Heat pump system thermal runaway treatment method, device, equipment and medium

Abstract

The invention discloses a thermal runaway processing method, device, equipment and medium for a heat pump system, and the method comprises the steps: extracting effective features from multi-source working condition data collected from a plurality of time steps of the heat pump system, inputting the effective features of the plurality of time steps into a pre-constructed thermal runaway risk early warning model based on a long-short-term memory neural network for processing, when the thermal runaway risk grade is the first grade, the load of a compressor is reduced, and the opening degree of an electronic expansion valve is reduced, when the thermal runaway risk grade is the second grade, the compressor is controlled to stop working, and a lateral flow guide fan is started, and when the thermal runaway risk grade is the third grade, the lateral flow guide fan is controlled to stop working. The risk level of thermal runaway of the heat pump system can be predicted in advance based on the multi-source working condition data of the heat pump system, corresponding treatment measures are executed based on the corresponding risk level, explosion caused by continuous increase of the thermal runaway risk of the heat pump system is avoided, and safety is improved.

Description

Technical Field

[0001] The present invention relates to thermal runaway processing technology, and in particular to a method, device, equipment and medium for thermal runaway processing of a heat pump system. Background Art

[0002] As an efficient heat energy conversion device, air source heat pump uses the heat in the air for cooling or heating. Its core components (compressor, circuit boards, refrigerant pipelines) face the risk of thermal runaway during long-term operation.

[0003] Existing air-energy heat pump thermal runaway treatment technologies focus more on how to prevent the spread of fire after thermal runaway occurs, such as using flame-retardant seals on electrical boxes and traditional fire extinguishing devices. These methods mainly prevent the spread of fire through structural design, which cannot be prevented in advance and cannot completely prevent the spread of fire, which may cause major safety accidents, especially for air-energy heat pumps with refrigerants such as R290 and R32. When the fire spreads completely, it may cause a unit explosion safety accident. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for handling thermal runaway of a heat pump system, which can predict the risk level of thermal runaway of the heat pump system in advance and execute corresponding handling measures based on the corresponding risk level, so as to avoid the continuous increase of the risk of thermal runaway of the heat pump system and cause explosion, thereby improving safety.

[0005] In a first aspect, the present invention provides a method for processing thermal runaway of a heat pump system, comprising:

[0006] Obtain multi-source operating data collected at multiple time steps of the heat pump system;

[0007] Extracting effective features from the multi-source operating condition data;

[0008] Inputting effective features of multiple time steps into a pre-built thermal runaway risk warning model based on a long short-term memory neural network for processing, thereby obtaining a thermal runaway risk level of the heat pump system;

[0009] When the thermal runaway risk level is the first level, reducing the load of the compressor and reducing the opening of the electronic expansion valve;

[0010] When the thermal runaway risk level is the second level, controlling the compressor to stop working and turning on the side guide fan;

[0011] When the thermal runaway risk level is the third level, the fire extinguishing device is activated to spray fire extinguishing aerosol.

[0012] Optionally, after determining that the thermal runaway risk level is level 1, the method further includes:

[0013] Acquire a first temperature gradient of a circuit board area of ​​the heat pump system and a refrigerant concentration transmitted back by a gas detector;

[0014] When the temperature gradient is greater than the preset gradient and the refrigerant concentration reaches the set concentration, the thermal runaway risk level is upgraded to the second level, the compressor is controlled to stop working, and the side guide fan is turned on.

[0015] Optionally, after determining that the thermal runaway risk level is the second level, the method further includes:

[0016] After a set time, determining whether the temperature gradient of the circuit board area of ​​the heat pump system drops to a second temperature gradient, the second temperature gradient being less than the first temperature gradient;

[0017] If the temperature gradient drops to the second temperature gradient, the thermal runaway risk level is maintained at the second level;

[0018] If the temperature gradient does not drop to the second temperature gradient, the thermal runaway risk level is upgraded to the third level, and the fire extinguishing device is activated to spray fire extinguishing aerosol.

[0019] Optionally, the long short-term memory neural network includes N transfer cells, and the effective features of multiple time steps are input into a pre-built thermal runaway risk warning model based on the long short-term memory neural network for processing to obtain the thermal runaway risk level of the heat pump system, including:

[0020] The first transfer cell receives the effective features of the first time step for calculation, and obtains the hidden state and cell state output by the first transfer cell;

[0021] The i-th transfer cell receives the effective features of the i-th time step, and calculates the hidden state and cell state output by the i-1-th transfer cell to obtain the hidden state and cell state output by the i-th transfer cell, where i is a positive integer greater than 1 and less than N;

[0022] The Nth transfer cell receives the effective features of the Nth time step, and calculates the hidden state and cell state output by the N-1th transfer cell to obtain the cell state output by the Nth transfer cell as the time series feature;

[0023] Mapping the time series characteristics to the risk level space to obtain the predicted probability value of each risk level;

[0024] The risk level corresponding to the maximum predicted probability value is used as the thermal runaway risk level of the heat pump system.

[0025] Optionally, before acquiring the multi-source operating data collected at multiple time steps of the heat pump system, the following is further included:

[0026] Obtain historical multi-source operating data;

[0027] Preprocessing the historical multi-source operating condition data;

[0028] Performing principal component analysis on the preprocessed historical multi-source operating condition data to determine effective features of the historical multi-source operating condition data;

[0029] The effective features of the historical multi-source operating condition data are used as a training set to train a thermal runaway risk warning model based on a long short-term memory neural network.

[0030] Optionally, preprocessing the historical multi-source operating condition data includes:

[0031] Filling missing values ​​of the historical multi-source operating condition data using linear interpolation;

[0032] Delete abnormal data that deviates from the mean by 3 times the standard deviation in the historical multi-source operating condition data.

[0033] Optionally, performing principal component analysis on the preprocessed historical multi-source operating condition data to determine effective features of the historical multi-source operating condition data includes:

[0034] Performing standardization processing on the historical multi-source operating condition data to obtain standardized data;

[0035] Calculating a covariance matrix of the standardized data;

[0036] Solving for the eigenvalues ​​and eigencomponents of the covariance matrix;

[0037] The characteristic components are arranged in descending order according to the size of the characteristic values, and the top k characteristic components are taken as the effective features of the historical multi-source operating condition data.

[0038] In a second aspect, the present invention further provides a heat pump system thermal runaway processing device, comprising:

[0039] A data acquisition module, used to acquire multi-source operating data collected at multiple time steps of the heat pump system;

[0040] A feature extraction module, used to extract effective features from the multi-source operating condition data;

[0041] A risk level determination module, used for inputting effective features of multiple time steps into a pre-built thermal runaway risk warning model based on a long short-term memory neural network for processing, so as to obtain a thermal runaway risk level of the heat pump system;

[0042] a first processing module, configured to reduce the load of the compressor and the opening of the electronic expansion valve when the thermal runaway risk level is the first level;

[0043] A second processing module is used to control the compressor to stop working and start the side guide fan when the thermal runaway risk level is the second level;

[0044] The third processing module is used to activate the fire extinguishing device to spray fire extinguishing aerosol when the thermal runaway risk level is the third level.

[0045] In a third aspect, the present invention further provides an electronic device, comprising:

[0046] one or more processors;

[0047] A storage device for storing one or more programs;

[0048] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for handling thermal runaway of a heat pump system as provided in the first aspect of the present invention.

[0049] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for handling thermal runaway of a heat pump system as provided in the first aspect of the present invention.

[0050] The method for handling thermal runaway of a heat pump system provided by the present invention obtains multi-source operating condition data collected at multiple time steps of the heat pump system, extracts effective features from the multi-source operating condition data, and inputs the effective features of the multiple time steps into a pre-constructed thermal runaway risk warning model based on a long short-term memory neural network for processing, so as to obtain the thermal runaway risk level of the heat pump system. When the thermal runaway risk level is the first level, the load of the compressor is reduced, and the opening of the electronic expansion valve is reduced. When the thermal runaway risk level is the second level, the compressor is controlled to stop working, and the lateral guide fan is turned on. When the thermal runaway risk level is the third level, the fire extinguishing device is activated to spray fire extinguishing aerosol. The risk level of thermal runaway of the heat pump system can be predicted in advance based on the multi-source operating condition data of the heat pump system, and corresponding handling measures are executed based on the corresponding risk level, so as to avoid the continuous increase of the thermal runaway risk of the heat pump system and cause explosion, thereby improving safety.

[0051] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 A flow chart of a method for processing thermal runaway of a heat pump system provided by the present invention;

[0054] Figure 2 A schematic diagram of the structure of a heat pump system thermal runaway processing device provided by the present invention;

[0055] Figure 3 The present invention provides a schematic structural diagram of an electronic device.

[0056] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0058] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0059] Figure 1This is a flow chart of a method for handling thermal runaway of a heat pump system provided by the present invention. This embodiment can be applied to thermal runaway risk warning of a heat pump system and to perform corresponding thermal runaway processing. The method can be executed by a device for handling thermal runaway of a heat pump system provided by the present invention. The device can be implemented by software and / or hardware and is usually configured in a computer device, such as Figure 1 As shown, the heat pump system thermal runaway processing method includes the following steps:

[0060] S101. Acquire multi-source operating data collected at multiple time steps of a heat pump system.

[0061] In an embodiment of the present invention, during the operation of the heat pump system, multi-source operating data collected at multiple time steps of the heat pump system are collected, wherein the multi-source operating data represent different operating data collected in various ways, such as heat pump operating parameters (including compressor current, refrigerant pressure, temperature of each part, etc.) and environmental perception data (infrared thermal imaging temperature field, volatile organic compound gas concentration, smoke particle size distribution), etc., which are not limited by the present invention. Exemplarily, various sensors are used to collect heat pump operating parameters in real time, such as compressor current can use current transformer, refrigerant pressure can use refrigerant pressure sensor, and temperature of each part can use temperature sensor; in terms of environmental perception data, infrared thermal imaging temperature field is obtained by infrared thermal imager, volatile organic compound gas concentration is detected by gas sensor, and smoke particle size distribution is measured by laser particle size analyzer. The collected data is recorded and stored at certain time intervals (such as every second, every minute).

[0062] S102, extracting effective features from multi-source operating condition data.

[0063] In the embodiment of the present invention, the acquired multi-source operating condition data may contain data types that are irrelevant to the thermal runaway risk prediction. Therefore, it is necessary to extract features that are important to the thermal runaway risk prediction from the original data as effective features. In the embodiment of the present invention, some collected data can be directly used as effective features. In addition to directly using the collected data, some derived features can also be calculated, such as various temperature change rates, pressure change rates, etc., which are not limited in the embodiment of the present invention.

[0064] S103, inputting the effective features of multiple time steps into a pre-built thermal runaway risk warning model based on a long short-term memory neural network for processing, and obtaining a thermal runaway risk level of the heat pump system.

[0065] In the embodiment of the present invention, the structure of the thermal runaway risk warning model is determined in advance, and then the thermal runaway risk warning model is trained to determine the model parameters. During the application process, the effective features of multiple time steps are input into the trained thermal runaway risk warning model for processing to obtain the thermal runaway risk level of the heat pump system.

[0066] Exemplarily, the thermal runaway risk warning model includes an input layer, a long short-term memory neural network (Long Short-Term Memory, LSTM), a fully connected layer and an output layer.

[0067] Among them, the input layer is used to receive valid features, and the number of nodes in the input layer corresponds to the number of valid features.

[0068] The long short-term memory neural network includes N transfer cells. The first transfer cell receives the effective features of the first time step for calculation, and obtains the hidden state and cell state output by the first transfer cell. The i-th transfer cell receives the effective features of the i-th time step, and calculates in combination with the hidden state and cell state output by the i-1-th transfer cell, and obtains the hidden state and cell state output by the i-th transfer cell, i is a positive integer greater than 1 and less than N, the N-th transfer cell receives the effective features of the N-th time step, and calculates in combination with the hidden state and cell state output by the N-1-th transfer cell, and obtains the cell state output by the N-th transfer cell as the time series feature.

[0069] The fully connected layer is used to perform nonlinear transformation on the output of LSTM and map the time series features to the risk level space.

[0070] The number of nodes in the output layer is 4, corresponding to four risk levels (level 0 P0, level 1 P1, level 2 P2, and level 3 P3). The softmax activation function is used to convert the output into the probability distribution of each risk level. The risk level corresponding to the maximum predicted probability value is taken as the thermal runaway risk level of the heat pump system.

[0071] For example, before the thermal runaway risk warning model is applied, it needs to be trained. The training process is as follows:

[0072] 1. Obtain historical multi-source operating data.

[0073] Exemplarily, historical multi-source operating data of the heat pump system is obtained, and the corresponding risk level (P0-P3) is marked for the data of each time step according to the actual thermal runaway risk classification level.

[0074] 2. Preprocess historical multi-source operating data.

[0075] Preprocess historical multi-source operating data to improve data accuracy.

[0076] For example, check whether there are missing values ​​in the collected data. For a small number of missing values, linear interpolation can be used to fill them; if the missing values ​​are large and continuous, consider deleting the data in that time period. For example, if the compressor current data at a certain moment is missing, linear interpolation can be performed based on the current values ​​at the adjacent moments to obtain an approximate value at that moment.

[0077] For example, outliers in the data are identified, such as pressure values ​​or temperature values ​​that are clearly beyond the normal range. Statistical methods, such as the 3σ principle, can be used to treat data that deviate from the mean by more than 3 standard deviations as outliers, which are then corrected to reasonable values ​​or deleted.

[0078] 3. Perform principal component analysis on the preprocessed historical multi-source operating condition data to determine the effective features of the historical multi-source operating condition data.

[0079] Principal Component Analysis (PCA) is a common data analysis method, often used for dimensionality reduction of high-dimensional data, and can be used to extract the main characteristic components of the data. The main idea of ​​PCA is to map n-dimensional features to k-dimensional features. These k-dimensional features are new orthogonal features also called principal components, which are reconstructed k-dimensional features based on the original n-dimensional features.

[0080] Exemplarily, the principal component analysis process is as follows:

[0081] 3.1. Standardize the historical multi-source operating data to obtain standardized data.

[0082] Each variable in the original data is standardized so that they have the same mean and variance and eliminate the influence of dimension and order of magnitude.

[0083] 3.2. Calculate the covariance matrix of the standardized data.

[0084] Covariance can represent the correlation between two variables. In order to allow the two variables to represent as much original information as possible, we hope that there is no linear correlation between them, because correlation means that the two variables are not completely independent and there must be repeated information.

[0085] 3.3. Solve the eigenvalues ​​and eigencomponents of the covariance matrix.

[0086] Solve the eigenvalues ​​and eigencomponents of the covariance matrix. The size of the eigenvalue reflects the importance of the principal component, and the eigenvector reflects the composition of the principal component.

[0087] 3.4. Arrange the characteristic components in descending order according to the size of the eigenvalues, and take the top k characteristic components as the effective features of the historical multi-source operating condition data.

[0088] The characteristic components are arranged in descending order according to the size of the eigenvalues, and the number of principal components to be extracted is determined according to the actual needs and the distribution of the eigenvalues. Usually, the k characteristic components with eigenvalues ​​greater than 1 and ranked at the top are selected as the effective features of the historical multi-source operating condition data, which contain most of the information of the original data.

[0089] 4. The effective features of historical multi-source operating condition data are used as training sets to train the thermal runaway risk warning model based on long short-term memory neural network.

[0090] For example, the effective features of historical multi-source operating condition data are divided into training set, validation set and test set according to a certain ratio, usually 7:2:1. The training set is used for model training, the validation set is used to adjust the model's hyperparameters, and the test set is used to evaluate the final performance of the model. The thermal runaway risk warning model is trained using the training set until the model converges.

[0091] S104: When the thermal runaway risk level is the first level, reduce the load of the compressor and decrease the opening of the electronic expansion valve.

[0092] In the embodiment of the present invention, when the thermal runaway risk level is level zero (P0), the unit operates normally without excessive interference adjustment.

[0093] When the thermal runaway risk level is level 1 (P1), the load on the compressor is reduced and the opening of the electronic expansion valve is decreased to try to suppress abnormal temperature rise.

[0094] After determining that the thermal runaway risk level is the first level, the first temperature gradient of the circuit board area of ​​the heat pump system and the refrigerant concentration transmitted back by the gas detector are obtained. When the temperature gradient is greater than the preset gradient and the refrigerant concentration reaches the set concentration, the thermal runaway risk level is upgraded to the second level, the compressor is controlled to stop working, and the side guide fan is turned on to avoid further increase in risk.

[0095] S105. When the thermal runaway risk level is the second level, the compressor is controlled to stop working, and the side guide fan is turned on.

[0096] When the thermal runaway risk level is the second level (P2), the compressor is controlled to stop working, and the side guide fan is turned on to increase internal air circulation for cooling.

[0097] After determining that the thermal runaway risk level is the second level, after a set period of time, determine whether the temperature gradient of the circuit board area of ​​the heat pump system drops to the second temperature gradient. The second temperature gradient is less than the first temperature gradient. If the temperature gradient drops to the second temperature gradient, the thermal runaway risk level is maintained at the second level. If the temperature gradient does not drop to the second temperature gradient, the thermal runaway risk level is upgraded to the third level, and the fire extinguishing device is activated to spray fire extinguishing aerosol to avoid explosion.

[0098] S106. When the thermal runaway risk level is the third level, activate the fire extinguishing device to spray fire extinguishing aerosol.

[0099] When the thermal runaway risk level is the third level, the fire extinguishing device is triggered to spray fire extinguishing aerosol. The aerosol generator (usually a solid mixture of potassium nitrate / strontium nitrate + carbon-based reducing agent) stored in the fire extinguishing device undergoes redox reaction at high temperature, generating a large amount of inert gas (N2, CO2), metal salt particles (K2CO3) and nano-scale solid particles (particle size <2μm). The generated high-temperature gas and particle mixture is rapidly cooled to 60-80℃ through the cooling layer, forming a stable aerosol cloud that spreads evenly to the protected area. K in the aerosol + , Sr 2 + and other active ions and OH in the combustion chain reaction - , H + Free radicals combine to interrupt the combustion reaction. Nano-sized metal salt particles are adsorbed on the surface of combustibles to form an isolation layer to prevent oxygen from contacting. Inert gases (N2, CO2) dilute the oxygen concentration, reducing the local oxygen content to below 15% (below the combustion threshold of most substances). Aerosols absorb environmental heat when released, and the water vapor in the reaction products evaporates to further reduce the temperature of the combustion zone.

[0100] The method for handling thermal runaway of a heat pump system provided by the present invention obtains multi-source operating condition data collected at multiple time steps of the heat pump system, extracts effective features from the multi-source operating condition data, and inputs the effective features of the multiple time steps into a pre-constructed thermal runaway risk warning model based on a long short-term memory neural network for processing, so as to obtain the thermal runaway risk level of the heat pump system. When the thermal runaway risk level is the first level, the load of the compressor is reduced, and the opening of the electronic expansion valve is reduced. When the thermal runaway risk level is the second level, the compressor is controlled to stop working, and the lateral guide fan is turned on. When the thermal runaway risk level is the third level, the fire extinguishing device is activated to spray fire extinguishing aerosol. The risk level of thermal runaway of the heat pump system can be predicted in advance based on the multi-source operating condition data of the heat pump system, and corresponding handling measures are executed based on the corresponding risk level, so as to avoid the continuous increase of the thermal runaway risk of the heat pump system and cause explosion, thereby improving safety.

[0101] Figure 2A schematic diagram of the structure of a heat pump system thermal runaway processing device provided by the present invention is shown in FIG. Figure 2 As shown, the heat pump system thermal runaway processing device comprises:

[0102] The data acquisition module 201 is used to acquire multi-source operating data collected at multiple time steps of the heat pump system;

[0103] A feature extraction module 202, used to extract effective features from the multi-source operating condition data;

[0104] The risk level determination module 203 is used to input the effective features of multiple time steps into a pre-built thermal runaway risk warning model based on a long short-term memory neural network for processing, so as to obtain the thermal runaway risk level of the heat pump system;

[0105] A first processing module 204 is used to reduce the load of the compressor and the opening of the electronic expansion valve when the thermal runaway risk level is the first level;

[0106] The second processing module 205 is used to control the compressor to stop working and start the side guide fan when the thermal runaway risk level is the second level;

[0107] The third processing module 206 is used to activate the fire extinguishing device to spray fire extinguishing aerosol when the thermal runaway risk level is the third level.

[0108] In some embodiments of the present invention, the heat pump system thermal runaway processing device further includes:

[0109] A temperature concentration acquisition module, used to acquire a first temperature gradient of a circuit board area of ​​the heat pump system and a refrigerant concentration transmitted back by a gas detector after determining that the thermal runaway risk level is the first level;

[0110] The first risk upgrade module is used to upgrade the thermal runaway risk level to the second level when the temperature gradient is greater than a preset gradient and the refrigerant concentration reaches a set concentration, and control the compressor to stop working and start the lateral guide fan.

[0111] In some embodiments of the present invention, the heat pump system thermal runaway processing device further includes:

[0112] a judgment module, configured to judge whether the temperature gradient of the circuit board area of ​​the heat pump system drops to a second temperature gradient after a set time period after determining that the thermal runaway risk level is the second level, and the second temperature gradient is less than the first temperature gradient;

[0113] a risk level maintaining module, configured to maintain the thermal runaway risk level at the second level when the temperature gradient drops to a second temperature gradient;

[0114] The second risk upgrade module is used to upgrade the thermal runaway risk level to the third level when the temperature gradient does not drop to the second temperature gradient, and activate the fire extinguishing device to spray fire extinguishing aerosol.

[0115] In some embodiments of the present invention, the long short-term memory neural network includes N transmission cells, and the risk level determination module 203 includes:

[0116] A first calculation submodule is used for the first transfer cell to receive the effective features of the first time step for calculation, and obtain the hidden state and cell state output by the first transfer cell;

[0117] The second calculation submodule is used for the i-th transfer cell to receive the effective features of the i-th time step, and to calculate the hidden state and cell state output by the i-1-th transfer cell to obtain the hidden state and cell state output by the i-th transfer cell, where i is a positive integer greater than 1 and less than N;

[0118] The third calculation submodule is used for the Nth transfer cell to receive the effective features of the Nth time step, and to calculate in combination with the hidden state and cell state output by the N-1th transfer cell, to obtain the cell state output by the Nth transfer cell as the time series feature;

[0119] The probability value calculation submodule is used to map the time series characteristics to the risk level space to obtain the predicted probability value of each risk level;

[0120] The risk level determination submodule is used to use the risk level corresponding to the maximum predicted probability value as the thermal runaway risk level of the heat pump system.

[0121] In some embodiments of the present invention, the heat pump system thermal runaway processing device further includes:

[0122] A historical data acquisition module, used for acquiring historical multi-source operating data before acquiring multi-source operating data collected at multiple time steps of the heat pump system;

[0123] A preprocessing module, used for preprocessing the historical multi-source operating condition data;

[0124] A principal component analysis module, used to perform principal component analysis on the preprocessed historical multi-source operating condition data to determine effective features of the historical multi-source operating condition data;

[0125] A training module is used to train a thermal runaway risk warning model based on a long short-term memory neural network using the effective features of the historical multi-source operating condition data as a training set.

[0126] In some embodiments of the present invention, the preprocessing module includes:

[0127] An interpolation submodule, used to fill in missing values ​​of the historical multi-source operating condition data using linear interpolation;

[0128] The deletion submodule is used to delete abnormal data that deviates from the mean by 3 times the standard deviation in the historical multi-source operating condition data.

[0129] In some embodiments of the present invention, the principal component analysis module includes:

[0130] A standardization submodule, used for performing standardization processing on the historical multi-source operating condition data to obtain standardized data;

[0131] A covariance matrix calculation submodule, used to calculate the covariance matrix of the standardized data;

[0132] An eigenvalue solving submodule is used to solve the eigenvalues ​​and eigencomponents of the covariance matrix;

[0133] The effective feature determination submodule is used to arrange the characteristic components in descending order according to the size of the characteristic values, and take the top k characteristic components as the effective features of the historical multi-source operating condition data.

[0134] The above-mentioned heat pump system thermal runaway processing device can execute the heat pump system thermal runaway processing method provided by the above-mentioned embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the heat pump system thermal runaway processing method.

[0135] Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention, the electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0136] like Figure 3As shown, the electronic device includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to 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.

[0137] A number 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 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.

[0138] The processor 11 may be a variety of general and / or special 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 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 executes the various methods and processes described above, such as a heat pump system thermal runaway processing method.

[0139] In some embodiments, the heat pump system thermal runaway processing method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on an electronic device via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the heat pump system thermal runaway processing method described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the heat pump system thermal runaway processing method in any other appropriate manner (e.g., by means of firmware).

[0140] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0142] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. 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.

[0143] To provide interaction with a user, the systems and techniques described herein may 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 trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0144] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may 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.

[0145] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may 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 difficult management and weak business scalability in traditional physical hosts and VPS services.

[0146] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the method for handling thermal runaway of a heat pump system as provided in any embodiment of the present application.

[0147] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can 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 the case of a remote computer, 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 can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0148] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0149] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for handling thermal runaway of a heat pump system, characterized in that: include: Obtain multi-source operating data collected at multiple time steps of the heat pump system; Extracting effective features from the multi-source operating condition data; Inputting effective features of multiple time steps into a pre-built thermal runaway risk warning model based on a long short-term memory neural network for processing, thereby obtaining a thermal runaway risk level of the heat pump system; When the thermal runaway risk level is the first level, reducing the load of the compressor and reducing the opening of the electronic expansion valve; When the thermal runaway risk level is the second level, controlling the compressor to stop working and turning on the side guide fan; When the thermal runaway risk level is the third level, the fire extinguishing device is activated to spray fire extinguishing aerosol.

2. The method for handling thermal runaway of a heat pump system according to claim 1, characterized in that: After determining that the thermal runaway risk level is level 1, the method further includes: Acquire a first temperature gradient of a circuit board area of ​​the heat pump system and a refrigerant concentration transmitted back by a gas detector; When the temperature gradient is greater than the preset gradient and the refrigerant concentration reaches the set concentration, the thermal runaway risk level is upgraded to the second level, the compressor is controlled to stop working, and the side guide fan is turned on.

3. The method for handling thermal runaway of a heat pump system according to claim 1 or 2, characterized in that: After determining that the thermal runaway risk level is level 2, the method further includes: After a set time, determining whether the temperature gradient of the circuit board area of ​​the heat pump system drops to a second temperature gradient, the second temperature gradient being less than the first temperature gradient; If the temperature gradient drops to the second temperature gradient, the thermal runaway risk level is maintained at the second level; If the temperature gradient does not drop to the second temperature gradient, the thermal runaway risk level is upgraded to the third level, and the fire extinguishing device is activated to spray fire extinguishing aerosol.

4. The method for handling thermal runaway of a heat pump system according to claim 1, characterized in that: The long short-term memory neural network includes N transfer cells, and the effective features of multiple time steps are input into a pre-built thermal runaway risk warning model based on the long short-term memory neural network for processing to obtain the thermal runaway risk level of the heat pump system, including: The first transfer cell receives the effective features of the first time step for calculation, and obtains the hidden state and cell state output by the first transfer cell; The i-th transfer cell receives the effective features of the i-th time step, and calculates the hidden state and cell state output by the i-1-th transfer cell to obtain the hidden state and cell state output by the i-th transfer cell, where i is a positive integer greater than 1 and less than N; The Nth transfer cell receives the effective features of the Nth time step, and calculates the hidden state and cell state output by the N-1th transfer cell to obtain the cell state output by the Nth transfer cell as the time series feature; Mapping the time series characteristics to the risk level space to obtain the predicted probability value of each risk level; The risk level corresponding to the maximum predicted probability value is used as the thermal runaway risk level of the heat pump system.

5. The method for handling thermal runaway of a heat pump system according to claim 1, characterized in that: Before obtaining the multi-source operating data collected at multiple time steps of the heat pump system, it also includes: Obtain historical multi-source operating data; Preprocessing the historical multi-source operating condition data; Performing principal component analysis on the preprocessed historical multi-source operating condition data to determine effective features of the historical multi-source operating condition data; The effective features of the historical multi-source operating condition data are used as a training set to train a thermal runaway risk warning model based on a long short-term memory neural network.

6. The method for handling thermal runaway of a heat pump system according to claim 5, characterized in that: Preprocessing the historical multi-source operating condition data includes: Filling missing values ​​of the historical multi-source operating condition data using linear interpolation; Delete abnormal data that deviates from the mean by 3 times the standard deviation in the historical multi-source operating condition data.

7. The method for handling thermal runaway of a heat pump system according to claim 5, characterized in that: The preprocessed historical multi-source operating condition data is subjected to principal component analysis to determine effective features of the historical multi-source operating condition data, including: Performing standardization processing on the historical multi-source operating condition data to obtain standardized data; Calculating a covariance matrix of the standardized data; Solving for the eigenvalues ​​and eigencomponents of the covariance matrix; The characteristic components are arranged in descending order according to the size of the characteristic values, and the top k characteristic components are taken as the effective features of the historical multi-source operating condition data.

8. A device for handling thermal runaway of a heat pump system, characterized in that: include: A data acquisition module, used to acquire multi-source operating data collected at multiple time steps of the heat pump system; A feature extraction module, used to extract effective features from the multi-source operating condition data; A risk level determination module, used for inputting effective features of multiple time steps into a pre-built thermal runaway risk warning model based on a long short-term memory neural network for processing, so as to obtain a thermal runaway risk level of the heat pump system; a first processing module, configured to reduce the load of the compressor and the opening of the electronic expansion valve when the thermal runaway risk level is the first level; A second processing module is used to control the compressor to stop working and start the side guide fan when the thermal runaway risk level is the second level; The third processing module is used to activate the fire extinguishing device to spray fire extinguishing aerosol when the thermal runaway risk level is the third level.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing 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 heat pump system thermal runaway processing method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for handling thermal runaway of a heat pump system as described in any one of claims 1 to 7 is implemented.

Images