Distribution line temperature diagnosis method and system based on intelligent Internet of Things

Abstract

The invention relates to the technical field of power distribution network abnormity diagnosis, in particular to a power distribution line temperature diagnosis method and system based on intelligent Internet of Things. The system comprises: a data acquisition module configured to acquire operating parameters of a distribution line and organize the operating parameters of the distribution line; the line temperature diagnosis module is configured to diagnose and predict the operating parameters of the distribution line by using a line temperature diagnosis model to obtain a line temperature diagnosis result; and the data processing module is configured to judge whether the wire temperature is abnormal in a preset time period or not according to the wire temperature diagnosis result, if yes, early warning is carried out, and if not, diagnosis continues to be carried out. According to the invention, real-time monitoring and early warning of the line temperature in the power distribution network can be realized, and advanced judgment can be carried out by using historical data of the line.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal diagnosis of distribution networks, and in particular to a method and system for diagnosing line temperature of distribution lines based on smart Internet of Things. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the development of production, the intelligence level of the power grid is becoming more and more important. Considering the direction of power flow, the smart grid is divided into five links: power generation, transmission, transformation, distribution, and users. Any link is related to the stability of the entire power grid. At present, the intelligence level of power generation, transmission, transformation, and users has made great progress, but the intelligence level of distribution lines is relatively low. Once a distribution line fails, it will seriously affect the safe and stable operation of the system. Therefore, it is very important to effectively monitor, manage, and maintain the distribution line.

[0004] The temperature state of the distribution network line directly affects its carrying capacity and operating efficiency. After a long period of operation, the equipment in the distribution network will generate heat due to the passage of current, especially at joints and connection points, which are prone to overheating. Long-term overheating will accelerate the aging and damage of equipment, and even cause serious accidents such as short circuits and fires. Safety accidents in the power system often cause serious casualties and property losses.

[0005] At present, how to conduct real-time monitoring of line temperature status in distribution networks and advance warning of abnormal line temperature has become a technical problem that needs to be urgently solved in existing technologies. Summary of the invention

[0006] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a distribution line temperature diagnosis method and system based on smart Internet of Things, which can realize real-time monitoring and early warning of line temperature in the distribution network, and can use historical line data for advanced judgment.

[0007] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0008] The first aspect of the present invention provides a distribution line temperature diagnosis system based on smart Internet of Things, comprising:

[0009] A data acquisition module is configured to acquire and organize the distribution line operation parameters;

[0010] A line temperature diagnosis module is configured to diagnose and predict the operating parameters of the distribution line using the line temperature diagnosis model to obtain a line temperature diagnosis result, wherein the historical operating parameters are used as a known data set, and the long short-term memory network is used to learn the time characteristics of the line temperature related data in the operating parameters of the known data set to complete the training of the line temperature diagnosis model;

[0011] The data processing module is configured to determine whether the line temperature is abnormal within a preset time period based on the line temperature diagnosis result. If so, an early warning is issued; if not, the diagnosis is continued.

[0012] A second aspect of the present invention provides a distribution line temperature diagnosis method based on smart Internet of Things, comprising the following steps:

[0013] Obtaining and arranging the operating parameters of the distribution lines;

[0014] The line temperature diagnosis model is used to diagnose and predict the operating parameters of the distribution line to obtain the line temperature diagnosis results. The historical operating parameters are used as a known data set, and the long short-term memory network is used to learn the time characteristics of the line temperature related data in the operating parameters of the known data set to complete the training of the line temperature diagnosis model.

[0015] According to the wire temperature diagnosis result, it is judged whether the wire temperature is abnormal within the preset time period. If so, an early warning is issued; if not, the diagnosis continues.

[0016] The third aspect of the present invention provides a medium on which a program is stored. When the program is executed by a processor, the steps in the distribution line temperature diagnosis method based on smart Internet of Things as described in the second aspect of the present invention are implemented.

[0017] The fourth aspect of the present invention provides a device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the distribution line temperature diagnosis method based on smart Internet of Things as described in the second aspect of the present invention are implemented.

[0018] One or more of the above technical solutions have the following beneficial effects:

[0019] The present invention discloses a distribution line temperature diagnosis method and system based on intelligent Internet of Things, which can monitor the temperature changes of distribution lines in real time and detect abnormal temperature in time. When the temperature exceeds the set threshold, the system can automatically send out an early warning signal to remind the operation and maintenance personnel to take measures in time to prevent fires or other safety accidents caused by excessive temperature, thereby improving the safety of power distribution lines.

[0020] The present invention realizes timely warning and fault detection by learning line temperature related data through LSTM network. The system can shorten the troubleshooting time, reduce the power outage time, and improve the power supply reliability. The system can intelligently dispatch the power load according to the real-time monitoring data, so that the load distribution between each circuit is more balanced, reduce the safety hazards caused by excessive load, and improve the safety of the power distribution lines of the power grid.

[0021] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0023] Figure 1 This is a structural diagram of a distribution line temperature diagnosis system based on smart IoT in Example 1 of the present invention. DETAILED DESCRIPTION

[0024] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0025] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "include" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or their combinations;

[0026] Embodiment 1:

[0027] Embodiment 1 of the present invention provides a distribution line temperature diagnosis system based on smart IoT, such as Figure 1 As shown, it includes a data acquisition module, a data processor module, an account management module, a line temperature diagnosis module, an early warning module, a data management module and a log recording module. The current distribution lines are designed and constructed based on the operation mode of the traditional power grid. The power grid distribution lines have poor safety, low informationization, low fault early warning capability, long fault recovery time, and reduce the overall reliability of the power grid. For this reason, this embodiment proposes a distribution line line temperature diagnosis system based on smart Internet of Things, and the specific structure is as follows:

[0028] The data acquisition module is configured to acquire and organize the distribution line operation parameters.

[0029] In this embodiment, the distribution line operating parameters include line temperature, current, voltage, ambient temperature and other data. The above historical data can be obtained in the data management module or other databases. The line temperature includes historical line temperature and real-time line temperature: in addition to historical data, the line temperature data also requires real-time monitoring data. The present invention utilizes a line temperature detection component to collect real-time distribution line temperature data in real time, and the line temperature detection component is a single-sided extended sensing chip. Specifically, the length of the single-sided temperature measurement sensing chip is extended so that it is inserted into the gap between the wire clamp and the wire and fixed. The sensing chip will feed back the measured contact point temperature data to the line temperature diagnosis module. This component can monitor the temperature changes of the power grid distribution line in real time to ensure timely grasp of the line temperature status.

[0030] The line temperature diagnosis module is configured to use the line temperature diagnosis model to diagnose and predict the distribution line operating parameters to obtain line temperature diagnosis results. The historical operating parameters are used as a known data set, and the long short-term memory network is used to learn the time characteristics of the line temperature related data in the known data set operating parameters to complete the training of the line temperature diagnosis model.

[0031] In a specific embodiment, the line temperature diagnosis module is used to monitor, analyze and diagnose the temperature of the power distribution line in real time. Specifically, the line temperature detection component is used to detect the temperature of the distribution line and process and analyze the temperature data to identify abnormal temperature conditions, such as excessive temperature, excessive temperature fluctuations, etc., and the line temperature abnormality diagnosis algorithm is used to diagnose the cause of the abnormal temperature in combination with the historical temperature data and current operating status of the line. Possible causes include overload, short circuit, poor contact, poor heat dissipation, etc.; thereby enabling the system to monitor the temperature changes of the distribution line in real time and detect temperature abnormalities in a timely manner. According to the abnormal temperature conditions, the system can automatically send out early warning signals to remind the operation and maintenance personnel to take timely measures to prevent fires or other safety accidents caused by excessive temperature, thereby improving the safety of the power distribution lines.

[0032] The wire temperature diagnosis module specifically includes a wire temperature real-time diagnosis module and a wire temperature abnormality prediction module. The wire temperature real-time diagnosis module receives real-time wire temperature data collected by the wire temperature detection component, and makes a judgment based on a preset wire temperature threshold. If the wire temperature exceeds the threshold, an early warning is issued, otherwise monitoring continues.

[0033] The line temperature anomaly prediction module includes a training set module, a model building module and a model training module.

[0034] The training set module is configured to perform data collection and preprocessing, and divide the preprocessed data set into a training set and a test set.

[0035] Data collection: Collect the historical temperature data of the line in the past year, including temperature records in different time periods. At the same time, collect the historical current, voltage, and ambient temperature of the line in the past year, and correspond to the corresponding time points as required.

[0036] Data preprocessing includes data cleaning and data standardization:

[0037] Data cleaning: missing values ​​and erroneous values ​​in the data set. For erroneous values, we use professional knowledge of electricity to delete them, and directly delete the erroneous data that obviously does not conform to common knowledge of electricity. We use linear interpolation to process missing values, and the algorithm can reasonably fill in the missing values ​​according to the actual situation. All data are completed to a set of data every 15 minutes to ensure data integrity. The formula of linear interpolation is as follows:

[0038] Y=((X-X1)(Y2-Y1) / (X2-X1))+Y1.

[0039] Among them, X1 represents the first target value, Y1 represents the first result value, X2 represents the second target value, Y2 represents the second result value, Y is the final result value, and X represents the initial target value.

[0040] Data standardization: Since the range of values ​​of parameters such as temperature, current, and voltage may vary greatly, all data are standardized to facilitate subsequent algorithm processing. Specifically, Z-score standardization is used, that is, each data point is subtracted from its mean and divided by its standard deviation, so that the mean of the data is 0 and the standard deviation is 1. The formula is:

[0041]

[0042] Among them, Z is the standardized data, X is the original data, μ is the mean, and σ is the standard deviation.

[0043] After preprocessing, the historical data is divided into a training set and a test set in a certain ratio of 7:3. The selected machine learning model is trained using the training set, and the parameters of the model (number of layers, number of neurons, learning rate, etc.) are adjusted so that the model can accurately learn the relationship between temperature anomalies and various features on the training set.

[0044] The model building module is configured to build a line temperature diagnosis model.

[0045] In this embodiment, the line temperature diagnosis model uses a long short-term memory network (LSTM) to process sequence data such as temperature, current, and voltage, including an input layer, an LSTM layer, and an output layer.

[0046] The input layer determines the dimension of the input data according to the number of selected features and the length of the time series. Using three operating status features of the past 96 time steps, namely current, voltage, and ambient temperature, the dimension of the input layer is expressed as (batch_size,96,3), where batch_size is the number of samples input at a time, 96 is the length of the time series, and 3 is the number of features.

[0047] LSTM layer, 3 LSTM units constitute the LSTM layer, the "un its" parameter is set to 3, and the "return_sequences" parameter is set to Fail se, which only returns the hidden state of the last time step.

[0048] The output layer is a fully connected layer (Dense Layer), followed by a Softmax activation function. According to business needs, the line temperature abnormality is distinguished from three possible temperature abnormality reasons such as overload, poor contact, and heat dissipation problems. Therefore, the fully connected layer (Dense Layer) requires 3 neurons.

[0049] The weights are initialized randomly. The Softmax function converts the values ​​output by the LSTM layer into the probability distribution corresponding to each category, and the sum of the probabilities is 1. This allows us to intuitively see the model's judgment on the possibility of each abnormal cause category. The Softmax activation function formula is:

[0050]

[0051] Among them, S(y i ) is the activation function, y i is the output of the ith neuron, y j is the output of the jth neuron, and n is the total number of neurons.

[0052] The model training module is configured to train the above-constructed line temperature diagnosis model using the divided training set, continuously adjust the network structure parameters, and test the trained model using the test set, and use the test results to further optimize the line temperature diagnosis model.

[0053] Combining convolution operation, gated recurrent unit and multi-layer perceptron deep learning technology, a line temperature anomaly deep learning prediction model is established. The line temperature anomaly prediction module collects historical temperature, current, voltage, ambient temperature and other data of the line as temperature anomaly related features. Among them, voltage data is collected through voltage transformers, current data is collected through current transformers, and ambient temperature data is collected through temperature sensors. These historical data are stored in the system and retrieved when needed.

[0054] The temperature data detected by the line temperature detection component is input into the trained line temperature diagnosis model. The model outputs the prediction result about the cause of temperature abnormality based on the input data, such as overload, line fault or other reasons.

[0055] The data processing module is configured to determine whether the line temperature is abnormal within a preset time period based on the line temperature diagnosis result. If so, an early warning is issued; if not, the diagnosis is continued.

[0056] In a specific implementation, the data processor module is used to process and analyze the data sent by each module, and generate corresponding instructions according to the processing results, and then send the instructions to the module that needs action.

[0057] In this embodiment, the line temperature diagnosis module will feed back the data after diagnosis and analysis to the data processor module. The data is further analyzed to determine whether an early warning is required, which can be achieved by setting an early warning threshold.

[0058] The data processor module will also clean and preprocess other collected data, including removing duplicate data, processing missing values, correcting outliers, etc., to ensure the accuracy and reliability of subsequent analysis results. The processed data will be stored and managed by the account management module or the data management module.

[0059] The account management module is used to manage the user information of the system to ensure the security and manageability of the system. The account management module is used to manage the user information of the system to ensure the security and manageability of the system. Specifically, the account management component can be used to register and log in the operation and maintenance personnel, and can also display the information of all users in the current system, including user name, password, permission level, etc. At the same time, the system administrator can view, edit or delete user information through this module to control the access rights of different users to the system, allow new users to register accounts, and review registration information to ensure that only legitimate users can access the system.

[0060] The early warning module includes an early warning information setting component and an early warning operation management component. The early warning module is used to receive the early warning instruction sent by the data processing module when the power distribution line of the power grid has temperature anomalies or potential failure risks, and send early warning signals to relevant personnel in advance.

[0061] The warning information setting component is used to set the parameters of the warning method. Specifically, the telephone number of the warning-related operation and maintenance personnel, the number of information warnings, the number of telephone warnings, the interval between information warnings and the interval between telephone warnings can be set.

[0062] The warning operation management component is used to manage the warning start and stop operations. The method can be customized. For example, when receiving a warning reminder, you need to press the confirmation button through the warning operation management component, otherwise the warning module will continue to remind you.

[0063] The early warning module is used to send early warning signals to relevant personnel in advance when abnormal temperature or potential failure risk occurs in the power distribution line of the power grid; specifically, the early warning module works closely with the data processor module. Once it is found that the result of the line diagnosis module shows abnormal temperature or there is a potential failure risk, the data processor module will generate an early warning instruction and send it to the early warning module. The early warning module will start immediately, and will give early warning reminders to the operation and maintenance personnel and the background, and send abnormal line temperature information to the mobile phone of the associated operation and maintenance personnel. At this time, the operation and maintenance personnel need to press the confirmation button on the APP. When the operation and maintenance personnel do not log in to the APP to press the confirmation button within the preset time, they will be reminded by SMS. Within the preset time range after the SMS reminder, when the operation and maintenance personnel still do not log in to the APP to press the confirmation button, they will be reminded by telephone voice. The operation and maintenance personnel need to take countermeasures and respond to the location of the abnormal line temperature; through timely early warning and fault detection, the system can shorten the troubleshooting time, reduce the power outage time, and improve the reliability of power supply. The system can intelligently dispatch the power load according to the real-time monitoring data, so that the load distribution between each circuit is more balanced, reduce the safety hazards caused by excessive load, and improve the safety of the power distribution line of the power grid.

[0064] The data management module includes a data transmission component and a data storage component. The data transmission component is used for data transmission, and the data storage component is used for data storage. The data management module is used to manage, process and store data related to line temperature.

[0065] Specifically, the data processing module will process the collected line temperature data and send it to the data management module. The data management module will display the received line temperature data in real time on the monitoring interface so that the operation and maintenance personnel can intuitively understand the temperature status of the current power grid distribution line. It provides a historical data query function, allowing users to retrieve past line temperature data according to time period, location and other conditions. This helps to analyze temperature change trends, evaluate system performance, and discover potential problems. At the same time, the relevant data of abnormal line temperature can be sorted, classified, stored and backed up to ensure data integrity and security.

[0066] The log recording module is used to record key information and events during the operation of the system. The log recording module includes a user operation recording component and a system operation recording component to facilitate subsequent auditing, troubleshooting and performance analysis. Among them, the user operation recording component is used to record user operations, and the system operation recording component is used to record system operations.

[0067] Specifically, the log recording module will record the operating status of the system in real time or periodically, including the operating status of each component, the usage of system resources, the operating behavior of the operation and maintenance personnel, etc.; when the system fails or is abnormal, the information saved in the log recording module can be used as an important basis for troubleshooting. By viewing the log, technicians can quickly locate the cause and location of the failure and take appropriate measures to repair it. The log recording module also plays an important role; by recording the operating behavior of the operation and maintenance personnel and the security incidents of the system, the system administrator can evaluate the security of the system and ensure that the system operation complies with relevant laws and regulations and policy requirements.

[0068] Embodiment 2:

[0069] Embodiment 2 of the present invention provides a method for diagnosing line temperature of a distribution line based on smart IoT, comprising the following steps:

[0070] Step 1: Obtain the distribution line operating parameters and organize the distribution line operating parameters.

[0071] Step 2: Use the line temperature diagnosis model to diagnose and predict the operating parameters of the distribution line to obtain the line temperature diagnosis results. The historical operating parameters are used as the known data set, and the long short-term memory network is used to learn the time characteristics of the line temperature related data in the operating parameters of the known data set to complete the training of the line temperature diagnosis model.

[0072] Step 3: Determine whether the line temperature is abnormal within a preset time period based on the line temperature diagnosis result. If so, issue a warning; if not, continue with the diagnosis.

[0073] Embodiment three:

[0074] Embodiment 3 of the present invention provides a medium on which a program is stored. When the program is executed by a processor, the steps in the distribution line temperature diagnosis method based on smart Internet of Things as described in Embodiment 2 of the present invention are implemented.

[0075] Embodiment 4:

[0076] Embodiment 4 of the present invention provides a device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the distribution line temperature diagnosis method based on smart Internet of Things as described in Embodiment 2 of the present invention are implemented.

[0077] The steps involved in the above embodiments 2, 3 and 4 correspond to the method embodiment 1. For the specific implementation methods, please refer to the relevant description part of embodiment 1.

[0078] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0079] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A distribution line temperature diagnosis system based on intelligent Internet of Things, characterized in that: include: A data acquisition module is configured to acquire and organize the distribution line operation parameters; A line temperature diagnosis module is configured to diagnose and predict the operating parameters of the distribution line using the line temperature diagnosis model to obtain a line temperature diagnosis result, wherein the historical operating parameters are used as a known data set, and the long short-term memory network is used to learn the time characteristics of the line temperature related data in the operating parameters of the known data set to complete the training of the line temperature diagnosis model; The data processing module is configured to determine whether the line temperature is abnormal within a preset time period based on the line temperature diagnosis result. If so, an early warning is issued; if not, the diagnosis is continued.

2. The distribution line temperature diagnosis system based on intelligent Internet of Things as claimed in claim 1 is characterized in that: The operating parameters of the distribution line include line temperature, current, voltage, and ambient temperature.

3. The distribution line temperature diagnosis system based on intelligent Internet of Things as claimed in claim 2, characterized in that: The line temperature includes historical line temperature and real-time line temperature. The real-time line temperature is collected by a line temperature detection component, which is a single-side extended sensing chip.

4. The distribution line temperature diagnosis system based on intelligent Internet of Things as claimed in claim 1, characterized in that: The line temperature anomaly prediction module includes a training set module, a model building module and a model training module. The training set module is configured to perform data collection and preprocessing, and divide the preprocessed data set into a training set and a test set; The model construction module is configured to construct a line temperature diagnosis model; the model training module is configured to use the divided training set to train the constructed line temperature diagnosis model, continuously adjust the network structure parameters, and use the test set to test the trained model, and use the test results to further optimize the line temperature diagnosis model.

5. The distribution line temperature diagnosis system based on intelligent Internet of Things as claimed in claim 4 is characterized in that: The line temperature diagnosis model includes an input layer, an LSTM layer, and an output layer. The dimension of the input data is determined according to the number of selected features and the length of the time series. The LSTM layer is composed of three LSTM units, and the output layer is a fully connected layer.

6. The distribution line temperature diagnosis system based on intelligent Internet of Things as claimed in claim 1, characterized in that: It also includes an account management module, a data management module and a log recording module; the account management module is used to manage the user information of the system; the data management module is used to manage, process and store data related to line temperature; the log recording module is used to record key information and events during the operation of the system.

7. The distribution line temperature diagnosis system based on intelligent Internet of Things as claimed in claim 1, characterized in that: It also includes an early warning module, which includes an early warning information setting component and an early warning operation management component; the early warning module is used to receive the early warning instruction sent by the data processing module when the power grid distribution line has a temperature abnormality or a potential failure risk, and send an early warning signal to relevant personnel in advance; the early warning information setting component is used to set the parameters of the early warning method; the early warning operation management component is used to manage the early warning start and stop operation.

8. A distribution line temperature diagnosis method based on intelligent Internet of Things, characterized in that: The following steps are involved: Obtaining and arranging the distribution line operation parameters; The line temperature diagnosis model is used to diagnose and predict the operating parameters of the distribution line to obtain the line temperature diagnosis results. The historical operating parameters are used as a known data set, and the long short-term memory network is used to learn the time characteristics of the line temperature related data in the operating parameters of the known data set to complete the training of the line temperature diagnosis model. According to the wire temperature diagnosis result, it is judged whether the wire temperature is abnormal within the preset time period. If so, an early warning is issued; if not, the diagnosis continues.

9. A computer-readable storage medium, characterized in that: A plurality of instructions are stored therein, and the instructions are suitable for being loaded by a processor of a terminal device and executing the distribution line temperature diagnosis method based on smart Internet of Things as described in claim 8.

10. A terminal device, characterized in that: It includes a processor and a computer-readable storage medium, the processor is used to implement each instruction; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the distribution line temperature diagnosis method based on smart Internet of Things as described in claim 8.

Images