Intelligent power distribution box communication method and device and storage medium

Abstract

The application relates to the technical field of electronic communication and the technical field of Internet of Things, and discloses a smart power distribution box communication method and device and a storage medium. The method comprises the following steps: generating a fault comprehensive score of a smart power distribution box according to a fault risk score generated by a long short-term memory network, a fault risk score generated by a random forest classifier, a fault risk score generated by a convolutional neural network and a comprehensive scoring model; when the fault comprehensive score of the smart power distribution box is greater than a preset score, obtaining a fault type and a fault occurrence time, packing the fault type and the fault occurrence time into fault information, generating a total score corresponding to each communication protocol through a protocol scoring model, selecting a communication protocol with the highest total score as an optimal communication protocol, and uploading the fault information to a cloud platform by using a communication module corresponding to the optimal communication protocol. The application improves the communication efficiency of the smart power distribution box.

Description

Technical Field

[0001] This application relates to the fields of electronic communication technology and Internet of Things technology, and in particular to a communication method, device and storage medium for an intelligent distribution box. Background Technology

[0002] Intelligent distribution boxes are a new type of power terminal device that deeply integrates traditional power distribution equipment with the Internet of Things. Their core function is to achieve real-time perception and remote management of the power distribution system by integrating multiple types of sensors, control modules and communication units.

[0003] However, current smart distribution boxes suffer from bottlenecks in the fault information uploading process, directly impacting the efficiency of rapid fault location and handling. The core cause of this bottleneck is the lack of a dynamic protocol selection mechanism in current smart distribution boxes. This prevents them from adaptively matching the optimal communication path based on real-time environmental parameters, leading to problems such as fault information upload failures and delays, increasing the risk of downtime. Therefore, how to effectively upload fault information from smart distribution boxes is a pressing technical problem that needs to be solved. Summary of the Invention

[0004] This application provides a communication method, device, and storage medium for intelligent distribution boxes to solve the aforementioned technical problem of how existing intelligent distribution boxes upload fault information.

[0005] In a first aspect, embodiments of this application provide a communication method for an intelligent distribution box, applied to an intelligent distribution box. The intelligent distribution box is equipped with a Long Short-Term Memory network, a Random Forest classifier, and a Convolutional Neural Network. The communication method for the intelligent distribution box includes: Acquire sensor data collected by sensors inside the smart distribution box, remove null and invalid values ​​from the sensor data, and obtain processed sensor data; Feature extraction is performed on the processed sensor data to obtain time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and operational feature vectors; A weighted fusion method is used to fuse the time-domain feature vector, frequency-domain feature vector, time-frequency feature vector, and runtime feature vector to obtain a fused feature vector. The fused feature vector is then normalized to obtain the processed fused feature vector. The processed fused feature vectors are input into a Long Short-Term Memory network, a Random Forest classifier, and a Convolutional Neural Network, respectively, to obtain the fault risk scores generated by the Long Short-Term Memory network, the Random Forest classifier, and the Convolutional Neural Network, respectively. Based on the fault risk scores generated by the Long Short-Term Memory Network, the Random Forest Classifier, the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained. The fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score is generated for each communication protocol. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform.

[0006] In one possible implementation of the first aspect, the step of acquiring sensor data collected by sensors within the intelligent distribution box, removing null and invalid values ​​from the sensor data, and obtaining processed sensor data includes: Send acquisition commands to the sensors in the smart distribution box and receive sensor data returned by the sensors according to the acquisition commands; The sensor data collected by the sensors in the intelligent power distribution box is obtained, and the null and invalid values ​​in the sensor data are removed to obtain the processed sensor data.

[0007] In one possible implementation of the first aspect, the step of generating a comprehensive fault score for the smart distribution box based on fault risk scores generated by a long short-term memory network, a random forest classifier, a convolutional neural network, and a comprehensive scoring model, and when the comprehensive fault score of the smart distribution box is greater than a preset score, obtaining the fault type and fault occurrence time, packaging the fault type and fault occurrence time into fault information, generating a total score for each communication protocol through a protocol scoring model, selecting the communication protocol with the highest total score as the optimal communication protocol, and using the communication module corresponding to the optimal communication protocol to upload the fault information to the cloud platform, including: Based on the fault risk scores generated by the Long Short-Term Memory Network, the fault risk scores generated by the Random Forest Classifier, the fault risk scores generated by the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the overall fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained from the event log of the smart distribution box, and the fault type and fault occurrence time are packaged into fault information in JSON format. The protocol scoring model generates a total score for each communication protocol. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is then used to upload the fault information to the cloud platform.

[0008] In one possible implementation of the first aspect, the protocol scoring model is defined as follows: ; Indicates the first The total score corresponding to each communication protocol; This represents the availability score of the nth communication protocol. This represents the priority score of the nth communication protocol. This represents the power consumption score of the nth communication protocol; This represents the rate score of the data transmission link corresponding to the nth communication protocol; This represents the bandwidth score of the nth communication protocol; It is the first weighting coefficient; It is the second weighting coefficient; It is the third weighting coefficient; It is the fourth weighting coefficient; It is the fifth weighting coefficient; In one possible implementation of the first aspect, the comprehensive scoring model is defined as follows: ; This represents the overall fault score of the intelligent distribution box. The higher the overall fault score, the higher the fault risk level of the intelligent distribution box; the lower the overall fault score, the lower the fault risk level of the intelligent distribution box. This represents the failure risk score generated by the Long Short-Term Memory network; This represents the fault risk score generated by the random forest classifier. This represents the fault risk score generated by the convolutional neural network; , , These are the first adjustment factor, the second adjustment factor, and the third adjustment factor.

[0009] In one possible implementation of the first aspect, after generating a comprehensive fault score for the smart distribution box based on the fault risk score generated by the Long Short-Term Memory Network, the fault risk score generated by the Random Forest Classifier, the fault risk score generated by the Convolutional Neural Network, and the comprehensive scoring model, when the comprehensive fault score of the smart distribution box is greater than a preset score, the fault type and fault occurrence time are obtained, the fault type and fault occurrence time are packaged into fault information, and a total score corresponding to each communication protocol is generated through the protocol scoring model. The communication protocol with the highest total score is selected as the optimal communication protocol, and the fault information is uploaded to the cloud platform using the communication module corresponding to the optimal communication protocol. The smart distribution box communication method then includes: Obtain a preset storage area and store the fault information in the storage area.

[0010] In one possible implementation of the first aspect, the time-domain feature vector includes voltage mean, voltage variance, voltage skewness, voltage kurtosis, voltage peak value, voltage RMS value, and voltage crest factor. The frequency domain eigenvectors include the dominant frequency, harmonic components, and spectral power distribution.

[0011] In one possible implementation of the first aspect, the time-frequency feature vector is used to characterize transient events and non-stationary signal characteristics; the operating feature vector includes load factor, duty cycle, temperature rise rate, and voltage imbalance.

[0012] Secondly, embodiments of this application provide a smart distribution box communication device, applied to a smart distribution box, wherein the smart distribution box is equipped with a long short-term memory network, a random forest classifier, and a convolutional neural network, including: The acquisition module is used to acquire sensor data collected by sensors in the smart distribution box, remove null and invalid values ​​from the sensor data, and obtain processed sensor data. The extraction module is used to extract features from the processed sensor data to obtain time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and runtime feature vectors. The fusion module is used to fuse time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and runtime feature vectors using a weighted fusion method to obtain a fused feature vector. The fused feature vector is then normalized to obtain a processed fused feature vector. The input module is used to input the processed fused feature vector into the Long Short-Term Memory Network, the Random Forest Classifier, and the Convolutional Neural Network, respectively, to obtain the fault risk score generated by the Long Short-Term Memory Network, the fault risk score generated by the Random Forest Classifier, and the fault risk score generated by the Convolutional Neural Network, respectively. The upload module is used to generate a comprehensive fault score for the smart distribution box based on the fault risk scores generated by the Long Short-Term Memory Network, the Random Forest Classifier, the Convolutional Neural Network, and the comprehensive scoring model. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained, and the fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score is generated for each communication protocol. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform.

[0013] Thirdly, embodiments of this application provide an intelligent distribution box, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent distribution box communication method described in the first aspect above.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the intelligent distribution box communication method described in the first aspect above.

[0015] Fifthly, embodiments of this application provide a computer program product that, when running on an intelligent distribution box, causes the intelligent distribution box to execute the intelligent distribution box communication method described in the first aspect.

[0016] The beneficial effects of the embodiments of this application are as follows: Firstly, based on the fault risk scores generated by the Long Short-Term Memory Network, the Random Forest Classifier, the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained, and the fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score corresponding to each communication protocol is generated. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform. This solves the technical problem of how the smart distribution box uploads fault information. Since there is no need for manual uploading of fault information, the uploading time of fault information is reduced, the uploading efficiency of fault information is improved, and thus the communication efficiency of the smart distribution box is improved. Secondly, uploading fault information to the cloud platform helps to shorten fault repair time, reduce the impact of power outages on production and daily life, and further improve the safety and reliability of electricity use. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is an application scenario diagram of the intelligent distribution box communication method provided in the embodiments of this application; Figure 2 This is a flowchart illustrating the intelligent distribution box communication method provided in an embodiment of this application; Figure 3 A flowchart showing the results of list processing is provided for embodiments of this application; Figure 4 A schematic block diagram of an intelligent distribution box communication device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of the intelligent distribution box provided in the embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0020] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0021] It should be understood that in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. The terms "comprising," "including," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0022] Furthermore, the technical solutions of the various embodiments can be combined with each other, but only if they are based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0023] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0024] The intelligent distribution box communication method provided in this application embodiment can be applied to intelligent distribution boxes. The intelligent distribution box is equipped with a long short-term memory network, a random forest classifier, and a convolutional neural network. The intelligent distribution box includes, but is not limited to, servers, mobile phones, tablets, wearable devices, vehicle-mounted devices, and laptops. This application embodiment does not impose any restrictions on the specific type of intelligent distribution box.

[0025] Please see Figure 1 , Figure 1 The application scenario diagram of the intelligent distribution box communication method provided in the embodiments of this application is described in detail below: The intelligent power distribution box is connected to the cloud platform; The intelligent distribution box acquires sensor data collected by the sensors, removes null and invalid values ​​from the sensor data, and obtains processed sensor data. The intelligent distribution box extracts features from the processed sensor data to obtain time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and operational feature vectors. The intelligent distribution box adopts a weighted fusion method to fuse time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and operational feature vectors to obtain a fused feature vector. The fused feature vector is then normalized to obtain a processed fused feature vector. The intelligent distribution box inputs the processed fused feature vector into a long short-term memory network, a random forest classifier, and a convolutional neural network, respectively, to obtain the fault risk score generated by the long short-term memory network, the fault risk score generated by the random forest classifier, and the fault risk score generated by the convolutional neural network, respectively. The intelligent distribution box generates a comprehensive fault score based on fault risk scores generated by Long Short-Term Memory Network, Random Forest Classifier, Convolutional Neural Network, and a comprehensive scoring model. When the comprehensive fault score of the intelligent distribution box is greater than the preset score, the fault type and fault occurrence time are obtained, and the fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score is generated for each communication protocol. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform.

[0026] In this embodiment, the intelligent distribution box selects the communication protocol with the highest total score as the optimal communication protocol and uses the communication module corresponding to the optimal communication protocol to upload fault information to the cloud platform. Compared with the traditional single protocol module, it can effectively avoid transmission interruption caused by signal attenuation and data packet loss caused by electromagnetic interference, ensuring that fault information is uploaded to the cloud platform with zero loss and no delay.

[0027] Please see Figure 2 , Figure 2 This is a flowchart illustrating the communication method for an intelligent distribution box provided in an embodiment of this application. This method can be applied to an intelligent distribution box, which is equipped with a long short-term memory network, a random forest classifier, and a convolutional neural network.

[0028] like Figure 2 As shown in the figure, the intelligent distribution box communication method provided in this application embodiment includes the following steps, which are detailed below: S201: Obtain sensor data collected by sensors in the intelligent power distribution box, remove null and invalid values ​​from the sensor data, and obtain processed sensor data; The process of acquiring sensor data collected by sensors within the intelligent distribution box, removing null and invalid values ​​from the sensor data, and obtaining processed sensor data includes: Send acquisition commands to the sensors in the smart distribution box and receive sensor data returned by the sensors according to the acquisition commands; The sensor data collected by the sensors in the intelligent power distribution box is obtained, and the null and invalid values ​​in the sensor data are removed to obtain the processed sensor data.

[0029] The sensors include voltage sensors and current sensors.

[0030] S202, extract features from the processed sensor data to obtain time-domain feature vector, frequency-domain feature vector, time-frequency feature vector and running feature vector; Among them, the time-domain feature vector includes voltage mean, voltage variance, voltage skewness, voltage kurtosis, voltage peak value, voltage RMS value, and voltage crest factor; The frequency domain eigenvectors include the dominant frequency, harmonic components, and spectral power distribution.

[0031] Among them, the time-frequency feature vector is used to characterize transient events and non-stationary signal characteristics; the operating feature vector includes load factor, duty cycle, temperature rise rate, and voltage imbalance.

[0032] S203 uses a weighted fusion method to fuse the time-domain feature vector, frequency-domain feature vector, time-frequency feature vector, and running feature vector to obtain a fused feature vector. The fused feature vector is then normalized to obtain the processed fused feature vector. Specifically, based on the weight values ​​corresponding to the time-domain feature vector, frequency-domain feature vector, time-frequency feature vector, and running feature vector, a weighted fusion method is used to fuse the time-domain feature vector, frequency-domain feature vector, time-frequency feature vector, and running feature vector to obtain a fused feature vector. The fused feature vector is then normalized to obtain the processed fused feature vector.

[0033] S204. The processed fused feature vector is input into the Long Short-Term Memory Network, the Random Forest Classifier, and the Convolutional Neural Network respectively to obtain the fault risk score generated by the Long Short-Term Memory Network, the fault risk score generated by the Random Forest Classifier, and the fault risk score generated by the Convolutional Neural Network respectively. S205. Based on the fault risk scores generated by the Long Short-Term Memory Network, the Fault Risk Score generated by the Random Forest Classifier, the Fault Risk Score generated by the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained. The fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score corresponding to each communication protocol is generated. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform.

[0034] The protocol scoring model is defined as follows: ; Indicates the first The total score corresponding to each communication protocol; This represents the availability score of the nth communication protocol. This represents the priority score of the nth communication protocol. This represents the power consumption score of the nth communication protocol; This represents the rate score of the data transmission link corresponding to the nth communication protocol; This represents the bandwidth score of the nth communication protocol; It is the first weighting coefficient; It is the second weighting coefficient; It is the third weighting coefficient; It is the fourth weighting coefficient; It is the fifth weighting coefficient; The process of obtaining the availability score of the nth communication protocol is as follows: Obtain the stable runtime of the data transmission link corresponding to the nth communication protocol, divide the stable runtime of the data transmission link corresponding to the nth communication protocol by the total statistical runtime to obtain the available time percentage of the nth communication protocol, convert the available time percentage of the nth communication protocol into a percentage to obtain the network availability score of the nth communication protocol.

[0035] The comprehensive scoring model is defined as follows: ; This represents the overall fault score of the intelligent distribution box. The higher the overall fault score, the higher the fault risk level of the intelligent distribution box; the lower the overall fault score, the lower the fault risk level of the intelligent distribution box. This represents the failure risk score generated by the Long Short-Term Memory network; This represents the fault risk score generated by the random forest classifier. This represents the fault risk score generated by the convolutional neural network; , , These are the first adjustment factor, the second adjustment factor, and the third adjustment factor.

[0036] The method for communicating with a smart distribution box involves generating a comprehensive fault score based on a fault risk score generated by a long short-term memory network, a fault risk score generated by a random forest classifier, a fault risk score generated by a convolutional neural network, and a comprehensive scoring model. When the comprehensive fault score of the smart distribution box is greater than a preset score, the fault type and fault occurrence time are obtained. These fault type and occurrence time are packaged into fault information. A total score is generated for each communication protocol using a protocol scoring model. The communication protocol with the highest total score is selected as the optimal communication protocol. The fault information is then uploaded to the cloud platform using the communication module corresponding to the optimal communication protocol. The communication method for the smart distribution box includes: Obtain a preset storage area and store the fault information in the storage area.

[0037] The beneficial effects of the embodiments of this application are as follows: Among them, the communication module corresponding to the optimal communication protocol is used to upload fault information to the cloud platform, which can ensure the stable transmission of fault information in complex scenarios.

[0038] For ease of explanation, the following example is provided: For example, a shopping mall's underground power distribution room is equipped with multiple smart distribution boxes. When these boxes detect that the GPRS signal strength is insufficient for transmission, they automatically switch to the more penetrating LoRa protocol and upload the fault information completely to the cloud platform. The cloud platform immediately pushes a fault alarm to the maintenance personnel's terminals, clearly indicating the location of the faulty distribution box and the type of fault. Maintenance personnel can then directly carry the corresponding spare parts to the site for emergency repairs without needing to debug the communication protocol on-site, completely preventing the escalation of the fault due to information transmission failure and ensuring the continuity of power supply to the mall.

[0039] For example, in a welding workshop of an automobile manufacturing plant, there was strong electromagnetic interference. After the intelligent power distribution box detected that the electromagnetic interference intensity exceeded the standard, it automatically switched to the fiber optic communication protocol with stronger anti-interference capabilities and uploaded the fault information to the cloud platform. The cloud platform, combined with the historical operating data of the equipment, accurately determined that the root cause of the fault was the instantaneous overload caused by the start-up and shutdown of the welding machine. Without the need for on-site inspection by maintenance personnel, the problem could be solved simply by remotely adjusting the protection threshold of the power distribution box, thus avoiding ineffective manual inspections and quickly eliminating potential faults.

[0040] Firstly, based on the fault risk scores generated by the Long Short-Term Memory Network, the Random Forest Classifier, the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained, and the fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score corresponding to each communication protocol is generated. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform. This solves the technical problem of how the smart distribution box uploads fault information. Since there is no need for manual uploading of fault information, the uploading time of fault information is reduced, the uploading efficiency of fault information is improved, and thus the communication efficiency of the smart distribution box is improved. Secondly, uploading fault information to the cloud platform helps to shorten fault repair time, reduce the impact of power outages on production and daily life, and further improve the safety and reliability of electricity use.

[0041] Please see Figure 3 , Figure 3 The flowchart for displaying the list processing results provided in this application embodiment is described in detail below: S301. Based on the fault risk scores generated by the Long Short-Term Memory Network, the fault risk scores generated by the Random Forest Classifier, the fault risk scores generated by the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. S302 When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained from the event log of the smart distribution box, and the fault type and fault occurrence time are packaged into fault information in JSON format. S303 generates a total score for each communication protocol through a protocol scoring model, selects the communication protocol with the highest total score as the optimal communication protocol, and uses the communication module corresponding to the optimal communication protocol to upload the fault information to the cloud platform.

[0042] In this embodiment, fault information is uploaded to the cloud platform, allowing maintenance personnel to view key information such as fault type and occurrence time without having to go to the site, thus solving the problems of scattered fault information and delayed acquisition in the traditional mode.

[0043] For the intelligent distribution box communication method described in the above embodiments, please refer to [link / reference]. Figure 4 , Figure 4 This is a schematic block diagram of the intelligent distribution box communication device provided in the embodiments of this application. Figure 4 The intelligent distribution box communication device 400 shown can be applied to, for example... Figure 1 The application scenario diagram shows a smart distribution box. The following section uses a smart distribution box as an example to illustrate this. Figure 4 The intelligent distribution box communication device 400 shown is described in detail. The intelligent distribution box communication device 400 may include an acquisition module 401, an extraction module 402, a fusion module 403, an input module 404, and an upload module 405.

[0044] The acquisition module 401 is used to acquire sensor data collected by sensors in the intelligent power distribution box, remove null and invalid values ​​from the sensor data, and obtain processed sensor data. The extraction module 402 is used to extract features from the processed sensor data to obtain time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and runtime feature vectors. The fusion module 403 is used to fuse the time-domain feature vector, frequency-domain feature vector, time-frequency feature vector and running feature vector in a weighted fusion manner to obtain a fused feature vector, and to normalize the fused feature vector to obtain a processed fused feature vector. Input module 404 is used to input the processed fused feature vector into the Long Short-Term Memory Network, the Random Forest Classifier, and the Convolutional Neural Network respectively, to obtain the fault risk score generated by the Long Short-Term Memory Network, the fault risk score generated by the Random Forest Classifier, and the fault risk score generated by the Convolutional Neural Network respectively. The upload module 405 is used to generate a comprehensive fault score for the smart distribution box based on the fault risk score generated by the Long Short-Term Memory Network, the fault risk score generated by the Random Forest Classifier, the fault risk score generated by the Convolutional Neural Network, and the comprehensive scoring model. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained, the fault type and fault occurrence time are packaged into fault information, and a total score is generated for each communication protocol through the protocol scoring model. The communication protocol with the highest total score is selected as the optimal communication protocol, and the communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform.

[0045] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0046] The beneficial effects of the embodiments of this application are as follows: Firstly, based on the fault risk scores generated by the Long Short-Term Memory Network, the Random Forest Classifier, the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained, and the fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score corresponding to each communication protocol is generated. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform. This solves the technical problem of how the smart distribution box uploads fault information. Since there is no need for manual uploading of fault information, the uploading time of fault information is reduced, the uploading efficiency of fault information is improved, and thus the communication efficiency of the smart distribution box is improved. Secondly, uploading fault information to the cloud platform helps to shorten fault repair time, reduce the impact of power outages on production and daily life, and further improve the safety and reliability of electricity use.

[0047] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of the intelligent distribution box provided in the embodiment of this application.

[0048] like Figure 5 As shown, Figure 5The intelligent distribution box 2 includes: at least one processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20, wherein the processor 20 executes the computer program 22 to implement the steps in any of the above method embodiments.

[0049] The intelligent distribution box 2 may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will understand that... Figure 5 This is merely an example of the intelligent distribution box 2 and does not constitute a limitation on the intelligent distribution box 2. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0050] The processor 20 is used to run a computer program 22 stored in the memory 21, and performs the following steps when executing the computer program 22: Acquire sensor data collected by sensors inside the smart distribution box, remove null and invalid values ​​from the sensor data, and obtain processed sensor data; Feature extraction is performed on the processed sensor data to obtain time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and operational feature vectors; A weighted fusion method is used to fuse the time-domain feature vector, frequency-domain feature vector, time-frequency feature vector, and runtime feature vector to obtain a fused feature vector. The fused feature vector is then normalized to obtain the processed fused feature vector. The processed fused feature vectors are input into a Long Short-Term Memory network, a Random Forest classifier, and a Convolutional Neural Network, respectively, to obtain the fault risk scores generated by the Long Short-Term Memory network, the Random Forest classifier, and the Convolutional Neural Network, respectively. Based on the fault risk scores generated by the Long Short-Term Memory Network, the Random Forest Classifier, the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained. The fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score is generated for each communication protocol. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform.

[0051] The processor 20 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors, field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0052] In some embodiments, the memory 21 may be an internal storage unit of the smart distribution box 2, such as a hard drive or memory of the smart distribution box 2. In other embodiments, the memory 21 may also be an external storage device of the smart distribution box 2, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on the smart distribution box 2.

[0053] Furthermore, the memory 21 may include both internal storage units of the intelligent power distribution box 2 and external storage devices. The memory 21 is used to store operating systems, applications, boot loaders, data, and other programs, such as the program code of the computer program. The memory 21 can also be used to temporarily store data that has been output or will be output.

[0054] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0055] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0056] The computer-readable storage medium may also be a communication device for the smart distribution box or an external storage device for the smart distribution box, such as a plug-in hard drive, a smart media card (SMC), a secure digital (SD) card, a flash card, or a non-transitory computer-readable storage medium.

[0057] Since the computer program stored in the computer-readable storage medium can execute any of the smart distribution box communication methods provided in the embodiments of this application, the computer-readable storage medium can achieve the beneficial effects that any of the smart distribution box communication methods provided in the embodiments of this application can achieve, as detailed in the preceding embodiments, and will not be repeated here.

[0058] This application provides a computer program product that, when running on an intelligent distribution box, causes the intelligent distribution box to execute the aforementioned intelligent distribution box communication method.

[0059] The computer program product, loaded into the intelligent distribution box, can perform the following steps: Acquire sensor data collected by sensors inside the smart distribution box, remove null and invalid values ​​from the sensor data, and obtain processed sensor data; Feature extraction is performed on the processed sensor data to obtain time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and operational feature vectors; A weighted fusion method is used to fuse the time-domain feature vector, frequency-domain feature vector, time-frequency feature vector, and runtime feature vector to obtain a fused feature vector. The fused feature vector is then normalized to obtain the processed fused feature vector. The processed fused feature vectors are input into a Long Short-Term Memory network, a Random Forest classifier, and a Convolutional Neural Network, respectively, to obtain the fault risk scores generated by the Long Short-Term Memory network, the Random Forest classifier, and the Convolutional Neural Network, respectively. Based on the fault risk scores generated by the Long Short-Term Memory Network, the Random Forest Classifier, the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained. The fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score is generated for each communication protocol. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform.

[0060] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0061] Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium includes: an entity or device for carrying the computer program code to the intelligent distribution box, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium.

[0062] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0063] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A smart electrical distribution box communication method, characterized by, Applied to intelligent distribution boxes, the intelligent distribution boxes are equipped with long short-term memory networks, random forest classifiers, and convolutional neural networks. The communication method of the intelligent distribution boxes includes: Acquire sensor data collected by sensors inside the smart distribution box, remove null and invalid values ​​from the sensor data, and obtain processed sensor data; Feature extraction is performed on the processed sensor data to obtain time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and operational feature vectors; A weighted fusion method is used to fuse the time-domain feature vector, frequency-domain feature vector, time-frequency feature vector, and runtime feature vector to obtain a fused feature vector. The fused feature vector is then normalized to obtain the processed fused feature vector. The processed fused feature vectors are input into a Long Short-Term Memory network, a Random Forest classifier, and a Convolutional Neural Network, respectively, to obtain the fault risk scores generated by the Long Short-Term Memory network, the Random Forest classifier, and the Convolutional Neural Network, respectively. Based on the fault risk scores generated by the Long Short-Term Memory Network, the Random Forest Classifier, the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained. The fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score is generated for each communication protocol. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform.

2. The smart electrical box communication method of claim 1, wherein, The process of acquiring sensor data collected by sensors within the intelligent power distribution box, removing null and invalid values ​​from the sensor data, and obtaining processed sensor data includes: Send acquisition commands to the sensors in the smart distribution box and receive sensor data returned by the sensors according to the acquisition commands; The sensor data collected by the sensors in the intelligent power distribution box is obtained, and the null and invalid values ​​in the sensor data are removed to obtain the processed sensor data.

3. The smart electrical box communication method of claim 1, wherein, The process involves generating a comprehensive fault score for the smart distribution box based on fault risk scores generated by a Long Short-Term Memory (LSTM) network, a random forest classifier, a convolutional neural network, and a comprehensive scoring model. When the comprehensive fault score of the smart distribution box exceeds a preset score, the fault type and fault occurrence time are obtained. These information are packaged into fault information, and a total score is generated for each communication protocol using a protocol scoring model. The communication protocol with the highest total score is selected as the optimal communication protocol. The fault information is then uploaded to the cloud platform using the communication module corresponding to the optimal communication protocol. This process includes: Based on the fault risk scores generated by the Long Short-Term Memory Network, the fault risk scores generated by the Random Forest Classifier, the fault risk scores generated by the Convolutional Neural Network, and the comprehensive scoring model, a comprehensive fault score for the smart distribution box is generated. When the overall fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained from the event log of the smart distribution box, and the fault type and fault occurrence time are packaged into fault information in JSON format. The protocol scoring model generates a total score for each communication protocol. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is then used to upload the fault information to the cloud platform.

4. The smart electrical box communication method of claim 1, wherein, The protocol scoring model is defined as follows: ； represents the total score corresponding to the first communication protocol; This represents the availability score of the nth communication protocol; This represents the priority score of the nth communication protocol. This represents the power consumption score of the nth communication protocol; This represents the rate score of the data transmission link corresponding to the nth communication protocol; This represents the bandwidth score of the nth communication protocol. It is the first weighting coefficient; It is the second weighting coefficient; It is the third weighting coefficient; It is the fourth weighting coefficient; It is the fifth weighting coefficient.

5. The intelligent distribution box communication method according to claim 1, characterized in that, The comprehensive scoring model is defined as follows: ； This indicates the overall fault score of the intelligent distribution box. The higher the overall fault score, the higher the fault risk level of the intelligent distribution box. The lower the overall fault score of the distribution box, the lower the fault risk level of the intelligent distribution box. This represents the failure risk score generated by the Long Short-Term Memory network; This represents the fault risk score generated by the random forest classifier. This represents the fault risk score generated by the convolutional neural network; , , These are the first adjustment factor, the second adjustment factor, and the third adjustment factor.

6. The intelligent distribution box communication method according to claim 1, characterized in that, The intelligent distribution box communication method generates a comprehensive fault score based on the fault risk score generated by the Long Short-Term Memory Network, the fault risk score generated by the Random Forest Classifier, the fault risk score generated by the Convolutional Neural Network, and the comprehensive scoring model. When the comprehensive fault score of the intelligent distribution box is greater than a preset score, the fault type and fault occurrence time are obtained, and the fault type and fault occurrence time are packaged into fault information. A total score is generated for each communication protocol using a protocol scoring model. The communication protocol with the highest total score is selected as the optimal communication protocol. After uploading the fault information to the cloud platform using the communication module corresponding to the optimal communication protocol, the method includes: Obtain a preset storage area and store the fault information in the storage area.

7. The intelligent distribution box communication method according to claim 1, characterized in that, The time-domain feature vector includes voltage mean, voltage variance, voltage skewness, voltage kurtosis, voltage peak value, voltage RMS value, and voltage crest factor. The frequency domain eigenvectors include the dominant frequency, harmonic components, and spectral power distribution.

8. The intelligent distribution box communication method according to claim 1, characterized in that, Time-frequency eigenvectors are used to characterize transient events and non-stationary signal characteristics; operating eigenvectors include load factor, duty cycle, temperature rise rate, and voltage imbalance.

9. A communication device for an intelligent distribution box, characterized in that, Applied to intelligent distribution boxes, which are equipped with long short-term memory networks, random forest classifiers, and convolutional neural networks, including: The acquisition module is used to acquire sensor data collected by sensors in the smart distribution box, remove null and invalid values ​​from the sensor data, and obtain processed sensor data. The extraction module is used to extract features from the processed sensor data to obtain time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and runtime feature vectors. The fusion module is used to fuse time-domain feature vectors, frequency-domain feature vectors, time-frequency feature vectors, and runtime feature vectors using a weighted fusion method to obtain a fused feature vector. The fused feature vector is then normalized to obtain a processed fused feature vector. The input module is used to input the processed fused feature vector into the Long Short-Term Memory Network, the Random Forest Classifier, and the Convolutional Neural Network, respectively, to obtain the fault risk score generated by the Long Short-Term Memory Network, the fault risk score generated by the Random Forest Classifier, and the fault risk score generated by the Convolutional Neural Network, respectively. The upload module is used to generate a comprehensive fault score for the smart distribution box based on the fault risk scores generated by the Long Short-Term Memory Network, the Random Forest Classifier, the Convolutional Neural Network, and the comprehensive scoring model. When the comprehensive fault score of the smart distribution box is greater than the preset score, the fault type and fault occurrence time are obtained, and the fault type and fault occurrence time are packaged into fault information. Through the protocol scoring model, a total score is generated for each communication protocol. The communication protocol with the highest total score is selected as the optimal communication protocol. The communication module corresponding to the optimal communication protocol is used to upload the fault information to the cloud platform.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the intelligent distribution box communication method as described in any one of claims 1 to 7.

Images