic index judgment threshold, construct the characteristic and root cause judgment matrix of the battery cell and generate the battery cell degradation root cause classification judgment benchmark. Step S1032: Based on the degradation root cause classification judgment criteria, the dispersion drift rate and dispersion drift rate judgment threshold of the spatiotemporal feature set are judged, and the aggregation feature index and aggregation feature index judgment threshold of the spatiotemporal feature set are judged to obtain the degradation root cause category of the cell. The degradation root cause category includes transient interference, environmental thermodynamic inconsistency and irreversible aging.

[0050] Optionally, a feature-root cause multidimensional decision matrix is ​​constructed. The dispersion drift rate threshold is set to θ. t (e.g. θ) t=0.05), the clustering characteristic index threshold is θ s (e.g. θ) s =0.6). Consistency anomalies are precisely categorized into three types, with clear distinctions made based on the following criteria: Category 1: Transient interference (false anomalies): Definition criteria: ΔD t <θ t And C s <θ s .

[0051] The distinction is based on the following criteria: a low drift rate indicates no sustained degradation, while a low clustering index indicates that the scattered points exhibit irregular random dispersion (no spatial clustering). This is determined to be occasional interference such as sensor noise or poor contact in the BMS sampling harness.

[0052] Category 2: Environmental thermodynamic inconsistency (recoverable anomaly): Definition criteria: θ t ≤ΔD t <2θ t (Medium drift), and C s ≥θ s .

[0053] Criteria for differentiation: A moderate drift rate but an extremely high aggregation index indicates that the anomaly is concentrated in a specific physical area (such as near a container door, a blind spot near an air conditioning vent, or the end of a liquid cooling channel). This is determined to be a recoverable inconsistency caused by localized temperature differences due to uneven flow field in the temperature control system.

[0054] Category 3: Irreversible cell aging (true degradation): Definition criteria: ΔD t ≥2θ t (Continuous high drift), and the scatter points deviate from the main distribution for a long time (manifested as stable outliers in the extreme value data table), and are not affected by the improvement of environmental temperature control.

[0055] Criteria for differentiation: The drift rate consistently exceeds the standard, and there is no obvious spatial clustering (or even if there is clustering, ΔD will decrease after improving temperature control). t (If the temperature does not drop), it is determined to be irreversible aging caused by the degradation of internal materials of the battery cell.

[0056] Steps S1031-S1032: By classifying and identifying the spatiotemporal feature set through preset root cause determination rules, it is possible to accurately distinguish three types of degradation root causes: transient interference, environmental thermodynamic inconsistency, and irreversible cell aging. This effectively avoids misjudgment problems caused by single threshold determination and reduces energy loss caused by ineffective equilibrium.

[0057] In one embodiment, step S104 involves generating a graded control command based on the type of degradation root cause, executing the graded control command, and obtaining the cell status feedback data after control. Specifically, this includes the following steps: Step S1041: If the root cause of degradation is transient interference, then generate instructions to shield the passive equalization trigger signal, as well as data filtering and sensor self-test instructions. Step S1042: If the root cause of degradation is environmental thermodynamic inconsistency, calculate the coordinates of the abnormal aggregation area based on the aggregation characteristics and generate a thermal management linkage adjustment command for the area coordinates. Step S1043: If the root cause of degradation is irreversible aging, compare the dispersion drift characteristics with the preset aging classification threshold. If it is in the mild aging range, generate a passive balancing instruction. If it is in the severe aging range, generate an active balancing instruction. When the active balancing cannot converge, generate a charge-discharge curve reconstruction instruction. Step S1044: Send each instruction to the corresponding execution unit, the execution unit performs the corresponding control operation, and collects the status data of each cell after control as cell status feedback data.

[0058] Optionally, based on the identification results of step S104, the control silos of the BMS, PCS, and thermal management system are broken down, and cross-domain collaborative hierarchical control commands are issued: First: Control commands for transient interference: Execution process: The passive equalization trigger signal of the BMS is blocked to prevent energy consumption due to ineffective equalization; at the same time, the "data filtering and sensor self-test" command is sent to the BMS to start the moving average filtering algorithm and detect the impedance of the sampling harness.

[0059] Second: Control instructions addressing inconsistencies in environmental thermodynamics: Execution process: Triggering the "thermal management linkage" command. The system, based on C... s The calculated coordinates of the abnormal accumulation areas are used to send local adjustment commands to the thermal management system (liquid cooling / air cooling). For example, the opening of the water valve in the corresponding liquid cooling branch may be dynamically increased, or the speed of the local fan may be increased to eliminate the spatial temperature gradient.

[0060] Third: Control commands for irreversible cell aging: Mild aging (ΔD) t In [2θ t , 3θ t [Interval]: Triggers BMS-level passive balancing command, using balancing resistors to consume excess power from high SOC cells.

[0061] Severe aging (ΔD) t >3θ t): Triggers a PCS-level active balancing command to transfer energy; if active balancing still fails to converge, a "charge and discharge curve reconstruction" command is sent to the PCS to dynamically reduce the charge and discharge cutoff voltage and maximum charge and discharge current of the battery cluster, preventing thermal runaway caused by overcharging and over-discharging of degraded cells.

[0062] Steps S1041-S1044 generate hierarchical control instructions based on different root causes of degradation and execute adaptive control, which can break the control silos of multiple systems, eliminate the consistency anomalies of different causes in a targeted manner, and improve the accuracy of control.

[0063] In one embodiment, step S105 involves extracting the spatial location information and historical status data of the corresponding deteriorated battery cell when the cell status feedback data indicates that regulation is ineffective and the corresponding root cause of degradation is irreversible aging. This process includes the following steps: Step S1051: Obtain the cell degradation root cause category and the cell status feedback data after adjustment, determine whether there is a cell whose degradation root cause type is irreversible aging and whose dispersion drift characteristics have not converged to the dispersion drift rate threshold after a preset number of charge and discharge cycles. If so, mark the cell as a degraded cell and trigger the operation and maintenance process. Step S1052: In response to the instruction of the operation and maintenance process, extract the physical space coordinates and unique device code of the degraded battery cell from the extreme value data table, and at the same time obtain the historical scatter drift curve, current internal resistance estimate and current capacity estimate of the degraded battery cell. Step S1053: Generate a structured maintenance work order based on the physical space coordinates, unique device code, historical scattered drift curve, current internal resistance estimate, and current capacity estimate. The work order includes the three-dimensional spatial location of the deteriorated cell, historical scattered drift curve, current internal resistance and capacity estimate, and suggested disposal plan. Step S1054: Push the structured operation and maintenance work order to the mobile terminal of the operation and maintenance personnel, and display the location of the degraded battery cell corresponding to the physical space coordinates in the three-dimensional digital twin visualization platform of the energy storage system.

[0064] Optionally, when the cell is determined to be "irreversible aging" and the balancing strategy is ineffective (e.g., ΔDt has not converged to the threshold after three consecutive charge-discharge cycles), a precise operation and maintenance process is triggered: First, coordinate extraction): The system automatically extracts the precise physical coordinates P of the degraded battery cell from the "Extreme Value Data Table". i (x,y,z) and a unique device code.

[0065] Secondly, work order generation: Automatically generate structured operation and maintenance work orders. The work order content includes: the three-dimensional spatial location of the deteriorated cell, the historical scattered drift curve (ΔDt evolution diagram), the current internal resistance / capacity estimate and the suggested disposal plan (such as "suggesting single cell replacement" or "suggesting downgraded use").

[0066] Finally, visual push notifications: Work orders are pushed to the mobile terminals of maintenance personnel, and the specific physical location of the deteriorated cell is displayed in red with flashing highlights in the 3D digital twin visualization platform of the energy storage power station, avoiding blind cluster inspections.

[0067] Step S105 ultimately generates and pushes a precise single-cell-level maintenance work order based on the adjusted cell status feedback data when adjustment is ineffective and the root cause of degradation is irreversible aging. This significantly improves maintenance and troubleshooting efficiency, avoids resource waste caused by blindly replacing entire clusters, and forms a complete technical closed loop from status analysis and collaborative management to precise maintenance. It addresses the problem of how to automatically generate maintenance work orders that integrate spatiotemporal features and accurately identify the root cause of degradation in related technologies.

[0068] In summary, this application provides a method for generating operation and maintenance work orders for energy storage systems based on multi-dimensional cell consistency. By constructing a three-dimensional feature model that integrates multi-dimensional operational data and spatial location information, it overcomes the limitations of traditional solutions that rely solely on time-series electrical values ​​for analysis. Based on this three-dimensional feature model, it simultaneously extracts time-dimensional dispersion drift features and spatial-dimensional clustering features to generate a spatiotemporal feature set. This allows for the simultaneous quantification of the time-series evolution trend and spatial distribution pattern of cell parameters, achieving a spatiotemporal joint assessment of consistency status. By classifying and identifying the spatiotemporal feature set using preset root cause determination rules, it can accurately distinguish transient interference and environmental thermodynamic inconsistencies. This approach addresses three root causes of irreversible cell aging, effectively avoiding misjudgments caused by single-threshold determinations and reducing energy loss due to ineffective balancing. It generates tiered control commands based on different root cause categories and executes adaptive controls, breaking down control silos across multiple systems and specifically eliminating consistency anomalies caused by different factors, thus improving control accuracy. Finally, based on the cell status feedback data after control, it generates and pushes precise single-unit-level maintenance work orders when control is ineffective and the root cause is irreversible aging. This significantly improves maintenance and troubleshooting efficiency, avoids resource waste caused by blindly replacing entire clusters, and forms a complete technical closed loop from status analysis and collaborative control to precise maintenance. It solves the problem of how to automatically generate maintenance work orders that integrate spatiotemporal features and accurately identify root causes of degradation in related technologies.

[0069] Secondly, embodiments of this application provide a system for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells. The system includes a module for constructing a three-dimensional feature model, a module for generating a spatiotemporal feature set, a module for classifying degradation root causes, a feedback data module, and a module for generating operation and maintenance work orders, wherein: A three-dimensional feature model module is constructed to obtain multi-dimensional operating data of each cell in the energy storage system, and a three-dimensional feature model is constructed based on the multi-dimensional operating data. The module for generating spatiotemporal feature sets is used to extract the discrete drift features of the battery cell in the time dimension and the clustering features in the spatial dimension based on the three-dimensional feature model and using a preset time window, to generate a spatiotemporal feature set. The degradation root cause category module is used to classify and identify the spatiotemporal feature set according to the preset root cause determination rules to obtain the degradation root cause category of the battery cell. The feedback data module is used to generate graded control instructions based on the type of root cause of degradation, execute the graded control instructions, and obtain the cell status feedback data after control. The module for generating maintenance work orders is used to extract the spatial location information and historical status data of the corresponding deteriorated battery cell when the cell status feedback data indicates that the control is ineffective and the corresponding root cause of degradation is irreversible aging, and then generate and push maintenance work orders.

[0070] In summary, this application provides an energy storage system operation and maintenance work order generation system based on multi-dimensional consistency of battery cells. Through the synergistic effect of modules for building a 3D feature model, generating a spatiotemporal feature set, classifying degradation root causes, providing feedback data, and generating operation and maintenance work orders, the system generates and pushes precise single-cell-level operation and maintenance work orders based on the feedback data of the adjusted battery cell status. This is especially useful when adjustments are ineffective and the degradation root cause is irreversible aging. This significantly improves the efficiency of operation and maintenance troubleshooting, avoids the resource waste caused by blindly replacing entire clusters, and forms a complete technical closed loop from status analysis and collaborative management to precise operation and maintenance. This addresses the problem in related technologies of how to automatically generate operation and maintenance work orders that integrate spatiotemporal features and accurately identify degradation root causes.

[0071] It should be noted that the energy storage system operation and maintenance work order generation system based on multi-dimensional consistency of battery cells provided in this embodiment is used to implement the above-described implementation methods, and will not be repeated as already described. As used above, the terms "module," "unit," "subunit," etc., can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the above embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0072] Thirdly, embodiments of this application provide an electronic device, Figure 2 This is a block diagram illustrating an electronic device according to an exemplary embodiment. (e.g.) Figure 2 As shown, the electronic device may include a processor 21 and a memory 22 storing computer program instructions.

[0073] Specifically, the processor 21 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0074] The memory 22 may include a mass storage device for data or instructions. For example, and not limitingly, the memory 22 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 22 may include removable or non-removable (or fixed) media. Where appropriate, the memory 22 may be internal or external to a data processing device. In a particular embodiment, the memory 22 is non-volatile memory. In a particular embodiment, the memory 22 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0075] The memory 22 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 21.

[0076] The processor 21 reads and executes the computer program instructions stored in the memory 22 to implement any of the above embodiments of the energy storage system operation and maintenance work order generation method based on cell multidimensional consistency.

[0077] In one embodiment, an energy storage system operation and maintenance work order generation device based on cell multidimensional consistency may further include a communication interface 23 and a bus 20. Wherein, as Figure 2 As shown, the processor 21, memory 22, and communication interface 23 are connected through bus 20 and complete communication with each other.

[0078] The communication interface 23 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of this application. The communication interface 23 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0079] Bus 20 includes hardware, software, or both, that couples together components of an energy storage system operation and maintenance work order generation device based on cell multidimensional consistency. Bus 20 includes, but is not limited to, at least one of the following: Data Bus, Address Bus, Control Bus, Expansion Bus, and Local Bus. For example, and not as a limitation, bus 20 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 20 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0080] Fourthly, embodiments of this application provide a computer-readable storage medium storing a program thereon. When the program is executed by a processor, it implements the energy storage system operation and maintenance work order generation method based on cell multidimensional consistency provided in the first aspect.

[0081] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0082] In a possible implementation, the present invention can also be implemented as a program product comprising program code, which, when the program product is run on a terminal device, causes the terminal device to execute the steps of the method for generating operation and maintenance work orders for an energy storage system based on multidimensional consistency of battery cells provided in the first aspect.

[0083] The program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0084] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0085] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells, characterized in that, The method includes: Acquire multi-dimensional operational data of each cell in the energy storage system, and construct a three-dimensional feature model based on the multi-dimensional operational data; Based on the three-dimensional feature model, the discrete drift features of the battery cell in the time dimension and the clustering features in the spatial dimension are extracted respectively to generate a spatiotemporal feature set; The spatiotemporal feature set is classified and identified by a preset root cause determination rule to obtain the category of the root cause of the cell's degradation. A graded control instruction is generated based on the type of degradation root cause, and the graded control instruction is executed to obtain the cell status feedback data after control. When the cell status feedback data indicates that the regulation is ineffective and the corresponding root cause of degradation is irreversible aging, the spatial location information and historical status data of the corresponding degraded cell are extracted, and a maintenance work order is generated and pushed.

2. The method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells according to claim 1, characterized in that, The process of acquiring multi-dimensional operational data of each cell in the energy storage system and constructing a three-dimensional feature model based on the multi-dimensional operational data includes: Real-time acquisition of multidimensional operation raw data of each cell at multiple times and the physical spatial coordinates of each cell within the battery cluster, and denoising and normalization processing of the multidimensional operation raw data to obtain standardized feature vectors; Based on the standardized feature vector and the physical space coordinates, the time series is mapped to the X-axis coordinates, the standardized feature vector is mapped to the Y-axis coordinates, and the physical space coordinates are mapped to the Z-axis spatial hierarchy index, thus establishing the mapping relationship of the battery cell in the three-dimensional coordinate system. Based on the mapping relationship, the spatial hierarchy index of the X-axis coordinate, Y-axis coordinate and Z-axis corresponding to the battery cell is fused and rendered in a three-dimensional coordinate system to generate a three-dimensional feature model representing time, value and spatial relationship.

3. The method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells according to claim 1, characterized in that, Based on the three-dimensional feature model, the discrete drift features of the battery cell in the time dimension and the clustering features in the spatial dimension are extracted respectively to generate a spatiotemporal feature set, including: Within a preset sliding time window, the variance of the battery cell is calculated, and the variance change is calculated based on the variance of adjacent periods. The variance change is linearly fitted, and the slope of the fitted line is determined as the dispersion drift rate in the time dimension. A spatial weight matrix is ​​constructed based on the physical spatial coordinates of the battery cell. The spatial lag value of the target operating parameters of the battery cell is calculated based on the spatial weight matrix. The aggregation feature index of the spatial dimension is calculated based on the global average value of the target operating parameters of the battery cell. The dispersion drift rate corresponding to the battery cell is associated and combined with the aggregation feature index to generate a spatiotemporal feature set including time and space dimensions.

4. The method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells according to claim 3, characterized in that, The process of constructing a spatial weight matrix based on the physical spatial coordinates of the battery cell, calculating the spatial lag value of the target operating parameters of the battery cell based on the spatial weight matrix, and calculating the spatial dimension aggregation characteristic index based on the global average value of the target operating parameters of the battery cell includes: A spatial weight matrix is ​​constructed based on the comparison result of the Euclidean distance between the two battery cells and a preset distance threshold. When the Euclidean distance is less than the preset distance threshold, the corresponding weight matrix element takes a value of 1, otherwise it takes a value of 0. The weighted average of the target operating parameters of the battery cell is calculated based on the spatial weight matrix and used as the spatial lag value of the corresponding battery cell. Based on the target operating parameter values ​​of the battery cell, the spatial lag value, the global average value, and the spatial weight matrix, the clustering characteristic index is calculated through spatial autocorrelation analysis.

5. The method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells according to claim 1, characterized in that, The step of classifying and identifying the spatiotemporal feature set using preset root cause determination rules to obtain the category of the cell's degradation root cause includes: Based on the preset discreteness drift rate judgment threshold and clustering characteristic index judgment threshold, the feature and root cause judgment matrix of the battery cell is constructed, and the degradation root cause classification judgment benchmark of the battery cell is generated. Based on the degradation root cause classification criteria, the dispersion drift rate of the spatiotemporal feature set is determined with the dispersion drift rate determination threshold, and the aggregation feature index of the spatiotemporal feature set is determined with the aggregation feature index determination threshold to obtain the degradation root cause category of the battery cell. The degradation root cause category includes transient interference, environmental thermodynamic inconsistency, and irreversible aging.

6. The method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells according to claim 1, characterized in that, The step of generating graded control instructions based on the root cause category of degradation, executing the graded control instructions, and obtaining the cell status feedback data after control includes: If the root cause of the degradation is transient interference, then generate instructions to shield the passive equalization trigger signal, as well as data filtering and sensor self-test instructions. If the root cause of the degradation is environmental thermodynamic inconsistency, then the coordinates of the abnormal aggregation area are calculated based on the aggregation characteristics, and a thermal management linkage adjustment command for the coordinates of the area is generated. If the root cause of degradation is irreversible aging, then the dispersion drift feature is compared with the preset aging classification threshold. If it is in the mild aging range, a passive balancing instruction is generated. If it is in the severe aging range, an active balancing instruction is generated. When the active balancing cannot converge, a charge-discharge curve reconstruction instruction is generated. Each instruction is sent to the corresponding execution unit, which performs the corresponding control operation and collects the status data of each cell after control as cell status feedback data.

7. The method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells according to claim 1, characterized in that, When the cell status feedback data indicates that regulation is ineffective, and the corresponding root cause of degradation is irreversible aging, the spatial location information and historical status data of the corresponding degraded cell are extracted, and a maintenance work order is generated and pushed, including: The deterioration root cause category of the battery cell and the battery cell status feedback data after adjustment are obtained. It is determined whether there is a battery cell whose deterioration root cause type is irreversible aging and whose dispersion drift characteristics have not converged to the dispersion drift rate threshold after a preset number of charge and discharge cycles. If so, the battery cell is marked as a deteriorated battery cell and the operation and maintenance process is triggered. In response to receiving the instructions of the operation and maintenance process, the physical space coordinates and unique device code of the degraded battery cell are extracted from the extreme value data table, and the historical scatter drift curve, current internal resistance estimate and current capacity estimate of the degraded battery cell are obtained at the same time. Based on the physical space coordinates, the unique device code, the historical scatter drift curve, the current internal resistance estimate, and the current capacity estimate, a structured maintenance work order is generated. The work order includes the three-dimensional spatial location of the degraded cell, the historical scatter drift curve, the current internal resistance and capacity estimate, and the suggested disposal plan. The structured operation and maintenance work order is pushed to the mobile terminal of the operation and maintenance personnel, and the location of the degraded battery cell corresponding to the physical space coordinates is displayed in the three-dimensional digital twin visualization platform of the energy storage system.

8. A system for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells, characterized in that, The system is used to execute the method according to any one of claims 1 to 7, and the system includes a module for constructing a three-dimensional feature model, a module for generating a spatiotemporal feature set, a module for classifying the root causes of degradation, a feedback data module, and a module for generating maintenance work orders, wherein: The module for constructing a three-dimensional feature model is used to acquire multi-dimensional operating data of each cell in the energy storage system and construct a three-dimensional feature model based on the multi-dimensional operating data. The module for generating a spatiotemporal feature set is used to extract the discrete drift features of the battery cell in the time dimension and the clustering features in the spatial dimension based on the three-dimensional feature model and using a preset time window, respectively, to generate a spatiotemporal feature set. The degradation root cause category module is used to classify and identify the spatiotemporal feature set according to a preset root cause determination rule to obtain the degradation root cause category of the battery cell. The feedback data module is used to generate a graded control instruction based on the type of deterioration root cause, execute the graded control instruction, and obtain the cell status feedback data after control. The module for generating maintenance work orders is used to extract the spatial location information and historical status data of the corresponding deteriorated battery cell when the cell status feedback data indicates that the control is ineffective and the corresponding root cause of degradation is irreversible aging, and then generate and push a maintenance work order.

9. An electronic device, characterized in that, The system includes a memory and a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a method for generating operation and maintenance work orders for an energy storage system based on multi-dimensional consistency of battery cells as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements a method for generating operation and maintenance work orders for energy storage systems based on multi-dimensional consistency of battery cells, as described in any one of claims 1 to 7.

Images