Safety management system and method of intelligent energy storage cabinet

Abstract

The invention discloses a safety management system and method for an intelligent energy storage cabinet, and relates to the technical field of epoxy zinc-rich primer preparation, the safety management system comprises an early warning response module, the early warning response module comprises a data acquisition unit, a real-time monitoring unit and a grading early warning unit; the data acquisition unit is used for acquiring parameters in the energy storage cabinet, and the parameters specifically comprise temperature, voltage, current and gas concentration; the real-time monitoring unit is used for monitoring and analyzing the data acquired by the data acquisition unit in real time to obtain monitoring data; the risk identification capability of the intelligent energy storage cabinet in the early stage of an accident can be effectively improved, the operation safety of equipment is protected, and untimely early warning caused by data acquisition delay or communication problems and early detection and early warning risks of battery thermal runaway are reduced. Meanwhile, by enhancing the safety and collaboration of system integration, the difficulty of maintenance and fault location can be reduced, the responsibility subject can be defined, and the efficiency and effect of accident handling can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent energy storage cabinets, and more specifically, to a safety management system and method for intelligent energy storage cabinets. Background Art

[0002] The application of intelligent energy storage cabinets in the industrial field is to cope with the problem of increasing volatility on both the supply and demand sides of the power system and to improve the flexibility and stability of the power grid. By storing and releasing electrical energy, the energy storage cabinet can balance the load of the power grid, reduce energy waste during peak hours, improve energy utilization, and thus reduce energy costs. In the event of sudden failure or power outage in the power system, the energy storage cabinet can provide emergency backup capacity to ensure the continuity of production and operation and improve the reliability of the power system. The core advantage of the energy storage cabinet lies in its adjustment flexibility and rapid response capability, which can solve the problems of three-phase imbalance and reactive power of users and become a high-quality flexibility resource.

[0003] However, in actual use, although the smart energy storage cabinet is equipped with an environmental monitoring module, it has limitations in accurately identifying risks and protecting equipment operation in the early stages of accidents, because data collection delays or communication problems lead to untimely warnings. In addition, there are risks in early detection and warning of battery thermal runaway;

[0004] Smart energy storage cabinets involve a variety of equipment and suppliers. The complexity of system integration leads to difficulties in maintenance and fault location. Electrical, fire protection, equipment installation and other issues involved in energy storage system integration are increasingly becoming the main cause of accidents. Most of the existing standards remain at the level of the safety of each system component itself, lacking system safety coordination. This leads to unclear problem location and unclear division of responsibilities when safety accidents occur, increasing the difficulty and complexity of accident handling. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a safety management system and method for an intelligent energy storage cabinet.

[0006] The present invention provides a safety management system for an intelligent energy storage cabinet, including an early warning response module, wherein the early warning response module includes a data acquisition unit, a real-time monitoring unit and a hierarchical early warning unit;

[0007] The data acquisition unit is used to collect parameters in the energy storage cabinet, including temperature, voltage, current and gas concentration;

[0008] The real-time monitoring unit is used to monitor and analyze the data collected by the data collection unit in real time, ensure that all parameters are within the safety threshold, and obtain monitoring data;

[0009] The hierarchical warning unit is used to analyze the monitoring data of the real-time monitoring unit and classify the analysis results to obtain a warning signal;

[0010] A collaborative maintenance module, the collaborative maintenance module comprising a maintenance unit and a fault location unit, the fault location unit being used to generate fault location data according to the warning signal of the warning response module and historical maintenance data;

[0011] The maintenance unit is used to identify the responsible party according to the fault location data, generate a maintenance signal, and transmit it;

[0012] A fault processing module is used to notify a responsible party to handle the fault according to the maintenance signal of the maintenance unit.

[0013] Preferably, the data acquisition unit is also used to predict the delay of data acquisition to adjust the acquired parameter data. The specific working steps are as follows:

[0014] Obtain parameter data in the energy storage cabinet and pre-process the collected data;

[0015] Create a data set and divide the preprocessed data into input and output. The length of each input is the preprocessed parameter data of the previous day of the current time period, and the output data is the parameter value of the next minute.

[0016] Define the LSTM network structure, including the input layer, LSTM layer and output layer. The dimension of the input layer is 4 and the dimension of the output layer is 1.

[0017] The dataset is divided into training set, validation set and test set, with a ratio of 70% training set, 15% validation set and 15% test set, and the input data is organized into sequence batches

[0018] Step 1: Initialize the LSTM model according to the defined network structure;

[0019] Step 2: Select mean square error as the loss function to measure the difference between the model prediction value and the actual value;

[0020] Step 3: Select the Adam optimizer to update the model weights;

[0021] Step 4: In each training batch, the input data is forward propagated through the LSTM model to obtain the prediction results;

[0022] Step 5: Use the loss function to calculate the difference between the predicted results and the actual output data;

[0023] Step 6: According to the loss value, back-propagate the model parameters and calculate the gradient;

[0024] Step 7: Use the optimizer to update the model weights based on the calculated gradients;

[0025] Step 8: Repeat steps 4 to 7 until the model reaches the preset maximum number of iterations to obtain a trained model;

[0026] After the acquisition unit obtains the acquired parameter data, the acquired parameter data is input into the trained model to obtain the adjusted parameter data.

[0027] Preferably, the specific working steps of the real-time monitoring unit are as follows:

[0028] Firstly, receiving the operating parameter data from the data acquisition unit, specifically including temperature, voltage, current and gas concentration;

[0029] Preset a safe threshold range for each operating parameter data;

[0030] If any operating parameter data exceeds a safe threshold range, the real-time monitoring unit generates monitoring data.

[0031] Preferably, the specific steps of generating the monitoring data are:

[0032] In the case of a single parameter abnormality: If only the temperature is abnormal but the voltage and current are normal, it is judged to be an environmental change or a problem with the cooling system of the smart energy storage cabinet, and monitoring data is generated;

[0033] If only the voltage is abnormal, it is judged that the battery of the smart energy storage cabinet is aging or there is a problem with the charging management system, and monitoring data is generated;

[0034] If only the current is abnormal, it is judged to be an internal problem of the battery of the smart energy storage cabinet or a change in the external load, and monitoring data is generated;

[0035] If only the gas concentration is abnormal, it is judged to be a battery chemical reaction or sealing problem of the smart energy storage cabinet, and monitoring data is generated;

[0036] In the case of multiple parameter abnormalities: If the temperature and voltage are abnormal at the same time, the smart energy storage cabinet battery is judged to be in thermal runaway and monitoring data is generated;

[0037] If both the temperature and current are abnormal, it is judged that the battery of the smart energy storage cabinet is overheated and causes overcurrent, and monitoring data is generated;

[0038] If both the voltage and current are abnormal, it is judged that there is a problem with the battery performance of the smart energy storage cabinet or a fault in the external circuit, and monitoring data is generated;

[0039] If three or more parameters are abnormal, the smart energy storage cabinet will immediately cut off power and generate monitoring data.

[0040] Preferably, the specific working steps of the hierarchical early warning unit are:

[0041] Acquire monitoring data of the monitoring unit, and obtain the degree to which each parameter exceeds a threshold value;

[0042] If only one parameter among all parameters is abnormal and no parameter exceeds 1% to 5%, a low risk signal is generated;

[0043] If among all the parameters, no more than two parameters are abnormal or there are parameters exceeding 5% to 10%, a risk signal is generated;

[0044] If among all the parameters, two or more parameters are abnormal or there are parameters exceeding 10%, a high-risk signal is generated, and the generated low-risk signal, medium-risk signal or high-risk signal is used as a warning signal.

[0045] Preferably, the specific working steps of the fault location unit are as follows:

[0046] Establishing a fault tree model, and determining the root cause of the fault according to the fault tree model after the fixed positioning unit receives the warning signal;

[0047] The location information of the smart energy storage cabinet equipment is obtained according to the early warning signal, and the location information of the smart energy storage cabinet equipment corresponding to the early warning signal and the root cause of the fault are used as fault location data.

[0048] Preferably, the specific establishment method of the fault tree model is as follows:

[0049] Select the fault state of the intelligent energy storage cabinet as the timing element;

[0050] Analyze the top event in depth and take the cause of the event as the next intermediate event of the fault tree;

[0051] Analyze each intermediate event in detail to find out the necessary and sufficient direct events for its occurrence, and use these events as the bottom-level events of the fault tree;

[0052] From top events to bottom events, events at all levels are connected with logical relationships to form a tree structure and obtain a fault tree model.

[0053] Preferably, the maintenance unit is used to divide the responsible parties according to the fault location data and the fault tree model to obtain a maintenance signal, and the specific steps are:

[0054] Associate each intermediate event and underlying event with the corresponding device and responsible subject;

[0055] According to the specific cause of the fault, the responsible party corresponding to the fault cause is obtained, the role and degree of responsibility of each responsible party in the occurrence of the fault are evaluated, the specific responsibilities of each responsible party are divided, and the specific responsibilities are used as maintenance signals.

[0056] Preferably, the fault processing module includes an electrical isolation unit and a fire control unit;

[0057] After receiving the maintenance signal transmitted by the maintenance unit, the electrical isolation unit performs signal isolation and power isolation. The specific working steps are as follows:

[0058] The electrical isolation unit first receives maintenance signals from the maintenance unit; these signals contain fault location data and responsible party information;

[0059] According to the early warning signal provided by the early warning response module, identify the circuit or system part that needs to be isolated;

[0060] Perform signal isolation and power isolation;

[0061] After receiving the maintenance signal transmitted by the maintenance unit, the fire control unit outputs the fire system status, and the specific steps are as follows:

[0062] The fire control unit receives the maintenance signal from the maintenance unit, and outputs the status of the fire protection system according to the abnormal data and fault location data in the maintenance signal.

[0063] The present invention also proposes a safety management system for an intelligent energy storage cabinet, and the specific working steps are as follows:

[0064] Step 1: Collect parameters in the energy storage cabinet, including temperature, voltage, current and gas concentration;

[0065] Step 2: Real-time monitoring and analysis of the data collected by the data acquisition unit to ensure that all parameters are within the safety threshold and obtain monitoring data;

[0066] Step 3: Classify the analysis results to obtain an early warning signal, generate fault location data according to the early warning signal of the early warning response module and the historical maintenance data, identify the responsible party according to the fault location data, generate a maintenance signal, and transmit it;

[0067] Step 4: Notify the responsible party to handle the problem according to the maintenance signal of the maintenance unit;

[0068] The specific steps of step 2 are:

[0069] In the case of a single parameter abnormality: If only the temperature is abnormal but the voltage and current are normal, it is judged to be an environmental change or a problem with the cooling system of the smart energy storage cabinet, and monitoring data is generated;

[0070] If only the voltage is abnormal, it is judged that the battery of the smart energy storage cabinet is aging or there is a problem with the charging management system, and monitoring data is generated;

[0071] If only the current is abnormal, it is judged to be an internal problem of the battery of the smart energy storage cabinet or a change in the external load, and monitoring data is generated;

[0072] If only the gas concentration is abnormal, it is judged to be a battery chemical reaction or sealing problem of the smart energy storage cabinet, and monitoring data is generated;

[0073] In the case of multiple parameter abnormalities: If the temperature and voltage are abnormal at the same time, the smart energy storage cabinet battery is judged to be in thermal runaway and monitoring data is generated;

[0074] If both the temperature and current are abnormal, it is judged that the battery of the smart energy storage cabinet is overheated and causes overcurrent, and monitoring data is generated;

[0075] If both the voltage and current are abnormal, it is judged that there is a problem with the battery performance of the smart energy storage cabinet or a fault in the external circuit, and monitoring data is generated;

[0076] If three or more parameters are abnormal, the smart energy storage cabinet will be powered off immediately and generate monitoring data. Beneficial effects: It can effectively improve the risk identification ability of the smart energy storage cabinet in the early stage of an accident, protect the safe operation of equipment, reduce the untimely warning caused by data collection delays or communication problems, and the early detection and warning risks of battery thermal runaway. At the same time, by enhancing the safety and coordination of system integration, it can reduce the difficulty of maintenance and fault location, clarify the responsible party, and improve the efficiency and effectiveness of accident handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a flow chart of the safety management system of the present invention. DETAILED DESCRIPTION

[0078] Application scenarios: In actual use, although the smart energy storage cabinet is equipped with an environmental monitoring module, it has limitations in accurately identifying risks and protecting equipment operation in the early stages of accidents, because data collection delays or communication problems lead to untimely warnings. In addition, there are risks in early detection and warning of battery thermal runaway;

[0079] Smart energy storage cabinets involve a variety of equipment and suppliers. The complexity of system integration leads to difficulties in maintenance and fault location. Electrical, fire protection, equipment installation and other issues involved in energy storage system integration are increasingly becoming the main cause of accidents. Most of the existing standards remain at the level of the safety of each system component itself, lacking system safety coordination. This leads to unclear problem location and unclear division of responsibilities when safety accidents occur, increasing the difficulty and complexity of accident handling.

[0080] like Figure 1 As shown: the safety management system of the intelligent energy storage cabinet includes an early warning response module, which includes a data acquisition unit, a real-time monitoring unit and a hierarchical early warning unit;

[0081] The data acquisition unit is used to collect parameters in the energy storage cabinet, including temperature, voltage, current and gas concentration. It should be noted that in this embodiment, the concentration of combustible gases in the energy storage cabinet is monitored, such as hydrogen (H2) and volatile organic compounds (VOCs), which may be precursors to thermal runaway of the battery.

[0082] The real-time monitoring unit is used to monitor and analyze the data collected by the data collection unit in real time, ensure that all parameters are within the safety threshold, and obtain monitoring data;

[0083] The hierarchical warning unit is used to analyze the monitoring data of the real-time monitoring unit and classify the analysis results to obtain a warning signal;

[0084] A collaborative maintenance module, the collaborative maintenance module comprising a maintenance unit and a fault location unit, the fault location unit being used to generate fault location data according to the warning signal of the warning response module and historical maintenance data;

[0085] The maintenance unit is used to identify the responsible party according to the fault location data, generate a maintenance signal, and transmit it; when a safety accident occurs, the specific problem can be located, the division of the responsible party can be clarified, and the difficulty and complexity of accident handling can be reduced.

[0086] A fault processing module is used to notify a responsible party to handle the fault according to the maintenance signal of the maintenance unit.

[0087] It can effectively improve the risk identification capability of smart energy storage cabinets in the early stage of accidents, protect the safe operation of equipment, reduce the untimely warning caused by data collection delays or communication problems, and the early detection and warning risks of battery thermal runaway. At the same time, by enhancing the safety and coordination of system integration, it can reduce the difficulty of maintenance and fault location, clarify the responsible parties, and improve the efficiency and effectiveness of accident handling;

[0088] As an optional embodiment: the data acquisition unit is further used to predict the delay of data acquisition to adjust the acquired parameter data, and the specific working steps are as follows:

[0089] Obtain parameter data in the energy storage cabinet and pre-process the collected data; it should be noted that an interpolation method (such as Lagrange interpolation or spline interpolation) is used to estimate missing data points, reduce data collection intervals, and standardize parameter data so that they are on the same scale;

[0090] Create a data set, divide the preprocessed data into input and output, the length of each input is the preprocessed parameter data of the previous day of the current time period, and the output data is the parameter value of the next minute; for each parameter, construct time series data, for example, if 1 day is selected as the input length, then each input sequence will contain the temperature, voltage, current and gas concentration data of the previous day of the current time period, and the output sequence will be the corresponding parameter value of the next minute of the current time period;

[0091] Define the LSTM network structure, including input layer, LSTM layer and output layer. The dimension of the input layer is 4, and the dimension of the output layer is 1. It should be noted that the input data includes four parameters: temperature, voltage, current and gas concentration, so the dimension of the input layer is 4. Each LSTM layer can have a different number of hidden units, which can be determined according to the complexity of the problem and the size of the data. The prediction is a single parameter value at a single time point, so the dimension of the output layer is;

[0092] The dataset is divided into training set, validation set and test set, with a ratio of 70% training set, 15% validation set and 15% test set, and the input data is organized into the form of sequence batch processing; specifically, the data is reshaped into the form of [batch size, time step, number of features]

[0093] Step 1: Initialize the LSTM model according to the defined network structure;

[0094] Step 2: Select mean square error as the loss function to measure the difference between the model prediction value and the actual value;

[0095] Step 3: Select the Adam optimizer to update the model weights;

[0096] Step 4: In each training batch, the input data is forward propagated through the LSTM model to obtain the prediction results;

[0097] Step 5: Use the loss function to calculate the difference between the predicted results and the actual output data;

[0098] Step 6: According to the loss value, back-propagate the model parameters and calculate the gradient;

[0099] Step 7: Use the optimizer to update the model weights based on the calculated gradients;

[0100] Step 8: Repeat steps 4 to 7 until the model reaches the preset maximum number of iterations to obtain a trained model;

[0101] After the acquisition unit obtains the acquired parameter data, it inputs the acquired parameter data into the trained model to obtain the adjusted parameter data. The data acquisition and analysis of the intelligent energy storage cabinet can be effectively processed to improve the accuracy of the data and the reliability of the early warning system. For example, if the prediction model shows that the temperature will rise in the future, and the current data has not yet shown this trend, the temperature reading can be appropriately adjusted to reduce the delay in data acquisition or the impact of communication problems.

[0102] As an optional embodiment: the specific working steps of the real-time monitoring unit are as follows:

[0103] Firstly, receiving the operating parameter data from the data acquisition unit, specifically including temperature, voltage, current and gas concentration;

[0104] A safe threshold range is preset for each operating parameter data; it should be noted that, in this embodiment, the safe threshold range can be obtained from the working environment data recommended by the manufacturer of the smart energy storage cabinet;

[0105] It should be noted that, in this embodiment, the temperature exceeds the preset safety threshold, causing the battery to overheat or the cooling system to malfunction;

[0106] The voltage exceeds or falls below the safe range, indicating that the battery charging status is abnormal or the battery performance is degraded;

[0107] The current exceeds the safety threshold, indicating overcurrent or internal battery short circuit;

[0108] The concentration of combustible gas exceeds the safety threshold, indicating that the battery is in thermal runaway or an impending fire;

[0109] If any operating parameter data exceeds a safe threshold range, the real-time monitoring unit generates monitoring data.

[0110] It should be noted that the monitoring data includes the current parameter value, the safety threshold range, whether the threshold is exceeded, the specific parameters that exceed the threshold, and the results represented by the parameter abnormality.

[0111] As an optional embodiment: the specific steps of generating the monitoring data are:

[0112] In the case of a single parameter abnormality: if only the temperature is abnormal but the voltage and current are normal, it is determined to be an environmental change or a problem with the cooling system of the smart energy storage cabinet, and monitoring data is generated; it should be noted that in this embodiment, it is necessary to further check the cooling system of the smart energy storage cabinet and the specific ambient temperature to confirm the problem;

[0113] If only the voltage is abnormal, it is judged that the battery of the smart energy storage cabinet is aging or there is a problem with the charging management system, and monitoring data is generated; it should be noted that in this embodiment, it is necessary to further check the BMS and battery status to confirm the problem;

[0114] If only the current is abnormal, it is determined that there is an internal problem with the battery of the smart energy storage cabinet or a change in the external load, and monitoring data is generated; it should be noted that in this embodiment, it is necessary to further check the battery and circuit connection to confirm the problem;

[0115] If only the gas concentration is abnormal, it is determined to be a battery chemical reaction or sealing problem of the smart energy storage cabinet, and monitoring data is generated; it should be noted that in this embodiment, it is necessary to further check the battery sealing and chemical stability to confirm the problem;

[0116] In the case of multiple parameter abnormalities: If the temperature and voltage are abnormal at the same time, the smart energy storage cabinet battery is judged to be in thermal runaway and monitoring data is generated;

[0117] If both the temperature and current are abnormal, it is judged that the battery of the smart energy storage cabinet is overheated and causes overcurrent, and monitoring data is generated;

[0118] If both the voltage and current are abnormal, it is judged that there is a problem with the battery performance of the smart energy storage cabinet or a fault in the external circuit, and monitoring data is generated;

[0119] If three or more parameters are abnormal, the smart energy storage cabinet will immediately cut off power and generate monitoring data.

[0120] For each of the above parameter abnormalities, the information transmitted by the monitoring data is different;

[0121] For example, if both the temperature and current are abnormal at the same time, the battery will overheat and cause an overcurrent warning signal.

[0122] As an optional embodiment: the specific working steps of the hierarchical warning unit are:

[0123] Acquire the monitoring data of the monitoring unit, and obtain the degree to which each parameter exceeds the threshold value; it should be noted that, in this embodiment, the threshold value represents the normal range of each parameter, which is obtained through the equipment recommended parameters of the manufacturer of the intelligent energy storage cabinet;

[0124] If only one parameter among all parameters is abnormal and no parameter exceeds 1% to 5%, a low risk signal is generated;

[0125] If among all the parameters, no more than two parameters are abnormal or there are parameters exceeding 5% to 10%, a risk signal is generated;

[0126] If there are more than two abnormal parameters or more than 10% of the parameters among all the parameters, a high risk signal is generated, and the generated low risk signal, medium risk signal or high risk signal is used as an early warning signal. In this embodiment, the early warning signal specifically includes abnormal time, corresponding smart energy storage cabinet equipment identification, parameter abnormality and other data.

[0127] As an optional embodiment: the specific working steps of the fault location unit are as follows;

[0128] Establishing a fault tree model, and determining the root cause of the fault according to the fault tree model after the fixed positioning unit receives the warning signal;

[0129] The location information of the smart energy storage cabinet equipment is obtained according to the early warning signal, and the location information of the smart energy storage cabinet equipment corresponding to the early warning signal and the root cause of the fault are used as fault location data.

[0130] As an optional embodiment: the specific method of establishing the fault tree model is as follows:

[0131] Select the fault state of the intelligent energy storage cabinet as the top event; in this embodiment, select the most undesirable fault state in the energy storage cabinet as the top event, such as battery thermal runaway or system shutdown;

[0132] In-depth analysis of the top event, the causes of the event as the next level of intermediate events in the fault tree; these causes may include battery failure, control system failure, environmental factors, etc.

[0133] Analyze each intermediate event in detail to find out the necessary and sufficient direct events for its occurrence, and use these events as the bottom-level events of the fault tree; for example, battery failure may be caused by voltage and current, and control system failure, environmental factors and other failures may be caused by temperature and gas concentration;

[0134] From top events to bottom events, events at all levels are connected with logical relationships to form a tree structure and obtain a fault tree model.

[0135] It should be noted that through fault tree analysis, we trace back from the bottom events to the top events to determine which combinations of bottom events may lead to intermediate events, and finally to the top events, to obtain the root cause of the fault;

[0136] For example, if the temperature in the energy storage cabinet suddenly rises (abnormal information) and the current exceeds the normal range, according to the fault tree, these two abnormal information may point to a battery failure (intermediate event), and the battery failure may be due to thermal runaway caused by overheating (top event). Therefore, it can be inferred that the cause of the failure may be thermal runaway caused by battery overheating.

[0137] As an optional embodiment: the maintenance unit is used to divide the responsible subjects according to the fault location data and the fault tree model to obtain a maintenance signal, and the specific steps are as follows:

[0138] Associate each intermediate event and underlying event with the corresponding device and responsible entity; it should be noted that in this embodiment, the responsible entity may include device manufacturers: including battery manufacturers, power storage converter (PCS) manufacturers, battery management system (BMS) providers, etc. They are responsible for the safety performance of the equipment they provide and ensure that the products meet safety standards;

[0139] System integrator: responsible for the integration of energy storage systems, including system design, installation and commissioning, to ensure the safety and reliability of the system;

[0140] Maintenance and operation team: responsible for the daily maintenance and operation management of the energy storage system to ensure the safe and stable operation of the system;

[0141] Fire and emergency management department: responsible for the fire safety management of energy storage systems, including the design, installation and maintenance of fire-fighting facilities, as well as the formulation and drills of emergency plans;

[0142] It should also be noted that, in this embodiment, the relationship between the fault cause and the corresponding responsible party is as follows:

[0143] Battery pack failure, responsible party: battery manufacturer (responsible for battery quality and performance);

[0144] Battery management system, responsible entity: battery management system provider (responsible for monitoring and managing battery pack status);

[0145] Charge and discharge controller failure, responsible party: Charge and discharge controller manufacturer (responsible for the stability and reliability of the control center);

[0146] Electrical failure, responsible party: system integrator (responsible for system design, installation and commissioning);

[0147] Environmental failure, responsible party: maintenance and operation team (responsible for daily maintenance and operation management);

[0148] PCS (energy storage converter) failure, responsible party: energy storage converter (PCS) manufacturer (responsible for power conversion and control);

[0149] Human operational errors, responsible parties: maintenance and operation teams (responsible for operational specifications and system maintenance);

[0150] Natural disasters and external force damage, responsible parties: fire and emergency management departments (responsible for fire safety management and emergency plans);

[0151] According to the specific cause of the fault, the responsible party corresponding to the fault cause is obtained to evaluate the role and degree of responsibility of each responsible party in the occurrence of the fault, divide the specific responsibilities of each responsible party, and use the specific responsibilities as maintenance signals. It should be noted that in order to quickly find the relevant responsible party when an accident occurs, the complexity of accident handling can be reduced;

[0152] It should also be noted that the specific method for evaluating the role and degree of responsibility of each responsible party in the occurrence of the failure is as follows:

[0153] In this embodiment, according to the classification of the warning signal, the low-risk signal is marked as 1 point, the medium-risk signal is marked as 2 points, and the high-risk signal is marked as 3 points. After the responsible party is obtained, according to the probability P of the failure of the intelligent energy storage cabinet related to the responsible party before the current time period, the score of the abnormal warning signal mark is multiplied by P to obtain the responsibility value of the responsible party in the consequences of the failure, and the responsibility value is used as the specific responsibility of each responsible party;

[0154] The calculated responsibility value can be used to prioritize the responsible entities, so that when a failure occurs, the responsible entities that need the most attention can be quickly identified, and resource allocation and response speed can be optimized;

[0155] By monitoring and analyzing the responsibility value, potential high-risk responsible parties can be identified, so that measures can be taken in advance to reduce the possibility of failures and enhance the safety and reliability of the system.

[0156] As an optional embodiment: the fault processing module includes an electrical isolation unit and a fire control unit;

[0157] After receiving the maintenance signal transmitted by the maintenance unit, the electrical isolation unit performs signal isolation and power isolation. The specific working steps are as follows:

[0158] The electrical isolation unit first receives maintenance signals from the maintenance unit; these signals contain fault location data and responsible party information;

[0159] According to the warning signal provided by the warning response module, the circuit or system part that needs to be isolated is identified; it should be noted that, in this embodiment, the circuit or system part of the abnormal intelligent energy storage cabinet is isolated;

[0160] Perform signal isolation and power isolation.

[0161] To ensure that signals are safely transmitted between different circuits or systems and to prevent signal interference, electrical isolation units perform signal isolation operations, which usually involves cutting off or rerouting signal paths to protect the system from interference;

[0162] Provide an independent power supply for the low-voltage side to prevent power failure from affecting the entire system. The electrical isolation unit will cut off the power supply to the faulty part while ensuring that the power supply to the non-faulty part is not affected;

[0163] It should be noted that it is necessary to ensure the safe transmission of signals between different circuits or systems, prevent signal interference, provide an independent power supply for the low-voltage side, and prevent power failure from affecting the entire system;

[0164] After receiving the maintenance signal transmitted by the maintenance unit, the fire control unit outputs the fire system status, and the specific steps are as follows:

[0165] The fire control unit receives the maintenance signal from the maintenance unit, and outputs the status of the fire protection system according to the abnormal data and fault location data in the maintenance signal.

[0166] If the abnormal data includes abnormal temperature, that is, when it is detected that the lithium battery may produce open fire, the fire control unit will start the inhibitor driving device, and the inhibitor will be sprayed at a fixed point through the main and branch pipelines according to the fault location data to extinguish the open fire;

[0167] After the open fire is extinguished, the fire control unit continues to start the inhibitor driving device and continues to spray the inhibitor at fixed points, thereby achieving the purpose of continuous cooling and preventing the lithium battery from reigniting.

[0168] It should be noted that the early warning response module provides real-time data to the electrical isolation unit and the fire suppression module so that they can respond accordingly; the collaborative maintenance module receives the early warning signal from the early warning response module to schedule maintenance tasks and locate faults; the electrical isolation unit and the fire suppression module perform isolation and fire fighting operations according to the early warning signal from the early warning response module to reduce the impact of accidents.

[0169] The present invention also proposes a safety management system for an intelligent energy storage cabinet, and the specific working steps are as follows:

[0170] Step 1: Collect parameters in the energy storage cabinet, including temperature, voltage, current and gas concentration;

[0171] Step 2: Real-time monitoring and analysis of the data collected by the data acquisition unit to ensure that all parameters are within the safety threshold and obtain monitoring data;

[0172] Step 3: Classify the analysis results to obtain an early warning signal, generate fault location data according to the early warning signal of the early warning response module and the historical maintenance data, identify the responsible party according to the fault location data, generate a maintenance signal, and transmit it;

[0173] Step 4: Notify the responsible party to handle the problem according to the maintenance signal of the maintenance unit;

[0174] The specific steps of step 2 are:

[0175] In the case of a single parameter abnormality: If only the temperature is abnormal but the voltage and current are normal, it is judged to be an environmental change or a problem with the cooling system of the smart energy storage cabinet, and monitoring data is generated;

[0176] If only the voltage is abnormal, it is judged that the battery of the smart energy storage cabinet is aging or there is a problem with the charging management system, and monitoring data is generated;

[0177] If only the current is abnormal, it is judged to be an internal problem of the battery of the smart energy storage cabinet or a change in the external load, and monitoring data is generated;

[0178] If only the gas concentration is abnormal, it is judged to be a battery chemical reaction or sealing problem of the smart energy storage cabinet, and monitoring data is generated;

[0179] In the case of multiple parameter abnormalities: If the temperature and voltage are abnormal at the same time, the smart energy storage cabinet battery is judged to be in thermal runaway and monitoring data is generated;

[0180] If both the temperature and current are abnormal, it is judged that the battery of the smart energy storage cabinet is overheated and causes overcurrent, and monitoring data is generated;

[0181] If both the voltage and current are abnormal, it is judged that there is a problem with the battery performance of the smart energy storage cabinet or a fault in the external circuit, and monitoring data is generated;

[0182] If three or more parameters are abnormal, the smart energy storage cabinet will immediately cut off power and generate monitoring data.

[0183] How it works

[0184] Collect parameters in the energy storage cabinet, including temperature, voltage, current and gas concentration;

[0185] Real-time monitoring and analysis of the data collected by the data acquisition unit to ensure that all parameters are within the safety threshold and obtain monitoring data;

[0186] The analysis results are graded to obtain an early warning signal, fault location data is generated according to the early warning signal of the early warning response module and historical maintenance data, the responsible party is identified according to the fault location data, and a maintenance signal is generated and transmitted;

[0187] Notifying the responsible party to handle the matter according to the maintenance signal of the maintenance unit;

[0188] It can effectively improve the risk identification capability of smart energy storage cabinets in the early stage of accidents, protect the safe operation of equipment, reduce the untimely warning caused by data collection delays or communication problems, and the early detection and warning risks of battery thermal runaway. At the same time, by enhancing the safety and coordination of system integration, it can reduce the difficulty of maintenance and fault location, clarify the responsible parties, and improve the efficiency and effectiveness of accident handling.

[0189] The above are only preferred implementations of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical staff in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of this template.

Claims

1. The safety management system of the intelligent energy storage cabinet is characterized by: It includes an early warning response module, which includes a data acquisition unit, a real-time monitoring unit and a hierarchical early warning unit; The data acquisition unit is used to collect parameters in the energy storage cabinet, including temperature, voltage, current and gas concentration; The real-time monitoring unit is used to monitor and analyze the data collected by the data collection unit in real time, ensure that all parameters are within the safety threshold, and obtain monitoring data; The hierarchical warning unit is used to analyze the monitoring data of the real-time monitoring unit and classify the analysis results to obtain a warning signal; A collaborative maintenance module, the collaborative maintenance module comprising a maintenance unit and a fault location unit, the fault location unit being used to generate fault location data according to the warning signal of the warning response module and historical maintenance data; The maintenance unit is used to identify the responsible party according to the fault location data, generate a maintenance signal, and transmit it; A fault processing module is used to notify a responsible party to handle the fault according to the maintenance signal of the maintenance unit.

2. The safety management system of the intelligent energy storage cabinet according to claim 1 is characterized in that: The data acquisition unit is also used to predict the delay of data acquisition to adjust the acquired parameter data. The specific working steps are as follows: Obtain parameter data in the energy storage cabinet and pre-process the collected data; Create a data set and divide the preprocessed data into input and output. The length of each input is the preprocessed parameter data of the previous day of the current time period, and the output data is the parameter value of the next minute. Define the LSTM network structure, including the input layer, LSTM layer and output layer. The dimension of the input layer is 4 and the dimension of the output layer is 1. The dataset is divided into training set, validation set and test set, with a ratio of 70% training set, 15% validation set and 15% test set, and the input data is organized into sequence batches Step 1: Initialize the LSTM model according to the defined network structure; Step 2: Select mean square error as the loss function to measure the difference between the model prediction value and the actual value; Step 3: Select the Adam optimizer to update the model weights; Step 4: In each training batch, the input data is forward propagated through the LSTM model to obtain the prediction results; Step 5: Use the loss function to calculate the difference between the predicted results and the actual output data; Step 6: According to the loss value, back-propagate the model parameters and calculate the gradient; Step 7: Use the optimizer to update the model weights based on the calculated gradients; Step 8: Repeat steps 4 to 7 until the model reaches the preset maximum number of iterations to obtain a trained model; After the acquisition unit obtains the acquired parameter data, the acquired parameter data is input into the trained model to obtain the adjusted parameter data.

3. The safety management system of the intelligent energy storage cabinet according to claim 1 is characterized in that: The specific working steps of the real-time monitoring unit are as follows: Firstly, receiving the operating parameter data from the data acquisition unit, specifically including temperature, voltage, current and gas concentration; Preset a safe threshold range for each operating parameter data; If any operating parameter data exceeds a safe threshold range, the real-time monitoring unit generates monitoring data.

4. The safety management system of the intelligent energy storage cabinet according to claim 3 is characterized in that: The specific steps of generating the monitoring data are: In the case of a single parameter abnormality: If only the temperature is abnormal but the voltage and current are normal, it is judged to be an environmental change or a problem with the cooling system of the smart energy storage cabinet, and monitoring data is generated; If only the voltage is abnormal, it is judged that the battery of the smart energy storage cabinet is aging or there is a problem with the charging management system, and monitoring data is generated; If only the current is abnormal, it is judged to be an internal problem of the battery of the smart energy storage cabinet or a change in the external load, and monitoring data is generated; If only the gas concentration is abnormal, it is judged to be a battery chemical reaction or sealing problem of the smart energy storage cabinet, and monitoring data is generated; In the case of multiple parameter abnormalities: If the temperature and voltage are abnormal at the same time, the smart energy storage cabinet battery is judged to be in thermal runaway and monitoring data is generated; If both the temperature and current are abnormal, it is judged that the battery of the smart energy storage cabinet is overheated and causes overcurrent, and monitoring data is generated; If both the voltage and current are abnormal, it is judged that there is a problem with the battery performance of the smart energy storage cabinet or a fault in the external circuit, and monitoring data is generated; If three or more parameters are abnormal, the smart energy storage cabinet will immediately cut off power and generate monitoring data.

5. The safety management system of the intelligent energy storage cabinet according to claim 4 is characterized in that: The specific working steps of the hierarchical early warning unit are: Acquire monitoring data of the monitoring unit, and obtain the degree to which each parameter exceeds a threshold value; If only one parameter among all parameters is abnormal and no parameter exceeds 1% to 5%, a low risk signal is generated; If among all the parameters, no more than two parameters are abnormal or there are parameters exceeding 5% to 10%, a risk signal is generated; If there are two or more abnormal parameters among all the parameters or if there are parameters exceeding 10%, a high-risk signal is generated, and the generated low-risk signal, medium-risk signal or high-risk signal is used as a warning signal.

6. The safety management system of the intelligent energy storage cabinet according to claim 5 is characterized in that: The specific working steps of the fault location unit are as follows: Establishing a fault tree model, and determining the root cause of the fault according to the fault tree model after the fixed positioning unit receives the warning signal; The location information of the smart energy storage cabinet equipment is obtained according to the early warning signal, and the location information of the smart energy storage cabinet equipment corresponding to the early warning signal and the root cause of the fault are used as fault location data.

7. The safety management system of the intelligent energy storage cabinet according to claim 6 is characterized in that: The specific establishment method of the fault tree model is as follows: Select the fault state of the intelligent energy storage cabinet as the timing element; Analyze the top event in depth and take the cause of the event as the next intermediate event of the fault tree; Analyze each intermediate event in detail to find out the necessary and sufficient direct events for its occurrence, and use these events as the bottom-level events of the fault tree; From top events to bottom events, events at all levels are connected with logical relationships to form a tree structure and obtain a fault tree model.

8. The safety management system of the intelligent energy storage cabinet according to claim 7 is characterized in that: The maintenance unit is used to divide the responsible parties according to the fault location data and the fault tree model to obtain a maintenance signal, and the specific steps are as follows: Associate each intermediate event and underlying event with the corresponding device and responsible subject; According to the specific cause of the fault, the responsible party corresponding to the fault cause is obtained, the role and degree of responsibility of each responsible party in the occurrence of the fault are evaluated, the specific responsibilities of each responsible party are divided, and the specific responsibilities are used as maintenance signals.

9. The safety management system of the intelligent energy storage cabinet according to claim 8, characterized in that: The fault processing module includes an electrical isolation unit and a fire control unit; After receiving the maintenance signal transmitted by the maintenance unit, the electrical isolation unit performs signal isolation and power isolation. The specific working steps are as follows: The electrical isolation unit first receives maintenance signals from the maintenance unit; these signals contain fault location data and responsible party information; According to the early warning signal provided by the early warning response module, identify the circuit or system part that needs to be isolated; Perform signal isolation and power isolation; After receiving the maintenance signal transmitted by the maintenance unit, the fire control unit outputs the fire system status, and the specific steps are as follows: The fire control unit receives the maintenance signal from the maintenance unit, and outputs the status of the fire protection system according to the abnormal data and fault location data in the maintenance signal.

10. A safety management method for an intelligent energy storage cabinet, applicable to the safety management system of the intelligent energy storage cabinet according to any one of claims 1 to 9, characterized in that: The specific working steps are: Step 1: Collect parameters in the energy storage cabinet, including temperature, voltage, current and gas concentration; Step 2: Real-time monitoring and analysis of the data collected by the data acquisition unit to ensure that all parameters are within the safety threshold and obtain monitoring data; Step 3: Classify the analysis results to obtain an early warning signal, generate fault location data according to the early warning signal of the early warning response module and the historical maintenance data, identify the responsible party according to the fault location data, generate a maintenance signal, and transmit it; Step 4: Notify the responsible party to handle the problem according to the maintenance signal of the maintenance unit; The specific steps of step 2 are: In the case of a single parameter abnormality: If only the temperature is abnormal but the voltage and current are normal, it is judged to be an environmental change or a problem with the cooling system of the smart energy storage cabinet, and monitoring data is generated; If only the voltage is abnormal, it is judged that the battery of the smart energy storage cabinet is aging or there is a problem with the charging management system, and monitoring data is generated; If only the current is abnormal, it is judged to be an internal problem of the battery of the smart energy storage cabinet or a change in the external load, and monitoring data is generated; If only the gas concentration is abnormal, it is judged to be a battery chemical reaction or sealing problem of the smart energy storage cabinet, and monitoring data is generated; In the case of multiple parameter abnormalities: If the temperature and voltage are abnormal at the same time, the smart energy storage cabinet battery is judged to be in thermal runaway and monitoring data is generated; If both the temperature and current are abnormal, it is judged that the battery of the smart energy storage cabinet is overheated and causes overcurrent, and monitoring data is generated; If both the voltage and current are abnormal, it is judged that there is a problem with the battery performance of the smart energy storage cabinet or a fault in the external circuit, and monitoring data is generated; If three or more parameters are abnormal, the smart energy storage cabinet will immediately cut off power and generate monitoring data.

Images