Temperature prediction method of power equipment, electronic equipment, storage medium and program product

Abstract

The invention discloses a temperature prediction method of power equipment, electronic equipment, a storage medium and a program product. The method comprises the steps of obtaining target operation data of target power equipment at multiple moments and target environment data of an environment where the target power equipment is located when the target operation data is generated; inputting the target operation data and the target environment data at the multiple moments into a temperature prediction model to obtain the equipment prediction temperature of the target power equipment; wherein the temperature prediction model is obtained by training a full-connection neural network according to sample operation data and sample environment data corresponding to the target power equipment; the full-connection neural network comprises a plurality of full-connection layers; the full connection layers are connected through an activation function. According to the scheme, the temperature of the target power equipment can be predicted based on the full-connection neural network, so that the accuracy and robustness of temperature prediction of the target power equipment are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment prediction, and in particular to a temperature prediction method for power equipment, electronic equipment, storage medium and program product. Background Art

[0002] In recent years, with the continuous growth of electricity demand and the aging of power equipment, the reliable operation of power equipment has become increasingly important. As key equipment in the power system, the temperature of power equipment directly affects the operating life and safety of power equipment. At present, the temperature detection and temperature prediction of power equipment mainly rely on regular manual maintenance and empirical formulas, which leads to certain limitations. It is difficult to accurately and effectively predict the temperature of power equipment in real time, resulting in insufficient prediction accuracy and robustness of the temperature of power equipment. Summary of the invention

[0003] The present invention provides a temperature prediction method for electric power equipment, electronic equipment, storage medium and program product to solve the problems of poor accuracy and insufficient robustness of temperature prediction of electric power equipment.

[0004] According to one aspect of the present invention, a method for predicting temperature of an electric power device is provided, the method comprising:

[0005] Acquire target operation data of the target power equipment at multiple times and target environment data of the environment in which the target power equipment is located when generating the target operation data;

[0006] The target operation data and target environment data at multiple moments are input into the temperature prediction model to obtain the predicted equipment temperature of the target power equipment; wherein the temperature prediction model is obtained by training a fully connected neural network based on sample operation data and sample environment data corresponding to the target power equipment; the fully connected neural network includes multiple fully connected layers; and the fully connected layers are connected by activation functions.

[0007] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0008] at least one processor; and

[0009] a memory communicatively connected to at least one processor; wherein,

[0010] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the temperature prediction method for electric power equipment according to any embodiment of the present invention.

[0011] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the temperature prediction method of the power equipment according to any embodiment of the present invention when executed.

[0012] According to another aspect of the present invention, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the temperature prediction method for electric power equipment as described in any embodiment of the present invention.

[0013] The technical solution of the embodiment of the present invention obtains the target operation data of the target power equipment at multiple moments and the target environment data of the environment in which the target power equipment is located when generating the target operation data, so as to provide effective data support for the subsequent temperature prediction of the target power equipment; the target operation data and the target environment data at multiple moments are input into the temperature prediction model to obtain the equipment predicted temperature of the target power equipment; wherein the temperature prediction model is obtained by training a fully connected neural network based on sample operation data and sample environment data corresponding to the target power equipment; the fully connected neural network includes multiple fully connected layers; the fully connected layers are connected by activation functions, so as to realize the prediction of the temperature of the target power equipment by the trained fully connected neural network, so as to better determine the nonlinear characteristics and dependencies in the operation process of the power equipment, thereby effectively improving the accuracy of the temperature prediction of the target power equipment and ensuring the safety and stability of the operation of the target power equipment.

[0014] 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

[0015] 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.

[0016] Figure 1 A flow chart of a method for predicting temperature of electric power equipment provided in Embodiment 1 of the present invention;

[0017] Figure 2 A flow chart of a method for predicting temperature of electric power equipment provided in Embodiment 2 of the present invention;

[0018] Figure 3 A structural diagram of a temperature prediction device for electric power equipment provided in Embodiment 3 of the present invention;

[0019] Figure 4 A schematic diagram of the structure of an electronic device for implementing a temperature prediction method for electric power equipment provided in a fourth embodiment of the present invention. DETAILED DESCRIPTION

[0020] 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.

[0021] 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.

[0022] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0024] It is understandable that before using the technical solutions disclosed in the embodiments of the present invention, the type, scope of use, usage scenarios, etc. of the personal information involved in the present invention should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0025] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present invention according to the prompt message.

[0026] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0027] It is understandable that the above notification and user authorization process is only illustrative and does not constitute a limitation on the implementation of the present invention. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present invention.

[0028] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0029] Embodiment 1

[0030] Figure 1 A flow chart of a temperature prediction method for electric equipment provided in Embodiment 1 of the present invention. This embodiment can be applied to predicting the temperature of the equipment when the electric equipment is running. The method can be performed by a temperature prediction device for the electric equipment. The temperature prediction device for the electric equipment can be implemented in the form of hardware and / or software. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC, or a server.

[0031] like Figure 1 As shown, the method may specifically include:

[0032] S101. Acquire target operation data of a target power device at multiple moments and target environment data of the environment in which the target power device is located when generating the target operation data.

[0033] In an embodiment of the present invention, the target power equipment may refer to equipment that operates in the power system for the production, transmission, conversion, distribution and consumption of electric energy. Exemplarily, the target power equipment may be a generator, a motor or a transformer. The target operation data may refer to the equipment parameter data when the target power equipment is in operation, wherein the equipment parameter data may be the load, voltage and current of the target power equipment. The target environment data may refer to the equipment environment data when the target power equipment is in operation to generate the target operation data, wherein the equipment environment data may be the temperature and wind speed of the environment where the target power equipment is located.

[0034] Specifically, the device parameter data of the target power equipment when it is running at multiple times can be used as the target operation data of the target power equipment, and the device environment data when the target power equipment is running at multiple times to generate the target operation data can be used as the target environment data of the target power equipment.

[0035] S102. Input the target operation data and target environment data at multiple moments into the temperature prediction model to obtain the predicted equipment temperature of the target power equipment; wherein the temperature prediction model is obtained by training a fully connected neural network based on sample operation data and sample environment data corresponding to the target power equipment; the fully connected neural network includes multiple fully connected layers; and the fully connected layers are connected by activation functions.

[0036] In an embodiment of the present invention, a fully connected neural network is a basic neural network structure, which consists of a fully connected layer and an activation function. A fully connected layer consists of multiple neurons, each of which is connected to all neurons in the previous layer, that is, the input of each neuron is the weighted sum of the outputs of all neurons in the previous layer. Multiple fully connected layers are used to characterize the dependencies between the operating states of power equipment. The fully connected layer generates output by performing a linear transformation on the input, and the calculation formula can be expressed as:

[0037] y=W×x+b,

[0038] Where W represents the weight matrix, x represents the input of the current time step, and b represents the bias term. The activation function is used to perform nonlinear transformation on the output of the fully connected layer, so that the fully connected neural network can learn and approximate complex nonlinear relationships to improve the nonlinear ability of the fully connected neural network. Exemplarily, the activation function can be a Sigmoid function or a linear rectifier function (Rectified Linear Unit, ReLU). The calculation formula of the Sigmoid function is expressed as:

[0039]

[0040] The calculation formula of the linear rectification function is expressed as:

[0041] RELU(x)=max(0,x).

[0042] The sample operation data may refer to the device parameter data corresponding to the target power device used for the fully connected neural network training, such as the device parameter data recorded by the target power device at a historical moment. The sample environment data may refer to the device environment data corresponding to the target power device used for the fully connected neural network training when the sample operation data is generated, such as the device environment data recorded by the target power device at a historical moment when the sample operation data is generated. The temperature prediction model may refer to a model for predicting the temperature of the target power device obtained by training the fully connected neural network with the collected sample operation data and sample environment data corresponding to the target power device.

[0043] Specifically, the target operation data and target environment data of the target power equipment at multiple times may be input into the temperature prediction model, and the predicted device temperature of the target power equipment may be obtained through the output of the temperature prediction model.

[0044] As an optional implementation of the embodiment of the present invention, the network parameters of the fully connected neural network are optimized by a pre-established variable parameter dynamics model; the variable parameter dynamics model is expressed as:

[0045]

[0046] Where t∈R represents time t; e(t)∈R represents the loss function used to calculate the temperature prediction loss between the actual output temperature and the expected output temperature of the fully connected neural network; the parameter λ>0, λ∈R is a constant that controls the convergence speed; the mapping function Φ(·) is a monotonically increasing odd function.

[0047] In the embodiment of the present invention, the functional relationship between the input data of the fully connected neural network and the output temperature can be expressed as:

[0048]

[0049] in, represents the output temperature of the fully connected neural network; x represents the input data of the fully connected neural network; ω∈R represents the learnable parameters of the fully connected neural network. Optimizing the network parameters of the fully connected neural network through the variable parameter dynamics model can refer to determining the optimal parameter matrix of the variable parameter dynamics model as the minimization objective function, that is:

[0050]

[0051] in, represents the objective function, which can refer to the loss function of the variable parameter dynamics model, such as the mean square error loss function or the cross entropy loss function. Then, it can be determined that:

[0052]

[0053] Without loss of generality, λ can be set to 0.1. Then, it can be equivalently expressed as:

[0054]

[0055] It can be further expressed as:

[0056]

[0057] in, Represents ξ ω The generalized inverse matrix of . In order to discretize the expression under continuous time, therefore, combined with the Euler discrete formula, it can be transformed into:

[0058]

[0059] in, and represents the discrete step length, for example It can be taken as 0.1; k>0 and k∈R represents discrete time. ω represents the loss value, i.e., the partial derivative with respect to each ω, and ξ ω The relationship with the fully connected neural network does not change due to the expression form, so ξ ω As a row vector, in order to reduce the number of parameters in the actual calculation of the fully connected neural network. Then, according to the pseudo-inverse solution method of the row vector, we can get:

[0060]

[0061] We can further get:

[0062]

[0063] Among them, α k represents the equivalent learning rate.

[0064] Specifically, by introducing a pre-established variable parameter dynamic model into the fully connected neural network, the network parameters of the fully connected neural network can be dynamically adjusted, and the learning ability of the fully connected neural network on the operating status data of the target power equipment can be enhanced, thereby ensuring that the fully connected neural network can quickly converge to obtain the optimal solution and improve the prediction accuracy and stability; and the network parameters of the fully connected neural network can be adaptively adjusted, so that the model maintains stable prediction performance when responding to different operating conditions and environmental changes, thereby improving the robustness and adaptability of the model.

[0065] As an optional implementation of the embodiment of the present invention, the mapping function is Φ(x)=x.

[0066] Specifically, the mapping function is set to Φ(x)=x so as to reduce the amount of calculation of the fully connected neural network, thereby improving the calculation efficiency.

[0067] As an optional implementation manner of an embodiment of the present invention, after obtaining the equipment predicted temperature of the target power equipment, it also includes: when the equipment predicted temperature meets the preset warning conditions, generating temperature warning information, and displaying the temperature warning information; wherein the preset warning conditions include the equipment predicted temperature reaching the preset temperature threshold and / or the temperature deviation between the equipment predicted temperature and the actual temperature of the equipment at the current moment reaches the preset deviation threshold.

[0068] Specifically, when the predicted device temperature of the target power device reaches a preset temperature threshold, the temperature deviation between the predicted device temperature and the actual device temperature at the current moment reaches a preset deviation threshold, or the predicted device temperature reaches a preset temperature threshold and the temperature deviation reaches a preset deviation threshold, it can be considered that the predicted device temperature of the target power device meets the preset warning condition. Among them, the temperature deviation can refer to the temperature difference or temperature ratio between the predicted device temperature and the actual device temperature. Furthermore, when the predicted device temperature of the target power device meets the preset warning condition, the temperature warning information of the target power device is generated and displayed.

[0069] Exemplarily, the temperature warning information may be information used to prompt the target power equipment of predicted temperature anomalies. The temperature warning information may be prompt information in at least one form such as text, graphics, and audio. Optionally, the temperature warning information may be displayed by playing it through a prompt display device, and / or the temperature warning information may be sent to a target prompt device, etc. By displaying the temperature warning information, it is convenient to remind relevant personnel to conduct safety inspections on the target power equipment, adjust the operating strategy of the target power equipment, prevent overheating of the target power equipment, and improve the safety and reliability of operation.

[0070] The technical solution of the embodiment of the present invention obtains the target operation data of the target power equipment at multiple moments and the target environment data of the environment in which the target power equipment is located when generating the target operation data, so as to provide effective data support for the subsequent temperature prediction of the target power equipment; the target operation data and the target environment data at multiple moments are input into the temperature prediction model to obtain the equipment predicted temperature of the target power equipment; wherein the temperature prediction model is obtained by training a fully connected neural network based on sample operation data and sample environment data corresponding to the target power equipment; the fully connected neural network includes multiple fully connected layers; the fully connected layers are connected by activation functions, so as to realize the prediction of the temperature of the target power equipment by the trained fully connected neural network, so as to better determine the nonlinear characteristics and dependencies in the operation process of the power equipment, thereby effectively improving the accuracy of the temperature prediction of the target power equipment and ensuring the safety and stability of the operation of the target power equipment.

[0071] Embodiment 2

[0072] Figure 2 A flow chart of a temperature prediction method for electric power equipment provided in the second embodiment of the present invention. The technical solution of this embodiment further refines the process of obtaining the target operating data of the target electric power equipment and the target environmental data of the environment in which the target electric power equipment is located when generating the target operating data in the aforementioned embodiment on the basis of the technical solution of the aforementioned embodiment. For the specific implementation method, please refer to the description of this embodiment. Among them, the technical features that are the same or similar to those in the aforementioned embodiment are not repeated here.

[0073] like Figure 2 As shown, the method may specifically include:

[0074] S201. Acquire original operation data of a target electric power device and original environment data of an environment in which the target electric power device is located when generating the original operation data.

[0075] Specifically, the actual device parameter data collected when the target power device is running can be used as the original operation data of the target power device, and the actual device environment data collected when the target power device is running to generate the original operation data can be used as the original environment data of the target power device. Exemplarily, the original operation data and original environment data of the target power device can be collected by a preset sensor.

[0076] S202 , respectively perform standardization processing on the original operation data and the original environment data to obtain target operation data and target environment data of the target power equipment.

[0077] Specifically, by performing standardization processing on the original operation data and the original environment data of the target power equipment, the target operation data and the target environment data of the target power equipment can be obtained, thereby ensuring the quality and consistency of the data. The standardization processing can be a normalization processing.

[0078] S203. Input the target operation data and target environment data at multiple moments into the temperature prediction model to obtain the predicted equipment temperature of the target power equipment; wherein the temperature prediction model is obtained by training a fully connected neural network based on sample operation data and sample environment data corresponding to the target power equipment; the fully connected neural network includes multiple fully connected layers; and the fully connected layers are connected by activation functions.

[0079] As an optional implementation of an embodiment of the present invention, the training process of the temperature prediction model includes: obtaining a sample data set of sample power equipment; wherein the sample data set includes a training data set and a test data set; both the training data set and the test data set include multiple sample data pairs and expected output temperatures corresponding to the sample data pairs; the sample data pairs include sample operation data and sample environment data corresponding to the sample operation data; at least some of the sample data pairs in the training data set and the test data set are different; the sample data pairs in the training data set are input into a fully connected neural network to obtain the model output temperature corresponding to the sample data pairs, determine the temperature prediction loss between the model output temperature and the expected output temperature according to a pre-established variable parameter dynamic model and a preset loss function, and adjust the network parameters of the fully connected neural network according to the temperature prediction loss; test the fully connected neural network after the network parameters are adjusted according to multiple sample data pairs in the test data set and the expected output temperature corresponding to the sample data pairs, and when the test results meet the preset conditions, determine the fully connected neural network as a temperature prediction model.

[0080] In an embodiment of the present invention, a sample data pair may refer to a data pair formed by sample operation data and sample environment data corresponding to the sample operation data. A sample data set may refer to a data set consisting of sample data pairs. A training data set and a test data set may be formed by dividing the sample data set, and there are at least some different sample data pairs in the training data set and the test data set. Exemplarily, the ratio between the amount of data in the training data set and the amount of data in the test data set is 9:1.

[0081] Specifically, by inputting the sample data pairs in the training data set into the fully connected neural network for learning and training, the model output temperature corresponding to the sample data pairs in the training data set output by the fully connected neural network is obtained. Then, the temperature prediction loss between the model output temperature corresponding to the sample data pairs in the training data set and the corresponding expected output temperature is determined according to the pre-established variable parameter dynamics model and the preset loss function, and the network parameters of the fully connected neural network are adjusted according to the temperature prediction loss.

[0082] After the fully connected neural network is trained through the training data set, the trained fully connected neural network can be tested and evaluated through the sample data pairs in the test data set, and the test results of the trained fully connected neural network are determined according to the expected output temperature corresponding to the sample data pairs in the test data set and the model output temperature corresponding to the sample data pairs in the test data set output by the trained fully connected neural network. Exemplarily, the test results of the trained fully connected neural network can be quantified by calculating the mean square error. Furthermore, if the test results of the trained fully connected neural network meet the preset conditions, the trained fully connected neural network is used as a temperature prediction model. If the test results of the trained fully connected neural network do not meet the preset conditions, the fully connected neural network is trained again through the training data set until the test results meet the preset conditions. Exemplarily, the preset condition can be that the temperature difference between the expected output temperature and the model output temperature meets the preset temperature difference threshold.

[0083] As an optional implementation manner of an embodiment of the present invention, the sample data pairs and the expected output temperatures corresponding to the sample data pairs are obtained based on a simulated operation experiment of the power equipment and / or by recording the equipment operation data, equipment environment data and equipment temperature data of sample equipment of the same equipment type as the power equipment in the target power grid at multiple times.

[0084] In the embodiment of the present invention, the device operation data of the target power device, the device environment data and the device temperature data corresponding to the device operation data can be obtained by performing a simulated operation experiment on the target power device, and a sample data pair and an expected output temperature corresponding to the sample data pair can be formed. At the same time, the device operation data of the sample device of the same device type as the target power device when it is running at multiple times, the device environment data and the device temperature data corresponding to the device operation data can also be recorded to form a sample data pair and an expected output temperature corresponding to the sample data pair.

[0085] The technical solution of the embodiment of the present invention obtains the original operation data of the target power equipment and the original environmental data of the environment in which the target power equipment is located when the original operation data is generated; the original operation data and the original environmental data are standardized respectively to obtain the target operation data and the target environmental data of the target power equipment, so as to obtain the target operation data and the target environmental data after the original operation data and the original environmental data are standardized respectively, thereby ensuring the quality and consistency of the data to improve the efficiency of temperature prediction of the target power equipment; the target operation data and the target environmental data at multiple moments are input into the temperature prediction model to obtain the equipment predicted temperature of the target power equipment; wherein the temperature prediction model is obtained by training a fully connected neural network according to the sample operation data and the sample environmental data corresponding to the target power equipment; the fully connected neural network includes multiple fully connected layers; the fully connected layers are connected by activation functions, so as to realize the prediction of the temperature of the target power equipment by the trained fully connected neural network, so as to better determine the nonlinear characteristics and dependencies in the operation process of the power equipment, thereby effectively improving the accuracy of the temperature prediction of the target power equipment and ensuring the safety and stability of the operation of the target power equipment.

[0086] Embodiment 3

[0087] Figure 3 This is a structural diagram of a temperature prediction device for electric equipment provided in the third embodiment of the present invention. This embodiment can be applied to predicting the temperature of the equipment when the electric equipment is running. The temperature prediction device for the electric equipment can be implemented in the form of hardware and / or software. Figure 3 As shown, the temperature prediction device of the electric power equipment may specifically include: a data acquisition module 301 and a device prediction temperature acquisition module 302. The data acquisition module 301 is used to acquire the target operation data of the target electric power equipment at multiple moments and the target environment data of the environment in which the target electric power equipment is located when generating the target operation data; the device prediction temperature acquisition module 302 is used to input the target operation data and the target environment data at multiple moments into the temperature prediction model to obtain the device prediction temperature of the target electric power equipment; the temperature prediction model is obtained by training a fully connected neural network according to the sample operation data and sample environment data corresponding to the target electric power equipment; the fully connected neural network includes multiple fully connected layers; and the fully connected layers are connected by activation functions.

[0088] The technical solution of the embodiment of the present invention obtains the target operation data of the target power equipment at multiple moments and the target environment data of the environment in which the target power equipment is located when generating the target operation data through the data acquisition module 301, so as to provide effective data support for the subsequent temperature prediction of the target power equipment; the target operation data and the target environment data at multiple moments are input into the temperature prediction model through the equipment prediction temperature acquisition module 302 to obtain the equipment prediction temperature of the target power equipment; wherein the temperature prediction model is obtained by training a fully connected neural network based on sample operation data and sample environment data corresponding to the target power equipment; the fully connected neural network includes multiple fully connected layers; the fully connected layers are connected by activation functions, so as to realize the prediction of the temperature of the target power equipment through the trained fully connected neural network, so as to better determine the nonlinear characteristics and dependencies in the operation process of the power equipment, thereby effectively improving the accuracy of the temperature prediction of the target power equipment and ensuring the safety and stability of the operation of the target power equipment.

[0089] Based on any of the above optional technical solutions, optionally, the network parameters of the fully connected neural network are optimized by a pre-established variable parameter dynamics model; the variable parameter dynamics model is expressed as:

[0090]

[0091] Where t∈R represents time t; e(t)∈R represents the loss function used to calculate the temperature prediction loss between the actual output temperature and the expected output temperature of the fully connected neural network; the parameter λ>0, λ∈R is a constant that controls the convergence speed; the mapping function Φ(·) is a monotonically increasing odd function.

[0092] Based on any of the above optional technical solutions, optionally, the mapping function is Φ(x)=x.

[0093] Based on any of the above optional technical solutions, optionally, the training process of the temperature prediction model includes: obtaining a sample data set of sample power equipment; wherein the sample data set includes a training data set and a test data set; both the training data set and the test data set include multiple sample data pairs and expected output temperatures corresponding to the sample data pairs; the sample data pairs include sample operation data and sample environment data corresponding to the sample operation data; at least some of the sample data pairs in the training data set and the test data set are different; the sample data pairs in the training data set are input into a fully connected neural network to obtain the model output temperature corresponding to the sample data pairs, determine the temperature prediction loss between the model output temperature and the expected output temperature according to a pre-established variable parameter dynamic model and a preset loss function, and adjust the network parameters of the fully connected neural network according to the temperature prediction loss; test the fully connected neural network after the network parameters are adjusted according to multiple sample data pairs in the test data set and the expected output temperature corresponding to the sample data pairs, and when the test results meet the preset conditions, determine the fully connected neural network as a temperature prediction model.

[0094] Based on any of the above-mentioned optional technical solutions, optionally, the sample data pairs and the expected output temperatures corresponding to the sample data pairs are obtained according to a simulated operation experiment of the power equipment and / or by recording the equipment operation data, equipment environment data and equipment temperature data of sample equipment of the same equipment type as the power equipment in the target power grid at multiple times.

[0095] Based on any of the above optional technical solutions, optionally, the data acquisition module includes 301: a first acquisition unit and a second acquisition unit. The first acquisition unit is used to acquire the original operation data of the target power equipment and the original environmental data of the environment in which the target power equipment is located when the original operation data is generated; the second acquisition unit is used to perform standardization processing on the original operation data and the original environmental data respectively to obtain the target operation data and target environmental data of the target power equipment.

[0096] On the basis of any of the above optional technical solutions, the temperature prediction device of the power equipment may further include: a temperature warning module. The temperature warning module is used to generate temperature warning information and display the temperature warning information after obtaining the predicted temperature of the target power equipment and when the predicted temperature of the equipment meets the preset warning conditions; wherein the preset warning conditions include that the predicted temperature of the equipment reaches a preset temperature threshold and / or the temperature deviation between the predicted temperature of the equipment and the actual temperature of the equipment at the current moment reaches a preset deviation threshold.

[0097] The temperature prediction device for electric power equipment provided in the embodiment of the present invention can execute the temperature prediction method for electric power equipment provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0098] Embodiment 4

[0099] Figure 4 A schematic diagram of the structure of an electronic device for implementing a temperature prediction method for power equipment provided in Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may 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 merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0100] like Figure 4 As shown, the electronic device 10 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 10 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.

[0101] A number of components in the electronic device 10 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 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0102] 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 temperature prediction method for power equipment.

[0103] In some embodiments, the temperature prediction method of the power device 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 the electronic device 10 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 temperature prediction method of the power device described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the temperature prediction method of the power device in any other appropriate manner (e.g., by means of firmware).

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] 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.

[0110] An embodiment of the present invention also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, it can implement the technical solution of the temperature prediction method of the power equipment in the above embodiment.

[0111] 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.

[0112] 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 temperature prediction method for electric power equipment, characterized in that: The method comprises: Acquire target operation data of a target electric power device at multiple moments and target environment data of an environment in which the target electric power device is located when generating the target operation data; The target operation data and the target environment data at multiple moments are input into a temperature prediction model to obtain the predicted equipment temperature of the target power equipment; wherein the temperature prediction model is obtained by training a fully connected neural network based on sample operation data and sample environment data corresponding to the target power equipment; the fully connected neural network includes multiple fully connected layers; the fully connected layers are connected by activation functions.

2. The method according to claim 1, characterized in that The network parameters of the fully connected neural network are optimized by a pre-established variable parameter dynamics model; the variable parameter dynamics model is expressed as: Wherein, t∈R represents time t; e(t)∈R represents a loss function for calculating the temperature prediction loss between the actual output temperature and the expected output temperature of the fully connected neural network; parameter λ>0, λ∈R is a constant for controlling the convergence speed; and mapping function Φ(·) is a monotonically increasing odd function.

3. The method according to claim 2, characterized in that The mapping function is Φ(x)=x.

4. The method according to claim 2, characterized in that: The training process of the temperature prediction model includes: Acquire a sample data set of a sample power device; wherein the sample data set includes a training data set and a test data set; the training data set and the test data set each include a plurality of sample data pairs and expected output temperatures corresponding to the sample data pairs; the sample data pairs include sample operation data and sample environment data corresponding to the sample operation data; at least some of the sample data pairs in the training data set and the test data set are different; Inputting the sample data pairs in the training data set into a fully connected neural network to obtain a model output temperature corresponding to the sample data pairs, determining a temperature prediction loss between the model output temperature and the expected output temperature according to a pre-established variable parameter dynamics model and a preset loss function, and adjusting network parameters of the fully connected neural network according to the temperature prediction loss; The fully connected neural network after adjusting the network parameters is tested according to a plurality of sample data pairs in the test data set and the expected output temperatures corresponding to the sample data pairs. When the test results meet preset conditions, the fully connected neural network is determined as a temperature prediction model.

5. The method according to claim 4, characterized in that The sample data pairs and the expected output temperatures corresponding to the sample data pairs are obtained based on a simulated operation experiment of the power equipment and / or by recording equipment operation data, equipment environment data and equipment temperature data of sample equipment of the same equipment type as the power equipment in the target power grid at multiple times.

6. The method according to claim 1, characterized in that The acquiring target operation data of the target electric power equipment and target environment data of the environment in which the target electric power equipment is located when generating the target operation data includes: Acquire original operation data of a target electric power device and original environment data of an environment in which the target electric power device is located when generating the original operation data; The original operation data and the original environment data are respectively standardized to obtain target operation data and target environment data of the target power equipment.

7. The method according to claim 1, characterized in that After obtaining the predicted device temperature of the target power device, the method further includes: When the predicted temperature of the device meets the preset warning conditions, temperature warning information is generated and displayed; wherein, the preset warning conditions include that the predicted temperature of the device reaches a preset temperature threshold and / or the temperature deviation between the predicted temperature of the device and the actual temperature of the device at the current moment reaches a preset deviation threshold.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the temperature prediction method for electric power equipment according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the temperature prediction method for electric power equipment according to any one of claims 1 to 7 when executed.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the temperature prediction method for electric power equipment according to any one of claims 1 to 7.

Images