A temperature and electrical fire operation monitoring system based on intelligent substations

Abstract

The present invention relates to a temperature and electrical fire operation monitoring system based on an intelligent substation, characterized in that it comprises: a physical entity layer, which comprises: a closed iron core, windings, pads, stays, an oil tank in a distribution transformer, and a temperature sensor and a smoke sensor installed on the transformer; a data layer, which transmits real-time data acquired by the temperature sensor and the smoke sensor to a digital twin transformer based on an Internet of Things cloud platform; and a user layer, which is used to create a temperature and electrical fire operation prediction model of an LSTM with time series as correlation for data analysis and prediction.

Description

Technical Field

[0001] The invention relates to the technical field of transformer substation monitoring, in particular to a temperature and electrical fire operation monitoring system based on an intelligent transformer substation. Background Art

[0002] Distribution transformers are key equipment for power transmission and transformation in power systems. If a fault occurs during operation, it will cause large-scale power outages and other accidents, causing serious economic losses and adverse social reactions. Transformer temperature is one of the important indicators of equipment operation. By monitoring its temperature, most safety hazards can be discovered and predicted in advance, thereby reducing the incidence of accidents and ensuring the safe and stable operation of equipment. During the operation of the distribution station area, not only gradual faults will occur, but also sudden faults. Although the system's temperature prediction can further solve the possibility of gradual faults evolving into more serious accidents, it cannot effectively solve sudden faults. Sudden faults, such as high-temperature fires, are difficult to handle quickly because they occur suddenly.

[0003] To address such issues, there is an urgent need to provide a temperature and electrical fire operation monitoring system based on intelligent distribution areas. When a fire or other accident is detected in the distribution area, the fire can be extinguished quickly to reduce the loss caused by the accident. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a temperature and electrical fire operation monitoring system based on an intelligent zone.

[0005] To solve the above problems, the technical solution adopted by the present invention is:

[0006] A temperature and electrical fire operation monitoring system based on intelligent substations, comprising:

[0007] The physical entity layer includes: the closed core, windings, spacers, stays, oil tanks in the distribution transformer, and temperature sensors and smoke sensors installed on the transformer;

[0008] A data layer, which transmits the real-time data acquired by the temperature sensor and the smoke sensor to the digital twin transformer based on the Internet of Things cloud platform;

[0009] The user layer is used to create a temperature and electrical fire operation prediction model with LSTM based on time series correlation for data analysis and prediction.

[0010] As an implementation mode of the present invention, the user layer relies on digital information technology, computer communication technology, big data technology, the Internet and database technology to collect and transmit the physical data of the transformer in real time, and integrates the digital twin model of the transformer, uses intelligent algorithms to analyze the gas data in the oil, realizes the interconnection and interactive mapping between the physical space and the virtual space of the transformer, and outputs the fault type to the engineering personnel, so as to achieve the purpose of real-time online monitoring of the internal operation of the transformer and timely arrange personnel for targeted maintenance.

[0011] As an embodiment of the present invention, it also includes: an intelligent perfluorohexanone fire extinguisher, which is connected to the layer for controlling the intelligent perfluorohexanone fire extinguisher to open when it is determined that the temperature reaches a temperature threshold and / or an electrical fire is predicted.

[0012] As an implementation mode of the present invention, a dual-circuit power supply mode is adopted. Under normal operating conditions, the system is powered by AC power to ensure the normal operation of the system while storing energy for the energy storage equipment. When a failure occurs in the distribution station area and power is unable to be supplied, the energy storage device has an inverter function and fast switching to ensure the normal operation of the system and quickly start the fire extinguishing system.

[0013] As an implementation mode of the present invention, the user layer carries out technical analysis of power and environmental monitoring of transformers in distribution substations, makes full use of its physical models, sensor data updates, operation history and other data, integrates multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, completes spatial mapping in the computer system, establishes an information mirror model of distribution substations, and realizes real-time monitoring of the operating status of transformers in distribution substations through the information mirror model.

[0014] As an embodiment of the present invention, the transformer temperature prediction model of the LSTM includes: an input layer, a hidden layer, an output layer and model training, wherein the input layer is used to read and preprocess the data set, and divide the training test data set; the hidden layer is used to build the LSTM hidden layer and the fully connected neural layer; the output layer is used as a verification process for the prediction result; and the model training is responsible for the loss function calculation, Adam algorithm optimization and iterative calculation of the model training.

[0015] As an implementation mode of the present invention, two loss functions are used for calculation, which makes the prediction results and the temperature melon degree higher and expands the difference between the relationships.

[0016] As an implementation mode of the present invention, the loss function is obtained by using the following formula:

[0017] loss=max(0,-y*(S(r;q)-S(r';q))+margin)

[0018] loss2=y*|cos(r,r')|*max(0,cos(r,r)-γ).

[0019] The beneficial effects of adopting the above technical solution are:

[0020] The temperature and electrical fire operation monitoring system based on the intelligent substation provided by the present invention is characterized in that it includes: a physical entity layer, which includes: a closed core, windings, pads, stays, oil tanks in the distribution transformer, and temperature sensors and smoke sensors installed on the transformer; a data layer, which transmits the real-time data obtained by the temperature sensor and smoke sensor to the digital twin transformer based on the Internet of Things cloud platform; a user layer, which is used to create a temperature and electrical fire operation prediction model with LSTM based on time series correlation for data analysis and prediction. The method realizes real-time monitoring of the operating status of the transformer in the distribution substation through the information mirror model, which is simple and has high accuracy in prediction results. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention is clearly and completely described below in conjunction with specific embodiments.

[0022] During the operation of the distribution area, not only gradual faults but also sudden faults may occur; the LSTM time series model used in the project can effectively predict the occurrence of gradual faults, and prevent possible safety accidents in advance, thereby ensuring the safe and stable operation of the equipment. However, when sudden high temperature faults and other problems occur, if they are not handled in time, they will cause major safety accidents such as electrical fires. In order to deal with such sudden electrical fires and minimize the losses caused by electrical fires, the present invention proposes a temperature and electrical fire operation monitoring system based on intelligent substations, which monitors the possibility of fires in distribution areas in real time and issues warnings, and quickly starts the system to extinguish the fire when a fire occurs, thereby effectively reducing the losses caused by fire accidents.

[0023] The temperature and electrical fire operation monitoring system based on the intelligent zone provided by the present invention includes:

[0024] The physical entity layer includes: the closed core, windings, spacers, stays, oil tanks in the distribution transformer, and temperature sensors and smoke sensors installed on the transformer;

[0025] A data layer, which transmits the real-time data acquired by the temperature sensor and the smoke sensor to the digital twin transformer based on the Internet of Things cloud platform;

[0026] The user layer is used to create a temperature and electrical fire operation prediction model with LSTM based on time series correlation for data analysis and prediction.

[0027] The model establishment based on digital twin technology is a complex system, which mainly includes the physical layer, data layer and user layer. The physical layer refers to the distribution transformer entity including closed core, winding, pads, stays, oil tank, etc., and the temperature, humidity, smoke and other sensors installed on the transformer are used to transmit the real-time data of the transformer to the digital twin transformer data layer based on the Internet of Things cloud platform.

[0028] Specifically, the user layer relies on digital information technology, computer communication technology, big data technology, the Internet and database technology to collect and transmit the physical data of the transformer in real time, and integrates the digital twin model of the transformer, and uses intelligent algorithms to analyze the gas data in the oil, so as to realize the interconnection and interactive mapping of the physical space and virtual space of the transformer, and output the fault type to the engineering personnel, so as to achieve real-time online monitoring of the internal operation of the transformer and timely arrange personnel for targeted maintenance.

[0029] Furthermore, the user layer conducts technical analysis of power and environmental monitoring of transformers in distribution substations, fully utilizes its physical models, sensor data updates, operation history and other data, integrates multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, completes spatial mapping in the computer system, and establishes an information mirror model for distribution substations. Through the information mirror model, real-time monitoring of the operating status of transformers in distribution substations is achieved.

[0030] Of course, it also includes: an intelligent perfluoroacetic acid ketone fire extinguisher, which is connected to the layer for controlling the opening of the intelligent perfluoroacetic acid ketone fire extinguisher when it is determined that the temperature reaches the temperature threshold and / or an electrical fire is predicted.

[0031] The present invention is based on the temperature sensor installed in the distribution station area, continuously collects data from the monitoring point, analyzes the temperature change data related to time, creates a mathematical model with time series as the correlation, and uses the model for data analysis and prediction. The LSTM model includes: an input layer, a hidden layer, an output layer and model training, wherein the input layer is used to read and preprocess the data set, and divide the training and test data set; the hidden layer is used to build the LSTM hidden layer and the fully connected neural layer; the output layer is used as a verification process for the prediction result; the model training is responsible for the loss function calculation, the Adam algorithm optimization and the iterative calculation of the model training.

[0032] In the LSTM model, two loss functions are used to calculate the predicted results and temperature melon degree, expanding the difference between the relationships. Furthermore, the loss function is obtained using the following formula:

[0033] loss=max(0,-y*(S(r;q)-S(r';q))+margin)

[0034] loss2=y*|cos(r,r')|*max(0,cos(r,r)-γ).

[0035] The temperature and electrical fire operation monitoring system based on the intelligent substation provided by the present invention is characterized in that it includes: a physical entity layer, which includes: a closed core, windings, pads, stays, oil tanks in the distribution transformer, and temperature sensors and smoke sensors installed on the transformer; a data layer, which transmits the real-time data obtained by the temperature sensor and smoke sensor to the digital twin transformer based on the Internet of Things cloud platform; a user layer, which is used to create a temperature and electrical fire operation prediction model with LSTM based on time series correlation for data analysis and prediction. The method realizes real-time monitoring of the operating status of the transformer in the distribution substation through the information mirror model, which is simple and has high accuracy in prediction results.

[0036] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art may still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A temperature and electrical fire operation monitoring system based on intelligent substations, characterized in that: It includes: The physical entity layer includes: the closed core, windings, spacers, stays, oil tanks in the distribution transformer, and temperature sensors and smoke sensors installed on the transformer; A data layer, which transmits the real-time data acquired by the temperature sensor and the smoke sensor to the digital twin transformer based on the Internet of Things cloud platform; The user layer is used to create a temperature and electrical fire operation prediction model with LSTM based on time series correlation for data analysis and prediction.

2. A temperature and electrical fire operation monitoring system based on intelligent substations according to claim 1, characterized in that: The user layer relies on digital information technology, computer communication technology, big data technology, the Internet and database technology to collect and transmit the physical data of the transformer in real time, and integrates the digital twin model of the transformer. It uses intelligent algorithms to analyze the gas data in oil, realizes the interconnection and interactive mapping of the physical space and virtual space of the transformer, and outputs the fault type to engineering personnel, so as to achieve real-time online monitoring of the internal operation of the transformer and timely arrange personnel for targeted maintenance.

3. The temperature and electrical fire operation monitoring system based on intelligent substations according to claim 1 is characterized in that: It also includes: an intelligent perfluoroacetic acid ketone fire extinguisher, which is connected to the layer for controlling the opening of the intelligent perfluoroacetic acid ketone fire extinguisher when it is determined that the temperature reaches a temperature threshold and / or an electrical fire is predicted.

4. A temperature and electrical fire operation monitoring system based on intelligent substations according to claim 3, characterized in that: A dual-circuit power supply mode is adopted. Under normal operating conditions, the system is powered by AC power to ensure the normal operation of the system while storing energy for the energy storage equipment. When a failure occurs in the distribution station area and power is lost, the energy storage device has an inverter function and fast switching to ensure the normal operation of the system and quickly start the fire extinguishing system.

5. The temperature and electrical fire operation monitoring system based on intelligent substations according to claim 1 is characterized in that: The user layer carries out technical analysis of power and environmental monitoring of transformers in distribution substations, makes full use of its physical models, sensor data updates, operation history and other data, integrates multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, completes spatial mapping in the computer system, and establishes an information mirror model for distribution substations. Through the information mirror model, real-time monitoring of the operating status of transformers in distribution substations is achieved.

6. The temperature and electrical fire operation monitoring system based on intelligent substations according to claim 1 is characterized in that: The LSTM model includes: an input layer, a hidden layer, an output layer and model training, wherein the input layer is used to read and preprocess the data set, as well as to divide the training and test data sets; the hidden layer is used to build the LSTM hidden layer and the fully connected neural layer; the output layer is used as a verification process for the prediction results; and the model training is responsible for the loss function calculation, Adam algorithm optimization and iterative calculation of the model training.

7. A temperature and electrical fire operation monitoring system based on intelligent substations according to claim 6, characterized in that: In the LSTM model, two loss functions are used for calculation, which makes the prediction results and temperature more accurate and expands the differences in the representation of the relationship.

8. The temperature and electrical fire operation monitoring system based on intelligent substations according to claim 7 is characterized in that: The loss function is obtained using the following formula: loss=max(0,-y*(S(r;q)-S(r';q))+margin) loss2=y*|cos(r,r')|*max(0,cos(r,r)-γ).