Diagnostic methods for energy storage systems and energy storage systems

By combining the validity verification and review modes of the operating data and link element information of the energy storage system, the problem of low accuracy in thermal runaway diagnosis in the existing technology is solved, and higher accuracy thermal runaway risk identification and false alarm suppression are achieved.

CN123112752APending Publication Date: 2026-11-17JINKO SOLAR CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611425304.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-14
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing methods for diagnosing thermal runaway in energy storage systems rely on single-sample threshold determination, resulting in low accuracy in diagnosing thermal runaway faults.

Method used

By acquiring the operating data of the energy storage system and its corresponding sampling link element information, the effectiveness is verified. Combining the operating data and link element information collected multiple times, a verification mode is adopted to diagnose thermal runaway and distinguish between sampling link failure and battery body thermal runaway risk.

Benefits of technology

It improves the accuracy of thermal runaway fault diagnosis, reduces false alarms, and ensures the reliability and precision of thermal runaway diagnosis results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123112752A_ABST
    Figure CN123112752A_ABST
Patent Text Reader

Abstract

This application relates to a diagnostic method for an energy storage system and an energy storage system itself. The method involves acquiring first operating data of the energy storage system and first link element information of the sampling link corresponding to the first operating data. The validity of the first operating data is verified based on the first link element information to obtain a validity verification result. Based on the validity verification result, the thermal runaway diagnostic result of the energy storage system is determined. This application simultaneously acquires the first operating data of the energy storage system and the corresponding first link element information, enabling the inclusion of abnormal information at the sampling link level, such as sampling communication, simulated front-end hardware, wiring harness faults, and sampling timing, into the validity verification process of the first operating data. This achieves joint judgment of the sampling link status and the battery's operating data, solving the problem that traditional solutions cannot distinguish between sampling link faults and actual battery thermal runaway risks.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of energy storage system technology, and in particular to a diagnostic method for an energy storage system and an energy storage system. Background Technology

[0002] With the large-scale application of electrochemical energy storage, lithium batteries, lead-carbon batteries, sodium-ion batteries and other types of batteries are widely used in power plants and industrial and commercial energy storage. All types of batteries have the risk of thermal runaway and fire. The battery management system (BMS) relies on the sampling data such as voltage and temperature signals collected by the analog front end (AFE) chip to determine and capture the precursors of thermal runaway and realize safety alarm and protection actions.

[0003] Currently, the diagnosis of thermal runaway in energy storage systems only uses a single sampling threshold determination method. Once discrete sampling data appears in the sampling data, it is considered that a thermal runaway fault has occurred, which reduces the accuracy of thermal runaway fault diagnosis. Summary of the Invention

[0004] Therefore, it is necessary to provide a diagnostic method and energy storage system for energy storage systems that can improve the accuracy of thermal runaway fault diagnosis, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a diagnostic method for an energy storage system, the diagnostic method for the energy storage system comprising:

[0006] Acquire first operating data of the energy storage system, and first link element information of the sampling link corresponding to the first operating data; the first operating data includes at least one of voltage, temperature, current, power and operating status, and the first link element information includes communication verification information, status information of the analog front-end chip, fault diagnosis information and sampling timing information;

[0007] The validity of the first running data is verified based on the first link meta-information to obtain the validity verification result corresponding to the first running data.

[0008] Based on the validity verification results corresponding to the first operating data, the thermal runaway diagnosis results of the energy storage system are determined.

[0009] In one embodiment, determining the thermal runaway diagnosis result of the energy storage system based on the validity verification result corresponding to the first operating data includes:

[0010] If the validity verification result corresponding to the first running data indicates that the first running data is valid, the first target evaluation value corresponding to the first running data is determined;

[0011] The thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and the first preset evaluation threshold.

[0012] In one embodiment, determining the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and the first preset evaluation threshold includes:

[0013] If the first target evaluation value is greater than the first preset evaluation threshold, the first target feature is extracted from the first running data;

[0014] If at least one first sub-feature in the first target feature satisfies the review triggering condition, the review mode corresponding to the at least one first sub-feature is determined, and multiple second operating data collected multiple times by the energy storage system and the second link element information of the sampling link corresponding to the multiple second operating data are obtained according to the review mode.

[0015] Based on the first target evaluation value, multiple second operating data, and second link element information, the thermal runaway diagnosis result of the energy storage system is determined.

[0016] In one embodiment, determining the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value, multiple second operating data, and second link element information includes:

[0017] Based on multiple second link element information, the validity of the second running data corresponding to the multiple second link element information is verified respectively, and the validity verification results corresponding to the multiple second running data are obtained.

[0018] When the validity verification result corresponding to the second operating data indicates that the second operating data is valid, and the second target evaluation value of the second operating data is greater than the first preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and multiple second operating data.

[0019] In one embodiment, determining the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and multiple second operating data includes:

[0020] Extract corresponding second target features from multiple second running data, and determine at least one second sub-feature from each second target feature that satisfies the review triggering condition;

[0021] Determine a first number of instances where the type of the at least one first sub-feature is consistent with the type of the at least one second sub-feature;

[0022] If the target ratio of the first quantity to the second quantity is greater than the first preset ratio, the thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and multiple second operating data; the second quantity is the number of valid second operating data whose second target evaluation value is greater than the first preset evaluation threshold.

[0023] In one embodiment, determining the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and multiple sets of second operating data when the target ratio of the first quantity to the second quantity is greater than a first preset ratio includes:

[0024] When the target ratio is greater than the second preset ratio, and the first target evaluation value is greater than the first preset evaluation threshold and less than or equal to the second preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on multiple second operating data; the second preset ratio is greater than the first preset ratio.

[0025] In one embodiment, the diagnostic method for the energy storage system further includes:

[0026] If the target ratio is greater than the first preset ratio and the first target evaluation value is greater than the second preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on multiple second operating data.

[0027] In one embodiment, determining the thermal runaway diagnosis result of the energy storage system based on a plurality of the second operating data includes:

[0028] Determine the data consistency type of multiple second running data;

[0029] If the data consistency type belongs to a preset consistency type set, then the thermal runaway diagnosis result is determined to be that the energy storage system does not have thermal runaway anomalies;

[0030] If the data consistency type does not belong to the preset consistency type set, then the thermal runaway diagnosis result is determined to be that the energy storage system has a thermal runaway anomaly.

[0031] In one embodiment, the diagnostic method for the energy storage system further includes:

[0032] If the target ratio is less than or equal to the first preset ratio, then the thermal runaway diagnosis result is determined to be that the energy storage system does not have thermal runaway anomaly.

[0033] Alternatively, if the feature representing link failure in the second target feature is stronger than the feature representing thermal runaway failure in the second target feature, then the thermal runaway diagnosis result is determined to be that the energy storage system does not have thermal runaway anomaly.

[0034] In one embodiment, determining the first target evaluation value corresponding to the first running data includes:

[0035] The initial evaluation value is adjusted based on the preset scoring rules to obtain the intermediate evaluation value;

[0036] The intermediate evaluation value is subjected to amplitude limiting processing based on a preset evaluation range to obtain the first target evaluation value.

[0037] In one embodiment, extracting the first target feature from the first running data includes:

[0038] Extract the first initial feature from the first running data;

[0039] If the duration for which the first initial feature does not trigger the preset clearing threshold meets the preset duration, the first initial feature is determined to be the first target feature.

[0040] Secondly, this application also provides an energy storage system, the energy storage system including a battery management system, the battery management system including:

[0041] The acquisition module is used to acquire first operating data of the energy storage system and first link element information of the sampling link corresponding to the first operating data; the first operating data includes at least one of voltage, temperature, current, power and operating status, and the first link element information includes communication verification information, status information of the analog front-end chip, fault diagnosis information and sampling timing information;

[0042] The verification module is used to verify the validity of the first running data based on the first link element information, and obtain the validity verification result corresponding to the first running data;

[0043] The determination module is used to determine the thermal runaway diagnosis result of the energy storage system based on the validity verification result corresponding to the first operating data.

[0044] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps provided in the first aspect.

[0045] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method steps provided in the first aspect.

[0046] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method steps provided in the first aspect.

[0047] The aforementioned diagnostic method and system for energy storage systems acquire first operating data of the energy storage system and first link element information of the sampling link corresponding to the first operating data. The first operating data is then validated based on the first link element information to obtain a validation result. Based on this validation result, the thermal runaway diagnostic result of the energy storage system is determined. The first operating data includes at least one of voltage, temperature, current, power, and operating condition. The first link element information includes communication verification information, state information of the simulated front-end chip, fault diagnosis information, and sampling timing information. This embodiment simultaneously acquires the first operating data of the energy storage system and the corresponding first link element information, no longer relying solely on battery operating data such as voltage and temperature for thermal runaway diagnosis. It incorporates abnormal information at the sampling link level, such as sampling communication, simulated front-end hardware, wiring harness faults, and sampling timing, into the validation process of the first operating data. This enables joint judgment of the sampling link status and battery operating data, solving the problem that traditional solutions cannot distinguish between sampling link faults and actual battery thermal runaway risks, and providing a complete input basis for subsequently suppressing false thermal runaway reports. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is an application environment diagram of a diagnostic method for an energy storage system in one embodiment;

[0050] Figure 2 This is a flowchart illustrating a diagnostic method for an energy storage system in one embodiment;

[0051] Figure 3 This is a schematic diagram of the first process of a method for determining thermal runaway diagnosis results in one embodiment;

[0052] Figure 4 This is a flowchart illustrating a method for obtaining the first target feature in one embodiment;

[0053] Figure 5 This is a schematic diagram of the second process of a method for determining thermal runaway diagnosis results in one embodiment;

[0054] Figure 6 This is a schematic diagram of the third process of a method for determining the diagnosis result of thermal runaway in one embodiment;

[0055] Figure 7 This is a schematic diagram of the fourth step in the method for determining the diagnosis result of thermal runaway in one embodiment;

[0056] Figure 8 This is a schematic diagram of the fifth step in the method for determining the diagnosis result of thermal runaway in one embodiment;

[0057] Figure 9 This is a structural block diagram of an energy storage system in one embodiment;

[0058] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0061] In energy storage systems, the sampling link of the analog front-end chip is prone to various anomalies. These anomalies are reflected in the operating data and corresponding link metadata. Common anomalies include, but are not limited to: Communication frame anomalies: Cyclic Redundancy Check (CRC) or Packet Error Check (PEC) failures, frame drops, duplicate frames, timing drift, etc., occur on the isolated link or serial bus, causing sampling message transmission errors, message loss, duplicate message reception, or message timing disorder; Channel multiplexing transient anomalies: Temperature and voltage signals are acquired using multiplexing, and the analog path is not fully stable after channel switching, resulting in ghost values, drift values, and other non-true sampling offsets in the first output sample; Open wire and poor contact anomalies: Negative temperature coefficient thermistors (NCTs) Open circuits in the Temperature Coefficient (NTC), poor crimping of the sampling harness, loose terminals, and contact failure of connectors due to vibration can cause instantaneous jumps in the initial operating data of voltage and temperature. Analog-to-Digital Converter (ADC) glitches and electromagnetic coupling interference: Electromagnetic coupling noise is introduced by high-current switching operations, contactor opening and closing operations, PWM interference from the Power Conversion System (PCS), and equalization switch operations, resulting in instantaneous outliers in the sampling results. Sampling period jitter: Affected by BMU task scheduling, bus congestion, and data upload congestion, the actual sampling interval deviates from the nominal period, artificially amplifying the temperature rise rate and voltage drop rate calculated based on differential calculations, causing rate characteristic distortion. Multi-level time asynchrony: Local timestamps in the Battery Monitoring Unit (BMU) and Battery Cluster Control Unit (BCCU) are inconsistent. The time stamp of the Unit (BCU) summary cannot be aligned with the current time stamp of the PCS, resulting in inconsistent time bases and distorted cross-domain consistency judgment results based on multi-source first operating data; pseudo-anomalies under long-term standby and low-rate operation: During long-term standby, low-rate charging and discharging, or periodic inspection of the energy storage system, single-point sampling jumps are prone to occur. These jumps have no physical correspondence with the actual heat accumulation process of the battery cell and belong to non-thermal risk pseudo-anomaly signals.

[0062] This application addresses energy storage power stations, commercial and industrial energy storage cabinets, residential energy storage systems, containerized energy storage systems, and other energy storage scenarios consisting of multiple battery clusters, battery packs, or battery modules. It provides a diagnostic method for energy storage systems to address various issues arising from the sampling link of the analog front-end chip, including communication anomalies, diagnostic anomalies, open sampling harnesses or poor connector contact, transient anomalies in multiplexed channels, sampling period jitter, and electromagnetic interference introduced by equalization or contactor operation. Before extracting the first target feature related to thermal runaway from the first operating data, this method relies on the first link element information corresponding to the sampling link to complete sample validity verification and credibility gating processing, filtering out low-credibility or invalid samples caused by link anomalies. Furthermore, when the first sub-feature meets the verification trigger condition and enters the candidate alarm stage, a matching verification mode is invoked to perform active verification. Combined with multiple sets of second operating data obtained from the verification and their corresponding second link element information, thermal runaway diagnosis is completed, thereby distinguishing between sampling link failures and the actual thermal runaway risk of the battery itself, and suppressing false alarms of thermal runaway caused by sampling link anomalies.

[0063] The diagnostic method for energy storage systems provided in this application can be applied to, for example... Figure 1 In the application environment shown, the diagnostic method for the energy storage system provided in this application embodiment is executed by the battery management system of the energy storage system. The battery management system adopts a distributed architecture, including a main controller, a BCU, and a BMU. The BMU is a data acquisition and management unit at the battery module level or battery pack level, which is usually connected to one or more AFEs. It is used to collect operating data such as individual cell voltage and temperature, and synchronously acquire the link element information corresponding to the sampling link. The BMU can perform local sampling, resampling, AFE self-test, and equalization control, and report the operating data and link element information to the BCU. The BCU, as the cluster-level controller of the battery cluster, aggregates the operating data and link element information reported by all BMUs under the battery cluster, and reports the cluster-level aggregated sampling data and status information to the main controller. The BCU receives control commands and configuration parameters issued by the main controller, forwards commands to each BMU, and realizes control actions such as intra-cluster sampling, resampling, and equalization.

[0064] The main controller, as the upper-level management unit of the BMS, receives cluster-level data reported by each BCU. It directly acquires system operating information such as contactor status, thermal management status, fire alarm linkage status, energy storage converter power, and policy commands issued by the energy management system. Externally, the main controller completes command interaction and status feedback with the energy management system, energy storage converter, contactors, thermal management system, and fire alarm system. Sampled data includes operational data and link element information.

[0065] The diagnostic method for energy storage systems disclosed in this application supports multiple deployment implementation methods: it can be implemented in a distributed and collaborative manner by the BMU and BCU, or the BCU can centrally complete all diagnostic processing logic; under this three-layer distributed architecture, the main controller can also complete the final reliability assessment, cross-domain consistency verification, thermal runaway state machine judgment based on the cluster-level data uploaded by each BCU, and output the thermal runaway diagnostic results and corresponding alarm and linkage control commands.

[0066] In one exemplary embodiment, such as Figure 2 As shown, a diagnostic method for an energy storage system is provided, which can be applied to... Figure 1 The following explanation uses the battery management system as an example, including the following steps S201 to S203. Wherein:

[0067] S201, acquire the first operating data of the energy storage system and the first link element information of the sampling link corresponding to the first operating data; the first operating data includes at least one of voltage, temperature, current, power and operating status, and the first link element information includes communication verification information, status information of the analog front-end chip, fault diagnosis information and sampling timing information.

[0068] The first operating data includes at least one of voltage, temperature, current, power, and operating condition. The operating condition may include at least one of contactor status, equalization status, and thermal management status. For example, voltage may be the voltage of a battery cell, the voltage of a series-connected individual cell, the voltage of the battery pack, the total voltage of the battery cluster, the voltage of the cabinet, etc.; similarly, current may be the current of the aforementioned battery cell, battery cluster, etc. Temperature may be the temperature collected at a location such as a battery cell, battery module, copper busbar, sampling board, or ambient environment. Power may be the power of the energy storage converter.

[0069] Simultaneously, the first link element information corresponding to the first running data is acquired. This first link element information includes communication verification information, analog front-end chip status information, fault diagnosis information, and sampling timing information. Communication verification information includes cyclic redundancy check, data packet error check, frame structure check results, frame sequence number, frame loss flag, and duplicate frame flag. Analog front-end chip status information includes conversion completion flag, ADC busy status, ADC timeout status, diagnostic register read value, reference source operating status, and internal self-test results. Fault diagnosis information includes NTC open circuit flag, NTC short circuit flag, sampling line open circuit flag, voltage sampling line abnormality diagnosis results, and connector poor contact suspected flag. Sampling timing information includes sampling timestamp, sampling period, battery monitoring unit upload delay, and BCU aggregation delay.

[0070] S202, the validity of the first running data is verified based on the first link element information to obtain the validity verification result corresponding to the first running data.

[0071] In this embodiment of the application, the validity of the first running data is verified based on the first link element information to obtain the validity verification result corresponding to the first running data. The validity verification result includes whether the first running data is valid or invalid.

[0072] The first link metadata can be compared with a preset invalid rule base. If the first link metadata matches the preset invalid rule base, the validity verification result corresponding to the first running data is determined to be invalid. If the first link metadata does not match the preset invalid rule base, the validity verification result corresponding to the first running data is determined to be valid. For example, the preset invalid rule base may include link metadata such as CRC / PEC / frame structure verification failure, AFE conversion incomplete, sampling timeout, sampling process interruption, reference source malfunction, ADC critical fault, internal self-test failure, missing sampling timestamp, and sampling period severely out of bounds.

[0073] S203, Based on the validity verification results corresponding to the first operating data, determine the thermal runaway diagnosis results of the energy storage system.

[0074] In this embodiment of the application, if the validity verification result corresponding to the first operating data indicates that the first operating data is valid, the first target evaluation value corresponding to the first operating data can be determined, and the thermal runaway diagnosis result of the energy storage system can be determined based on the first target evaluation value and the first preset evaluation threshold.

[0075] In some possible implementations, if the validity verification result indicates that the first running data is invalid, a measurement link failure handling, re-acquisition, or degradation strategy can be initiated.

[0076] In the aforementioned diagnostic method for energy storage systems, first operating data of the energy storage system and first link element information of the sampling link corresponding to the first operating data are acquired. The validity of the first operating data is verified based on the first link element information to obtain the validity verification result corresponding to the first operating data. Based on the validity verification result corresponding to the first operating data, the thermal runaway diagnostic result of the energy storage system is determined. The first operating data includes at least one of voltage, temperature, current, power, and operating condition status. The first link element information includes communication verification information, status information of the simulated front-end chip, fault diagnosis information, and sampling timing information. This application embodiment simultaneously acquires the first operating data of the energy storage system and the corresponding first link element information, no longer relying solely on battery operating data such as voltage and temperature for thermal runaway diagnosis. It can incorporate abnormal information at the sampling link level, such as sampling communication, simulated front-end hardware, wiring harness faults, and sampling timing, into the validity verification process of the first operating data. This enables joint judgment of the sampling link status and battery operating data, solving the problem that traditional solutions cannot distinguish between sampling link faults and actual battery thermal runaway risks, and providing a complete input basis for subsequently suppressing false thermal runaway reports.

[0077] Figure 3 This is a schematic diagram of the first process of a method for determining the diagnosis result of thermal runaway in one embodiment, as shown below. Figure 3 As shown, this application embodiment relates to a possible implementation of how to determine the thermal runaway diagnosis result of an energy storage system based on the validity verification result, including the following steps:

[0078] S301, if the validity verification result corresponding to the first running data indicates that the first running data is valid, determine the first target evaluation value corresponding to the first running data.

[0079] In the embodiments of this application, combined with Figure 4 As shown, when the validity verification result indicates the first running data, the preset initial evaluation value can be adjusted based on the preset scoring rules to obtain an intermediate evaluation value, which is then used as the first target evaluation value.

[0080] In some possible implementations, determining the first target evaluation value corresponding to the first running data includes: adjusting the preset initial evaluation value based on preset scoring rules to obtain an intermediate evaluation value; and limiting the intermediate evaluation value based on a preset evaluation range to obtain the first target evaluation value.

[0081] The first target evaluation value can be determined by score=clamp(100-Σw_i, 0, 100). Here, w_i is the deduction weight corresponding to each preset scoring rule, the preset initial evaluation value is 100, and clamp means truncating the target evaluation value to the preset evaluation range of [0, 100]. This can both perform weight deduction on various soft anomalies to achieve reliable quantification and limit the first target evaluation value to a reasonable range, preventing the first target evaluation value from overflowing out of bounds, ensuring that the output result of the first target evaluation value is stable and controllable, and providing a standardized quantitative indicator for subsequent threshold comparison.

[0082] The preset scoring rules may include: sampling period deviating from the nominal range, frame loss, duplicate frames, abnormal frame sequence numbers, reuse of the first sample after switching (the current data is the first running data after the channel has just completed the switch, which is prone to ghosting values) or sampling starting before the stable waiting time is met after the channel has completed the switch, slightly suspicious diagnosis (such as suspected open line / short circuit), the jump of the first running data between two adjacent times exceeds the physical limit, neighborhood consistency failure (e.g., current is close to zero but the voltage of a single battery cell drops sharply, and the total voltage of the battery cluster does not change accordingly), cross-domain consistency failure, the sampling time of the first running data is within the window of known interference (e.g., within the window of contactor, equalization, PCS power step, etc.), poor consistency of running data repeatedly sampled from the same channel, and unstable first target evaluation value. Each preset scoring rule corresponds to a preset deduction weight.

[0083] Optionally, the preset initial evaluation value can be 100, 50, or 10, etc. If the preset initial evaluation value is 50, clamp means that the first target evaluation value is truncated to the preset evaluation range of [0, 50].

[0084] S302, determine the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and the first preset evaluation threshold.

[0085] In this embodiment of the application, when the first target evaluation value is greater than the first preset evaluation threshold, the first target feature is extracted from the first operating data. When at least one first sub-feature in the first target feature satisfies the review trigger condition, the review mode corresponding to at least one first sub-feature is determined. Multiple second operating data collected multiple times by the energy storage system and the second link element information of the sampling link corresponding to the multiple second operating data are obtained according to the review mode. The thermal runaway diagnosis result of the energy storage system is determined according to the first target evaluation value, the multiple second operating data and the second link element information.

[0086] In some possible implementations, if the first target evaluation value is less than or equal to the first preset evaluation threshold, new first operating data of the energy storage system and new first link element information of the sampling link corresponding to the new first operating data are obtained, and the thermal runaway diagnosis result of the energy storage system is determined based on the new first operating data and the new first link element information.

[0087] For example, the first target evaluation value is truncated to a preset evaluation range of [0, 100]. The first preset evaluation threshold can be 50. The purpose of the first preset evaluation threshold is to ensure that the credibility of the first running data meets the requirements.

[0088] In this embodiment, when the validity verification result corresponding to the first operating data indicates that the first operating data is valid, a first target evaluation value corresponding to the first operating data is determined. Based on the target evaluation value and a first preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined. This embodiment, based on the validity verification of the first operating data, introduces a first target evaluation value combined with a first preset evaluation threshold to conduct thermal runaway diagnosis. This differs from the traditional method of directly issuing alarms based on sampled numerical thresholds. By quantifying the first target evaluation value, the reliability of the first operating data is quantitatively measured, avoiding the direct output of thermal runaway diagnosis results from valid but low-reliability first operating data. This improves the precision of thermal runaway diagnosis and provides a quantitative basis for subsequent triggering of the review process.

[0089] Figure 5 This is a schematic diagram of the second process of a method for determining thermal runaway diagnosis results in one embodiment, as shown below. Figure 5 As shown, this application embodiment relates to a possible implementation of how to determine the thermal runaway diagnosis result of an energy storage system based on a first target evaluation value and a first preset evaluation threshold, including the following steps:

[0090] S401, if the first target evaluation value is greater than the first preset evaluation threshold, extract the first target feature from the first running data.

[0091] In this embodiment of the application, a first initial feature can be extracted from the first running data. If the duration for which the first initial feature does not trigger a preset clearing threshold meets the preset duration, the first initial feature is determined to be the first target feature.

[0092] In some possible implementations, if the first initial feature does not trigger the preset clearing threshold, then the first initial feature can be used as the first target feature, or the first initial feature can be directly used as the first target feature.

[0093] In some other possible implementations, the first initial feature can be used as the first target feature if the duration of the first initial feature meets the preset duration.

[0094] For example, the first initial feature includes, but is not limited to: static threshold feature, rate feature, gradient feature, trend feature, and confidence auxiliary feature.

[0095] Static threshold features can include the highest temperature, lowest voltage, battery cell overheating (temperature greater than the temperature threshold), battery cell undervoltage (voltage less than the voltage threshold), and significant out-of-bounds errors in the first operating data. Rate features can include the rate of temperature rise and the rate of voltage drop. Rate features preferentially use the regression slope, median slope, or robust estimation after statistical truncation within a sliding window (sorting the first operating data within the sliding window, removing a predetermined proportion of extremely large and extremely small samples, retaining only the intermediate normal samples, and then estimating the rate slope), rather than single-point differencing. Gradient features can include the temperature difference within the battery module, the temperature difference between the highest and average temperatures within the battery cluster, the voltage difference between battery cells, and the deviation of abnormal battery cells relative to their neighboring cells. The deviation can be the deviation corresponding to voltage, current, temperature, etc. Trend features can include whether the temperature rise is continuous, whether the voltage drop is continuous, the synchronicity of temperature rise and voltage drop, and the duration of abnormal features (such as overheating, large temperature rise rate). The credibility auxiliary features may include the proportion of the first running data within the preset window, the average target evaluation value within the preset window, the minimum target evaluation value within the preset window, the dispersion of the second running data obtained in the review mode, and the number of measurement link failures within the preset window.

[0096] S402, if at least one first sub-feature in the first target feature satisfies the verification triggering condition, determine the verification mode corresponding to at least one first sub-feature, and obtain multiple second operating data collected multiple times by the energy storage system according to the verification mode, as well as the second link element information of the sampling link corresponding to the multiple second operating data respectively.

[0097] In the embodiments of this application, such as Figure 6 As shown, if at least one of the first sub-features in the first target feature meets the verification trigger condition, the system transitions from the normal state to the suspicious state. Verification is performed in the suspicious state, and only after successful verification can the system enter the confirmation state. Verification failure / false positives result in the suppression alarm state; if the measurement link anomaly is clear, the system enters the link measurement fault state and can proceed to degraded operation. After completing risk mitigation measures in the confirmation state, the system enters the recovery state; the recovery state requires meeting the conditions of a conservative clearing window before entering the suppression alarm state. Link measurement faults return to the normal state when the measurement link is restored and continuous reliable data is normal; the suspicious state fault can directly return to the normal state after it is resolved.

[0098] The verification pattern corresponding to at least one first sub-feature can be determined as shown in Table 1.

[0099] Table 1

[0100]

[0101] Optionally, when the AFE status is suspicious, the transition timeout occurs, the reference source is abnormal, or the internal diagnostic flag changes, the AFE diagnostic register is read for verification. The purpose of the verification mode is to distinguish between sampling front-end faults and actual cell abnormalities. When the temperature jumps suddenly, the voltage exceeds the limit, or the sampling line is suspected of having poor contact, an open-circuit / short-circuit diagnosis is performed for verification. The purpose of the verification mode is to confirm the integrity of the sensor and wiring harness. When a single-point temperature or voltage spike occurs and the neighboring points do not change, the adjacent channels or adjacent AFEs are compared. The purpose of the verification mode is to identify local sampling faults by utilizing spatial neighborhood consistency. When the voltage of a single battery cell drops rapidly but the total voltage / current of the battery cluster does not change accordingly, the total voltage of the battery cluster, the current of the battery cluster, and the PCS power are compared to identify spurious voltage drops by utilizing cross-domain consistency at the energy storage cluster level.

[0102] S403, based on the first target evaluation value, multiple second operating data and second link element information, determine the thermal runaway diagnosis result of the energy storage system.

[0103] In this embodiment, the validity of the second operating data corresponding to the multiple second link element information can be verified according to the multiple second link element information to obtain the validity verification results corresponding to the multiple second operating data. When the validity verification result corresponding to the second operating data indicates that the second operating data is valid, and the second target evaluation value of the second operating data is greater than the first preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined according to the first target evaluation value and the second operating data.

[0104] In some possible implementations, when the validity verification result corresponding to the second operating data indicates that the second operating data is valid, and the second target evaluation value of the second operating data is greater than the first preset evaluation threshold, the corresponding second target features are extracted from multiple second operating data, the semantic similarity between the first target features and each second target feature is determined, and the thermal runaway diagnosis result of the energy storage system is determined based on each semantic similarity.

[0105] In this embodiment, when the first target evaluation value is greater than the first preset evaluation threshold, a first target feature is extracted from the first operating data. If at least one first sub-feature among the first target features meets the verification trigger condition, a verification mode corresponding to at least one first sub-feature is determined. Multiple second operating data collected from the energy storage system are obtained according to the verification mode, along with second link element information of the sampling links corresponding to the multiple second operating data. Based on the first target evaluation value, the multiple second operating data, and the second link element information, the thermal runaway diagnosis result of the energy storage system is determined. In this embodiment, after the first target feature is extracted when the first target evaluation value meets the first preset evaluation threshold condition, when the first sub-feature meets the verification trigger condition, the corresponding verification mode is triggered, and multiple sets of second operating data and second link element information are obtained. This realizes an active verification mechanism after the candidate thermal runaway risk is triggered, rather than directly outputting the thermal runaway diagnosis result. By acquiring multiple sets of second operating data through multiple collections for secondary verification, false features caused by single sampling spikes and transient interference can be effectively filtered out, avoiding direct output of thermal runaway alarms from single abnormal sampling, thus balancing thermal runaway risk identification capability and false alarm suppression capability.

[0106] Figure 7 This is a schematic diagram of the fourth process of a method for determining thermal runaway diagnosis results in one embodiment, as shown below. Figure 7 As shown, this application embodiment relates to a possible implementation of how to determine the thermal runaway diagnosis result of an energy storage system based on multiple second operating data and second link element information, including the following steps:

[0107] S501, based on multiple second link element information, the validity of the second running data corresponding to the multiple second link element information is verified respectively, and the validity verification results corresponding to the multiple second running data are obtained.

[0108] In the embodiments of this application, the specific implementation method can be found in S202 above.

[0109] S502, when the validity verification result corresponding to the second operating data indicates that the second operating data is valid, and the second target evaluation value of the second operating data is greater than the first preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and multiple second operating data.

[0110] In this embodiment, a second target feature can be extracted from the second operating data, and at least one second sub-feature that meets the review triggering condition can be determined from the second target feature. A first number of at least one first sub-feature whose type is consistent with the type of at least one second sub-feature can be determined. If the target ratio of the first number to the second number is greater than the first preset ratio, the thermal runaway diagnosis result of the energy storage system can be determined based on the first target evaluation value and multiple second operating data. The second number is the number of second operating data that are valid and whose second target evaluation value is greater than the first preset evaluation threshold.

[0111] For example, the first preset ratio is three-fifths, that is, the first number of the first sub-features that trigger the verification mode in the first operating data and the second sub-features that trigger the verification mode in multiple second operating data must be greater than three-fifths. Based on the first target evaluation value and multiple second operating data, the thermal runaway diagnosis result of the energy storage system can be determined.

[0112] In some possible implementations, when the validity verification result corresponding to the second operating data indicates that the second operating data is valid, and the second target evaluation value of the second operating data is greater than the first preset evaluation threshold, multiple second operating data are filtered according to the first target evaluation value, and the thermal runaway diagnosis result of the energy storage system is determined based on the filtered second operating data.

[0113] In this embodiment, based on multiple second link element information, the validity of the second operating data corresponding to each of the multiple second link element information is verified to obtain validity verification results for the multiple second operating data. When the validity verification results for the second operating data indicate that the second operating data is valid, and the target evaluation value of the second operating data is greater than a first preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and the multiple second operating data. In this embodiment, each set of second operating data obtained through verification is also validated in conjunction with the corresponding second link element information. Only second operating data that simultaneously meets the requirements of data validity and a second target evaluation value exceeding the first preset evaluation threshold is selected for subsequent diagnosis. This avoids interference from invalid verification samples caused by communication anomalies or sampling hardware failures during the verification process, ensuring the reliability of the verification samples involved in the thermal runaway determination, preventing invalid verification samples from interfering with the final diagnostic conclusion, and improving the reliability of the output data in the verification process.

[0114] Figure 8 This is a schematic diagram of the fifth step in the method for determining the diagnosis result of thermal runaway in one embodiment, as shown below. Figure 8 As shown, this application embodiment relates to a possible implementation of how to determine the thermal runaway diagnosis result of an energy storage system based on a first target evaluation value and multiple second operating data, including the following steps:

[0115] S601, extract the corresponding second target features from multiple second running data, and determine at least one second sub-feature from each second target feature that satisfies the review triggering condition.

[0116] In the embodiments of this application, the specific implementation method can be found in S401 above.

[0117] S602, determine a first number of types that are consistent with the type of at least one first sub-feature and at least one second sub-feature.

[0118] In this embodiment of the application, a first number is determined where the type of at least one first sub-feature is consistent with the type of at least one second sub-feature. For example, the first sub-feature that triggers the verification mode in the first target feature is a voltage / temperature change in a battery cell, but without a significant power change. There are six second sub-features that trigger the verification mode in the second target feature, of which four are also voltage / temperature changes in a battery cell, but without a significant power change. Therefore, the first number is four.

[0119] S603, if the target ratio of the first quantity to the second quantity is greater than the first preset ratio, determine the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and multiple second operating data; the second quantity is the number of valid second operating data whose second target evaluation value is greater than the first preset evaluation threshold.

[0120] In this embodiment of the application, if the target ratio of the first quantity to the second quantity is greater than the first preset ratio, and if the first target evaluation value is greater than the second preset evaluation threshold, then the thermal runaway diagnosis result of the energy storage system is determined based on multiple second operating data.

[0121] In some possible implementations, when the target ratio is greater than the second preset ratio, since the second preset ratio is greater than the first preset ratio, the thermal runaway diagnosis result of the energy storage system can be determined based on multiple second operating data as long as the first target evaluation value is greater than the first preset evaluation threshold and less than or equal to the second preset evaluation threshold.

[0122] In this embodiment, a second target feature is extracted from the second operating data, and at least one second sub-feature satisfying the review triggering condition is determined from the second target feature. A first quantity whose type is consistent with the type of at least one first sub-feature is determined. If the target ratio of the first quantity to the second quantity is greater than a first preset ratio, the thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and the second operating data. This embodiment statistically analyzes the first quantity in the second operating data that is consistent with the type of the first sub-feature, and combines it with the second quantity to make a ratio judgment, achieving a statistical feature judgment similar to K-of-M, reducing the impact of single-point transient anomalies on the diagnosis result, and reducing misjudgments of thermal runaway caused by accidental interference.

[0123] In one embodiment, if the target ratio of the first quantity to the second quantity is greater than a first preset ratio, the thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and the second operating data, including:

[0124] In the first scenario: when the target ratio is greater than the second preset ratio, and the first target evaluation value is greater than the first preset evaluation threshold and less than or equal to the second preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on the second operating data; the second preset ratio is greater than the first preset ratio.

[0125] The second scenario: When the target ratio is greater than the first preset ratio and the first target evaluation value is greater than the second preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on the second operating data.

[0126] Optionally, for example, the first preset ratio is three-fifths, the second preset ratio can be four-fifths, or the second preset ratio can be two-thirds; the first preset ratio can be one-half, and the second preset ratio can be two-thirds, as long as the second preset ratio is greater than the first preset ratio. This application embodiment does not impose specific restrictions on this.

[0127] In this embodiment of the application, when the target ratio is greater than the second preset ratio and the first target evaluation value is greater than the first preset evaluation threshold and less than or equal to the second preset evaluation threshold, or when the target ratio is greater than the first preset ratio and the first target evaluation value is greater than the second preset evaluation threshold, the data consistency type of the second operating data can be determined. If the data consistency type belongs to the preset consistency type set, the thermal runaway diagnosis result is determined to be that the energy storage system does not have a thermal runaway anomaly. If the data consistency type does not belong to the preset consistency type set, the thermal runaway diagnosis result is determined to be that the energy storage system has a thermal runaway anomaly.

[0128] The first and second preset evaluation thresholds categorize the reliability of the first operational data into three levels: low, medium, and high. When the target ratio is greater than the second preset ratio, and the first target evaluation value is greater than the first preset evaluation threshold but less than or equal to the second preset evaluation threshold (i.e., the reliability of the first operational data is medium), the target ratio needs to be greater than a relatively stringent second preset ratio to balance false alarm suppression. When both the target ratio and the first target evaluation value are greater than the first preset ratio (i.e., the reliability of the first operational data is high), the target ratio only needs to be greater than either of the first preset ratios to ensure response speed.

[0129] In this embodiment, different target ratio judgment conditions are matched according to different threshold ranges in which the first target evaluation value is located. Different upgrade thresholds are set for the first operating data with different confidence levels. When the first target evaluation value is in the medium range, a higher second preset ratio is used as the judgment condition. The alarm upgrade threshold is increased for the first operating data with medium confidence, further suppressing false alarms caused by medium confidence samples, while taking into account the diagnostic flexibility of samples with different risk levels. For high confidence scenarios where the first target evaluation value is greater than the second preset evaluation threshold, diagnosis is directly carried out based on the second operating data under the condition of meeting the basic first preset ratio. This ensures the diagnostic response speed in real thermal runaway scenarios, avoids excessive verification causing thermal runaway alarm delay, and achieves a balance between false alarm suppression and alarm response timeliness.

[0130] In an exemplary embodiment, the above-mentioned determination of the thermal runaway diagnosis result of the energy storage system based on the second operating data includes the following steps: determining the data consistency type of multiple second operating data; if the data consistency type belongs to a preset consistency type set, then the thermal runaway diagnosis result is determined to be that the energy storage system does not have a thermal runaway anomaly; if the data consistency type does not belong to the preset consistency type set, then the thermal runaway diagnosis result is determined to be that the energy storage system has a thermal runaway anomaly.

[0131] In the embodiments of this application, the preset consistency type set is shown in Table 2.

[0132] Table 2

[0133]

[0134] In this embodiment, the data consistency type of multiple second operating data is determined. If the data consistency type belongs to a preset consistency type set, the thermal runaway diagnosis result is determined to be that the energy storage system does not have a thermal runaway anomaly. If the data consistency type does not belong to the preset consistency type set, the thermal runaway diagnosis result is determined to be that the energy storage system has a thermal runaway anomaly. This embodiment performs data consistency type judgment on multiple second operating data. When the performance of the reviewed sample data conforms to the preset consistency type set corresponding to the link fault, it is determined that there is no thermal runaway anomaly. This can identify false anomaly scenarios in the sampling link, such as large sampling dispersion and inability to reproduce features, and decouple the anomaly caused by the sampling link from the thermal runaway risk of the battery itself, further reducing the probability of false thermal runaway alarms.

[0135] In one exemplary embodiment, the diagnostic method for the energy storage system further includes:

[0136] If the target ratio is less than or equal to the first preset ratio, the thermal runaway diagnosis result is determined to be that the energy storage system does not have thermal runaway anomaly; or, if the feature representing link failure in the second target feature is stronger than the feature representing thermal runaway failure in the second target feature, the thermal runaway diagnosis result is determined to be that the energy storage system does not have thermal runaway anomaly.

[0137] In this embodiment, if the target ratio is less than or equal to the first preset ratio, it means that the original abnormal characteristics cannot be reproduced by multiple verification samples, and it is directly determined that there is no thermal runaway anomaly. At the same time, a fault evidence comparison logic is set up to count the total weight of suspected faults and large discrete link fault evidence reported by the second link element information in the second operating data, as well as the total weight of thermal runaway characteristic evidence such as temperature rise and pressure drop. When the weight of link fault evidence is greater than the weight of thermal runaway evidence, it is considered that the link fault characteristics are dominant, and it is determined that there is no thermal runaway anomaly in the energy storage system.

[0138] In this embodiment, two judgment paths are set up to determine the absence of thermal runaway anomalies. When the proportion of samples meeting the conditions in the valid review samples is insufficient, or when the link failure characteristics in the review samples are stronger than the thermal runaway failure characteristics, it is directly determined that there is no thermal runaway anomaly. This can directly suppress alarms when the statistical voting is not up to standard or the evidence is more biased towards the sampling failure, and avoid outputting thermal runaway anomaly diagnosis results when the evidence chain is biased towards the sampling link failure, thereby further enhancing the filtering capability of false thermal runaway signals.

[0139] In an exemplary embodiment, extracting a first target feature from the first running data includes: extracting a first initial feature from the first running data; if the duration for which the first initial feature does not trigger a preset clearing threshold meets a preset duration, determining the first initial feature as the first target feature.

[0140] Optionally, different types of first initial features can correspond to different preset durations, or they can be the same preset duration. For example, the preset duration can be 5 seconds, 7 seconds, 10 seconds, etc.

[0141] Optionally, different types of first initial features correspond to different preset clearing thresholds. For example,

[0142] In this embodiment, the first initial feature is extracted from the first running data based on the above method. The first initial feature is only determined to be the first target feature if the duration of the duration for which the first initial feature fails to meet the preset clearing threshold reaches a preset duration. This filters out transient spike features with very short durations and excludes transiently changing interference signals from the first target feature. This avoids interference features that appear and disappear instantaneously and then disappear easily triggering the review process, reduces unnecessary review actions, and lowers the computation and communication overhead of the BMS and communication link.

[0143] In an exemplary embodiment, within a short time window following a power step in the PCS or the contactor action of a battery cluster, a single cell voltage in the first operational data acquired by an energy storage cabinet experiences a momentary drop. A significant voltage drop rate characteristic is calculated based on single-point differential analysis. According to traditional diagnostic methods, this voltage drop rate characteristic can easily be combined with temperature characteristics to directly trigger a thermal runaway warning.

[0144] The diagnostic method for energy storage systems provided in this application is used to acquire first operating data and corresponding first link element information. The first link element information is used to identify that the current sampling occurs within a known interference window, such as a power step in the PCS or contactor action in the battery cluster. The CRC check result, frame number, and sampling period in the sampling timing information are read from the communication verification information. Simultaneously, the total voltage of the battery cluster in the first operating data is extracted for cross-domain consistency verification. After verification, the instantaneous drop in individual cell voltage is not reflected in the total voltage of the battery cluster. A further review mode is executed to acquire multiple sets of second operating data and corresponding second link element information. The re-sampled second operating data returns to the normal range. Based on this, the first target evaluation value corresponding to the first operating data is deducted, reducing the sample reliability. The thermal runaway diagnosis result is classified as a suppressed alarm or a measured link fault, and event recording is completed. No escalation is performed to confirm the presence of thermal runaway anomalies. This embodiment demonstrates the interference window weighting mechanism for sampled link element information and the pseudo-anomaly identification logic based on cluster-level cross-domain consistency verification.

[0145] In an exemplary embodiment, during the operation of a battery module, the temperature probe acquires first operating data showing a momentary high temperature. The adjacent temperature points, battery cluster current, PCS power, and thermal management status within the extracted first operating data do not exhibit any change characteristics matching the high temperature. Using the diagnostic method for energy storage systems provided in this application, the validity of the first operating data is verified. If the first operating data is valid and the calculated first target evaluation value is greater than the first preset evaluation threshold, the first target feature is extracted. If the first sub-feature meets the review trigger condition, it enters the candidate state. The corresponding review mode is selected, and NTC open-line fault diagnosis, multiple repeated sampling of the same channel, and data comparison of adjacent channels are performed to obtain multiple sets of second operating data and their corresponding second link element information. The validity of the second operating data is verified and the second target feature is extracted. The review result outputs the fault diagnosis information of suspected open-line fault. The dispersion of the repeated sampling of multiple sets of second operating data is large, and the neighborhood consistency check fails. Among the second target features, the feature representing link fault is stronger than the feature representing thermal runaway fault. The thermal runaway diagnosis result is classified as a measurement link fault, and the wiring harness or sensor operation and maintenance check prompt is output. The confirmed diagnosis result of thermal runaway anomaly in the energy storage system is not output.

[0146] In an exemplary embodiment, the analog front-end chip uses multiplexing to collect multiple temperature and voltage channels. The first operating data output after channel switching is the first sample. Due to insufficient stabilization time of the analog path, the sampled values ​​show abnormal deviations. Using the diagnostic method for energy storage systems provided in this application embodiment, the multiplexed channel information in the first link element information is read, and the current first operating data is identified as the first sample after multiplexing switching. According to the preset scoring rules, the first target evaluation value is deducted, or the first operating data is directly excluded from the rate-type feature calculation. The corresponding review mode is triggered, and a second sampling is performed after discarding the first sample after multiplexing switching to obtain multiple sets of second operating data and corresponding second link element information. If the sampled values ​​of the second operating data obtained from the review return to normal, it is determined that the thermal runaway anomaly confirmation condition is not met, and no diagnostic result of thermal runaway anomaly in the energy storage system is output. Only events related to the stability of the multiplexed channel are recorded.

[0147] In an exemplary embodiment, when the energy storage system performs active or passive balancing, the balancing branch disturbs the sampling loop, causing some individual cell voltage sampling values ​​in the acquired first operating data to deviate. Using the diagnostic method for the energy storage system provided in this application embodiment, the validity verification result indicates that the first operating data is valid, the first target evaluation value is greater than the first preset evaluation threshold, the first target feature is extracted, and the first sub-feature meets the verification trigger condition; the verification mode of re-sampling after balancing is closed is selected, and multiple samplings are performed after briefly closing the corresponding balancing channel to obtain multiple sets of second operating data and their corresponding second link element information; after verification, after closing the balancing channel, the individual cell voltage in the second operating data returns to normal, and at the same time, the total voltage and cluster current of the battery cluster in the first operating data and the second operating data do not show abnormal change trends; after cross-domain consistency verification, it is determined that the abnormality is caused by balancing interference, and the confirmed diagnostic result of thermal runaway abnormality in the energy storage system is not upgraded and output.

[0148] In an exemplary embodiment, a battery module exhibits a continuous temperature rise and an abnormal drop in cell voltage. Adjacent temperature points within the first operating data rise synchronously, and the current of the battery cluster, the power of the PCS, and the physical laws of cell heat accumulation are matched. At the same time, the communication verification of the first link element information and the status information of the simulated front-end chip are all normal, and the multiple sets of second operating data obtained in the verification mode and the corresponding second link element information verification results are all normal. Using the diagnostic method for energy storage systems provided in this application, the validity of the first operating data is verified, and the calculated first target evaluation value is of high confidence level, greater than the second preset evaluation threshold. The first target feature is extracted, and the first sub-feature meets the review trigger condition. The review is performed and multiple sets of second operating data are obtained. The first number of first sub-features and second sub-features of the same type and the second number of valid second target evaluation values ​​greater than the first preset evaluation threshold are counted. The calculated target ratio is greater than the first preset ratio, which meets the K-of-M upgrade condition. The neighborhood and cross-domain consistency verification of multiple sets of second operating data is passed, and the thermal runaway diagnosis result is determined to be that the energy storage system has a thermal runaway anomaly. Based on the confirmed diagnosis result, the linkage response is performed, and control commands are output for PCS de-rating or shutdown, disconnection of cluster-level contactors, activation of thermal management forced operation, and fire pre-linkage. This application, through the confidence level differentiated upgrade logic, will not cause a significant delay in the response to the real thermal runaway risk due to the review process.

[0149] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0150] Based on the same inventive concept, this application also provides an energy storage system for implementing the diagnostic method for the energy storage system described above. The solution provided by this energy storage system is similar to the solution described in the above method; therefore, the specific limitations in one or more energy storage system embodiments provided below can be found in the limitations of the diagnostic method for the energy storage system described above, and will not be repeated here.

[0151] In one exemplary embodiment, such as Figure 9 As shown, an energy storage system is provided, which includes a battery management system, the battery management system including:

[0152] The acquisition module 11 is used to acquire the first operating data of the energy storage system and the first link element information of the sampling link corresponding to the first operating data; the first operating data includes at least one of voltage, temperature, current, power and operating status, and the first link element information includes communication verification information, status information of the analog front-end chip, fault diagnosis information and sampling timing information;

[0153] Verification module 12 is used to verify the validity of the first running data based on the first link element information, and obtain the validity verification result corresponding to the first running data;

[0154] The determination module 13 is used to determine the thermal runaway diagnosis result of the energy storage system based on the validity verification result corresponding to the first operating data.

[0155] In an exemplary embodiment, the determining module 13 is configured to determine a first target evaluation value corresponding to the first operating data when the validity verification result corresponding to the first operating data indicates that the first operating data is valid; and determine the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and a first preset evaluation threshold.

[0156] In an exemplary embodiment, the determining module 13 is configured to: extract a first target feature from the first operating data when the first target evaluation value is greater than a first preset evaluation threshold; determine a verification mode corresponding to at least one first sub-feature when at least one first sub-feature in the first target feature satisfies the verification trigger condition; acquire multiple second operating data collected multiple times from the energy storage system according to the verification mode, and second link element information of the sampling links corresponding to the multiple second operating data respectively; and determine the thermal runaway diagnosis result of the energy storage system according to the first target evaluation value, the multiple second operating data and the second link element information.

[0157] In an exemplary embodiment, the determining module 13 is configured to perform validity verification on the second operating data corresponding to the multiple second link element information according to the multiple second link element information, and obtain the validity verification results corresponding to the multiple second operating data; when the validity verification results corresponding to the second operating data indicate that the second operating data is valid, and the second target evaluation value of the second operating data is greater than the first preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined according to the first target evaluation value and the second operating data.

[0158] In an exemplary embodiment, the determining module 13 is configured to extract corresponding second target features from the second operating data, and determine at least one second sub-feature that satisfies the review triggering condition from each second target feature; determine a first number whose type of at least one first sub-feature is consistent with the type of at least one second sub-feature; and, if the target ratio of the first number to the second number is greater than a first preset ratio, determine the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and the second operating data; the second number is the number of second operating data that are valid and whose second target evaluation value is greater than the first preset evaluation threshold.

[0159] In an exemplary embodiment, the determining module 13 is used to determine the thermal runaway diagnosis result of the energy storage system based on multiple second operating data when the target ratio is greater than the second preset ratio and the first target evaluation value is greater than the first preset evaluation threshold and less than or equal to the second preset evaluation threshold; the second preset ratio is greater than the first preset ratio.

[0160] In an exemplary embodiment, the determining module 13 is used to determine the thermal runaway diagnosis result of the energy storage system based on multiple second operating data when the target ratio is greater than a first preset ratio and the first target evaluation value is greater than a second preset evaluation threshold.

[0161] In an exemplary embodiment, the determining module 13 is used to determine the data consistency type of multiple second operating data; if the data consistency type belongs to a preset consistency type set, the thermal runaway diagnosis result is determined to be that the energy storage system does not have a thermal runaway anomaly; if the data consistency type does not belong to the preset consistency type set, the thermal runaway diagnosis result is determined to be that the energy storage system has a thermal runaway anomaly.

[0162] In an exemplary embodiment, the determining module 13 is configured to determine that the thermal runaway diagnosis result is that the energy storage system does not have a thermal runaway anomaly if the target ratio is less than or equal to a first preset ratio; or, if the feature representing link failure in the second target feature is stronger than the feature representing thermal runaway failure in the second target feature, then determine that the thermal runaway diagnosis result is that the energy storage system does not have a thermal runaway anomaly.

[0163] In an exemplary embodiment, the determining module 13 is used to adjust the preset initial evaluation value based on the preset scoring rules to obtain an intermediate evaluation value; and to perform amplitude limiting processing on the intermediate evaluation value based on the preset evaluation range to obtain a first target evaluation value.

[0164] In an exemplary embodiment, the determining module 13 is used to extract a first initial feature from the first running data; if the duration for which the first initial feature does not trigger a preset clearing threshold meets the preset duration, the first initial feature is determined to be a first target feature.

[0165] The modules in the aforementioned battery management system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0166] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores data related to diagnostic methods for energy storage systems. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a diagnostic method for an energy storage system.

[0167] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0168] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above method embodiments.

[0169] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above method embodiments.

[0170] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of any of the above method embodiments.

[0171] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0172] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0173] 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 application.

[0174] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. 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 application should be determined by the appended claims.

Claims

1. A diagnostic method for an energy storage system, characterized in that, The diagnostic methods for the energy storage system include: Acquire first operating data of the energy storage system, and first link element information of the sampling link corresponding to the first operating data; the first operating data includes at least one of voltage, temperature, current, power and operating status, and the first link element information includes communication verification information, status information of the analog front-end chip, fault diagnosis information and sampling timing information; The validity of the first running data is verified based on the first link meta-information to obtain the validity verification result corresponding to the first running data. Based on the validity verification results corresponding to the first operating data, the thermal runaway diagnosis results of the energy storage system are determined.

2. The diagnostic method for an energy storage system according to claim 1, characterized in that, The step of determining the thermal runaway diagnosis result of the energy storage system based on the validity verification result corresponding to the first operating data includes: If the validity verification result corresponding to the first running data indicates that the first running data is valid, the first target evaluation value corresponding to the first running data is determined; The thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and the first preset evaluation threshold.

3. The diagnostic method for an energy storage system according to claim 2, characterized in that, The step of determining the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and the first preset evaluation threshold includes: If the first target evaluation value is greater than the first preset evaluation threshold, the first target feature is extracted from the first running data; If at least one first sub-feature in the first target feature satisfies the review triggering condition, the review mode corresponding to the at least one first sub-feature is determined, and multiple second operating data collected multiple times by the energy storage system and the second link element information of the sampling link corresponding to the multiple second operating data are obtained according to the review mode. Based on the first target evaluation value, multiple second operating data, and second link element information, the thermal runaway diagnosis result of the energy storage system is determined.

4. The diagnostic method for an energy storage system according to claim 3, characterized in that, The step of determining the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value, multiple second operating data, and second link element information includes: Based on multiple second link element information, the validity of the second running data corresponding to the multiple second link element information is verified respectively, and the validity verification results corresponding to the multiple second running data are obtained. When the validity verification result corresponding to the second operating data indicates that the second operating data is valid, and the second target evaluation value of the second operating data is greater than the first preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and multiple second operating data.

5. The diagnostic method for an energy storage system according to claim 4, characterized in that, The step of determining the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and multiple second operating data includes: Extract corresponding second target features from multiple second running data, and determine at least one second sub-feature from each second target feature that satisfies the review triggering condition; Determine a first number of instances where the type of the at least one first sub-feature is consistent with the type of the at least one second sub-feature; If the target ratio of the first quantity to the second quantity is greater than the first preset ratio, the thermal runaway diagnosis result of the energy storage system is determined based on the first target evaluation value and multiple second operating data; the second quantity is the number of valid second operating data whose second target evaluation value is greater than the first preset evaluation threshold.

6. The diagnostic method for an energy storage system according to claim 5, characterized in that, When the target ratio of the first quantity to the second quantity is greater than the first preset ratio, determining the thermal runaway diagnosis result of the energy storage system based on the first target evaluation value and multiple second operating data includes: When the target ratio is greater than the second preset ratio, and the first target evaluation value is greater than the first preset evaluation threshold and less than or equal to the second preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on multiple second operating data; the second preset ratio is greater than the first preset ratio.

7. The diagnostic method for an energy storage system according to claim 6, characterized in that, The diagnostic method for the energy storage system also includes: If the target ratio is greater than the first preset ratio and the first target evaluation value is greater than the second preset evaluation threshold, the thermal runaway diagnosis result of the energy storage system is determined based on multiple second operating data.

8. The diagnostic method for an energy storage system according to claim 6 or 7, characterized in that, The step of determining the thermal runaway diagnosis result of the energy storage system based on multiple sets of second operating data includes: Determine the data consistency type of multiple second running data; If the data consistency type belongs to a preset consistency type set, then the thermal runaway diagnosis result is determined to be that the energy storage system does not have thermal runaway anomalies. If the data consistency type does not belong to the preset consistency type set, then the thermal runaway diagnosis result is determined to be that the energy storage system has a thermal runaway anomaly.

9. The diagnostic method for an energy storage system according to claim 5, characterized in that, The diagnostic method for the energy storage system also includes: If the target ratio is less than or equal to the first preset ratio, then the thermal runaway diagnosis result is determined to be that the energy storage system does not have thermal runaway anomaly. Alternatively, if the feature representing link failure in the second target feature is stronger than the feature representing thermal runaway failure in the second target feature, then the thermal runaway diagnosis result is determined to be that the energy storage system does not have thermal runaway anomaly.

10. The diagnostic method for an energy storage system according to claim 2, characterized in that, Determining the first target evaluation value corresponding to the first running data includes: The initial evaluation value is adjusted based on the preset scoring rules to obtain the intermediate evaluation value; The intermediate evaluation value is subjected to amplitude limiting processing based on a preset evaluation range to obtain the first target evaluation value.

11. The diagnostic method for an energy storage system according to claim 3, characterized in that, The step of extracting the first target feature from the first running data includes: Extract the first initial feature from the first running data; If the duration for which the first initial feature does not trigger the preset clearing threshold meets the preset duration, the first initial feature is determined to be the first target feature.

12. An energy storage system, characterized in that, The energy storage system includes a battery management system, which includes: The acquisition module is used to acquire first operating data of the energy storage system and first link element information of the sampling link corresponding to the first operating data; the first operating data includes at least one of voltage, temperature, current, power and operating status, and the first link element information includes communication verification information, status information of the analog front-end chip, fault diagnosis information and sampling timing information; The verification module is used to verify the validity of the first running data based on the first link element information, and obtain the validity verification result corresponding to the first running data; The determination module is used to determine the thermal runaway diagnosis result of the energy storage system based on the validity verification result corresponding to the first operating data.