Fault detection method for stringed pcs

Abstract

The embodiment of the present application relates to a kind of fault detection methods of group string type PCS, comprising the following steps: the first operating parameter of alternating current bus and the first fault judgment model are judged to fault shutdown probability index;When the fault shutdown probability index meets the first condition, the second operating parameter of energy storage line and the second fault judgment model are used to carry out energy storage line positioning to fault;For fault energy storage line, the third fault judgment model is used to predict the fault degree of battery group, and according to the fault degree, fault handling is carried out.The technical scheme provided by the embodiment of the present application provides preliminary judgment basis for fault detection based on the first fault judgment model, in the case where system can continue to operate, second fault judgment model and third fault judgment model are used for fault positioning and fault degree prediction respectively, hierarchical detection and positioning of fault are realized, and the efficiency of fault detection can be improved in the case where system safety is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of energy storage system control technology, specifically to a fault detection method for a string PCS. Background Technology

[0002] In existing technologies, fault location in string PCS energy storage systems is quite complex. This is because energy storage systems contain multiple interconnected components, such as AC buses, multiple energy storage lines, and battery packs, and fault signals can influence and propagate within the system. Traditional fault detection methods may only detect individual components or a single level. When a fault occurs, it is difficult to quickly and accurately determine its exact location within the system, or the complex location methods may lead to fault escalation and system inoperability. Summary of the Invention

[0003] Based on the above-mentioned situation of the prior art, the purpose of this embodiment of the invention is to provide a fault detection method for a serial PCS, which can improve the efficiency and accuracy of fault detection while ensuring system safety.

[0004] To achieve the above objectives, according to one aspect of the present invention, a fault detection method for a string PCS is provided, wherein a plurality of energy storage lines are respectively connected to an AC bus, and each energy storage line includes a battery pack and a string PCS; the method includes the following steps:

[0005] The probability index of fault shutdown is determined based on the first operating parameters and the first fault judgment model of the AC bus.

[0006] When the failure downtime probability index meets the first condition, the energy storage line is located based on the second operating parameters of the energy storage line and the second fault judgment model.

[0007] For faulty energy storage lines, the degree of fault of the battery pack is predicted based on a third fault judgment model, and fault handling is carried out according to the degree of fault.

[0008] The first operating parameters of the AC bus include voltage, current, active power, reactive power, voltage amplitude change rate, current amplitude change rate, and power change rate; the second operating parameters of the energy storage line include output voltage, output current, and output power.

[0009] Furthermore, the first fault judgment model is an LSTM network model, and the output features of the first fault judgment model are fault probability and emergency shutdown probability.

[0010] The loss function L of the failure probability f for:

[0011]

[0012] The loss function L of the emergency shutdown probability e for:

[0013]

[0014] Where M represents the number of training samples, y f-i P represents the true fault label of the i-th training sample. f-i y represents the failure probability output by the model. e-i P represents the true emergency stop label of the i-th training sample. e-i This represents the probability of an emergency shutdown output by the model.

[0015] Furthermore, the failure downtime probability index includes the failure probability and the emergency downtime probability;

[0016] The first condition is that the probability of failure is greater than or equal to the failure threshold and the probability of emergency shutdown is less than the emergency shutdown threshold.

[0017] The second condition is that the probability of failure is greater than or equal to the failure threshold and the probability of emergency shutdown is greater than or equal to the emergency shutdown threshold.

[0018] Furthermore, when the failure downtime probability index meets the second condition, an emergency shutdown operation is performed.

[0019] Furthermore, the second fault judgment model is expressed as:

[0020]

[0021] Among them, F i Let r represent the probability of the i-th energy storage line failing. i (t) represents the power percentage of the i-th energy storage line at time t, ΔV bi (t) represents the rate of change of the output voltage of the battery pack in the i-th energy storage line at time t, ΔI bi (t) represents the rate of change of the output current of the battery pack in the i-th energy storage line at time t, Δt represents the sampling time interval, and r th V represents the power change threshold. bn Indicates the rated voltage of the battery pack, I bn This represents the rated current of the battery pack, and α and β represent the threshold adjustment parameters, respectively.

[0022] Furthermore, predicting the degree of battery pack failure based on the third fault judgment model includes the following steps:

[0023] Construct the state transition probability matrix and the observation matrix;

[0024] Based on the real-time state parameters, state transition probability matrix, and observation matrix of the faulty energy storage line, the forward prediction vector and the backward prediction vector are calculated.

[0025] Based on the forward prediction vector and the backward prediction vector, the probability value of the failure level of the battery pack in the faulty energy storage line is calculated.

[0026] The degree of failure of the battery pack is predicted based on the probability value of the degree of failure.

[0027] Furthermore, the state transition probability matrix is ​​expressed as:

[0028]

[0029] Among them, P ij This represents the probability that the battery pack transitions from state i to state j, where i = 0, 1, 2, 3; j = 0, 1, 2, 3; the states include 0: normal state, 1: slightly abnormal state, 2: moderately abnormal state, and 3: severely abnormal state.

[0030] Furthermore, the observation matrix is ​​an N×M matrix, M = M1×M2×M3, where M1 represents the number of intervals divided for the first observation, M2 represents the number of intervals divided for the second observation, M3 represents the number of intervals divided for the third observation, and N represents the number of battery pack states; the element B of the observation matrix ij Represented as:

[0031]

[0032] Let the combination of observation intervals corresponding to j be ? n ij This indicates that in historical data, when the battery pack is in state i, the first observation is observed in the interval [i, 2000]. The second observation is in the interval The third observation is in the interval The number of times.

[0033] Furthermore, the forward prediction vector is obtained recursively according to the following formula:

[0034]

[0035] Where, α t (j) is the forward prediction vector, representing the prediction vector at time t based on the observation sequence O1, O2, ..., O t The probability that the battery pack is in state j;

[0036] The backward prediction vector is obtained recursively according to the following formula:

[0037]

[0038] Where, β t (i) is the backward prediction vector, representing the prediction vector at time t based on the observation sequence O. t+1 O t+2 , ..., O T The probability that the battery pack is in state i.

[0039] Furthermore, the probability value of the degree of failure is calculated according to the following formula:

[0040]

[0041] Where, γ t (i) is the probability value of the degree of failure, which represents the probability of the battery pack being in each state.

[0042] In summary, this invention provides a fault detection method for a string PCS, comprising the following steps: determining a fault shutdown probability index based on first operating parameters of the AC bus and a first fault judgment model; when the fault shutdown probability index meets a first condition, locating the fault in the energy storage line based on second operating parameters of the energy storage line and the second fault judgment model; for the faulty energy storage line, predicting the fault severity of the battery pack based on a third fault judgment model, and handling the fault according to the fault severity. The technical solution provided by this invention, based on the first fault judgment model, determines whether a fault may occur and whether the fault requires emergency shutdown, providing a preliminary basis for fault detection. When the system can continue to operate, the second and third fault judgment models are used for fault location and fault severity prediction, respectively, achieving layered fault detection and location. This improves the efficiency of fault detection while ensuring system safety. Furthermore, corresponding fault judgment models are provided for different levels of fault detection, allowing for targeted detection based on the characteristics of operating parameters and fault modes at each level, thus improving the accuracy of fault detection results. Attached Figure Description

[0043] Figure 1 This is a flowchart of the charging and discharging control method for a string PCS provided in an embodiment of the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0045] It should be noted that, unless otherwise defined, the technical or scientific terms used in one or more embodiments of the present invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in one or more embodiments of the present invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the element or object listed following the word and its equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0046] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings. An embodiment of the present invention provides a fault detection method for a string PCS (Power Conversion System). The string PCS is a key component for realizing bidirectional power flow between an energy storage system and the power grid. In this embodiment, the energy storage system includes several energy storage lines, each connected to an AC bus. Each energy line includes a battery pack and a string PCS. Preferably, the battery pack can be connected to the string PCS via a DC / DC converter circuit. The AC bus can be connected to the power grid, for example, via a transformer or other equipment. Figure 1 The flowchart of the fault detection method for a serial PCS provided in an embodiment of the present invention is shown below. Figure 1 As shown, the fault detection method includes the following steps:

[0047] S202. The fault shutdown probability index is determined based on the first operating parameters of the AC bus and the first fault judgment model. The fault shutdown probability index includes the fault probability and the emergency shutdown probability. The first operating parameters of the AC bus include the AC bus voltage, AC bus current, AC bus active power, AC bus reactive power, AC bus voltage amplitude change rate, AC bus current amplitude change rate, and AC bus power change rate. These first operating parameters can be monitored by various sensors installed on the AC bus and calculated based on the sensor monitoring data. The first fault judgment model adopts a Long Short-Term Memory (LSTM) network model, and its output features are the fault probability and the emergency shutdown probability. That is, the first fault judgment model determines the probability of a current fault and the probability of needing an emergency shutdown based on the current first operating parameters. The core of the LSTM network model is the memory unit, which can effectively remember information in long-term time-series data. In this embodiment of the invention, when processing time-series data of AC buses (such as voltage, current, rate of change, etc. that change over time), LSTM can remember the operating status of the AC bus over a long period of time, thereby better capturing long-term trends and periodic changes in the data. Since fault occurrence is a gradual process closely related to past operating conditions, the LSTM network model can determine whether a fault may occur based on current operating parameters, and whether the fault requires emergency shutdown, providing a preliminary basis for fault detection.

[0048] In this embodiment of the invention, the LSTM network model is a multi-layer LSTM network, including an input layer, multiple LSTM hidden layers, and an output layer. The number of nodes in the input layer is equal to the number of input features (i.e., the first running parameters). The number of nodes in the hidden layer can be determined based on experiments and data complexity. The output layer has two nodes, used to output the failure probability and the emergency shutdown probability, respectively. A standard activation function is used in the LSTM network model. In the output layer, for example, a sigmoid function can be used to map the output to an interval to represent the probability. The loss function of the LSTM network model is set as the loss function for the failure probability and the loss function for the emergency shutdown probability. The failure probability loss function L... f Represented as:

[0049]

[0050] Loss function L of emergency stop probability e Represented as:

[0051]

[0052] Where M represents the number of training samples, y f-iP represents the true fault label of the i-th training sample. f-i y represents the failure probability output by the model. e-i P represents the true emergency stop label of the i-th training sample. e-i This represents the probability of an emergency shutdown output by the model.

[0053] The Adam optimization algorithm can be used to train the network model, adjusting the weights and biases to minimize the loss function. By inputting the real-time collected and preprocessed time-series data of the first operating parameters into the trained LSTM network model (the first fault diagnosis model), the fault probability and emergency shutdown probability can be obtained.

[0054] S204. When the fault outage probability index meets the first condition, the fault is located in the energy storage line based on the second operating parameters and the second fault judgment model. The first condition refers to the situation where the fault probability is greater than or equal to the fault threshold and the emergency shutdown probability is less than the emergency shutdown threshold. That is, under the first condition, it is determined that the energy storage system has failed, but the fault is not a fault that will cause a significant impact on the system and does not require immediate shutdown. In this case, the fault can be located in the line using the second fault judgment model and further processing can be carried out. If the output of the first fault judgment model shows that the fault probability is greater than or equal to the fault threshold and the emergency shutdown probability is greater than or equal to the emergency shutdown threshold, that is, when the fault outage probability index meets the second condition, an emergency shutdown operation is performed.

[0055] The second operating parameters of the energy storage line include output voltage, output current, and output power. These parameters are collected from the DC-side voltage, DC-side current, AC-side voltage, and AC-side current of the string PCS in the energy storage line, as well as the output voltage and current of the battery pack. The power contribution of this line to the AC bus is calculated using the AC-side voltage and current of the string PCS. Dividing this power contribution by the total power of the AC bus yields the power ratio of the energy storage line. Based on the output voltage and current of the battery pack at each sampling time, the rate of change of the battery pack's output voltage and output current are calculated.

[0056] The second fault diagnosis model is used to determine which energy storage line the fault occurred in. The second fault diagnosis model is expressed as follows:

[0057]

[0058] Among them, F i Let r represent the probability of the i-th energy storage line failing. i (t) represents the power percentage of the i-th energy storage line at time t, ΔV bi (t) represents the rate of change of the output voltage of the battery pack in the i-th energy storage line at time t, ΔI bi(t) represents the rate of change of the output current of the battery pack in the i-th energy storage line at time t, Δt represents the sampling time interval, and r th V represents the power change threshold. bn Indicates the rated voltage of the battery pack, I bn The rated current of the battery pack is represented by α, and β represents the threshold adjustment parameters. When the power percentage of the energy storage line decreases beyond a set threshold, and both the output voltage change rate and output current change rate of the battery pack exceed the set thresholds, the energy storage line is considered to have failed. According to some optional embodiments, the AC side voltage and AC side current change rate of the string PCS can also be used as the basis for judgment.

[0059] S206. For faulty energy storage lines, the degree of battery pack failure is predicted based on a third fault judgment model, and fault handling is performed according to the degree of failure. In this embodiment of the invention, a third fault judgment model based on the state transition probability matrix and the observation matrix is ​​used to predict the possible degree of failure based on the current state of the battery pack, thereby enabling targeted handling in advance. The prediction of the degree of battery pack failure based on the third fault judgment model can be performed according to the following steps:

[0060] S2061. Construct the state transition probability matrix and the observation matrix. The state transition probability matrix can be represented as:

[0061]

[0062] Among them, P ij Let P represent the probability that the battery pack transitions from state i to state j, where i = 0, 1, 2, 3; j = 0, 1, 2, 3. The probability is calculated by dividing the number of transitions from state i to state j by the total number of transitions originating from state i. For example, Pi. 01 = Number of transitions from state 0 to state 1 / Total number of transitions starting from state 0. In the state transition probability matrix, the sum of the elements in each row is 1. A value of 0 represents a normal state, a value of 1 represents a slightly abnormal state, a value of 2 represents a moderately abnormal state, and a value of 3 represents a severely abnormal state. The parameter ranges of the battery pack for each state can be preset. For example, in a normal state, the battery pack SOC is between 40% and 60%, the battery internal resistance is stable and within the normal resistance range, and the temperature is maintained between 20℃ and 35℃; in a slightly abnormal state, the battery pack SOC deviates from the normal range by 20%-40% or 60%-80%, the battery internal resistance increases within a certain threshold, and the temperature is between 35℃ and 45℃; the moderate and severely abnormal states are similar and can be set according to actual needs. The above state transition probability matrix can be generated based on the historical operating data of the battery pack, including state records at different time points and the transitions between states.

[0063] Multiple observations reflecting the battery pack state are selected, such as SOC, temperature, internal resistance, and the difference between the maximum and minimum values ​​of individual cell voltages. Each observation is divided into intervals; for example, SOC can be divided into five intervals: [0-20%), (20%-40%), (40%-60%), (60%-80%), and (80%-100%). In this embodiment, three observations are selected to construct an observation matrix, which is an M×M matrix, M = M1×M2×M3. M1 represents the number of intervals for the first observation, M2 represents the number of intervals for the second observation, and M3 represents the number of intervals for the third observation. N represents the number of battery pack states (corresponding to the states in the state transition probability matrix above, N = 4). The element B of the observation matrix... ij Represented as:

[0064]

[0065] Let the combination of observation intervals corresponding to j be ? n ij This indicates that in historical data, when the battery pack is in state i, the first observation is observed in the interval [i, 2000]. The second observation is in the interval The third observation is in the interval The number of times. B ij Let B represent the probability of observing a combination belonging to the j-th observation interval in state i. Calculate B. ij In the historical data, the number of times the observation combination in state i falls into the j-th interval combination is counted and divided by the total number of observations in state i.

[0066] S2062. Based on the real-time state parameters, state transition probability matrix, and observation matrix of the faulty energy storage line, calculate the forward prediction vector and the backward prediction vector. Determine the probability of the energy storage line's current state in each state based on the real-time state parameters of the faulty energy storage line as the initial state probability vector. For example, if the current state is normal, then the initial state probability vector π(0) = [1, 0, 0, 0]. Construct the observation sequence O = (O1, O2, ..., O...). T ), T represents the length of the observation sequence (i.e., the number of time steps), O t This represents the observation value at time t. Real-time measurements of each observation are collected at the initial time, and the combination of observation intervals to which they belong is determined, serving as the initial observation value O0.

[0067] Forward prediction vector α t (i) represents that at time t, based on the observation sequence O1, O2, ..., O t The probability that the battery pack is in state i, with an initial value of For t = 2, 3, ..., T, where T represents the length of the observation sequence, it can be obtained through recursion:

[0068]

[0069] Backward prediction vector β t (i) indicates that at time t, based on the observation sequence O t+1 O t+2 , ..., O T The probability that the battery pack is in state i is initially β(i) = 1 (for all i). For t = T-1, T-2, ..., 1, it is obtained through recursion:

[0070]

[0071] S2063. Based on the forward prediction vector and the backward prediction vector, calculate the probability value of the fault degree of the battery pack in the faulty energy storage line.

[0072] Based on the forward and backward prediction vectors, calculate the probability γ of the battery pack being in each state under a given observation sequence. t (i):

[0073]

[0074] S2064. Predict the degree of failure of the battery pack based on the aforementioned failure degree probability value. Based on γ t (i) to predict the possible degree of battery pack failure. For example, if γ t If (0) (i.e., the probability that the battery pack is in normal condition at time t) is greater than 0.8, then the battery pack is considered to be basically normal in the short term; if γ t (1) Maximum and greater than 0.5, or γ t (0)+γ t (1)>0.8 and γ t (1) If the value is relatively large, it is judged that a minor fault may occur in the short term; if γ t (2) Maximum and greater than 0.5, or γ t (0)+γ t (1)+γ t (2)>0.8 and γ t (2) If the value is relatively large, it is judged that a moderate fault is likely to occur in the short term; if γ t (3) Maximum and greater than 0.5, or γ t (0)+γ t (1)+γ t (2)+γ t (3) > 0.8 and γ t (3) If it is relatively large, it is judged that a serious fault may occur in the short term.

[0075] Fault handling should be based on the severity of the fault. When the fault is basically in a normal state or a minor fault may occur in the short term, it indicates that the battery pack fault will not affect the operation of the entire system in the short term. The fault can be recorded, and each battery pack can be inspected according to the maintenance cycle. When the fault is moderate or a severe fault may occur in the short term, the energy storage line can be disconnected from the AC bus as needed to avoid the fault of the energy storage line from having a significant impact on the operation of the entire system. After disconnecting the energy storage line, the power can be redistributed based on the output power of the remaining lines and the required total power.

[0076] In this embodiment of the invention, a third fault judgment model is constructed based on the state transition probability matrix and the observation matrix to predict the degree of battery pack failure. The state transition probability matrix describes the probability of the battery pack transitioning from one state to another. Based on historical operating data and inherent patterns, the state transition probability matrix can reflect the dynamic process of battery pack failure development. The observation matrix, on the other hand, links the real-time observed battery pack parameters with different states, quantifying the probability of observing a specific combination of parameters in each state. The observation matrix can infer the most likely state of the current battery pack based on the actual observed values ​​of these parameters. By combining the state transition probability matrix and the observation matrix, the individual differences and common patterns of different battery packs, as well as the influence of historical extrapolation patterns and real-time state conditions, are considered simultaneously, thus providing a more accurate fault prediction.

[0077] In summary, this invention relates to a fault detection method for a string PCS (Power Conversion System). The method includes the following steps: determining a fault shutdown probability index based on first operating parameters of the AC bus and a first fault judgment model; when the fault shutdown probability index meets a first condition, locating the fault in the energy storage line based on second operating parameters of the energy storage line and the second fault judgment model; for the faulty energy storage line, predicting the fault severity of the battery pack based on a third fault judgment model, and handling the fault according to the fault severity. The technical solution provided by this invention determines whether a fault may occur and whether the fault requires emergency shutdown based on the first fault judgment model, providing a preliminary basis for fault detection. When the system can continue to operate, the second and third fault judgment models are used for fault location and fault severity prediction, respectively, achieving layered fault detection and location. This improves the efficiency of fault detection while ensuring system safety. Furthermore, corresponding fault judgment models are provided for different levels of fault detection, allowing for targeted detection based on the characteristics of operating parameters and fault modes at each level, thus improving the accuracy of fault detection results.

[0078] It should be understood that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples. Within the framework of this invention, technical features of the above embodiments or different embodiments can also be combined, steps can be implemented in any order, and many other variations exist regarding different aspects of one or more embodiments of the invention as described above, which are not provided in the details for the sake of brevity. The specific embodiments described above are merely illustrative or explanatory of the principles of the invention and do not constitute a limitation thereof. Therefore, any modifications, equivalent substitutions, improvements, etc., made without departing from the spirit and scope of the invention should be included within the protection scope of the invention. Furthermore, the appended claims are intended to cover all variations and modifications falling within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries.

Claims

1. A fault detection method for a serial PCS, characterized in that, Several energy storage lines are connected to an AC bus, and each energy storage line includes a battery pack and a string PCS; the method includes the following steps: The probability index of fault shutdown is determined based on the first operating parameters and the first fault judgment model of the AC bus. When the failure downtime probability index meets the first condition, the energy storage line is located based on the second operating parameters of the energy storage line and the second fault judgment model. For faulty energy storage lines, the degree of fault of the battery pack is predicted based on a third fault judgment model, and fault handling is carried out according to the degree of fault. The first operating parameters of the AC bus include voltage, current, active power, reactive power, voltage amplitude change rate, current amplitude change rate, and power change rate; the second operating parameters of the energy storage line include output voltage, output current, and output power. Predicting the degree of battery pack failure based on a third fault diagnosis model includes the following steps: Construct the state transition probability matrix and the observation matrix; Based on the real-time state parameters, state transition probability matrix, and observation matrix of the faulty energy storage line, the forward prediction vector and the backward prediction vector are calculated. Based on the forward prediction vector and the backward prediction vector, the probability value of the failure level of the battery pack in the faulty energy storage line is calculated. Predict the degree of failure of the battery pack based on the aforementioned failure probability value; The state transition probability matrix is ​​expressed as follows: in, This represents the probability that the battery pack transitions from state i to state j. The states include 0: normal state, 1: mild abnormal state, 2: moderate abnormal state, and 3: severe abnormal state. The observation matrix is The matrix, , This indicates the number of intervals into which the first observation is divided. This indicates the number of intervals into which the second observation is divided. The number of intervals divided for the third observation. The number of battery pack states; the elements of the observation matrix. Represented as: Among them, let The corresponding combination of observation intervals is , , , ; This indicates that in historical data, when the battery pack is in state i, the first observation is observed in the interval [i, 2000]. The second observation is in the interval The third observation is in the interval The number of times; The forward prediction vector is obtained recursively according to the following formula: in, Let be the forward prediction vector, representing the prediction vector at time t based on the observation sequence. The probability that the battery pack is in state j; The backward prediction vector is obtained recursively according to the following formula: in, Let be the backward prediction vector, representing the prediction vector at time t based on the observation sequence. The probability that the battery pack is in state i; The probability value of the degree of failure is calculated according to the following formula: in, This is the probability value for the degree of failure, representing the probability that the battery pack is in each of its various states.

2. The method according to claim 1, characterized in that, The first fault diagnosis model is an LSTM network model, and the output features of the first fault diagnosis model are fault probability and emergency shutdown probability. The loss function of the failure probability for: The loss function of the emergency shutdown probability for: Where M represents the number of training samples. This represents the true fault label of the i-th training sample. This represents the failure probability output by the model. This represents the true emergency stop label for the i-th training sample. This represents the probability of an emergency shutdown output by the model.

3. The method according to claim 2, characterized in that, The failure downtime probability index includes the failure probability and the emergency downtime probability; The first condition is that the probability of failure is greater than or equal to the failure threshold and the probability of emergency shutdown is less than the emergency shutdown threshold. The second condition is that the probability of failure is greater than or equal to the failure threshold and the probability of emergency shutdown is greater than or equal to the emergency shutdown threshold.

4. The method according to claim 3, characterized in that, When the failure downtime probability index meets the second condition, an emergency shutdown operation is performed.

5. The method according to claim 1, characterized in that, The second fault diagnosis model is represented as follows: in, This represents the probability of the i-th energy storage line failing. This represents the power percentage of the i-th energy storage line at time t. This represents the rate of change of the output voltage of the battery pack in the i-th energy storage line at time t. Let represent the rate of change of the output current of the battery pack in the i-th energy storage line at time t. Indicates the sampling time interval. Indicates the power change threshold. Indicates the rated voltage of the battery pack. Indicates the rated current of the battery pack. and These represent the threshold adjustment parameters.

Images