Indoor substation disaster monitoring and early warning system and monitoring method

Abstract

The invention discloses an indoor transformer substation disaster monitoring and early warning system, and the system comprises a monitoring and early warning platform which comprises an information collection module, an information assembly module, an inspection module, and a first wireless signal receiving and transmitting device; after the information acquisition module assembles the acquired information by the information assembly module, the information is screened and filtered by the inspection module to form early warning information, and the early warning information is sent by the wireless signal transceiver; and the cloud monitoring platform is used for receiving the early warning information, comparing the early warning information and then taking early warning measures. The system has the beneficial effects that data acquisition, immediate early warning and immediate measures can be carried out from multiple aspects, the quick response capability to emergencies is improved, and the property loss of the indoor transformer substation caused by the emergencies is reduced to the greatest extent.

Description

Technical Field

[0001] The present invention relates to the technical field of disaster monitoring, and in particular to an indoor substation disaster monitoring and early warning system and a monitoring method. Background Art

[0002] It is very important to implement and improve the disaster warning and monitoring system of indoor substations, which can greatly shorten the time of disaster response and improve people's ability to respond quickly to emergencies. A complete disaster warning and monitoring system can send out warning signals when a disaster is about to happen or when a disaster just starts.

[0003] Chinese patent application publication number: CN 108898798A discloses a power grid earthquake early warning method and system, the earthquake early warning method is based on setting up earthquake monitoring points in substations, and sending early warning information through the internal communication network of the power grid or smart meters; the method includes obtaining seismic waveform data from the earthquake monitoring points, extracting characteristic values ​​of the seismic waveform data and sending them to an earthquake early warning data center; then the earthquake early warning data center performs earthquake quick judgment based on the characteristic values ​​to obtain quick judgment information, and publishes the quick judgment information to the early warning information receiving object according to a preset range and method.

[0004] The power grid earthquake early warning method and system provide guarantees for the operation and maintenance of the earthquake monitoring network by arranging the earthquake monitoring network in the power grid; at the same time, the acquired earthquake characteristic values ​​are sent to the power grid early warning center through the existing communication method of the power grid, providing a channel for the transmission of earthquake information. Although the power grid earthquake early warning method and system realize intelligent connection in a wide area and strengthen the earthquake emergency response capability of the power grid, it only obtains quick judgment information by quickly judging the earthquake through the characteristic values ​​of the vibration waveform data. It only provides guarantees for the accuracy of early warning of earthquakes occurring in substations and / or substation rooms, and does not provide early warnings for other serious natural disasters or other emergencies. Preventive emergency management not only provides early warnings for disasters such as earthquakes, but also includes early warnings for other emergencies.

[0005] Chinese patent application publication number: CN 113392500A discloses a geological disaster monitoring and early warning system, including an Internet of Things data collection module, an unmanned aerial vehicle data collection module, a big data management module and a monitoring and early warning module, wherein the Internet of Things data collection module is used to obtain the first geological monitoring data collected from the monitoring area, the unmanned aerial vehicle collection module is used to obtain the second geological monitoring data collected from the monitoring area, the big data management module is used to obtain the first geological monitoring data of the Internet of Things data collection module, and is also used to obtain the second geological monitoring data of the unmanned aerial vehicle data collection module, and the monitoring and early warning module is used to determine whether the monitoring area reaches a preset early warning level according to the first geological monitoring data and the second geological monitoring data, and generate an early warning prompt for the monitoring area that reaches the early warning level. Although the geological disaster monitoring and early warning system can intelligently monitor geological disasters and improve the accuracy of geological disaster early warning, it still has the following problems: the Internet of Things and the unmanned aerial vehicle need to collect data separately, the data collection procedure is cumbersome, and multiple data collection cannot be performed, and immediate early warning and immediate measures cannot be implemented. Summary of the invention

[0006] The present invention aims to overcome the deficiencies of the above-mentioned prior art and provides an indoor substation disaster monitoring and early warning system and a monitoring method, which are specifically implemented by the following technical solutions:

[0007] The indoor substation disaster monitoring and early warning system comprises:

[0008] The monitoring and early warning platform includes: an information collection module, an information compilation module, an inspection module, and a first wireless signal transceiver; the information collection module compiles the collected information by the information compilation module, and the information is screened and filtered by the inspection module to form early warning information, which is then sent through the wireless signal transceiver;

[0009] Cloud monitoring platform: receives the warning information, and takes warning measures after comparing the warning information.

[0010] A further design of the indoor substation disaster monitoring and early warning system is that the information collection module includes: an alarm module, an image information transmission module containing a camera, a temperature information transmission module containing a temperature sensor, and a smoke information transmission module containing a smoke sensor. The camera, temperature sensor and smoke sensor transmit abnormal information to the alarm module, and the alarm module, image information transmission module, temperature information transmission module and smoke information transmission module are respectively communicated with the information assembly module.

[0011] A further design of the indoor substation disaster monitoring and early warning system is that the inspection module includes a disaster identification model trained using a deep learning framework that can identify fires and other types of disasters.

[0012] A further design of the indoor substation disaster monitoring and early warning system is that the disaster identification model uses predicted values ​​and actual label values ​​to calculate losses during training, then updates model parameters through error back propagation, calculates the accuracy of the model, and saves the model with the highest accuracy to complete the training.

[0013] A further design of the indoor substation disaster monitoring and early warning system is that the model preprocesses data including adjusting the collected images to a set size and performing a series of operations including normalization.

[0014] A further design of the indoor substation disaster monitoring and early warning system is that the model assigns corresponding keys to the temperature and smoke information after data preprocessing according to the type of information, and the value corresponding to each key is a list containing time series data or NumPy array data; the model extracts features from the preprocessed collected information, specifically: the maximum value and average value of the temperature change rate and the average value of the smoke concentration are combined into a feature dictionary for model retrieval.

[0015] A further design of the indoor substation disaster monitoring and early warning system is that the cloud monitoring platform includes: a second wireless signal transceiver, a manager module, an information decompression module, a big data information comparison module, an information decision module and an information release module. The second wireless signal transceiver collects the early warning information and transmits it to the information decompression module through the manager module. The information decompression module is communicated with the information comparison module, and after transmitting the analyzed information to the information decision module, it is finally transmitted to the information release module from the manager module.

[0016] According to the indoor substation disaster monitoring and early warning system, a method for monitoring indoor substation disasters is proposed, which includes the following steps:

[0017] Step 1) Data collection: Use the image acquisition system to collect real-time images or video streams in the substation and convert the video streams into frame sequences for model processing;

[0018] Step 2) Data preprocessing: performing preprocessing operations on the collected images including image resizing and standardization;

[0019] Step 3) Disaster Identification: Use the trained model and input the preprocessed image. The model will output the prediction result of whether there is fire or smoke in each frame.

[0020] Step 4) Disaster warning: When the model predicts fire or smoke, the system will immediately issue an alarm, and the warning signal will be sent to the fire protection system, related mobile equipment or operation and maintenance personnel so that action can be taken as soon as possible;

[0021] Step 5) Data storage and analysis: All warning events and video records need to be saved for further analysis and optimization.

[0022] The present invention also provides an electronic device, comprising a memory, a processor and a computer program, wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the indoor substation disaster monitoring method.

[0023] The present invention also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement the indoor substation disaster monitoring method.

[0024] The advantages of the present invention are as follows:

[0025] The indoor substation disaster monitoring and early warning system and monitoring method of the present invention utilizes an information collection module to summarize information in the monitoring area. The collected information is immediately identified and authenticated by the AI ​​neural network inspection module, and compared with the temperature information range of the pre-input electrical equipment, thereby analyzing and comparing the abnormal information, and issuing an early warning based on the read information. On the one hand, the early warning system issues an early warning, and on the other hand, the information is transmitted to the cloud monitoring platform via the Internet, so that disaster information can be released immediately, and immediate early warning and immediate measures can be implemented. The present invention can collect data from multiple aspects, issue immediate early warnings, and implement immediate measures, thereby improving the ability to respond quickly to emergencies and minimizing the property losses caused by emergencies to indoor substations. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a principle block diagram of the indoor substation disaster monitoring and early warning system of the present invention.

[0027] Figure 2 The present invention is a flow chart of the monitoring method of the indoor substation disaster monitoring and early warning system. DETAILED DESCRIPTION

[0028] The technical solution of the present invention is described in detail below.

[0029] like Figure 1The indoor substation disaster monitoring and early warning system of this embodiment is mainly composed of: a monitoring and early warning platform and a cloud monitoring platform. Among them, the monitoring and early warning platform includes: an information collection module, an information compilation module, an inspection module, and a first wireless signal transceiver; the information collection module compiles the collected information by the information compilation module, and the inspection module compares the abnormal information identified by the information collection module with the pre-programmed normal information to avoid misidentification, and the inspection module forms early warning information after screening and filtering, and sends it through the wireless signal transceiver. Cloud monitoring platform: receives the early warning information, and takes early warning measures after comparing the early warning information.

[0030] The information collection module includes: an alarm module, an image information transmission module including a camera, a temperature information transmission module including a temperature sensor, and a smoke information transmission module including a smoke sensor. The camera, the temperature sensor, and the smoke sensor transmit abnormal information to the alarm module. The alarm module, the image information transmission module, the temperature information transmission module, and the smoke information transmission module are respectively communicated with the information assembly module.

[0031] The inspection module includes a disaster recognition model trained using a deep learning framework that can identify fires and other types of disasters.

[0032] During training, the disaster identification model uses the predicted value and the actual label value to calculate the loss, then back-propagates the error to update the model parameters, calculates the accuracy of the model, and saves the model with the highest accuracy to complete the training. The implementation code of the training process is as follows:

[0033]

[0034]

[0035] The model preprocesses the data, including adjusting the collected images to the set size and performing a series of operations including normalization. The model assigns corresponding keys to the temperature and smoke information after data preprocessing according to the type of information. The value corresponding to each key is a list containing time series data or NumPy array data; the model extracts features from the collected information after preprocessing, specifically: the maximum value and average value of the temperature change rate and the average value of the smoke concentration are combined into a feature dictionary for model retrieval. The specific implementation code is as follows:

[0036]

[0037] The cloud monitoring platform of this embodiment mainly consists of: a second wireless signal transceiver, a manager module, an information decompression module, a big data information comparison module, an information decision module and an information release module. The second wireless signal transceiver collects warning information and transmits it to the information decompression module through the manager module. The information decompression module is connected to the information comparison module, and the analyzed information is transmitted to the information decision module, and finally transmitted to the manager module to the information release module.

[0038] Furthermore, the big data information comparison module includes: a temperature information comparison module, a smoke information comparison module and an information reading module. The information reading module includes an image information reading module, a temperature information reading module and a smoke information reading module. The temperature information comparison module is connected to the temperature information reading module, and the smoke information comparison module is connected to the smoke information reading module.

[0039] The image information reading module, the temperature information reading module and the smoke information reading module are all connected to the information decision module.

[0040] The information decompression module includes: a temperature information decoding module of the cloud monitoring platform, a smoke information decoding module of the cloud monitoring platform, and a management information decoding module.

[0041] The following code is for the cloud monitoring platform to issue an alarm when a fire is predicted, such as sending a warning message to a designated mailbox or mobile phone or activating a fire prevention system:

[0042]

[0043]

[0044] According to the indoor substation disaster monitoring and early warning system, a method for monitoring indoor substation disasters is proposed, which includes the following steps:

[0045] Step 1) Data collection: Use the image acquisition system to collect real-time images or video streams in the substation and convert the video streams into frame sequences for model processing;

[0046] Step 2) Data preprocessing: preprocess the collected images, including adjusting the image size and standardization, so that the images can be correctly processed by the model;

[0047] Step 3) Disaster Identification: Use the trained model and input the preprocessed image. The model will output the prediction result of whether there is fire or smoke in each frame.

[0048] Step 4) Disaster warning: When the model predicts fire or smoke, the system will immediately issue an alarm, and the warning signal will be sent to the fire protection system, related mobile equipment or operation and maintenance personnel so that action can be taken as soon as possible;

[0049] Step 5) Data storage and analysis: All warning events and video records need to be saved for further analysis and optimization.

[0050] This embodiment further provides an electronic device, including a memory, a processor, and a computer program, wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the indoor substation disaster monitoring method.

[0051] This embodiment provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement the indoor substation disaster monitoring method.

[0052] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An indoor substation disaster monitoring and early warning system, It is characterized in that include: The monitoring and early warning platform includes: an information collection module, an information compilation module, an inspection module, and a first wireless signal transceiver; the information collection module compiles the collected information by the information compilation module, and the information is screened and filtered by the inspection module to form early warning information, which is then sent through the wireless signal transceiver; Cloud monitoring platform: receives the warning information, and takes warning measures after comparing the warning information.

2. The indoor substation disaster monitoring and early warning system according to claim 1, It is characterized in that The information acquisition module includes: an alarm module, an image information transmission module including a camera, a temperature information transmission module including a temperature sensor, and a smoke information transmission module including a smoke sensor. The camera, the temperature sensor, and the smoke sensor transmit abnormal information to the alarm module. The alarm module, the image information transmission module, the temperature information transmission module, and the smoke information transmission module are respectively communicated with the information assembly module.

3. The indoor substation disaster monitoring and early warning system according to claim 1, It is characterized in that The inspection module includes a disaster recognition model trained using a deep learning framework that can recognize fires and other types of disasters.

4. The indoor substation disaster monitoring and early warning system according to claim 3, It is characterized in that During training, the disaster identification model uses predicted values ​​and actual label values ​​to calculate losses, then back-propagates errors to update model parameters, calculates the accuracy of the model, and saves the model with the highest accuracy to complete the training.

5. The indoor substation disaster monitoring and early warning system according to claim 3, It is characterized in that The model's data preprocessing includes adjusting the acquired images to a set size and performing a series of operations including normalization.

6. The indoor substation disaster monitoring and early warning system according to claim 3, It is characterized in that The model assigns corresponding keys to the temperature and smoke information after data preprocessing according to the type of information. The value corresponding to each key is a list containing time series data or NumPy array data. The model extracts features from the preprocessed collected information, specifically: the maximum and average values ​​of the temperature change rate and the average value of the smoke concentration are combined into a feature dictionary for model retrieval.

7. The indoor substation disaster monitoring and early warning system according to claim 1, It is characterized in that The cloud monitoring platform includes: a second wireless signal transceiver, a manager module, an information decompression module, a big data information comparison module, an information decision module and an information release module. The second wireless signal transceiver collects warning information and transmits it to the information decompression module through the manager module. The information decompression module is communicated with the information comparison module, and after transmitting the analyzed information to the information decision module, it is finally transmitted to the information release module from the manager module.

8. An indoor substation disaster monitoring method using the indoor substation disaster monitoring and early warning system according to any one of claims 1 to 7, It is characterized in that The following steps are involved: Step 1) Data collection: Use the image acquisition system to collect real-time images or video streams in the substation and convert the video streams into frame sequences for model processing; Step 2) Data preprocessing: Perform preprocessing operations on the collected images, including resizing and standardization; Step 3) Disaster identification: Use the trained model and input the preprocessed images. The model will output the prediction results of whether there is fire or smoke in each frame of the image; Step 4) Disaster warning: When the model predicts fire or smoke, the system will immediately issue an alarm, and the warning signal will be sent to the fire protection system, related mobile equipment or operation and maintenance personnel so that action can be taken as soon as possible; Step 5) Data storage and analysis: All warning events and video records need to be saved for further analysis and optimization.

9. An electronic device, It is characterized in that The system comprises a memory, a processor and a computer program, wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the indoor substation disaster monitoring method according to claim 8.

10. A computer-readable storage medium, Features The storage medium stores a computer program, and the computer program is executed by a processor to implement the indoor substation disaster monitoring method according to claim 8.

Images