Intelligent safety monitoring system and method for electrochemical energy storage power station

Abstract

The present disclosure relates to an intelligent safety monitoring system and method for an electrochemical energy storage power station. The method comprises: integrating the acquired key parameters according to the parameter sample dimensions and performing sequence encoding respectively, and then processing them through a battery current-voltage timing interactive fusion module to obtain a battery voltage-battery current timing interactive fusion feature vector; performing battery temperature semantic mapping reasoning based on the battery voltage-battery current timing interactive fusion feature vector, and determining whether there is an abnormality in the operating state of the electrochemical energy storage power station based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature timing associated implicit feature vector. In this way, intelligent safety monitoring of the electrochemical energy storage power station can be achieved, thereby improving the safety and operating efficiency of the power station and reducing potential risks and the possibility of accidents.

Description

Technical Field

[0001] The present disclosure relates to the technical field of electrochemical energy storage power stations, and in particular, to an intelligent safety monitoring system and method for electrochemical energy storage power stations. Background Art

[0002] Electrochemical energy storage power stations refer to facilities that use chemical reactions to convert electrical energy into chemical energy for storage, and then convert chemical energy back into electrical energy for power supply. As an important energy storage method, electrochemical energy storage power stations play an important role in the power system, which can improve the stability, flexibility and reliability of the power grid and promote the large-scale application of renewable energy. However, there are a series of safety hazards in the operation of electrochemical energy storage power stations, such as overcharging, over-discharging, short circuit and other problems. Therefore, it is particularly important to carry out safety monitoring of electrochemical energy storage power stations.

[0003] However, traditional electrochemical energy storage power station safety monitoring solutions usually rely on manual inspections and regular testing, which cannot achieve real-time and comprehensive power station monitoring and are prone to ignoring potential safety risks. In addition, some existing electrochemical energy storage power station safety monitoring methods monitor the safety parameter data in the power station and compare it with the predetermined threshold to determine whether there is a safety problem. However, this method can only rely on threshold monitoring of single data for risk warning, lacks intelligent analysis of complex situations, and results in limited ability to identify and warn of abnormal situations in electrochemical energy storage power stations. At the same time, this method often needs to wait until the problem occurs before responding, lacking preventive and proactive nature.

[0004] Therefore, an intelligent safety monitoring system for electrochemical energy storage power stations is desired. Summary of the invention

[0005] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0006] In a first aspect, the present disclosure provides an intelligent safety monitoring system for an electrochemical energy storage power station, the system comprising:

[0007] An electrochemical energy storage power station parameter acquisition module is used to monitor the key parameters of the electrochemical energy storage power station in real time through a sensor network to obtain a time series of the key parameters, wherein the key parameters include battery voltage, battery current and battery temperature;

[0008] A power station parameter data time series integration module, used to integrate the time series of the key parameters according to the parameter sample dimensions to obtain the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature;

[0009] A power station parameter time series feature extraction module, used for respectively performing sequence encoding on the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature to obtain a battery voltage time series associated implicit feature vector, a battery current time series associated implicit feature vector and a battery temperature time series associated implicit feature vector;

[0010] A battery voltage-battery current time series feature interactive fusion module, used to process the battery voltage time series associated implicit feature vector and the battery current time series associated implicit feature vector using the battery current-voltage time series interactive fusion module to obtain a battery voltage-battery current time series interactive fusion feature vector;

[0011] The power station operation status abnormality detection module is used to perform battery temperature semantic mapping reasoning based on the battery voltage-battery current time series interactive fusion feature vector to obtain a battery temperature semantic reasoning mapping feature vector, and determine whether the operation status of the electrochemical energy storage power station is abnormal based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector.

[0012] Optionally, the power station parameter timing feature extraction module is used to: pass the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature through a sequence encoder based on an RNN model to obtain the battery voltage timing-related implicit feature vector, the battery current timing-related implicit feature vector and the battery temperature timing-related implicit feature vector.

[0013] Optionally, the battery voltage-battery current timing feature interactive fusion module includes: a battery voltage-battery current timing association encoding unit, used to multiply the battery voltage timing association implicit feature vector and the battery current timing association implicit feature vector by position point to obtain a battery voltage-battery current timing association feature vector; and an associated feature multi-modulation optimization unit, used to perform multi-modulation optimization on the battery voltage-battery current timing association feature vector to obtain the battery voltage-battery current timing interactive fusion feature vector.

[0014] Optionally, the associated feature multi-modulation optimization unit includes: a linear term modulation subunit, which is used to perform linear term modulation on each position characteristic value in the battery voltage-battery current timing interaction fusion characteristic vector to obtain a linear term modulated battery voltage-battery current timing association characteristic vector; a quadratic term modulation subunit, which is used to perform quadratic term modulation on each position characteristic value in the battery voltage-battery current timing interaction fusion characteristic vector to obtain a quadratic term modulated battery voltage-battery current timing association characteristic vector; a multi-modulation subunit, which is used to add the linear term modulated battery voltage-battery current timing association characteristic vector and the quadratic term modulated battery voltage-battery current timing association characteristic vector by position to obtain a multi-modulated battery voltage-battery current timing association characteristic vector; a constant term modulation addition subunit, which is used to perform constant plus one modulation on each position characteristic value in the multi-modulated battery voltage-battery current timing association characteristic vector to obtain the battery voltage-battery current timing interaction fusion characteristic vector.

[0015] Optionally, the linear modulation subunit includes: an exponential modulation secondary subunit, used to calculate an exponential function value raised to the power of the eigenvalues ​​at each position in the battery voltage-battery current timing association characteristic vector to obtain an exponentially modulated battery voltage-battery current timing association characteristic vector; and a first parameter adjustment secondary subunit, used to multiply the exponentially modulated battery voltage-battery current timing association characteristic vector by a first predetermined adjustment hyperparameter to obtain the linear modulation battery voltage-battery current timing association characteristic vector.

[0016] Optionally, the quadratic term modulation subunit includes: an exponential quadratic modulation secondary subunit, used to calculate an exponential function value raised to the square of the eigenvalue at each position in the battery voltage-battery current timing association characteristic vector to obtain an exponential quadratic modulation battery voltage-battery current timing association characteristic vector; and a second parameter adjustment secondary subunit, used to multiply the exponential quadratic modulation battery voltage-battery current timing association characteristic vector by a second predetermined adjustment hyperparameter to obtain the quadratic term modulation battery voltage-battery current timing association characteristic vector.

[0017] Optionally, the power station operation status abnormality detection module includes: a battery temperature semantic mapping reasoning unit, which is used to pass the battery voltage-battery current timing interactive fusion feature vector through a decoder-based battery temperature semantic reasoning mapper to obtain the battery temperature semantic reasoning mapping feature vector; a battery temperature timing feature comparison unit, which is used to calculate the Hamming distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature timing associated implicit feature vector; and an operation status abnormality judgment unit, which is used to determine whether the operation status of the electrochemical energy storage power station is abnormal based on the comparison between the Hamming distance and a predetermined threshold.

[0018] Optionally, it also includes a training module for training the RNN model-based sequence encoder, the battery current-voltage timing interaction fusion module and the decoder-based battery temperature semantic reasoning mapper.

[0019] Optionally, the training module includes: a training electrochemical energy storage power station parameter acquisition unit, which is used to monitor the training key parameters of the electrochemical energy storage power station in real time through the sensor network to obtain the time series of the training key parameters, wherein the training key parameters include training battery voltage, training battery current and training battery temperature; a training power station parameter data timing integration unit, which is used to integrate the time series of the training key parameters according to the parameter sample dimension to obtain the time series of the training battery voltage, the time series of the training battery current and the time series of the training battery temperature; a training power station parameter timing feature extraction unit, which is used to sequence encode the time series of the training battery voltage, the time series of the training battery current and the time series of the training battery temperature respectively to obtain the training battery voltage timing-related implicit feature vector, the training battery current timing-related implicit feature vector and the training battery temperature timing-related implicit feature vector; a training battery voltage-battery current timing feature interactive fusion unit, which is used to use the The battery current-voltage timing interaction fusion module processes the training battery voltage timing-associated implicit feature vector and the training battery current timing-associated implicit feature vector to obtain a training battery voltage-battery current timing interaction fusion feature vector; a training battery temperature semantic mapping reasoning unit is used to pass the training battery voltage-battery current timing interaction fusion feature vector through the decoder-based battery temperature semantic reasoning mapper to obtain a training battery temperature semantic reasoning mapping feature vector; a training battery temperature timing feature comparison unit is used to calculate a specific loss function value between the training battery temperature semantic reasoning mapping feature vector and the training battery temperature timing-associated implicit feature vector; a training unit is used to train the RNN model-based sequence encoder, the battery current-voltage timing interaction fusion module and the decoder-based battery temperature semantic reasoning mapper based on the specific loss function value, and in each iterative training, optimize the training battery temperature semantic reasoning mapping feature vector.

[0020] In a second aspect, the present disclosure provides a method for intelligent safety monitoring of an electrochemical energy storage power station, the method comprising:

[0021] Real-time monitoring of key parameters of the electrochemical energy storage power station through a sensor network to obtain a time series of the key parameters, wherein the key parameters include battery voltage, battery current and battery temperature;

[0022] Integrate the time series of the key parameters according to the parameter sample dimensions to obtain a time series of battery voltage, a time series of battery current, and a time series of battery temperature;

[0023] Sequentially encoding the time series of the battery voltage, the time series of the battery current, and the time series of the battery temperature to obtain a battery voltage time series associated implicit feature vector, a battery current time series associated implicit feature vector, and a battery temperature time series associated implicit feature vector;

[0024] Using a battery current-voltage time series interactive fusion module to process the battery voltage time series associated implicit feature vector and the battery current time series associated implicit feature vector to obtain a battery voltage-battery current time series interactive fusion feature vector;

[0025] Based on the battery voltage-battery current time series interactive fusion feature vector, battery temperature semantic mapping reasoning is performed to obtain a battery temperature semantic reasoning mapping feature vector, and based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector, it is determined whether the operating status of the electrochemical energy storage power station is abnormal.

[0026] The above technical solution is adopted to integrate the acquired key parameters according to the parameter sample dimensions and perform sequence encoding respectively, and then process them through the battery current-voltage time series interactive fusion module to obtain the battery voltage-battery current time series interactive fusion feature vector; perform battery temperature semantic mapping reasoning based on the battery voltage-battery current time series interactive fusion feature vector, and determine whether the operating state of the electrochemical energy storage power station is abnormal based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector. In this way, intelligent safety monitoring of the electrochemical energy storage power station can be realized, thereby improving the safety and operating efficiency of the power station and reducing the possibility of potential risks and accidents.

[0027] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0029] Figure 1 It is a block diagram of a smart safety monitoring system for an electrochemical energy storage power station according to an exemplary embodiment.

[0030] Figure 2 It is a flow chart of a method for intelligent safety monitoring of an electrochemical energy storage power station according to an exemplary embodiment.

[0031] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0032] Figure 4 It is an application scenario diagram of an intelligent safety monitoring system for an electrochemical energy storage power station according to an exemplary embodiment. DETAILED DESCRIPTION

[0033] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0034] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0035] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0036] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0037] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0038] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0039] In order to solve the above problems, the present disclosure provides an intelligent safety monitoring system and method for an electrochemical energy storage power station, which integrates the acquired key parameters according to the parameter sample dimensions and performs sequence encoding respectively, and then processes them through the battery current-voltage time series interactive fusion module to obtain a battery voltage-battery current time series interactive fusion feature vector; performs battery temperature semantic mapping reasoning based on the battery voltage-battery current time series interactive fusion feature vector, and determines whether the operating state of the electrochemical energy storage power station is abnormal based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector. In this way, intelligent safety monitoring of the electrochemical energy storage power station can be realized, thereby improving the safety and operating efficiency of the power station and reducing the possibility of potential risks and accidents.

[0040] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0041] Figure 1 It is a block diagram of a smart safety monitoring system for an electrochemical energy storage power station according to an exemplary embodiment.

[0042] like Figure 1 As shown, the system 100 includes:

[0043] The electrochemical energy storage power station parameter acquisition module 101 is used to monitor the key parameters of the electrochemical energy storage power station in real time through a sensor network to obtain a time series of the key parameters, wherein the key parameters include battery voltage, battery current and battery temperature;

[0044] The power station parameter data time series integration module 102 is used to integrate the time series of the key parameters according to the parameter sample dimensions to obtain the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature;

[0045] A power station parameter time series feature extraction module 103, used to perform sequence encoding on the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature to obtain a battery voltage time series associated implicit feature vector, a battery current time series associated implicit feature vector and a battery temperature time series associated implicit feature vector;

[0046] A battery voltage-battery current time series feature interactive fusion module 104 is used to process the battery voltage time series associated implicit feature vector and the battery current time series associated implicit feature vector using a battery current-voltage time series interactive fusion module to obtain a battery voltage-battery current time series interactive fusion feature vector;

[0047] The power station operation status abnormality detection module 105 is used to perform battery temperature semantic mapping reasoning based on the battery voltage-battery current time series interactive fusion feature vector to obtain a battery temperature semantic reasoning mapping feature vector, and determine whether the operation status of the electrochemical energy storage power station is abnormal based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector.

[0048] In response to the above technical problems, in the technical solution of this application, an intelligent safety monitoring system for electrochemical energy storage power stations is proposed, which can monitor and collect key parameters of electrochemical energy storage power stations in real time through a sensor network, including battery voltage, battery current and battery temperature, and introduce artificial intelligence-based data processing and analysis algorithms at the back end to perform time-series collaborative correlation analysis of these key parameters, so as to detect and judge abnormalities in the operating status of electrochemical energy storage power stations. In this way, intelligent safety monitoring of electrochemical energy storage power stations can be achieved, thereby improving the safety and operating efficiency of power stations and reducing potential risks and the possibility of accidents.

[0049] Specifically, in the technical solution of the present application, first, the key parameters of the electrochemical energy storage power station are monitored in real time through a sensor network to obtain a time series of the key parameters, wherein the key parameters include battery voltage, battery current and battery temperature. It should be understood that sensor network technology is the basis for realizing intelligent monitoring of electrochemical energy storage power stations. By deploying sensors at key locations, important parameters such as battery voltage, current and temperature can be monitored in real time to obtain accurate electrochemical energy storage power station operation data. These data can not only reflect the real-time operating status of the power station, but also provide a basis for subsequent safety analysis and early warning.

[0050] Next, considering that the key parameter data of the electrochemical energy storage power station, such as battery voltage, battery current and battery temperature, will continue to change over time in the time dimension, that is, these key parameter data have dynamic change laws and characteristics of time series. Based on this, in order to better analyze and understand the time series characteristics and correlations of these key parameters, so as to achieve comprehensive monitoring and analysis of the operating status of the power station, in the technical solution of the present application, it is necessary to integrate the time series of the key parameters according to the parameter sample dimension to obtain the time series of battery voltage, the time series of battery current and the time series of battery temperature. In this way, the time series information of the battery voltage, battery current and battery temperature in the key parameters in the time dimension can be integrated, and the position information of these key parameters in the time series can be retained, which is conducive to more fully capturing the dynamic characteristics and change laws of the battery voltage, current and temperature in the time series, so as to detect abnormal conditions in time.

[0051] Then, in order to capture the time series pattern and characteristic information of the key parameters of the electrochemical energy storage power station in the time dimension, the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature are passed through the sequence encoder based on the RNN model to obtain the battery voltage time series associated implicit feature vector, the battery current time series associated implicit feature vector and the battery temperature time series associated implicit feature vector. Through the processing of the sequence encoder based on the RNN model, the time series association and dynamic change characteristics of the battery voltage, battery current and battery temperature in the time dimension can be effectively captured, so as to reflect the law and trend of these key parameters changing over time, and provide strong data support for the subsequent electrochemical energy storage power station operation status analysis and anomaly detection tasks.

[0052] In one embodiment of the present disclosure, the power station parameter timing feature extraction module is used to: pass the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature through a sequence encoder based on an RNN model to obtain the battery voltage timing-related implicit feature vector, the battery current timing-related implicit feature vector and the battery temperature timing-related implicit feature vector.

[0053] It should be understood that battery current and voltage are two very important parameters in the battery's electrochemical energy storage system, and the timing correlation relationship between them can reveal the internal state and characteristics of the battery, thereby reflecting the battery temperature timing semantics. Based on this, in order to more accurately utilize the timing synergistic correlation characteristics between the battery current and voltage to perform timing semantic reasoning of the battery temperature, it is necessary to more comprehensively characterize the operating state and dynamic characteristics of the battery system. Specifically, in the technical solution of the present application, the battery current-voltage timing interaction fusion module is further used to process the battery voltage timing association implicit feature vector and the battery current timing association implicit feature vector to obtain a battery voltage-battery current timing interaction fusion feature vector. By applying the battery current-voltage timing interaction fusion module, the battery voltage timing characteristics and the battery current timing characteristics can be interactively fused, so that the timing correlation characteristics and dynamic change laws between the battery voltage and current can be better captured, so as to more comprehensively describe the operating state of the battery system, and provide more useful information and support for subsequent battery temperature timing semantic reasoning and energy storage power station operating state detection.

[0054] In particular, in a specific example of the present application, the battery current-voltage timing interaction fusion module is used to process the battery voltage timing-related implicit feature vector and the battery current timing-related implicit feature vector using the following timing feature interaction fusion formula to obtain the battery voltage-battery current timing interaction fusion feature vector;

[0055] The interactive fusion formula of the time series features is:

[0056]

[0057] in, is the eigenvalue of the ith position in the implicit eigenvector associated with the battery voltage time series, is the eigenvalue of the ith position in the implicit eigenvector associated with the battery current timing, α and β are adjustment hyperparameters, and v ci is the eigenvalue of the i-th position in the battery voltage-battery current time series interactive fusion eigenvector.

[0058] In one embodiment of the present disclosure, the battery voltage-battery current timing feature interactive fusion module includes: a battery voltage-battery current timing association encoding unit, which is used to multiply the battery voltage timing association implicit feature vector and the battery current timing association implicit feature vector by position point to obtain a battery voltage-battery current timing association feature vector; and an association feature multi-modulation optimization unit, which is used to perform multi-modulation optimization on the battery voltage-battery current timing association feature vector to obtain the battery voltage-battery current timing interactive fusion feature vector.

[0059] Further, in one embodiment of the present disclosure, the associated feature multi-modulation optimization unit includes: a linear term modulation subunit, which is used to perform linear term modulation on each position feature value in the battery voltage-battery current timing interaction fusion feature vector to obtain a linear term modulated battery voltage-battery current timing association feature vector; a quadratic term modulation subunit, which is used to perform quadratic term modulation on each position feature value in the battery voltage-battery current timing interaction fusion feature vector to obtain a quadratic term modulated battery voltage-battery current timing association feature vector; a multi-modulation subunit, which is used to add the linear term modulated battery voltage-battery current timing association feature vector and the quadratic term modulated battery voltage-battery current timing association feature vector by position to obtain a multi-modulated battery voltage-battery current timing association feature vector; a constant term modulation addition subunit, which is used to perform constant plus one modulation on each position feature value in the multi-modulated battery voltage-battery current timing association feature vector to obtain the battery voltage-battery current timing interaction fusion feature vector.

[0060] Among them, the first-order modulation subunit includes: an exponential modulation secondary subunit, which is used to calculate the exponential function value raised to the power of the eigenvalues ​​of each position in the battery voltage-battery current timing correlation characteristic vector to obtain the exponentially modulated battery voltage-battery current timing correlation characteristic vector; and a first parameter adjustment secondary subunit, which is used to multiply the exponentially modulated battery voltage-battery current timing correlation characteristic vector by a first predetermined adjustment hyperparameter to obtain the first-order modulation battery voltage-battery current timing correlation characteristic vector.

[0061] The quadratic term modulation subunit includes: an exponential quadratic modulation secondary subunit, which is used to calculate an exponential function value with the square of the characteristic value of each position in the battery voltage-battery current timing correlation characteristic vector as a power to obtain an exponential quadratic modulation battery voltage-battery current timing correlation characteristic vector; and a second parameter adjustment secondary subunit, which is used to multiply the exponential quadratic modulation battery voltage-battery current timing correlation characteristic vector by a second predetermined adjustment hyperparameter to obtain the quadratic term modulation battery voltage-battery current timing correlation characteristic vector.

[0062] Furthermore, considering that the battery voltage-battery current timing interaction fusion feature vector contains the timing interaction fusion feature information between the battery voltage timing features and the battery current timing features, this feature information can reflect the state and dynamic characteristics of the battery system. Therefore, a semantic reasoning mapper can be used to learn and model the deep relationship between battery temperature and voltage and current, and use this relationship to map the timing interaction fusion semantics of the battery voltage and current into the timing semantic space of the battery temperature, thereby obtaining the mapping reasoning semantics of the battery temperature. Specifically, in the technical solution of the present application, the battery voltage-battery current timing interaction fusion feature vector is passed through a decoder-based battery temperature semantic reasoning mapper to obtain a battery temperature semantic reasoning mapping feature vector.

[0063] Then, the Hamming distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector is calculated to measure the similarity between the battery temperature time series mapping semantic reasoning feature and the battery temperature time series associated implicit feature. That is to say, by comparing the Hamming distance between the battery temperature reasoning mapping feature vector and the original time series associated implicit feature vector, the difference between the battery temperature reasoning semantics and the actual monitoring situation can be evaluated, thereby helping to diagnose the fault of the battery system. Furthermore, based on the comparison between the Hamming distance and the predetermined threshold, it is determined whether the operating state of the electrochemical energy storage power station is abnormal. In particular, in response to the Hamming distance being greater than the predetermined threshold, it is determined that the operating state of the electrochemical energy storage power station is abnormal. In this way, hidden safety hazards and problems can be discovered in time through the time series analysis of the key parameters of the electrochemical energy storage power station and the comparison of the differences in battery temperature, avoiding serious safety accidents caused by the hysteresis of the response, thereby improving the safety and operating efficiency of the power station and reducing the possibility of potential risks and accidents.

[0064] In one embodiment of the present disclosure, the power station operation state abnormality detection module includes: a battery temperature semantic mapping reasoning unit, which is used to pass the battery voltage-battery current timing interactive fusion feature vector through a decoder-based battery temperature semantic reasoning mapper to obtain the battery temperature semantic reasoning mapping feature vector; a battery temperature timing feature comparison unit, which is used to calculate the Hamming distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature timing associated implicit feature vector; an operation state abnormality judgment unit, which is used to determine whether the operation state of the electrochemical energy storage power station is abnormal based on the comparison between the Hamming distance and a predetermined threshold.

[0065] Furthermore, in one embodiment of the present disclosure, the electrochemical energy storage power station intelligent safety monitoring system also includes a training module for training the RNN model-based sequence encoder, the battery current-voltage timing interaction fusion module, and the decoder-based battery temperature semantic reasoning mapper. The training module includes: a training electrochemical energy storage power station parameter acquisition unit, which is used to monitor the training key parameters of the electrochemical energy storage power station in real time through the sensor network to obtain the time series of the training key parameters, wherein the training key parameters include the training battery voltage, the training battery current and the training battery temperature; a training power station parameter data time series integration unit, which is used to integrate the time series of the training key parameters according to the parameter sample dimension to obtain the time series of the training battery voltage, the time series of the training battery current and the time series of the training battery temperature; a training power station parameter time series feature extraction unit, which is used to respectively perform sequence encoding on the time series of the training battery voltage, the time series of the training battery current and the time series of the training battery temperature to obtain the training battery voltage time series associated implicit feature vector, the training battery current time series associated implicit feature vector and the training battery temperature time series associated implicit feature vector; a training battery voltage-battery current time series feature interactive fusion unit, which is used to use the battery The current-voltage timing interaction fusion module processes the training battery voltage timing-associated implicit feature vector and the training battery current timing-associated implicit feature vector to obtain a training battery voltage-battery current timing interaction fusion feature vector; the training battery temperature semantic mapping reasoning unit is used to pass the training battery voltage-battery current timing interaction fusion feature vector through the decoder-based battery temperature semantic reasoning mapper to obtain a training battery temperature semantic reasoning mapping feature vector; the training battery temperature timing feature comparison unit is used to calculate the specific loss function value between the training battery temperature semantic reasoning mapping feature vector and the training battery temperature timing-associated implicit feature vector; the training unit is used to train the RNN model-based sequence encoder, the battery current-voltage timing interaction fusion module and the decoder-based battery temperature semantic reasoning mapper based on the specific loss function value, and in each iterative training, the training battery temperature semantic reasoning mapping feature vector is optimized.

[0066] In the technical solution of the present application, the training battery temperature semantic reasoning mapping feature vector is obtained by performing feature timing interactive fusion encoding on the training battery voltage timing-related implicit feature vector and the training battery current timing-related implicit feature vector and decoding by a decoder-based battery temperature semantic reasoning mapper, that is, the training battery temperature semantic reasoning mapping feature vector has a complex multi-domain and multi-modal timing feature association representation dimension of the encoding domain-decoding domain. Therefore, the feature expression effect under the complex multi-domain and multi-modal timing feature association representation dimension of the encoding domain-decoding domain is improved during the model iteration process.

[0067] Based on this, the applicant of the present application optimizes the training battery temperature semantic reasoning mapping feature vector, for example, denoted as V, during each iteration of the model, which is expressed as follows: in each iteration training, the training battery temperature semantic reasoning mapping feature vector is optimized to obtain the optimized training battery temperature semantic reasoning mapping feature vector; wherein the optimization formula is:

[0068]

[0069] Among them, μ, σ and v max They are the feature sets v i ∈V, log is the logarithmic function with base 2, and α is the weight hyperparameter, V is the training battery temperature semantic reasoning mapping feature vector, V′ is the optimized training battery temperature semantic reasoning mapping feature vector, v max -1 is the feature set v i ∈V is the inverse of its maximum value, represents positional addition, represents positional subtraction, and ⊙ represents positional multiplication.

[0070] Here, we use an interactive representation containing probability statistics features represented by mean μ and standard value σ and v as a latent variable feature. i and v maxThe short sequence of the distribution interaction representation is used as the sub-manifold potential motif under the complex manifold network of the training battery temperature semantic reasoning mapping feature vector V, and the obtained potential motif feature information pattern and feature distribution pattern of the training battery temperature semantic reasoning mapping feature vector V are used as its global structure inference unit, so as to reconstruct the complex manifold structure of the training battery temperature semantic reasoning mapping feature vector V in the form of a global structure potential motif dictionary based on connection, so as to improve the generation and evolution understanding ability of the model in the iterative process for the manifold structure corresponding to the temporal correlation feature of the complex multi-domain and multi-modal temporal feature association representation dimension of the encoding domain-decoding domain, and improve the feature expression effect under the complex multi-domain and multi-modal temporal feature association representation dimension of the encoding domain-decoding domain during the model iteration process. In this way, the calculation accuracy of the Hamming distance between the training battery temperature semantic reasoning mapping feature vector and the battery temperature temporal association implicit feature vector is improved. In this way, the safety monitoring of the electrochemical energy storage power station can be carried out more accurately, thereby improving the safety and operation efficiency of the power station and reducing the possibility of potential risks and accidents.

[0071] In summary, the above scheme is adopted to monitor and collect the key parameters of the electrochemical energy storage power station in real time through the sensor network, including battery voltage, battery current and battery temperature, and introduce artificial intelligence-based data processing and analysis algorithms at the back end to perform time series collaborative correlation analysis of these key parameters, so as to detect and judge the operating status of the electrochemical energy storage power station. In this way, intelligent safety monitoring of the electrochemical energy storage power station can be realized, thereby improving the safety and operating efficiency of the power station and reducing the possibility of potential risks and accidents.

[0072] Figure 2 is a flow chart of a method for intelligent safety monitoring of an electrochemical energy storage power station according to an exemplary embodiment. Figure 2 As shown, the method includes:

[0073] Step 201: monitor key parameters of an electrochemical energy storage power station in real time through a sensor network to obtain a time series of the key parameters, wherein the key parameters include battery voltage, battery current and battery temperature;

[0074] Step 202: integrating the time series of the key parameters according to the parameter sample dimensions to obtain a time series of battery voltage, a time series of battery current, and a time series of battery temperature;

[0075] Step 203, respectively performing sequence encoding on the time series of the battery voltage, the time series of the battery current, and the time series of the battery temperature to obtain a battery voltage time series associated implicit feature vector, a battery current time series associated implicit feature vector, and a battery temperature time series associated implicit feature vector;

[0076] Step 204: Use a battery current-voltage time series interactive fusion module to process the battery voltage time series associated implicit feature vector and the battery current time series associated implicit feature vector to obtain a battery voltage-battery current time series interactive fusion feature vector;

[0077] Step 205: Perform battery temperature semantic mapping reasoning based on the battery voltage-battery current time series interactive fusion feature vector to obtain a battery temperature semantic reasoning mapping feature vector, and determine whether there is an abnormality in the operating status of the electrochemical energy storage power station based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector.

[0078] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0079] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0080] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0081] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0082] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0083] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0084] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0085] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0086] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0087] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device".

[0088] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0089] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0090] Figure 4 FIG. 1 is an application scenario diagram of an electrochemical energy storage power station smart safety monitoring system according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, the key parameters of the electrochemical energy storage power station are monitored in real time through a sensor network to obtain a time series of the key parameters, wherein the key parameters include the battery voltage (for example, Figure 4 C1 as shown in FIG), battery current (e.g., Figure 4 C2 as shown in FIG. 1 ) and the battery temperature (e.g., Figure 4 Then, the obtained battery voltage, battery current and battery temperature are input to a server (for example, Figure 4 In the S) shown in , the server is capable of processing the battery voltage, the battery current and the battery temperature based on the intelligent safety monitoring algorithm of the electrochemical energy storage power station to determine whether there is any abnormality in the operating status of the electrochemical energy storage power station.

[0091] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0092] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0093] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. Intelligent safety monitoring system for electrochemical energy storage power station, characterized by: include: An electrochemical energy storage power station parameter acquisition module is used to monitor the key parameters of the electrochemical energy storage power station in real time through a sensor network to obtain a time series of the key parameters, wherein the key parameters include battery voltage, battery current and battery temperature; A power station parameter data time series integration module, used to integrate the time series of the key parameters according to the parameter sample dimensions to obtain the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature; A power station parameter time series feature extraction module, used for respectively performing sequence encoding on the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature to obtain a battery voltage time series associated implicit feature vector, a battery current time series associated implicit feature vector and a battery temperature time series associated implicit feature vector; A battery voltage-battery current time series feature interactive fusion module, used to process the battery voltage time series associated implicit feature vector and the battery current time series associated implicit feature vector using the battery current-voltage time series interactive fusion module to obtain a battery voltage-battery current time series interactive fusion feature vector; A power station operation state abnormality detection module, used to perform battery temperature semantic mapping reasoning based on the battery voltage-battery current time series interactive fusion feature vector to obtain a battery temperature semantic reasoning mapping feature vector, and determine whether the operation state of the electrochemical energy storage power station is abnormal based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector; The power station operation status abnormality detection module includes: A battery temperature semantic mapping inference unit, used for passing the battery voltage-battery current time series interaction fusion feature vector through a decoder-based battery temperature semantic inference mapper to obtain the battery temperature semantic inference mapping feature vector; A battery temperature time series feature comparison unit, used to calculate the Hamming distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector; The operation state abnormality judgment unit is used to determine whether the operation state of the electrochemical energy storage power station is abnormal based on the comparison between the Hamming distance and a predetermined threshold.

2. The electrochemical energy storage power station intelligent safety monitoring system according to claim 1 is characterized in that: The power station parameter time series feature extraction module is used to: pass the time series of the battery voltage, the time series of the battery current and the time series of the battery temperature through a sequence encoder based on an RNN model to obtain the battery voltage time series associated implicit feature vector, the battery current time series associated implicit feature vector and the battery temperature time series associated implicit feature vector.

3. The electrochemical energy storage power station intelligent safety monitoring system according to claim 2 is characterized in that: The battery voltage-battery current time series feature interactive fusion module includes: A battery voltage-battery current time series correlation encoding unit, used for performing position point multiplication of the battery voltage time series correlation implicit feature vector and the battery current time series correlation implicit feature vector to obtain a battery voltage-battery current time series correlation feature vector; The associated feature multi-modulation optimization unit is used to perform multi-modulation optimization on the battery voltage-battery current time series associated feature vector to obtain the battery voltage-battery current time series interactive fusion feature vector.

4. The electrochemical energy storage power station intelligent safety monitoring system according to claim 3 is characterized in that: The associated feature multi-item modulation optimization unit comprises: A linear modulation subunit, used for performing linear modulation on each position characteristic value in the battery voltage-battery current time series interactive fusion characteristic vector to obtain a linear modulation battery voltage-battery current time series correlation characteristic vector; A quadratic term modulation subunit, used for performing quadratic term modulation on each position characteristic value in the battery voltage-battery current time series interactive fusion characteristic vector to obtain a quadratic term modulated battery voltage-battery current time series correlation characteristic vector; A multi-modulation subunit, used for adding the first-order modulation battery voltage-battery current timing correlation characteristic vector and the second-order modulation battery voltage-battery current timing correlation characteristic vector according to position to obtain a multi-modulation battery voltage-battery current timing correlation characteristic vector; The constant term modulation addition subunit is used to modulate each position characteristic value in the multiple modulated battery voltage-battery current time series associated characteristic vector by adding a constant to obtain the battery voltage-battery current time series interactive fusion characteristic vector.

5. The electrochemical energy storage power station intelligent safety monitoring system according to claim 4 is characterized in that: The primary modulation subunit comprises: An exponential modulation secondary subunit, used to calculate an exponential function value raised to the power of the characteristic value of each position in the battery voltage-battery current time series correlation characteristic vector to obtain an exponential modulation battery voltage-battery current time series correlation characteristic vector; The first parameter adjustment secondary subunit is used to multiply the exponentially modulated battery voltage-battery current timing correlation characteristic vector by a first predetermined adjustment super parameter to obtain the first-order modulated battery voltage-battery current timing correlation characteristic vector.

6. The electrochemical energy storage power station intelligent safety monitoring system according to claim 5 is characterized in that: The quadratic term modulation subunit comprises: An exponential quadratic modulation secondary subunit, used to calculate an exponential function value with the square of the characteristic value of each position in the battery voltage-battery current time series correlation characteristic vector as a power to obtain an exponential quadratic modulation battery voltage-battery current time series correlation characteristic vector; The second parameter adjustment secondary subunit is used to multiply the exponential quadratic modulation battery voltage-battery current timing correlation characteristic vector by a second predetermined adjustment super parameter to obtain the quadratic term modulation battery voltage-battery current timing correlation characteristic vector.

7. The electrochemical energy storage power station intelligent safety monitoring system according to claim 6 is characterized in that: It also includes a training module for training the RNN model-based sequence encoder, the battery current-voltage timing interaction fusion module, and the decoder-based battery temperature semantic reasoning mapper.

8. The electrochemical energy storage power station intelligent safety monitoring system according to claim 7 is characterized in that: The training module comprises: A training electrochemical energy storage power station parameter acquisition unit, used to monitor the training key parameters of the electrochemical energy storage power station in real time through the sensor network to obtain a time series of the training key parameters, wherein the training key parameters include training battery voltage, training battery current and training battery temperature; A training power station parameter data time series integration unit, used to integrate the time series of the training key parameters according to the parameter sample dimensions to obtain a training battery voltage time series, a training battery current time series and a training battery temperature time series; A training power station parameter time series feature extraction unit, used to respectively perform sequence encoding on the time series of the training battery voltage, the time series of the training battery current, and the time series of the training battery temperature to obtain a training battery voltage time series associated implicit feature vector, a training battery current time series associated implicit feature vector, and a training battery temperature time series associated implicit feature vector; A training battery voltage-battery current timing feature interactive fusion unit, used to use the battery current-voltage timing interactive fusion module to process the training battery voltage timing-related implicit feature vector and the training battery current timing-related implicit feature vector to obtain a training battery voltage-battery current timing interactive fusion feature vector; A training battery temperature semantic mapping reasoning unit, used for passing the training battery voltage-battery current time series interaction fusion feature vector through the decoder-based battery temperature semantic reasoning mapper to obtain a training battery temperature semantic reasoning mapping feature vector; A training battery temperature time series feature comparison unit, used to calculate a specific loss function value between the training battery temperature semantic reasoning mapping feature vector and the training battery temperature time series associated implicit feature vector; A training unit is used to train the RNN model-based sequence encoder, the battery current-voltage timing interaction fusion module and the decoder-based battery temperature semantic reasoning mapper based on the specific loss function value, and in each iterative training, the training battery temperature semantic reasoning mapping feature vector is optimized.

9. A smart safety monitoring method for an electrochemical energy storage power station, characterized in that: include: Real-time monitoring of key parameters of the electrochemical energy storage power station through a sensor network to obtain a time series of the key parameters, wherein the key parameters include battery voltage, battery current and battery temperature; Integrate the time series of the key parameters according to the parameter sample dimensions to obtain a time series of battery voltage, a time series of battery current, and a time series of battery temperature; Sequentially encoding the time series of the battery voltage, the time series of the battery current, and the time series of the battery temperature to obtain a battery voltage time series associated implicit feature vector, a battery current time series associated implicit feature vector, and a battery temperature time series associated implicit feature vector; Using a battery current-voltage time series interactive fusion module to process the battery voltage time series associated implicit feature vector and the battery current time series associated implicit feature vector to obtain a battery voltage-battery current time series interactive fusion feature vector; Performing battery temperature semantic mapping reasoning based on the battery voltage-battery current time series interactive fusion feature vector to obtain a battery temperature semantic reasoning mapping feature vector, and determining whether the operating state of the electrochemical energy storage power station is abnormal based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector; Among them, the battery temperature semantic mapping reasoning is performed based on the battery voltage-battery current time series interactive fusion feature vector to obtain a battery temperature semantic reasoning mapping feature vector, and based on the distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector, it is determined whether the operating state of the electrochemical energy storage power station is abnormal, including: Passing the battery voltage-battery current time series interaction fusion feature vector through a decoder-based battery temperature semantic reasoning mapper to obtain the battery temperature semantic reasoning mapping feature vector; Calculating the Hamming distance between the battery temperature semantic reasoning mapping feature vector and the battery temperature time series associated implicit feature vector; Based on the comparison between the Hamming distance and a predetermined threshold, it is determined whether there is an abnormality in the operation state of the electrochemical energy storage power station.

Images