Battery thermal runaway early warning method, device and equipment of energy storage power station and medium

Abstract

The application discloses a battery thermal runaway early warning method, device and equipment of energy storage power station and medium, using neural network to predict the battery thermal runaway risk of energy storage power station, early warning before the battery thermal runaway of energy storage power station, improve the safety.In addition, first train the probabilistic neural network with a small amount of training samples, and after the convergence of the probabilistic neural network, train the back propagation neural network with the soft label output by the probabilistic neural network, solve the problem of slow learning speed and insufficient training samples in the initial training of the back propagation neural network, and improve the model training efficiency.At the same time, the soft label can solve the problem that the back propagation neural network is easy to fall into local minimum value in the training process.

Description

TECHNICAL FIELD

[0001] The present application relates to battery thermal runaway early warning technology, and in particular to a battery thermal runaway early warning method, device, equipment and medium of an energy storage power station. BACKGROUND

[0002] The energy storage power station is a device system that stores, converts and releases recyclable electric energy by using electrochemical cells as energy storage media, and plays a role in balancing power supply and demand, that is, stores electric energy during the peak load period of the power system, and releases electric energy when the load is low, thereby balancing the difference between power supply and demand.

[0003] Most energy storage power stations use lithium ion batteries as energy storage media, and there is a high risk of thermal runaway in the use of lithium ion batteries. Existing research shows that before the thermal runaway of lithium ion batteries, the chemical reaction is relatively slow, but a small amount of gas, smoke and heat will be released. As the internal heat continues to accumulate, when the critical temperature is reached, the battery will undergo thermal runaway, triggering a series of violent chain reactions, and eventually causing severe burning or even explosion.

[0004] At present, for the thermal runaway detection of lithium ion batteries, data collected by sensors such as gas composition detectors, temperature sensors and photoelectric smoke detectors are used for judgment. Although it can detect the violent changes when thermal runaway occurs, it cannot issue an alarm at the best opportunity before thermal runaway, and there are a large number of false positives caused by environmental factors. This detection lag and false positives seriously limit the early warning capability of energy storage power stations in the early stage of fire, and it is difficult to meet the actual application requirements. SUMMARY

[0005] The present application provides a battery thermal runaway early warning method, device, equipment and medium of an energy storage power station to realize early warning before the thermal runaway of the battery of the energy storage power station and improve safety.

[0006] In a first aspect, the present application provides a battery thermal runaway early warning method of an energy storage power station, comprising:

[0007] The probability neural network and the back propagation neural network are trained using a training set until the probability neural network converges, the training set includes a plurality of first training samples with hard labels, the training samples include sensor data collected by at least one sensor, and the hard labels represent that the battery of the energy storage power station has thermal runaway or does not have thermal runaway;

[0008] The converged probability neural network is used to predict a second training sample without a label to obtain a soft label of the second training sample, and the soft label represents a probability value of thermal runaway of the battery of the energy storage power station;

[0009] training the back propagation neural network by using a plurality of second training samples with soft labels until the back propagation neural network converges;

[0010] processing the real-time collected sensing data from the energy storage power station by using the converged back propagation neural network to predict whether the battery of the energy storage power station has a risk of thermal runaway;

[0011] when the battery of the energy storage power station has a risk of thermal runaway, issuing a thermal runaway early warning.

[0012] Optionally, after the sensing data is collected, the method further comprises:

[0013] reconstructing the sensing data into three-channel data with three dimensions of space of the energy storage power station as the three channels;

[0014] inputting the three-channel data into a deep separable convolution network for processing to obtain a feature map;

[0015] performing global pooling processing on the feature map to obtain a pooled feature;

[0016] performing batch normalization processing on the pooled feature to obtain input features of a probabilistic neural network and a back propagation neural network.

[0017] Optionally, inputting the three-channel data into a deep separable convolution network for processing to obtain a feature map comprises:

[0018] performing spatial convolution processing on each channel data in the three-channel data to obtain a spatial convolution feature map;

[0019] splicing the spatial convolution feature maps of the channel data in the dimension to obtain a spliced feature map;

[0020] performing point-by-point convolution processing on the spliced feature map to obtain a feature map.

[0021] Optionally, performing batch normalization processing on the pooled feature to obtain input features of a probabilistic neural network and a back propagation neural network comprises:

[0022] calculating a mean and a variance of the pooled feature;

[0023] normalizing the pooled feature based on the mean and the variance to obtain a normalized feature;

[0024] performing translation scaling on the normalized feature to obtain input features of a probabilistic neural network and a back propagation neural network.

[0025] Optionally, after the convergence of the converged back propagation neural network, the method further comprises:

[0026] The prediction result is used as a training set to train the probabilistic neural network and the back propagation neural network, and to optimize network parameters of the probabilistic neural network and the back propagation neural network.

[0027] Optionally, the sensor data comprises gas composition information measured by a gas composition detector, temperature information measured by a temperature sensor, and visible light information measured by a photoelectric smoke detector.

[0028] In a second aspect, the present application further provides a battery thermal runaway early warning device for an energy storage power station, comprising:

[0029] A first training module is configured to train a probabilistic neural network and a back propagation neural network using a training set until the probabilistic neural network converges, wherein the training set comprises a plurality of first training samples with hard labels, the training samples comprise sensor data collected by at least one sensor, and the hard labels represent whether a battery of an energy storage power station has thermal runaway or not.

[0030] A soft label generation module is configured to use the converged probabilistic neural network to predict a second training sample without a label to obtain a soft label of the second training sample, wherein the soft label represents a probability value of whether the battery of the energy storage power station has thermal runaway.

[0031] A second training module is configured to train the back propagation neural network using a plurality of second training samples with soft labels until the back propagation neural network converges.

[0032] A risk prediction module is configured to use the converged back propagation neural network to process sensor data collected in real time from the energy storage power station to predict whether the battery of the energy storage power station has thermal runaway risk.

[0033] A thermal runaway early warning module is configured to issue a thermal runaway early warning when the battery of the energy storage power station has thermal runaway risk.

[0034] In a third aspect, the present application further provides an electronic device, comprising:

[0035] One or more processors;

[0036] A storage device configured to store one or more programs;

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the battery thermal runaway early warning method for an energy storage power station according to the first aspect of the present application.

[0038] In a fourth aspect, the present application further provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the battery thermal runaway early warning method of the energy storage power station according to the first aspect of the present application.

[0039] In a fifth aspect, the present application further provides a computer program product comprising a computer program which, when executed by a processor, implements the battery thermal runaway early warning method of the energy storage power station according to the first aspect of the present application.

[0040] The battery thermal runaway early warning method of the energy storage power station provided by the present application trains a probabilistic neural network and a back propagation neural network using a training set until the probabilistic neural network converges, the training set comprising a plurality of first training samples with hard labels, the training samples comprising sensor data collected by at least one sensor, and the hard labels indicating that the battery of the energy storage power station has thermal runaway or has not had thermal runaway, uses the converged probabilistic neural network to predict second training samples without labels to obtain soft labels of the second training samples, the soft labels indicating a probability value of the battery of the energy storage power station having thermal runaway, trains the back propagation neural network using a plurality of second training samples with soft labels until the back propagation neural network converges, processes sensor data collected in real time from the energy storage power station using the converged back propagation neural network to predict whether the battery of the energy storage power station has a thermal runaway risk, and issues a thermal runaway early warning when the battery of the energy storage power station has a thermal runaway risk. The present application uses neural networks to predict the thermal runaway risk of the battery of the energy storage power station, issues an early warning before the battery of the energy storage power station has thermal runaway, and improves safety. In addition, the probabilistic neural network is first trained using a small amount of training samples, and the back propagation neural network is trained using the soft labels output by the probabilistic neural network after the probabilistic neural network converges, thereby solving the problems of slow learning speed and insufficient training samples in the initial training of the back propagation neural network, and improving the model training efficiency. At the same time, the soft labels can solve the problem of easily falling into a local minimum value in the training process of the back propagation neural network.

[0041] It should be understood that the description in this section is not intended to identify key or critical features of embodiments of the present application or to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0043] Figure 1 A flow chart of a battery thermal runaway early warning method of an energy storage power station provided by the present application;

[0044] Figure 2 A training schematic diagram of a battery thermal runaway early warning model of an energy storage power station provided by the present application;

[0045] Figure 3 A structural schematic diagram of a battery thermal runaway early warning device of an energy storage power station provided by the present application;

[0046] Figure 4 A structural schematic diagram of an electronic device provided by the present application.

[0047] Through the above-mentioned drawings, the specific embodiments of the present application have been shown, and will be described in more detail hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making any creative efforts should fall within the scope of protection of the present application.

[0049] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0050] Figure 1 A flow chart of a battery thermal runaway early warning method of an energy storage power station provided by the present application, the present embodiment can be applicable to early warning of battery thermal runaway of an energy storage power station, the method can be executed by a battery thermal runaway early warning device of an energy storage power station provided by the present application, the device can be realized by software and / or hardware, and is usually configured in an electronic device, such as Figure 1As shown, the battery thermal runaway early warning method of the energy storage power station specifically includes the following steps:

[0051] S101, train the probabilistic neural network and the back propagation neural network using the training set until the probabilistic neural network converges.

[0052] In the embodiment of the present application, a small amount of training set is first acquired, and the training set includes a plurality of first training samples with hard labels. The training samples include sensing data collected by at least one sensor, and the hard label indicates that the battery of the energy storage power station has thermal runaway or does not have thermal runaway. The sensing data can include gas composition information measured by a gas composition detector, temperature information measured by a temperature sensor, and visible light information measured by a photoelectric smoke detector, and these sensors are arranged inside the energy storage power station.

[0053] Figure 2 A training schematic diagram of the battery thermal runaway early warning model of the energy storage power station provided by the present application is shown in Figure 2 As shown, in the embodiment of the present application, a small amount of first training sample is input into the probabilistic neural network (Probabilistic Neural Network, PNN) and the back propagation neural network (Back Propagation Network, BP) for training until the probabilistic neural network converges. The probabilistic neural network is mainly divided into four network levels including an input layer, a sample layer, a summation layer, and a competitive output layer in structure. The input layer is used to calculate the distance between the input vector and all training sample vectors, the main function of the sample layer is to perform weighted summation operation on the input signal, and the next layer is sent after operation through an activation function, wherein the activation function is a Gaussian function, the summation layer adds the outputs of the sample layer by class, and the competitive output layer outputs the decision result, i.e., the probability of predicting that the first training sample has battery thermal runaway risk.

[0054] Compared with the traditional neural network, the biggest advantage of the probabilistic neural network is that it can obtain the converged Bayes optimization solution without multiple calculations. Therefore, when debugging and identifying, the probabilistic neural network can obtain the expected test result with fewer training times. Therefore, the probabilistic neural network can converge before the back propagation neural network.

[0055] In some embodiments of the present application, after the first training sample is acquired, the first training sample can be preprocessed and then sent into the probabilistic neural network and the back propagation neural network for training. The preprocessing process is as follows, for example:

[0056] 1. Taking the three-dimensional space of the energy storage power station as three channels, the sensing data is reconstructed into three-channel data.

[0057] In the embodiment of the present application, the sensing data is reconstructed into three-channel data with three channels in the spatial three-dimension of the energy storage power station. For example, taking one of the coordinate axes of the spatial three-dimension as an example, the sensing data on all sampling sections perpendicular to the coordinate axis is determined as the channel data of the channel, and thus the sensing data is reconstructed into three-channel data.

[0058] 2. The three-channel data is input into a deep separable convolution network for processing to obtain a feature map.

[0059] For example, as shown in Figure 2 the three-channel data is input into a deep separable convolution network (DSC) for processing to obtain a feature map. The deep separable convolution is an algorithm obtained by improving the standard convolution calculation in the convolutional neural network, which reduces the number of parameters required for convolution calculation and improves the use efficiency of the convolution kernel parameters by splitting the correlation between the spatial dimension and the channel (depth) dimension.

[0060] For example, spatial convolution processing is performed on each channel data in the three-channel data to obtain a spatial convolution feature map, the spatial convolution feature maps of the channel data are spliced in the dimension to obtain a spliced feature map, and point-by-point convolution processing is performed on the spliced feature map to obtain a feature map.

[0061] 3. Global pooling processing is performed on the feature map to obtain a pooled feature.

[0062] For example, as shown in Figure 2 global pooling processing (pooling) is performed on the feature map output by the deep separable convolution network to obtain a pooled feature. In the embodiment of the present application, the global pooling processing can include global average pooling and global maximum pooling, which are not limited in the embodiment of the present application. The purpose of the pooling is to reduce the dimension and strengthen the feature, and the specific formula is:

[0063]

[0064] wherein down is a pooling function, for example, a maximum pooling function or an average pooling function, and s is the size of the pooling window.

[0065] 4. Batch normalization processing is performed on the pooled feature to obtain an input feature of a probabilistic neural network and a back propagation neural network.

[0066] For example, as shown in Figure 2 batch normalization processing (Batch Normalization) is performed on the pooled feature to obtain an input feature of a probabilistic neural network and a back propagation neural network.

[0067] Specifically, the mean and variance of the pooled features are calculated, the pooled features are normalized based on the mean and variance to obtain normalized features, and the normalized features are translated and scaled to obtain input features of the probabilistic neural network and the back propagation neural network. The formula of the batch normalization processing is as follows:

[0068]

[0069] wherein, sigma 2 is the variance of all elements in the pooled features, mu is the mean of all elements in the pooled features, epsilon is an infinitesimal number, is an element in the normalized features, gamma and beta are linear parameters obtained by training for scaling and translating the normalized features.

[0070] S102, predicting the unlabeled second training sample by using the converged probabilistic neural network to obtain the soft label of the second training sample.

[0071] For example, the sensing data in the energy storage power station can be collected as the unlabeled second training sample in actual application. After the probabilistic neural network converges, the unlabeled second training sample is predicted by using the converged probabilistic neural network to obtain the soft label of the second training sample, and the soft label represents the probability value of thermal runaway of the battery in the energy storage power station.

[0072] S103, training the back propagation neural network by using the plurality of second training samples with soft labels until the back propagation neural network converges.

[0073] In the embodiment of the present application, the back propagation neural network is trained by using the plurality of second training samples with soft labels until the back propagation neural network converges, thereby solving the problem of slow learning speed and insufficient training samples in the initial stage of training the back propagation neural network, and improving the model training efficiency. At the same time, since the second training sample has a soft label, the problem of easily falling into a local minimum value in the training process of the back propagation neural network can be solved.

[0074] S104, processing the real-time collected sensing data from the energy storage power station by using the converged back propagation neural network to predict whether the battery in the energy storage power station has a thermal runaway risk.

[0075] In the embodiment of the present application, the converged back propagation neural network is used to process the real-time collected sensing data from the energy storage power station to predict whether the battery of the energy storage power station has a thermal runaway risk. The back propagation neural network is a multi-layer feedforward network trained by error back propagation (error back propagation for short), and its algorithm is called BP algorithm. The basic idea of the back propagation neural network is the gradient descent method, and the gradient search technology is used to minimize the error mean square difference between the actual output value and the expected output value of the network. The back propagation neural network has strong non-linear mapping capability and flexible network structure, and by modifying the weight of each neuron, the error signal is minimized to improve the prediction accuracy.

[0076] S105, when the battery of the energy storage power station has a thermal runaway risk, issuing a thermal runaway early warning.

[0077] When the battery of the energy storage power station has a thermal runaway risk, the thermal runaway early warning is issued in advance, the thermal runaway early warning of the battery of the energy storage power station is realized in advance, and the safety is improved.

[0078] In the embodiment of the present application, as shown in Figure 2 After the converged back propagation neural network is used to process the real-time collected sensing data from the energy storage power station to predict whether the battery of the energy storage power station has a thermal runaway risk, the following steps are further included:

[0079] The prediction result is used as a training set to train the probability neural network and the back propagation neural network, and the network parameters of the probability neural network and the back propagation neural network are continuously optimized to improve the prediction accuracy of the model.

[0080] The application provides a battery thermal runaway early warning method of an energy storage power station, a probability neural network and a back propagation neural network are trained by using a training set until the probability neural network converges, the training set comprises a plurality of first training samples with hard labels, the training sample comprises sensing data collected by at least one sensor, and the hard label indicates that the battery of the energy storage power station has thermal runaway or does not have thermal runaway, the converged probability neural network is used to predict a second training sample without a label, to obtain a soft label of the second training sample, the soft label indicates a probability value of thermal runaway of the battery of the energy storage power station, the back propagation neural network is trained by using a plurality of second training samples with soft labels until the back propagation neural network converges, and the converged back propagation neural network is used to process real-time sensing data collected from the energy storage power station, to predict whether the battery of the energy storage power station has a thermal runaway risk, and an early warning of thermal runaway is given when the battery of the energy storage power station has a thermal runaway risk. The application predicts the thermal runaway risk of the battery of the energy storage power station by using a neural network, gives an early warning before the battery of the energy storage power station has thermal runaway, and improves safety. In addition, the probability neural network is trained by using a small amount of training samples first, and the back propagation neural network is trained by using the soft label output by the probability neural network after the probability neural network converges, so that the problem of slow learning speed and insufficient training samples of the back propagation neural network in the initial training stage is solved, and the model training efficiency is improved. Meanwhile, the soft label can solve the problem that the back propagation neural network is easily trapped in a local minimum value in the training process.

[0081] Figure 3 A structure diagram of a battery thermal runaway early warning device of an energy storage power station provided by the application is shown in Figure 3 The battery thermal runaway early warning device of the energy storage power station comprises:

[0082] A first training module 201 is configured to train a probability neural network and a back propagation neural network by using a training set until the probability neural network converges, the training set comprises a plurality of first training samples with hard labels, the training sample comprises sensing data collected by at least one sensor, and the hard label indicates that the battery of the energy storage power station has thermal runaway or does not have thermal runaway.

[0083] A soft label generation module 202 is configured to predict a second training sample without a label by using the converged probability neural network, to obtain a soft label of the second training sample, and the soft label indicates a probability value of thermal runaway of the battery of the energy storage power station.

[0084] A second training module 203 is configured to train the back propagation neural network by using a plurality of second training samples with soft labels until the back propagation neural network converges.

[0085] The risk prediction module 204 is configured to process the real-time collected sensing data of the energy storage power station by using the converged back propagation neural network, and predict whether the battery of the energy storage power station has a thermal runaway risk.

[0086] The thermal runaway early warning module 205 is configured to issue a thermal runaway early warning when the battery of the energy storage power station has a thermal runaway risk.

[0087] In some embodiments of the present application, the battery thermal runaway early warning device of the energy storage power station further comprises:

[0088] The data reconstruction module is configured to reconstruct the sensing data into three-channel data by taking the three-dimensional space of the energy storage power station as three channels after collecting the sensing data.

[0089] The separable convolution module is configured to input the three-channel data into a deep separable convolution network for processing to obtain a feature map.

[0090] The pooling module is configured to perform global pooling processing on the feature map to obtain a pooled feature.

[0091] The normalization module is configured to perform batch normalization processing on the pooled feature to obtain input features of a probabilistic neural network and a back propagation neural network.

[0092] In some embodiments of the present application, the separable convolution module comprises:

[0093] The spatial convolution submodule is configured to perform spatial convolution processing on each channel of the three-channel data to obtain a spatial convolution feature map.

[0094] The feature concatenation submodule is configured to concatenate the spatial convolution feature maps of the channel data in the dimension to obtain a concatenated feature map.

[0095] The point-wise convolution submodule is configured to perform point-wise convolution processing on the concatenated feature map to obtain a feature map.

[0096] In some embodiments of the present application, the normalization module comprises:

[0097] The mean and variance calculation submodule is configured to calculate the mean and variance of the pooled feature.

[0098] The normalization submodule is configured to normalize the pooled feature based on the mean and the variance to obtain a normalized feature.

[0099] The translation and scaling submodule is configured to perform translation and scaling on the normalized feature to obtain input features of a probabilistic neural network and a back propagation neural network.

[0100] In some embodiments of the present application, the battery thermal runaway early warning device of the energy storage power station further comprises:

[0101] The model optimization module is configured to, after processing the real-time collected sensing data of the energy storage power station by using the converged back propagation neural network, predicting whether the battery of the energy storage power station has a thermal runaway risk, and taking the prediction result as a training set, training the probabilistic neural network and the back propagation neural network, and optimizing the network parameters of the probabilistic neural network and the back propagation neural network.

[0102] In some embodiments of the present application, the sensing data includes gas composition information measured by a gas composition detector, temperature information measured by a temperature sensor, and visible light information measured by a photoelectric smoke detector.

[0103] The battery thermal runaway early warning device of the energy storage power station described above can execute the battery thermal runaway early warning method of the energy storage power station provided in the foregoing embodiments of the present application, and has the corresponding functional modules and beneficial effects of executing the battery thermal runaway early warning method of the energy storage power station.

[0104] Figure 4 A block diagram of an electronic device according to an embodiment of the present application is provided. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headgear, eyewear, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the applications described and / or claimed in this document.

[0105] As shown in Figure 4 The electronic device includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., connected to the at least one processor 11 in communication, where the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0106] A plurality of components in the electronic device are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0107] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the battery thermal runaway early warning method of the energy storage power station.

[0108] In some embodiments, the battery thermal runaway early warning method of the energy storage power station can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the battery thermal runaway early warning method of the energy storage power station described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the battery thermal runaway early warning method of the energy storage power station by any other appropriate means, such as by means of firmware.

[0109] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0110] Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, enables the functions / acts specified in the flowcharts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0111] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0113] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by 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), a blockchain network, and the Internet.

[0114] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0115] The embodiment of the present application further provides a computer program product, comprising a computer program which, when executed by a processor, implements the battery thermal runaway early warning method of the energy storage power station as provided in any embodiment of the present application.

[0116] The computer program code implementing the application can be written in one or more programming languages or combinations of languages including object oriented languages such as Java, Smalltalk, C++ or conventional procedural programming languages such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can 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 the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0117] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps recited in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0118] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A battery thermal runaway early warning method for an energy storage power station, characterized in that, The method comprises the following steps: training a probabilistic neural network and a back propagation neural network using a training set until the probabilistic neural network converges, the training set comprising a plurality of first training samples with hard labels, the training samples comprising sensor data collected by at least one sensor, and the hard labels representing whether thermal runaway occurs in a battery of an energy storage power station; predicting a second training sample without a label using the converged probabilistic neural network to obtain a soft label of the second training sample, the soft label representing a probability value of whether thermal runaway occurs in the battery of the energy storage power station; training the back propagation neural network using a plurality of second training samples with soft labels until the back propagation neural network converges; processing real-time sensor data collected from the energy storage power station using the converged back propagation neural network to predict whether thermal runaway occurs in the battery of the energy storage power station; issuing a thermal runaway warning when thermal runaway occurs in the battery of the energy storage power station.

2. The battery thermal runaway pre-alarm method of an energy storage power plant according to claim 1, characterized in that, After the sensor data is collected, the method further comprises the following steps: reconstructing the sensor data into three-channel data by taking the three-dimensional space of the energy storage power station as three channels; inputting the three-channel data into a deep separable convolution network for processing to obtain a feature map; performing global pooling processing on the feature map to obtain a pooled feature; performing batch normalization processing on the pooled feature to obtain input features of the probabilistic neural network and the back propagation neural network.

3. The battery thermal runaway pre-alarm method of an energy storage power plant according to claim 2, characterized in that, The method of inputting the three-channel data into a deep separable convolution network for processing to obtain a feature map comprises the following steps: performing spatial convolution processing on each channel of the three-channel data to obtain a spatial convolution feature map; splicing the spatial convolution feature maps of the channel data in the dimension to obtain a spliced feature map; performing point-by-point convolution processing on the spliced feature map to obtain a feature map.

4. The battery thermal runaway pre-alarm method of energy storage power stations according to claim 2, characterized in that, The method of performing batch normalization processing on the pooled feature to obtain input features of the probabilistic neural network and the back propagation neural network comprises the following steps: calculating the mean and variance of the pooled feature; normalizing the pooled feature based on the mean and the variance to obtain a normalized feature; performing translation scaling on the normalized feature to obtain input features of the probabilistic neural network and the back propagation neural network.

5. The battery thermal runaway early warning method for energy storage plants according to any of claims 1-3, characterized in that, After processing real-time sensor data collected from the energy storage power station using the converged back propagation neural network to predict whether thermal runaway occurs in the battery of the energy storage power station, the method further comprises the following steps: training the probabilistic neural network and the back propagation neural network using the prediction result as a training set to optimize network parameters of the probabilistic neural network and the back propagation neural network.

6. The battery thermal runaway early warning method of energy storage power plants according to any of claims 1-3, characterized in that, The sensor data comprises gas composition information measured by a gas composition detector, temperature information measured by a temperature sensor, and visible light information measured by a photoelectric smoke detector.

7. A battery thermal runaway early warning device for an energy storage power plant, characterized in that, The method comprises the following steps: The first training module is configured to train the probabilistic neural network and the back propagation neural network using a training set until the probabilistic neural network converges, the training set comprising a plurality of first training samples with hard labels, the training samples comprising sensor data collected by at least one sensor, and the hard labels representing whether thermal runaway of the battery of the energy storage power station occurs or not; The soft label generation module is configured to predict, using the converged probabilistic neural network, a second training sample without a label to obtain a soft label of the second training sample, the soft label representing a probability value of thermal runaway of the battery of the energy storage power station; The second training module is configured to train the back propagation neural network using a plurality of second training samples with soft labels until the back propagation neural network converges; The risk prediction module is configured to process, using the converged back propagation neural network, real-time sensor data collected from the energy storage power station to predict whether the battery of the energy storage power station has a thermal runaway risk; The runaway early warning module is configured to issue a thermal runaway early warning when the battery of the energy storage power station has a thermal runaway risk.

8. An electronic device, comprising: comprise: one or more processors; a memory device configured to store one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method for early warning of thermal runaway of a battery of an energy storage power station according to any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method for early warning of thermal runaway of a battery of an energy storage power station according to any one of claims 1-6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method for early warning of thermal runaway of a battery of an energy storage power station according to any one of claims 1-6.

Images