Energy storage cabinet operation monitoring system and method

Abstract

The present invention provides an energy storage cabinet operation monitoring system and method, the system includes at least one battery module group, the battery module group is composed of a plurality of single cells; a temperature monitoring module, including a plurality of temperature probes, configured to obtain temperature information of at least one battery module group; a battery management module, configured to monitor the electric energy data of the single cells, and to adjust the working parameters of the single cells; an environmental control module, configured to adjust the environmental control device in the energy storage cabinet; a network communication module, configured to realize the communication connection between the monitoring system and the operator server and / or the user client; a processor, respectively connected to the at least one battery module, the temperature monitoring module, the battery management module, and the environmental control module.

Description

Technical Field

[0001] The present invention relates to the field of battery energy storage, and in particular to a system and method for monitoring the operation of an energy storage cabinet. Background Art

[0002] An energy storage cabinet is a device that can store electrical energy. It can store electrical energy and release it for power supply when needed. It is usually used to provide backup power and stabilize grid voltage. However, during the operation of the energy storage cabinet, the internal temperature is prone to change due to the heat generated by the charging and discharging process of the battery pack and the influence of environmental factors. Excessive temperature will not only affect the performance and life of the battery, but may even cause safety accidents such as fire. Therefore, real-time temperature monitoring and early warning of the energy storage cabinet are of great significance to ensure the safe operation of the energy storage system.

[0003] Regarding how to conduct real-time temperature monitoring and early warning of energy storage cabinets. CN110444828B discloses a thermal runaway early warning method for a lithium phosphate battery safety management system for energy storage, and establishes an energy storage battery thermal runaway early warning system consisting of a remote server, a BMS main control system, and an energy storage battery pack. However, thermal runaway has already occurred, and the impact on the performance of the energy storage cabinet is difficult to avoid.

[0004] Therefore, it is hoped to provide an energy storage cabinet operation monitoring system and method to timely discover energy storage cabinet operation risks, thereby providing early warning and early intervention. Summary of the invention

[0005] One or more embodiments of the present specification provide an energy storage cabinet operation monitoring system, the energy storage cabinet operation monitoring system comprising at least one battery module group, the battery module group consisting of a plurality of single cells; a temperature monitoring module comprising a plurality of temperature probes configured to obtain temperature information of the at least one battery module group; a battery management module configured to monitor the electric energy data of the single cells and to regulate the working parameters of the single cells; an environmental control module configured to regulate the environmental control device within the energy storage pair; a network communication module configured to realize the communication connection between the monitoring system and the operator server and / or the user client; and a processor, respectively. The system is communicatively connected with the at least one battery module, the temperature monitoring module, the battery management module, and the environmental control module, and is configured to: determine sensitivity distribution data of at least one position in the energy storage cabinet, wherein the sensitivity distribution data characterizes the degree of influence of temperature on the at least one position in the energy storage cabinet; generate three-dimensional temperature distribution information based on the temperature information and the sensitivity distribution data; determine an operation risk data sequence of the energy storage cabinet based on the three-dimensional temperature distribution information and the electric energy data; and determine alarm information based on the operation risk data sequence, wherein the alarm information includes at least one of an alarm level and an alarm type.

[0006] One or more embodiments of the present specification provide a method for monitoring the operation of an energy storage cabinet, the method being executed by a processor, including: acquiring temperature information of at least one battery module group; determining sensitivity distribution data of at least one position in the energy storage cabinet, the sensitivity distribution data characterizing the degree of influence of temperature on the at least one position in the energy storage cabinet; generating three-dimensional temperature distribution information based on the temperature information and the sensitivity distribution data; determining an operation risk data sequence of the energy storage cabinet based on the three-dimensional temperature distribution information and the electric energy data; and determining alarm information based on the operation risk data sequence.

[0007] Through the aforementioned energy storage cabinet operation monitoring system and method, the operation risks at multiple time points in the future can be obtained, and alarm information can be determined based on the operation risks, so that the temperature anomaly of the energy storage cabinet can be discovered in a timely and effective manner, thereby prompting relevant staff to intervene in advance to reduce the adverse effects caused by the temperature anomaly. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 is an exemplary module diagram of an energy storage cabinet operation monitoring system according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of an energy storage cabinet operation monitoring method according to some embodiments of this specification;

[0011] Figure 3 is a schematic diagram of a method for generating three-dimensional temperature distribution information according to some embodiments of this specification;

[0012] Figure 4 is a schematic diagram of a method for determining alarm information according to some embodiments of this specification;

[0013] Figure 5 It is a schematic diagram of determining adjustment parameters according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] Figure 1 is an exemplary module diagram of an energy storage cabinet operation monitoring system according to some embodiments of this specification.

[0019] In some embodiments, the energy storage cabinet operation monitoring system 100 may include a temperature detection module 110 , a battery management module 120 , an environment control module 130 , a network communication module 140 , and a processor 150 .

[0020] The temperature monitoring module 11 is configured to obtain temperature information of the at least one battery module group. In some embodiments, the temperature detection module may include multiple temperature probes, which are distributed at at least one position in the energy storage cabinet to obtain temperature information at the corresponding position.

[0021] The battery management module 120 is configured to monitor the power data of the single battery and regulate the working parameters of the single battery.

[0022] The power data refers to the working data actually measured when the battery is working. For example, the power data may include at least one of the voltage, current, state of charge (SOC), and state of health (SOH) of the battery.

[0023] The operating parameters of the battery refer to parameter values ​​set when the battery is working. For example, the operating parameters of the battery may include at least one of charging current and voltage, and discharging power and discharging current.

[0024] In some embodiments, the processor can control the battery management module to adjust the operating parameters of the battery, thereby controlling the operating temperature of the battery module. For example, the charging voltage is usually appropriately reduced at high temperatures; reducing the discharge power or limiting the discharge current can reduce the thermal load of the battery and prevent overheating. In extreme cases, it may be necessary to temporarily stop discharging until the temperature returns to normal.

[0025] The environmental control module 130 is configured to regulate the environmental control device in the energy storage cabinet. In some embodiments, the environmental control module may include at least one of a heat dissipation device and a humidity control device. The heat dissipation device may include at least one of an air-cooled heat dissipation device and a water-cooled heat dissipation device, which is used to reduce the temperature of at least one battery module. The humidity control device may include at least one of a condensing initial device and an adsorption regeneration dehumidifier, which is used to reduce the humidity of the environment where the at least one battery module is located.

[0026] The network communication module 140 is configured to realize the communication connection between the monitoring system and the operator server and / or the user client.

[0027] The processor 150 is configured to determine the sensitivity distribution data of at least one position in the energy storage cabinet, generate three-dimensional temperature distribution information based on the temperature information and the sensitivity distribution data; determine the operation risk data sequence of the energy storage cabinet based on the three-dimensional temperature distribution information and the electric energy data; and determine the alarm information based on the operation risk data sequence.

[0028] In some embodiments, the processor is further configured to: determine sensitivity distribution data based on historical temperature information, historical power data, and current working status of at least one battery module; construct a three-dimensional model of the energy storage cabinet; and generate three-dimensional temperature distribution information based on the sensitivity distribution data, temperature information, and three-dimensional model.

[0029] In some embodiments, the processor is further configured to: determine an operation risk data sequence of at least one location based on three-dimensional temperature distribution information, power data and environmental data; determine a high-risk data sequence based on the operation risk data sequence and a risk coefficient threshold; and determine alarm information based on the high-risk data sequence.

[0030] In some embodiments, the processor is further configured to: in response to the alarm level being greater than the alarm threshold, send alarm information to the operator server and / or user client, and control the alarm device to send an alarm signal; in response to the alarm level being not greater than the alarm threshold and greater than the safety threshold, determine the adjustment parameters based on the operation risk data sequence and the electric energy data.

[0031] In some embodiments, the energy storage cabinet operation monitoring system may further include an airflow monitoring module 160 and an alarm device 170. The airflow monitoring module 160 is configured to monitor airflow data in the energy storage cabinet, and the alarm device 170 is configured to send an alarm signal.

[0032] For detailed information about the energy storage cabinet operation monitoring system and processor functions, please refer to Figure 2-Figure 5 Related description in .

[0033] It should be noted that the above description of the intelligent cabinet operation monitoring system and its modules is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem connected with other modules without deviating from this principle.

[0034] Figure 2 is an exemplary flow chart of an energy storage cabinet operation monitoring system according to some embodiments of this specification. In some embodiments, the process may be executed by the processor 150.

[0035] Step 210: Determine sensitivity distribution data of at least one position in the energy storage cabinet.

[0036] The sensitivity distribution data represents the sensitivity distribution of at least one position in the energy storage cabinet.

[0037] Sensitivity refers to the degree of influence of temperature on a certain position in the energy storage cabinet. Sensitivity can be expressed by level or value. For example, sensitivity can include different levels such as low sensitivity, medium sensitivity, and high sensitivity. For another example, sensitivity can be expressed by a value, and the larger the value, the higher the sensitivity. Generally, the more sensitive the position is, the more sensitive it is to temperature changes, and the temperature changes will be more obvious under the influence of temperature, while the components with low sensitivity will be more stable under temperature changes.

[0038] In some embodiments, the sensitivity distribution data may include the sensitivity of the energy storage cabinet material or the energy storage cabinet operation in response to changes in ambient temperature.

[0039] In some embodiments, the processor may determine at least one position in the energy storage cabinet as a position that needs to be monitored based on historical operation data of the energy storage cabinet. For example, a position prone to failure is determined based on historical operation data, and the position prone to failure and several positions around it are determined as positions that need to be monitored.

[0040] In some embodiments, the sensitivity distribution data may include at least one position and the sensitivity of the position. For example, the sensitivity distribution data may be expressed as (( , ),……,( , )),in, ,……, Indicates the A position can be represented by coordinates. ,……, Indicates the energy storage cabinet The sensitivity values ​​corresponding to each position.

[0041] In some embodiments, the processor may determine the sensitivity distribution data in a variety of ways. For example, the processor may predetermine the sensitivity of different locations based on the component types corresponding to the locations, such as the location of the single battery is highly sensitive, the location of the heat sink is medium sensitive, etc.

[0042] In some embodiments, the processor may determine the sensitivity of the corresponding position based on the status of the battery module and its related components.

[0043] In some embodiments, the processor may also determine the sensitivity distribution data based on the initial sensitivity distribution data and the sensitivity correction coefficient of at least one position in the energy storage cabinet.

[0044] More information on determining sensitivity distribution data can be found in this manual Figure 3 See the relevant instructions in .

[0045] Step 220: Generate three-dimensional temperature distribution information based on the temperature information and the sensitivity distribution data.

[0046] The three-dimensional temperature distribution information represents the spatial distribution of the temperature at at least one location inside the energy storage cabinet.

[0047] In some embodiments, the processor may generate three-dimensional temperature distribution information based on the temperature information and the sensitivity distribution data.

[0048] The temperature information refers to the temperature value of at least one location acquired by a temperature probe in the energy storage cabinet.

[0049] In some embodiments, the processor may determine the three-dimensional temperature distribution information in a variety of ways. For example, the processor may obtain a three-dimensional model of the energy storage cabinet, map the temperature information obtained by the temperature probe to the three-dimensional model, and thus obtain the three-dimensional temperature distribution information.

[0050] In some embodiments, the processor may also simplify the temperature information of the low-sensitivity position based on the sensitivity distribution data, and perform mapping based on the simplified temperature information to obtain three-dimensional temperature distribution information.

[0051] For more information on generating three-dimensional temperature distribution information, see this manual Figure 3 See the relevant instructions in .

[0052] Step 230: Determine the operation risk data sequence of the energy storage cabinet based on the three-dimensional temperature distribution information and the electric energy data.

[0053] The operation risk sequence refers to the operation risk data of the energy storage cabinet at multiple time points.

[0054] The operation risk data refers to risk data related to temperature anomaly. In some embodiments, the operation risk data may include at least one of a risk location, a risk type, and a risk coefficient.

[0055] In some embodiments, the processor can determine the operation risk data sequence of the energy storage cabinet in a variety of ways based on the three-dimensional temperature distribution information and the electric energy data. For example, the higher the temperature, the greater the voltage, and the greater the current at a certain location at a certain time point, the greater the operation risk of the location.

[0056] In some embodiments, the processor may determine an initial operation risk data sequence of the at least one location based on the three-dimensional temperature distribution information, the power data, and the environmental data, and determine a high-risk data sequence based on the initial operation risk sequence.

[0057] In some embodiments, the processor may also construct a diffusion characteristic map based on the initial operation risk data sequence, sensitivity distribution data, and airflow data, and estimate the comprehensive risk data sequence through the operation risk determination model based on the diffusion characteristic map.

[0058] For more information on determining operational risk data series, high risk data series, and comprehensive risk data series, please refer to this manual. Figure 4 See the relevant instructions in .

[0059] Step 240 , determining alarm information based on the operational risk data sequence.

[0060] Alarm information refers to information used to prompt that there are risks in the operation of the energy storage cabinet.

[0061] In some embodiments, the alarm information may include at least one of an alarm type and an alarm level.

[0062] The alarm type refers to the type of operation risk, which may include high temperature alarm, abnormal temperature gradient, uneven temperature distribution, and abnormal electrical performance caused by temperature. Among them, high temperature alarm means that the temperature exceeds the safe temperature threshold; abnormal temperature gradient means that an abnormal temperature gradient change will be measured, at which time there may be a problem of local overheating or abnormal heat dissipation in the energy storage cabinet; uneven temperature distribution means that the temperature difference between different positions in the energy storage cabinet is too large; abnormal electrical performance caused by temperature may include abnormal voltage, sudden current change, abnormal battery charge state, etc. caused by temperature change.

[0063] The alert level is used to reflect the degree of risk. The greater the risk, the greater the alert level.

[0064] In some embodiments, the processor may determine in a variety of ways based on the operational risk data sequence. For example, in response to the presence of a certain location risk level higher than a risk threshold, the processor may generate an alarm message, the greater the risk level, the higher the alarm level, and the alarm type may be determined based on the actual risk situation.

[0065] In some embodiments, the processor may determine a high-risk operation sequence based on the operation risk data sequence, and determine the alarm information based on the high-risk operation sequence.

[0066] For more information on determining alarm information, please refer to this manual Figure 4 See the relevant instructions in .

[0067] In some embodiments of the present specification, by determining the operation risk sequence of at least one position of the energy storage cabinet, the operation risks at multiple time points in the future can be obtained, and alarm information can be determined based on the operation risks, so that the temperature anomaly of the energy storage cabinet can be discovered in a timely and effective manner, thereby prompting relevant personnel to intervene in advance to reduce the adverse effects of the temperature anomaly.

[0068] Figure 3 1 is a schematic diagram of a method for generating three-dimensional temperature distribution information according to some embodiments of this specification. In some embodiments, the method may be executed by the processor 150.

[0069] In some embodiments, the processor can determine sensitivity distribution data 340 based on historical temperature information 310, historical power data 320 and current working status 330 of at least one battery module; construct a three-dimensional model 350 of the energy storage cabinet; and generate three-dimensional temperature distribution information 370 based on the sensitivity distribution data 340, temperature information 360 and the three-dimensional model 350 of the energy storage cabinet.

[0070] In some embodiments, the processor may determine the sensitivity of the corresponding position based on the state of the battery module and its related components, wherein the aforementioned state may include one of an operating state and a standby state.

[0071] As an example only, the processor may mark the location of the battery module and related components in the standby state as low sensitivity, and mark the location of the battery module and related components in the running state as high sensitivity. Among them, the sensitivity of the battery module in the standby state is higher than the related components in the standby state, and the sensitivity of the battery module in the running state is higher than the related components in the running state. The aforementioned related components refer to other components in the energy storage cabinet that do not belong to the battery module.

[0072] In some embodiments, for a battery module in operation, its sensitivity is positively correlated with the temperature influence coefficient of the battery module.

[0073] The temperature influence coefficient is an evaluation parameter for the effect of temperature on the performance of the battery module. It is used to characterize the comprehensive impact of temperature on the rate of change of battery module voltage and the rate of change of health status.

[0074] In some embodiments, the temperature influence coefficient of the battery module may be determined based on the voltage change rate, temperature change rate, and health state change rate of the battery module.

[0075] The voltage change rate refers to the change characteristics of the battery module voltage. The temperature change rate refers to the change characteristics of the battery module temperature. In some embodiments, the voltage change rate and the temperature change rate can be determined by the processor by performing first-order difference on the voltage data and the temperature data at each preset time point within the historical preset time.

[0076] The health status change rate refers to the change characteristics of the health status of the battery module, where the health status can be expressed as a percentage, and the higher the percentage value, the better the health status of the battery module. In some embodiments, the health status change rate can be determined by the processor by first-order difference of the health status at each preset time point within the historical preset time. The health status at each preset time point can be determined based on the health monitoring module set in the energy storage cabinet.

[0077] In some embodiments, the health detection module can monitor the voltage, current, temperature, internal resistance and other parameters of the battery module in the energy storage cabinet in real time, and process and analyze the collected data in combination with the analysis algorithm to evaluate the health status of the battery module and transmit the health status to the processor. As an example only, the aforementioned analysis algorithm may include at least one of internal resistance analysis, electrochemical impedance spectroscopy analysis, differential analysis, or other algorithms capable of performing corresponding processing.

[0078] Among them, the historical preset time and the preset time point can be preset based on prior experience and / or actual needs, and the processor can directly call the preset related data for the above processing.

[0079] In some embodiments, the processor can determine a first ratio feature based on the ratio of the voltage change rate and the temperature change rate, determine a second ratio feature based on the ratio of the health state change rate and the temperature change rate, and determine the temperature influence coefficient based on a weighted sum of the first ratio feature and the second ratio feature.

[0080] As an example only, the processor may determine the temperature influence coefficient by the following formula:

[0081]

[0082] in, Refers to the temperature influence coefficient; Refers to the rate of change of voltage; Refers to the rate of temperature change; Refers to the rate of change of health status; is the first ratio feature; is the second ratio feature; is a weight coefficient not less than 0, and may be preset based on prior experience and / or actual needs.

[0083] In some embodiments, the processor may also determine the sensitivity distribution data based on the initial sensitivity distribution data and the sensitivity correction coefficient of at least one position in the energy storage cabinet.

[0084] The initial sensitivity distribution data represents the degree to which at least one position of the energy storage cabinet is affected by temperature before the energy storage cabinet is put into use.

[0085] In some embodiments, the initial sensitivity distribution data may be determined based on known sensitivity of components and materials in the energy storage cabinet to temperature and experimental data, wherein the known sensitivity may be determined based on analysis of historical operating data of the energy storage cabinet, or may be pre-set based on prior experience.

[0086] The aforementioned experimental data refers to data obtained by performing a sensitivity test on the energy storage cabinet. In some embodiments, the processor can obtain multiple sets of experimental data for multiple energy storage cabinets of the same specifications. As an example only, during the experiment, the experimental environment can be controlled by an adjustable environmental chamber and / or a temperature control system, and the normal working range and the working environment of the energy storage cabinet at extreme temperatures can be simulated by changing the environmental parameters such as temperature, humidity, and airflow in the laboratory, and a temperature sensor and an electrical performance detection device are set at at least one position of the energy storage cabinet to capture the changes in the electrical performance of the energy storage cabinet with temperature.

[0087] For example, the processor can control the aforementioned adjustable environmental chamber and / or temperature control system, starting from a preset initial temperature, gradually increasing the temperature of the laboratory to the upper limit of the safe temperature, and obtaining the temperature data and electrical performance data of at least one position in the energy storage cabinet at at least one time point in real time through a temperature sensor and an electrical performance detection device; the processor can also simulate the temperature changes in the actual operation of the energy storage cabinet, quickly heat up and cool down, or maintain a constant temperature, and obtain the electrical performance data of the electrical performance of the energy storage cabinet under different temperature conditions. Among them, the initial temperature can be determined based on actual needs, for example, the initial temperature is set to room temperature, or the lowest operating temperature of the energy storage cabinet, etc.

[0088] The electrical performance data refers to data reflecting the electrical parameters of the energy storage cabinet during operation, and may include at least one of voltage, current, and battery charge state. In some embodiments, the electrical performance data may also include other parameters reflecting the electrical characteristics of the energy storage cabinet, which may be determined according to actual needs.

[0089] In some embodiments, the processor may process and analyze the temperature data and electrical performance data obtained from the experiment. For example, based on the temperature data and electrical performance data at at least one time point, a temperature change curve and a performance parameter change curve of the energy storage cabinet are obtained, and based on the aforementioned temperature change curve and performance parameter change curve, an initial sensitivity of at least one position in the energy storage cabinet is calculated.

[0090] In some embodiments, the processor may determine the initial sensitivity based on the known sensitivity of the components and materials of the energy storage cabinet to temperature and the impact quantification index. The impact quantification index is used to measure the impact of temperature on the performance of the battery module, and may be determined based on the percentage of battery module performance degradation caused by each 1°C increase in temperature.

[0091] In some embodiments, the processor may determine the initial sensitivity of at least one position of the energy storage cabinet by the following formula:

[0092]

[0093] in, Refers to the initial sensitivity, Refers to the known sensitivity, Refers to the quantitative indicators of impact, , is a coefficient and can be preset based on prior experience.

[0094] In some embodiments, the processor may determine initial sensitivity distribution data of the energy storage cabinet based on the initial sensitivity of at least one location.

[0095] In some embodiments, the processor may determine the sensitivity distribution data of the energy storage cabinet based on the initial sensitivity distribution data and historical maintenance data of the energy storage cabinet. For example, the processor may determine the sensitivity correction coefficient of the energy storage cabinet based on the historical maintenance data of the energy storage cabinet; determine the sensitivity at the current time point based on the sensitivity correction coefficient and the initial sensitivity, and then determine the sensitivity distribution data at the current time point.

[0096] In some embodiments, the processor can determine the fault events related to abnormal temperature based on the historical maintenance data of the energy storage cabinet, and obtain the specific location of the fault, temperature data, fault description and measures taken. If it is found that the fault at a certain location is directly related to the abnormal temperature, the sensitivity of the location is increased according to the preset rules. The preset rules may include increasing the sensitivity level, or increasing the sensitivity value according to a certain ratio, etc.

[0097] In some embodiments, the processor may determine a sensitivity correction factor based on fault data of at least one location of the energy storage cabinet. For example, the more faults directly related to temperature anomalies recorded at the location, the greater the sensitivity correction factor.

[0098] There are battery modules and related components in the energy storage cabinet. The location of the battery module is affected by the self-heating of the battery module when working and has dynamic temperature sensitivity, while the location of the related components does not have dynamic sensitivity.

[0099] In some embodiments, for a position without dynamic sensitivity, the processor may determine the sensitivity at the current time point based on the initial sensitivity and the sensitivity correction coefficient. For example, the processor may determine the sensitivity at the current time point by the following formula:

[0100]

[0101] in, Refers to the sensitivity corresponding to the position where there is no dynamic sensitivity; Refers to initial sensitivity; Refers to the sensitivity correction factor.

[0102] In some embodiments, for a location with dynamic sensitivity, the processor may determine the sensitivity at the current time point based on the initial sensitivity, the dynamic sensitivity, and the sensitivity correction coefficient. For example, the processor may determine the sensitivity at the current time point using the following formula:

[0103]

[0104] in, Refers to the sensitivity corresponding to the position where dynamic sensitivity exists; Refers to initial sensitivity; Refers to dynamic sensitivity; Refers to the sensitivity correction factor; , is a weighting coefficient, which can be preset based on prior experience.

[0105] The dynamic sensitivity may be determined based on the temperature influence coefficient, and detailed descriptions may be found in the foregoing description of this specification.

[0106] In some embodiments, the weighting coefficient is related to the usage time and the accumulated charge and discharge amount of the energy storage cabinet. For example, the longer the usage time and the greater the accumulated charge and discharge amount, The smaller the value, The larger the value.

[0107] In some embodiments of the present specification, obtaining the initial sensitivity distribution data of the energy storage cabinet is conducive to ensuring that more comprehensive sensitivity distribution data is obtained, thereby avoiding the problem of not being able to obtain data at some locations during the actual operation of the energy storage cabinet; correcting the sensitivity distribution data based on the fault data in the historical maintenance data can make the determined temperature sensitivity more consistent with the actual operating conditions, thereby better ensuring the accuracy of the sensitivity distribution data.

[0108] A 3D model is a digital representation of a virtual energy storage cabinet created using 3D computer graphics technology. The model can accurately and intuitively display the appearance, structure, internal components and spatial relationships of the energy storage cabinet.

[0109] In some embodiments, the aforementioned three-dimensional model may include at least one battery module of the energy storage cabinet, the layout of electrical components, etc.

[0110] In some embodiments, the processor may obtain a three-dimensional model of the energy storage cabinet through modeling software based on drawings related to the energy storage cabinet or on-site scanning data of the energy storage cabinet.

[0111] In some embodiments, the processor can obtain temperature information collected by each temperature probe, map the processed temperature information to the corresponding coordinates of the three-dimensional model according to the position of the temperature probe, and form an initial temperature distribution map; based on the aforementioned sensitivity distribution data, the initial temperature distribution map is further adjusted to obtain initial three-dimensional temperature distribution information.

[0112] In some embodiments, the processor may adjust the initial temperature distribution diagram based on the sensitivity distribution data of the energy storage cabinet. For example, for areas with a sensitivity higher than a first sensitivity threshold, more details and temperature gradient changes are retained; for areas with a sensitivity lower than a second sensitivity threshold, the temperature change display is appropriately simplified. The first sensitivity threshold is greater than the second sensitivity threshold, and the first sensitivity threshold and the second sensitivity threshold can be preset based on prior experience and / or actual needs.

[0113] As an example only, if the temperature change value is less than the change threshold (e.g., the temperature change range is 25°C-25.1°C, and the change threshold is 1°C), if the sensitivity of the area is higher than the first sensitivity threshold, 25°C-25.1°C is displayed in the three-dimensional temperature distribution information; if the sensitivity of the area is lower than the second sensitivity threshold, only 25°C is displayed in the three-dimensional temperature distribution information.

[0114] Adjusting the detail of temperature changes in three-dimensional temperature distribution information based on sensitivity can reduce interference data, reduce the amount of data processing, and thus improve processing efficiency, which is beneficial to ensuring the normal operation of the system when processor computing resources are limited.

[0115] By mapping the temperature data acquired by the temperature probe to the corresponding coordinates of the three-dimensional model, initial three-dimensional temperature distribution information with discrete temperature data can be obtained, and the processor can further process the discrete temperature data to obtain continuous data.

[0116] In some embodiments, the processor may use a variety of numerical analysis methods, such as Kriging interpolation and finite element method, to interpolate the temperature data acquired by the temperature probe, further refine the initial three-dimensional temperature distribution information, and generate continuous three-dimensional temperature distribution information.

[0117] In some embodiments, the three-dimensional temperature distribution information is also related to the importance of at least one position in the energy storage cabinet. For example, for a position whose importance is higher than a preset value, regardless of the sensitivity of the position, it should be highlighted in the three-dimensional temperature distribution information without simplifying its temperature change.

[0118] In some embodiments, the importance of at least one location can be determined in a variety of ways. For example, the processor can determine the initial importance of at least one location by obtaining a preset importance manually input, and determine the initial importance as the importance corresponding to the at least one location. For another example, the processor can modify the initial importance based on historical maintenance data to determine the importance.

[0119] As an example only, the processor can obtain at least one fault event corresponding to a certain location in the historical data, and determine at least one correction value of the importance based on the severity of the consequences corresponding to the at least one fault event. The higher the severity, the higher the corresponding correction value. The processor can determine the importance of the location based on the sum of the initial importance of the location and the at least one correction value of the importance.

[0120] Considering the importance of the location when generating the three-dimensional temperature distribution information can better display the temperature changes at important locations, so that the generated three-dimensional temperature distribution information can fully display the temperature conditions at important locations, which is conducive to more comprehensive and accurate determination of the risk conditions at different locations of the energy storage cabinet.

[0121] In some embodiments of the present specification, by constructing a three-dimensional model of the energy storage cabinet and generating three-dimensional temperature distribution information of the energy storage cabinet, the temperature condition of the energy storage cabinet can be reflected in more detail, thereby providing a more accurate reference for determining the risk conditions at different positions of the energy storage cabinet, which is conducive to better early warning based on risk conditions.

[0122] Figure 4 It is a schematic diagram of a method for determining alarm information according to some embodiments of this specification.

[0123] In some embodiments, the processor may also determine an operation risk data sequence 430 of at least one location based on the three-dimensional temperature distribution information 370, the power data 410, and the environmental data 420; determine a high-risk data sequence based on the operation risk data sequence 430 and a risk coefficient threshold; and determine alarm information based on the high-risk data sequence.

[0124] For more information about three-dimensional temperature distribution information and electrical energy data, see Figure 2 and related instructions.

[0125] Environmental data refers to various data related to the operating environment of the energy storage cabinet. In some embodiments, the environmental data may include temperature data, humidity data, etc. inside the energy storage cabinet and the external environment where the energy storage cabinet is located.

[0126] In some embodiments, environmental data can be acquired through sensors such as temperature sensors and humidity sensors.

[0127] The temperature and humidity fluctuations in the environment where the energy storage cabinet is located may affect the heat exchange efficiency and internal temperature distribution of the energy storage cabinet. For example, in a high temperature environment, the heat exchange rate between the energy storage cabinet and the outside world is reduced, causing heat accumulation inside the energy storage cabinet, which may make heat-sensitive areas more prone to overheating. Conversely, in a low temperature environment, the electrochemical reaction rate of the battery module is reduced, and the starting performance and charging efficiency are reduced, which may cause the performance of the battery module in the low temperature sensitive area to decay faster.

[0128] For example, in a high humidity environment, the performance of the insulation material inside the energy storage cabinet will be reduced, which may cause electrical failures. In a low humidity environment, static electricity is easily accumulated inside the energy storage cabinet, which may cause static electricity damage to electronic components.

[0129] Too high or too low ambient temperature and humidity will increase the operating risk of the energy storage cabinet. In order to accurately predict the operating risk, it is necessary to collect the environmental data of the energy storage cabinet so that the energy storage cabinet can make corresponding adjustments.

[0130] An operation risk data sequence refers to a sequence obtained by arranging multiple groups of operation risk data within a preset time. The preset time refers to a pre-specified time range for obtaining operation risk data. In some embodiments, the preset time can be set based on historical experience and / or actual needs. In some embodiments, the operation risk data sequence can include at least one operation risk data at the current and future time points.

[0131] In some embodiments, the operational risk data may be data of operational risks related to temperature. In some embodiments, the operational risk data may include at least one of a risk location, a risk type, and a risk coefficient.

[0132] The risk location refers to a specific location where the energy storage cabinet may have risks. In some embodiments, the risk location may be a position, coordinate, component, or area where risks may exist. For example, the risk location is heat sink 1. For another example, the risk location is area 2.

[0133] The risk type refers to the specific cause or nature of the risk. In some embodiments, the risk type may include temperature anomaly, local overheating, uneven temperature distribution, voltage anomaly, current mutation, etc.

[0134] The risk factor refers to data used to assess the severity of the risk. The risk factor can be represented by a numerical value, a level, a text, etc. In some embodiments, the risk factor can be determined based on the severity of the consequences caused by the abnormal situation. The more serious the consequences, the higher the risk factor.

[0135] In some embodiments, the processor may determine the operational risk data by receiving data from various sensors such as temperature sensors, humidity sensors, etc.

[0136] In some embodiments, the processor may determine the operation risk data sequence of at least one location in a plurality of ways based on the three-dimensional temperature distribution information, the power data, and the environmental data.

[0137] In some embodiments, the processor can construct a risk feature vector based on three-dimensional temperature distribution information, power data and environmental data, perform similarity search in an abnormal feature database based on the risk feature vector, obtain a reference risk feature vector whose similarity to the risk feature vector is greater than a similarity threshold, and determine a row risk data sequence based on a reference risk data sequence corresponding to the reference risk feature vector.

[0138] If there is no reference risk feature vector whose similarity with the risk feature vector is greater than the similarity threshold, it is considered that the energy storage cabinet can operate safely and no processing is required.

[0139] The abnormal feature database refers to a database used to store, index and query vectors. The abnormal feature database stores multiple reference risk feature vectors and their corresponding multiple reference risk data sequences.

[0140] The reference risk feature vector can be constructed based on historical three-dimensional temperature distribution information, historical power data and historical environmental data when the risk actually occurred in history. The reference risk data sequence can be determined based on the historical risk data sequence when the risk actually occurred in history, or it can be determined by manual annotation.

[0141] The similarity can be calculated by Euclidean distance, cosine similarity, etc. The similarity threshold can be manually preset.

[0142] The risk factor threshold is a value used to determine whether measures need to be taken for the risk. For example, when the risk factor exceeds the risk factor threshold, it means that measures need to be taken.

[0143] Risk Factor Threshold Risk factors can be expressed in numerical values, levels, text, etc.

[0144] In some embodiments, the risk factor threshold may be determined based on manual presets.

[0145] A high-risk data sequence refers to a sequence of risk data whose risk coefficient exceeds the risk coefficient threshold within a preset time period.

[0146] In some embodiments, the processor may determine the high-risk data sequence in a variety of ways based on the operational risk data and the risk factor threshold.

[0147] In some embodiments, the processor may determine an operating data sequence whose risk factor continuously exceeds a risk factor threshold within a preset time period as a high-risk data sequence.

[0148] The preset time period may be determined based on prior experience and / or actual demand.

[0149] In some embodiments, the processor may also determine the alarm information in a variety of ways based on the high-risk data sequence.

[0150] For detailed information about the alarm, see Figure 2 and related instructions.

[0151] In some embodiments, the processor may screen out risk positions in the operational risk data sequence whose weighted risk coefficients are greater than a risk coefficient threshold within a preset time period, and determine the risk type corresponding to the risk position as an alarm type.

[0152] For example, assuming that the operation risk data sequence includes operation risk data at multiple time points in the next hour, and the preset time period is the next 10 minutes, then within the next 10 minutes, the risk type corresponding to all risk positions whose weighted risk coefficients are greater than the risk coefficient threshold can be determined as an alarm type.

[0153] The weighted risk factor is an indicator that estimates the severity of the risk that may occur in a certain risk location in the future. In some embodiments, the weighted risk factor can be determined by weighted summing the operational risk factors of the same location at multiple time points. For example, it can be determined by the following formula:

[0154]

[0155] in, represents the weighted risk factor, From the present to the future A point in time, Indicates The weighting coefficient corresponding to each time point, Indicates In some embodiments, the weighting coefficient is negatively correlated to the distance between the corresponding time point and the current time point.

[0156] In some embodiments, the processor may determine the alarm coefficient based on the weighted risk coefficients corresponding to the risk locations. For example, the average of the weighted risk coefficients of the multiple risk locations may be used as the alarm coefficient.

[0157] In some embodiments, the processor may determine an alarm coefficient based on the weighted risk coefficient corresponding to the risk position screened out above; and determine an alarm level by querying a first preset table based on the alarm coefficient.

[0158] The first preset table refers to a table of correspondence between alarm coefficients and alarm levels. The preset table can be established based on manual preset.

[0159] In some embodiments, the processor may calculate the weighted risk coefficient of the risk position The average value is determined as the alarm coefficient.

[0160] Some embodiments of this specification dynamically monitor the operating risks of different locations of the energy storage cabinet through comprehensive analysis of multi-dimensional data, thereby improving the comprehensiveness and accuracy of risk identification. By screening high-risk data sequences and generating alarm information, false alarms and missed alarms can be reduced, and the reliability of alarms can be enhanced. Through comprehensive risk analysis at multiple locations and multiple time points, operation and maintenance decisions are optimized, the safety and reliability of the energy storage cabinet operation monitoring system are significantly improved, and operation and maintenance costs are reduced.

[0161] In some embodiments, the processor may also determine alarm information based on the importance of different positions of the energy storage cabinet and operational risk data.

[0162] For a detailed description of the importance of different positions in the energy storage cabinet, see Figure 3 and related instructions.

[0163] In some embodiments, the processor may further calculate the weighted risk factor of the risk position based on the above risk position. The alarm coefficient is determined by weighted summing the risk data corresponding to at least one risk location. The weight of the weighted summation is positively correlated to the importance of the risk location.

[0164] The importance of the risk position is determined in a similar manner to the importance of at least one position in the energy storage cabinet, see Figure 2 See the relevant instructions in .

[0165] In some embodiments of this specification, the alarm coefficient is calculated by assigning a weight coefficient according to the importance of each position, so that more important positions can receive more attention, thereby improving the accuracy of risk identification and significantly improving the safety and reliability of the energy storage cabinet operation monitoring system.

[0166] In some embodiments, the processor can also be configured to construct a diffusion characteristic map 450 based on the operation risk data sequence 430, the sensitivity distribution data 340, and the airflow data 440; based on the diffusion characteristic map 450, through the operation risk determination model 460, estimate the comprehensive risk data sequence 470.

[0167] The diffusion characteristic map refers to a graph structure that reflects the diffusion characteristics of temperature, airflow, etc. in the energy storage cabinet. In some embodiments, the diffusion characteristic map may include at least one node and at least one edge.

[0168] In some embodiments, the node 451 may include a temperature probe node. The node characteristics may include an operation risk data sequence, sensitivity distribution data, airflow data, etc. at the location of the temperature probe.

[0169] In some embodiments, the air flow data refers to the air flow conditions inside and outside the battery module, such as air flow speed, air flow area, etc. The air flow conditions inside and outside the battery module will affect the heat transfer and cooling efficiency of the battery module.

[0170] In some embodiments, the airflow data of the node can be obtained by an air sensor set at the node position.

[0171] For a detailed description of the sensitivity distribution data, see Figure 2 and related instructions.

[0172] In some embodiments, the diffusion characteristic map may include multiple groups of nodes, each group of nodes may correspond to a battery module, and each node in the same group of nodes may correspond to a temperature probe in the same battery module.

[0173] In some embodiments, nodes may be connected with edges.

[0174] In some embodiments, edges 452 may include intra-group edges and inter-group edges.

[0175] The intra-group edge is used to connect adjacent nodes within the same battery module whose distance is less than the distance threshold. The intra-group edge can reflect the heat conduction and airflow interaction between temperature probes that are close to each other in the same battery module.

[0176] The inter-group edge is used to connect nodes between different battery modules whose distance is less than the distance threshold. The inter-group edge can reflect the possible heat radiation between battery modules and the overall ambient temperature impact.

[0177] The aforementioned distance threshold may be determined based on prior experience and / or actual needs.

[0178] In some embodiments, the processor may also estimate a comprehensive operational risk data sequence based on the diffusion characteristic map and through an operational risk determination model.

[0179] The operation risk determination model refers to a model used to predict the operation risks of different positions of the energy storage cabinet. For example, the operation risk determination model can be a machine learning model.

[0180] In some embodiments, the operational risk determination model 460 may include a diffusion characteristic determination layer 460 - 1 and a risk data determination layer 460 - 2 .

[0181] The diffusion feature determination layer can output the risk diffusion features of the edges in the diffusion feature map based on the diffusion feature map. The risk diffusion feature refers to a quantified indicator that reflects the risk transmission status on each edge. For example, the risk diffusion feature can reflect the propagation path and intensity of the risk inside the energy storage cabinet.

[0182] The risk diffusion characteristics output by the diffusion characteristic determination layer can be used as the input of the risk data determination layer.

[0183] The risk data determination layer can determine the comprehensive operation risk data sequence based on risk diffusion characteristics, current and historical power data, and current and historical three-dimensional temperature distribution information.

[0184] The current and historical power data and the current and historical three-dimensional temperature distribution information are obtained in a similar way. Figure 2 For detailed information on how to obtain power data and three-dimensional temperature distribution information, see Figure 2and related instructions.

[0185] The comprehensive operation risk data refers to the operation risk data sequence of different positions of the energy storage cabinet determined based on the operation risk determination model. Similar to the above operation risk data, the comprehensive operation risk data may also include risk position, risk type, and risk coefficient.

[0186] For more information about comprehensive operational risk data, please refer to the relevant explanations of the above operational risk data.

[0187] In some embodiments, the diffusion feature determination layer may be a graph neural network model (Graph Neural Networks, GNN), and the risk data determination layer may be a recurrent neural network model (Recurrent Neural Network, RNN).

[0188] In some embodiments, the diffusion characteristic determination layer and the risk data determination layer may also be other models.

[0189] In some embodiments, the operational risk determination model may be obtained based on joint training of the diffusion feature determination layer and the risk data determination layer.

[0190] In some embodiments, the sample data for joint training includes sample diffusion feature maps, sample electrical energy data, and sample three-dimensional temperature information corresponding to the sample energy storage cabinet, and the label is a sample comprehensive risk sequence corresponding to the sample energy storage cabinet.

[0191] The sample diffusion feature map is input into the diffusion feature determination layer to obtain the risk diffusion feature; the risk diffusion feature is input into the risk data determination layer together with the sample electric energy data and the sample three-dimensional temperature distribution information to obtain the comprehensive risk data sequence output by the risk data determination layer.

[0192] Based on the comprehensive risk sequence and the comprehensive risk data sequence output by the risk data determination layer, a loss function is constructed, and the parameters of the diffusion feature determination layer and the risk data determination layer are updated synchronously. Through parameter updating, the trained diffusion feature determination layer and risk data determination layer are obtained.

[0193] In some embodiments, when the trained diffusion feature determination layer and risk data determination layer meet preset conditions, the model training ends. The preset conditions may be that the loss function result converges or is less than a preset threshold.

[0194] In some embodiments, the label may be determined by annotating experimental data.

[0195] Exemplarily, in the first step, a sample risk index may be determined through multiple experiments. The sample risk index refers to a sample parameter that may cause a risk to occur. For example, temperature exceeding the standard, voltage abnormality, current mutation, temperature gradient change of the battery module, etc. In some embodiments, the sample risk index may include a sample risk type.

[0196] In the second step, the sample operation risk coefficient can be determined according to the sample risk type and sample risk size, and the corresponding operation risk data at multiple time points constitute the sample comprehensive risk sequence.

[0197] In some embodiments, the sample operation risk coefficient can be determined according to the sample risk type and the sample risk size. For example, if the sample risk type is temperature exceeding the normal range, when the temperature exceeds the normal range by 1°C to 3°C, the sample risk coefficient is set to 20; when the temperature exceeds the normal range by 4°C to 5°C, the sample risk coefficient is set to 50; when the temperature exceeds the normal range by 6°C to 10°C, the sample risk coefficient is set to 80; when the temperature exceeds the normal range by more than 10°C, the sample risk coefficient is set to 100.

[0198] In some embodiments, the sample risk index and the sample risk coefficient may also be determined based on manual presets. For example, when a failure such as an energy storage cabinet overload power failure or an energy storage cabinet fire occurs in the past, the sample risk coefficient is set to 100.

[0199] The third step is to label the sample comprehensive risk sequence based on the sample risk type, sample risk coefficient, and sample risk position. In some embodiments, the labeling method can be manual labeling, automatic labeling, etc.

[0200] In some embodiments, the processor may determine the alarm information 480 based on the comprehensive risk data sequence 470. In some embodiments, the processor may determine the alarm information based on the comprehensive risk data sequence in a manner similar to the aforementioned manner of determining the alarm information based on the high risk data sequence, and for detailed description, please refer to the aforementioned related description.

[0201] In some embodiments of this specification, the multi-dimensional data such as the operation risk data sequence, sensitivity distribution data and airflow data are integrated through the diffusion characteristic diagram, so that the operation risk determination model can more effectively identify the risk propagation path and intensity of the internal space of the energy storage cabinet, and improve the evaluation of the risk diffusion characteristics. The energy storage cabinet operation monitoring system can provide more detailed and efficient risk assessment and prediction in a complex operating environment, greatly improving the safety and performance of the energy storage cabinet.

[0202] Figure 5 FIG. 1 is a schematic diagram of determining adjustment parameters according to some embodiments of this specification. Figure 5As shown, the method includes the following steps. In some embodiments, steps 510 to 522 can be executed by a processor.

[0203] In some embodiments, in response to the alarm level 510 being greater than the alarm threshold 520 , the processor may send alarm information to the operator server and / or the user client, and control the alarm device to send out an alarm signal 530 .

[0204] An alarm signal refers to an early warning or warning issued by an alarm device. In some embodiments, the alarm signal may be at least one of a light, a sound, etc., to indicate that there is a risk in the operation of the energy storage cabinet. For example, when there is a risk of fire in the energy storage cabinet, the alarm device may emit a buzzer.

[0205] For more information about the operator server and user client, see Figure 1 For detailed description of alarm levels, please refer to this manual. Figure 2 See the relevant instructions in .

[0206] In some embodiments, in response to the alarm level 510 being not greater than the alarm threshold 520 and greater than the safety threshold 540 , the processor may determine the adjustment parameter 550 based on the operational risk data sequence 430 and the power data 410 .

[0207] For detailed description of the operational risk data series, see Figure 4 For more information about power data, see Figure 2 and related instructions.

[0208] The alarm threshold refers to the limit value for determining whether the alarm device triggers an alarm signal. For example, the alarm threshold can be preset to an alarm level of 80. When the alarm level is less than 80, the alarm signal is not triggered; when the alarm level is greater than or equal to 80, an alarm signal is issued.

[0209] The safety threshold refers to the minimum indicator value for judging whether the operation of the energy storage cabinet is safe.

[0210] In some embodiments, the alarm threshold and the safety threshold may be determined in a variety of ways, for example, based on prior experience and / or actual needs.

[0211] In some embodiments, the alarm threshold and the safety threshold may be determined based on the stability of the energy storage cabinet, historical charging and discharging data, and future ambient temperature data.

[0212] The stability of the energy storage cabinet refers to the degree of stability of the operation of the energy storage cabinet. In some embodiments, the stability of the energy storage cabinet can be characterized by at least one of converter efficiency, response speed, and smoothness of charge and discharge curves.

[0213] Among them, the converter efficiency may be negatively correlated to the energy loss during the electrical energy conversion of the energy storage cabinet.

[0214] Response speed refers to the response speed of the energy storage cabinet after receiving instructions and commands.

[0215] The smoothness of the charge and discharge curves may be negatively correlated to the variance of the locker charge and discharge data.

[0216] The stability of the energy storage cabinet may be positively correlated with the converter efficiency, response speed, and charge-discharge curve smoothness. For example, the higher the converter efficiency, and / or the faster the response speed, and / or the higher the charge-discharge curve smoothness, the higher the stability of the energy storage cabinet.

[0217] The historical charge and discharge data may be the average of the historical charge and discharge amounts of the energy storage cabinet. The historical charge and discharge data may represent the charge and discharge behavior of the energy storage cabinet over a period of time in the past.

[0218] Future temperature data refers to the ambient temperature for a period of time in the future. In some embodiments, the future temperature data can be obtained based on weather forecasts.

[0219] The stability of the energy storage cabinet, historical charge and discharge data, and future ambient temperature data can characterize the possibility of risk in the energy storage cabinet. For example, the higher the stability of the energy storage cabinet, and / or the higher the historical charge and discharge data, and / or the higher the future ambient temperature data, the higher the possibility of risk in the energy storage cabinet, and the lower the alarm threshold should be, and the higher the safety threshold should be.

[0220] Some embodiments of this specification can improve the accuracy and efficiency of safety monitoring of energy storage cabinet operation by dynamically adjusting alarm thresholds and safety thresholds.

[0221] The adjustment parameter refers to a parameter used to adjust the device to be adjusted when the alarm level is between the safety threshold and the alarm threshold. In some embodiments, the adjustment parameter may include multiple devices to be adjusted and their corresponding adjustment values.

[0222] The device to be adjusted refers to the components, modules, etc. that need to be adjusted in the energy storage cabinet, such as heat dissipation device 1 and battery module 2. The adjustment value refers to the specific value for controlling the adjustment of the device to be adjusted.

[0223] In some embodiments, the adjustment parameter may include at least one of a first adjustment parameter and a second adjustment parameter.

[0224] The first adjustment parameter refers to an initial parameter used to adjust the device to be adjusted.

[0225] In some embodiments, the processor can construct an adjustment feature vector based on high-risk data, environmental data, and power data, perform a similarity search in a vector database based on the adjustment feature vector, and when a reference adjustment feature vector similar to the adjustment feature vector is retrieved, the reference adjustment parameter corresponding to the adjustment feature vector is determined as the first adjustment parameter.

[0226] Among them, the vector database stores multiple reference adjustment feature vectors and their corresponding multiple reference adjustment parameters. The reference adjustment feature vector can be constructed based on historical actual high-risk data, historical actual environmental data, and historical actual electric energy data. The reference adjustment parameter can be determined based on the historical adjustment parameter of the effective adjustment of the device to be adjusted in the historical data, or it can be determined by manual marking. Among them, effective adjustment means that after adjustment based on the historical adjustment parameter, the historical alarm level decreases.

[0227] In some embodiments, the first adjustment parameter determined by the vector database may not be accurate, but it can provide a starting point for the entire adjustment work, so that subsequent adjustment work can be performed based on the starting point.

[0228] The second adjustment parameter refers to a dynamic parameter used to make further adjustments to the device to be adjusted, which is determined based on the alarm level corresponding to the energy storage cabinet after the device to be adjusted is adjusted for the first time.

[0229] In some embodiments, the processor may query a second preset table based on the alarm level re-determined after the last adjustment to determine the second adjustment parameter. The second preset table refers to a correspondence table between the alarm level and the second adjustment parameter, which may be determined based on historical experience.

[0230] In some embodiments, the processor may also query a third preset table based on the risk level of the area where the device to be adjusted is located, and determine the second adjustment parameter based on the first correction ratio. The scope, location, size, etc. of the area may be determined based on manual presets.

[0231] The third preset table refers to a table of correspondence between risk levels and first correction ratios, which can be determined based on historical experience. The first correction ratio refers to a value that requires additional adjustment of the adjustment value.

[0232] When the alarm is triggered, the processor can send instructions to the environmental control module to adjust the temperature of the energy storage cabinet. In some embodiments, the priorities of different adjustment parameters can be preset according to different stages of regulation. Exemplarily, in the early stage of regulation, the priority of the adjustment parameter that has the greatest impact on temperature regulation is set to the highest. For example, heat dissipation device, dehumidification device, etc. When the highest priority adjustment parameter cannot reduce the alarm level, the priority of the adjustment parameter of the battery module is set to the highest.

[0233] In some embodiments, the priorities of different adjustment parameters can be preset according to the working status of the battery module.

[0234] Exemplarily, if the battery module is in working condition, when the input and output power of the battery module are reduced to the power threshold, the adjustment parameters of the battery module are reduced to the minimum, and the priority of the heat dissipation device, dehumidification device, etc. is set to the highest.

[0235] In some embodiments, the second adjustment parameter is also related to the sensitivity distribution data. For more information about the sensitivity distribution data, see Figure 2 and related instructions.

[0236] The higher the temperature sensitivity of the area where the device to be adjusted is located, the faster the device to be adjusted will be affected. Therefore, the highly sensitive area should be restored to a safe state as quickly as possible.

[0237] In some embodiments, the processor may also query a fourth preset table based on the sensitivity distribution data of the area where the device to be adjusted is located, and determine the second adjustment parameter based on the second correction ratio.

[0238] The fourth preset table refers to a table of correspondence between risk levels and second correction ratios, which can be determined based on historical experience. The second correction ratio refers to a value that requires additional adjustment of the adjustment value.

[0239] Highly sensitive areas are more susceptible to abnormal conditions and require more attention. In some embodiments of this specification, by utilizing temperature sensitivity data, the energy storage cabinet operation monitoring system can pay special attention to highly sensitive areas and prioritize rapid adjustments to these areas, which helps to restore their safe state in a short time, thereby reducing the risk of the overall system.

[0240] Some embodiments of this specification can realize real-time monitoring and dynamic regulation of energy storage cabinets by introducing alarm devices and dynamic adjustment based on risk data and power data, significantly improving the safety, response speed and management efficiency of the energy storage cabinet operation monitoring system. The multi-level alarm mechanism improves the effective operation and intervention efficiency of the energy storage cabinet operation monitoring system at different risk levels.

[0241] The basic concepts have been described herein. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to this specification. Such modifications, improvements and amendments are suggested in this specification, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary embodiments of this specification.

[0242] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0243] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0244] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0245] Each patent, patent application, patent application publication and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions and / or use of terms in this specification shall prevail.

[0246] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. An energy storage cabinet operation monitoring system, characterized in that: include: at least one battery module group, the battery module group comprising a plurality of single cells; a temperature monitoring module, comprising a plurality of temperature probes, configured to obtain temperature information of the at least one battery module group; A battery management module, configured to monitor the power data of the single battery and regulate the working parameters of the single battery; An environmental control module, configured to regulate an environmental control device within the energy storage pair; A network communication module is configured to realize a communication connection between the monitoring system and an operator server and / or a user client; The processor is communicatively connected to the at least one battery module, the temperature monitoring module, the battery management module, and the environment control module, and is configured to: Determining sensitivity distribution data of at least one position in the energy storage cabinet, wherein the sensitivity distribution data represents the degree of influence of temperature on the at least one position in the energy storage cabinet; Determining the sensitivity distribution data based on historical temperature information, historical electric energy data, and current working status of the at least one battery module; Constructing a three-dimensional model of the energy storage cabinet; Generate three-dimensional temperature distribution information based on the sensitivity distribution data, the temperature information, and the three-dimensional model; The three-dimensional temperature distribution information is also related to the position importance of the at least one position in the energy storage cabinet; determining an operation risk data sequence of the at least one location based on the three-dimensional temperature distribution information, the electric energy data and the environmental data; Determining a high-risk data sequence based on the operational risk data sequence and the risk coefficient threshold; Based on the high-risk data sequence, alarm information is determined.

2. The energy storage cabinet operation monitoring system according to claim 1, characterized in that: The system further comprises an alarm device, wherein the alarm device is configured to emit an alarm signal; the alarm information comprises an alarm level; The processor is further configured to: In response to the alarm level being greater than the alarm threshold, sending the alarm information to the operator server and / or the user client, and controlling the alarm device to send out the alarm signal; In response to the alarm level being not greater than the alarm threshold and greater than a safety threshold, an adjustment parameter is determined based on the operation risk data sequence and the electric energy data.

3. A method for monitoring the operation of an energy storage cabinet, characterized in that: The method is executed by a processor, comprising: Acquiring temperature information of at least one battery module group; Determining sensitivity distribution data of at least one position in the energy storage cabinet, wherein the sensitivity distribution data represents the degree of influence of temperature on the at least one position in the energy storage cabinet; Determining the sensitivity distribution data based on historical temperature information, historical electric energy data, and current working status of the at least one battery module; Constructing a three-dimensional model of the energy storage cabinet; Generate three-dimensional temperature distribution information based on the sensitivity distribution data, the temperature information, and the three-dimensional model; The three-dimensional temperature distribution information is also related to the position importance of at least one position in the energy storage cabinet; determining an operation risk data sequence of the at least one location based on the three-dimensional temperature distribution information, the power data and the environmental data; Determining a high-risk data sequence based on the operational risk data sequence and the risk coefficient threshold; Based on the high-risk data sequence, alarm information is determined.

4. The energy storage cabinet operation monitoring method according to claim 3, characterized in that: The alarm information includes an alarm level; the method further includes: In response to the alarm level being greater than the alarm threshold, sending the alarm information to the operator server and / or the user client, and controlling the alarm device to send out an alarm signal; In response to the alarm level being not greater than the alarm threshold and greater than a safety threshold, an adjustment parameter is determined based on the operation risk data sequence and the electric energy data.

Images