A safety early warning method for emergency response to power accidents
By building an electrical equipment map network and a fault information database, an area power accident emergency response system equipped with deep learning algorithms is provided, targeted early warning and animation simulation demonstrations are solved, and safety hazards caused by insufficient knowledge in electrical equipment fault handling are improved. Correctness and safety in handling electrical faults.
Patent Information
- Application Number
- CN202111251528.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-27
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2041-10-27
AI Technical Summary
When electrical equipment fails, maintenance workers are prone to making mistakes in judgment due to insufficient reserve of power knowledge, resulting in unpredictable consequences, resulting in electrical accidents and safety hazards.
By counting relevant information about electrical equipment, building an electrical equipment map network and fault information database, an area power accident emergency response system equipped with deep learning algorithms, using mobile APP for fault identification and early warning, providing targeted prompts and prevention measures, combined with animation Simulation demonstrations increase staff vigilance.
It effectively avoids electrical accidents caused by improper handling methods, reduces the scope of the accident and losses, and improves the correctness and safety of staff when dealing with electrical faults.
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of electric power accident early warning, and in particular to a safety early warning method for emergency disposal of electric power accidents. Background Art
[0002] With the widespread use of electricity, electrical equipment has become quite common in all walks of life. If electrical equipment is not installed properly, used irrationally, and repaired in time, especially if electrical workers lack the necessary knowledge of telegraph safety, it will not only cause waste of electricity, but also electrical accidents, endangering personal safety and causing significant losses to the country and the people. In fact, there are a large number of electrical unsafe phenomena in machinery, chemical industry, metallurgy and other industrial and mining industries, and electrical accidents have become an important cause of personal injury, explosion and fire accidents. Therefore, electrical safety has received increasing attention and attention from people. Electrical safety mainly includes personal safety and equipment safety. Personal safety refers to the safety of personnel during work and the operation and use of electrical equipment; equipment safety refers to the safety of electrical equipment and other related equipment and buildings. Electrical accidents are often not caused by a single reason. In order to do a good job in electrical safety, it is necessary to take measures including technology and organizational management. With the advancement of science and technology, countries are actively researching and continuously introducing advanced electrical safety technologies, improving and revising electrical safety technical standards and regulations, which are very important for protecting the safety and health of workers and the safety of electrical equipment.
[0003] In the prior art, when electrical equipment fails, inspection workers are often required to perform maintenance and protection. Since most maintenance workers do not have sufficient knowledge of electricity and cannot clearly recognize the potential dangers of the failure, when electrical equipment fails, the staff are prone to misjudgment and incorrect handling, which can easily lead to unpredictable consequences. Summary of the invention
[0004] To this end, the present invention provides a safety early warning method for emergency handling of power accidents to solve the problems raised in the above background technology.
[0005] In order to achieve the above-mentioned purpose, the embodiment of the present invention provides the following technical solution: a safety early warning method for emergency handling of power accidents, comprising the following specific steps:
[0006] Step 1: Count the relevant information of all electrical equipment in the specified area, including the GPS coordinates of each electrical equipment, the circuit pipeline information of each electrical equipment, whether each electrical equipment contains flammable and explosive substances, the service life of the electrical equipment, and the maintenance and replacement records. It also includes the environmental information around the electrical equipment: whether there are flammable and explosive substances around, the ambient temperature, ambient humidity and weather conditions, and store it in the basic information database;
[0007] Step 2: Connect the GPS coordinates of each electrical device in the designated area to form an electrical device map network, and then store the electrical device map network in the basic information database in step 1;
[0008] Step 3: Collect the possible faults of each electrical equipment from the Internet, list the power accidents that may be caused by each fault, and then store the possible faults of each electrical equipment and the safety accidents caused in the fault information database; the fault information database also stores the solutions to the relevant electrical equipment faults, potential safety accidents and effective measures to prevent the safety accidents;
[0009] Step 4: Build a regional power accident emergency response system, upload the information in the basic information database and the fault information database to the regional power accident emergency response system, and install the system on a mobile phone APP for power workers to carry with them. The regional power accident emergency response system is connected to the camera on the mobile phone. The system is also equipped with a deep learning algorithm, which is used to process the pictures taken by the mobile phone camera.
[0010] Step 5. When an electrical equipment failure occurs, the staff arrives in time, and then makes a preliminary judgment on the fault location based on the staff's work experience, takes a picture of the fault location with the camera on the mobile phone they carry with them, and then uploads the captured image information to the regional power accident emergency response system. The uploaded image information is analyzed using the deep learning algorithm in the system, and the features on the image information are extracted. The type of fault that has occurred is then identified through feature comparison. The regional power accident emergency response system then combines the relevant information of the electrical equipment and the surrounding environmental information to match the fault with the accident type in the fault information database, selects 5 potential power accidents with a high probability of occurrence, and provides targeted warnings and prompts to the staff based on the selected potential power accidents, prompting the staff to take preventive measures.
[0011] Furthermore, the designated area in step one refers to a place where a large number of electrical equipment are installed, including schools, office buildings, factories, and residential areas. The present invention can effectively provide early warning for electrical equipment in a concentrated area, making it convenient for staff to promptly discover power failures during inspections and to resolve them using correct methods.
[0012] Furthermore, in the electrical equipment map network in step 2, by selecting an electrical equipment at one of the coordinate points, the locations of other electrical equipment associated with it and the relevant information of the electrical equipment associated with it can be viewed. By connecting multiple electrical equipment within the selected area on the same map, the impact of the faulty electrical equipment on the surrounding equipment can be directly viewed, so as to facilitate timely protective measures for the surrounding equipment to avoid expanding the scope of the accident, thereby minimizing the losses caused by the accident in a timely manner.
[0013] Furthermore, the fault information database in step three also stores solutions to related electrical equipment faults, potential safety accidents, and effective measures to prevent such safety accidents, so as to provide staff with correct handling methods to avoid electrical accidents caused by improper handling methods.
[0014] Furthermore, the deep learning algorithm in step four includes a convolutional neural network. A convolutional neural network is a feedforward neural network whose artificial neurons can respond to surrounding units within a part of the coverage area and have excellent performance in large-scale image processing. The basic structure of a convolutional neural network includes two layers. One is a feature extraction layer. The input of each neuron is connected to the local receptive field of the previous layer and extracts the local feature. Once the local feature is extracted, its positional relationship with other features is also determined. The second is a feature mapping layer. Each computing layer of the network is composed of multiple feature maps. Each feature map is a plane. The weights of all neurons on the plane are equal. The feature mapping structure uses a sigmoid function with a small influence function kernel as the activation function of the convolutional network, so that the feature map has displacement invariance. By using a convolutional neural network, the pictures taken by the mobile phone can be accurately processed, and feature information about the fault can be extracted from the pictures to help the staff correctly handle electrical faults.
[0015] Furthermore, the five potential power accidents selected in step five are arranged in order of possibility from high to low, and displayed to the staff through the mobile phone display screen, among which the potential power accident with the highest possibility is highlighted. The highlighted display can help the staff to see it directly and avoid the staff from missing important information.
[0016] Furthermore, the regional power accident emergency handling system in step four also includes an animation simulation demonstration module, which is used to simulate and demonstrate power accidents that may be caused by faults identified in the system. The content of the simulation demonstration includes the degree of direct harm caused by the power accident to the staff who operate incorrectly, the degree of damage to the surrounding environment, the degree of impact on other electrical equipment associated with the electrical equipment, and the scope of impact of the accident. The animation simulation demonstration module can most intuitively display the impact caused by the fault, so as to improve the vigilance of the staff and enable the staff to be in a serious, rigorous and careful state when handling electrical faults, which can facilitate the staff to make correct handling methods and prevent problems before they occur.
[0017] The present invention has the following advantages:
[0018] 1. The present invention places all electrical equipment in a specified area in the same network by establishing an electrical equipment map network in a regional area, so that it is convenient to understand the relevant information of each electrical equipment and its connected electrical equipment, so that the staff can understand the possible impact range of the faulty electrical equipment. By building a regional power accident emergency handling system and installing a deep learning algorithm in the system, the deep learning algorithm is used to help the staff identify electrical faults and provide the staff with correct handling methods to avoid electrical accidents caused by improper handling methods, thereby avoiding unpredictable consequences;
[0019] 2. The present invention installs animation demonstrations in the regional power accident emergency handling system, and uses animation to demonstrate to the staff the possible consequences of incorrect operations and the impact on the surrounding areas, so as to increase the vigilance of the staff, so that the staff can be in a serious, rigorous and careful state when handling electrical faults, thereby facilitating the staff to make correct handling methods and prevent accidents before they occur. DETAILED DESCRIPTION
[0020] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0021] The present invention provides a safety early warning method for emergency handling of power accidents, comprising the following specific steps:
[0022] Step 1: Count the relevant information of all electrical equipment in the specified area, including the GPS coordinates of each electrical equipment, the circuit pipeline information of each electrical equipment, whether each electrical equipment contains flammable and explosive substances, the service life of the electrical equipment, and the maintenance and replacement records. It also includes the environmental information around the electrical equipment: whether there are flammable and explosive substances around, the ambient temperature, ambient humidity and weather conditions, and store it in the basic information database;
[0023] The designated area refers to a place where a large number of electrical equipment are installed, including schools, office buildings, factories, and residential areas. The present invention can effectively provide early warning for electrical equipment in a concentrated area, making it convenient for staff to promptly discover power failures during inspections and to use correct methods to solve them.
[0024] Step 2: Connect the GPS coordinates of each electrical device in the designated area, and then store the electrical device map network into the basic information database in step 1. In the electrical device map network, by selecting an electrical device at one of the coordinate points, the locations of other electrical devices associated with it and the related information of the electrical devices associated with it can be viewed. By connecting multiple electrical devices within the selected area on the same map, the impact of the faulty electrical device on the surrounding devices can be directly viewed, so as to facilitate timely taking of protective measures for the surrounding devices, so as to avoid expanding the scope of the accident, and thus timely minimize the losses caused by the accident;
[0025] GPS coordinates are short for global positioning system coordinates, which are generally composed of two parameters: longitude and latitude, also called longitude and latitude. The earth is divided into 180 longitudes from Greenwich to the east and west; from the equator, it is divided into 90 latitudes to the south and north. The unit is sexagesimal (degrees: minutes: seconds, letters indicate direction) or decimal (positive / negative decimal degrees). It can also be called the real-world coordinate system, which is a coordinate system used to determine the location of objects on the earth and form an electrical equipment map network.
[0026] Step 3. Collect possible faults of each electrical equipment from the Internet, and list the power accidents that may be caused by each fault one by one. Then store the possible faults of each electrical equipment and the safety accidents caused in the fault information database. The fault information database also stores solutions to related electrical equipment faults, potential safety accidents and effective measures to prevent the safety accidents, so as to provide correct handling methods for staff to avoid electrical accidents caused by improper handling methods.
[0027] Step 4: Build a regional power accident emergency response system, upload the information in the basic information database and the fault information database to the regional power accident emergency response system, and install the system on a mobile phone APP for power workers to carry with them. The regional power accident emergency response system is connected to the camera on the mobile phone. The system is also equipped with a deep learning algorithm, which is used to process the pictures taken by the mobile phone camera.
[0028] Deep learning algorithms include convolutional neural networks. Convolutional neural networks are a type of feedforward neural network whose artificial neurons can respond to surrounding units within a certain coverage area. They have excellent performance in large-scale image processing. The basic structure of convolutional neural networks includes two layers. The first is the feature extraction layer. The input of each neuron is connected to the local receptive field of the previous layer and extracts the local features. Once the local feature is extracted, its positional relationship with other features is also determined. The second is the feature mapping layer. Each computing layer of the network consists of multiple feature maps. Each feature map is a plane. The weights of all neurons on the plane are equal. The feature mapping structure uses the sigmoid function with a small influence function kernel as the activation function of the convolutional network, which makes the feature map displacement invariant. By using the convolutional neural network, the pictures taken by the mobile phone can be accurately processed, and the feature information about the fault can be extracted from the pictures to help the staff to correctly handle the electrical fault.
[0029] Convolutional neural networks are mainly used to identify two-dimensional graphics that are invariant to displacement, scaling, and other forms of distortion. Since the feature detection layer of a convolutional neural network is learned through training data, when using a convolutional neural network, explicit feature extraction is avoided, and learning is implicitly performed from the training data; furthermore, since the weights of neurons on the same feature map are the same, the network can learn in parallel, which is also a major advantage of convolutional networks over networks in which neurons are connected to each other. Convolutional neural networks have unique advantages in speech recognition and image processing due to their special structure of local weight sharing. Their layout is closer to actual biological neural networks, and weight sharing reduces the complexity of the network. In particular, the image of a multi-dimensional input vector can be directly input into the network, which avoids the complexity of data reconstruction during feature extraction and classification.
[0030] In addition, the regional power accident emergency response system also includes an animation simulation demonstration module, which is used to simulate and demonstrate power accidents that may be caused by faults identified in the system. The content of the simulation demonstration includes the degree of direct harm caused by the power accident to the staff who operate incorrectly, the degree of damage to the surrounding environment, the degree of impact on other electrical equipment associated with the electrical equipment, and the scope of impact of the accident. The animation simulation demonstration module can most intuitively display the impact caused by the fault, so as to improve the vigilance of the staff and enable the staff to be in a serious, rigorous and careful state when dealing with electrical faults, which can facilitate the staff to make correct handling methods and prevent problems before they occur.
[0031] Step 5. When an electrical equipment fails, the staff arrives in time, and then makes a preliminary judgment on the fault location based on the staff's work experience, takes a picture of the fault location with the camera on the mobile phone carried with them, and then uploads the captured picture information to the regional power accident emergency response system. The uploaded picture information is analyzed using the deep learning algorithm in the system, and the features on the picture information are extracted. Then, the type of fault that occurred is identified through feature comparison. Then, the regional power accident emergency response system combines the relevant information of the electrical equipment and the surrounding environmental information, matches the fault with the accident type in the fault information database, selects 5 potential power accidents with a high probability of occurrence, and gives targeted warnings and prompts to the staff based on the selected potential power accidents, prompting the staff to take preventive measures. Among them, the selected 5 potential power accidents are arranged in order from high to low probability, and displayed to the staff through the mobile phone display screen, among which the potential power accident with the highest probability is emphasized. The emphasized display can help the staff to see directly and avoid the staff from missing important information.
[0032] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.
Claims
1. A safety early warning method for emergency handling of power accidents, characterized by: The specific steps include: Step 1: Count the relevant information of all electrical equipment in the specified area, including the GPS coordinates of each electrical equipment, the circuit pipeline information of each electrical equipment, whether each electrical equipment contains flammable and explosive substances, the service life of the electrical equipment, and the maintenance and replacement records. It also includes the environmental information around the electrical equipment: whether there are flammable and explosive substances around, the ambient temperature, ambient humidity and weather conditions, and store it in the basic information database; Step 2: Connect the GPS coordinates of each electrical device in the designated area to form an electrical device map network, and then store the electrical device map network in the basic information database in step 1; Step 3: Collect the possible faults of each electrical equipment from the Internet, list the possible power accidents caused by each fault, and then store the possible faults of each electrical equipment and the safety accidents caused in the fault information database; Step 4: Build a regional power accident emergency response system, upload the information in the basic information database and the fault information database to the regional power accident emergency response system, and install the system on a mobile phone APP for power workers to carry with them. The regional power accident emergency response system is connected to the camera on the mobile phone. The system is also equipped with a deep learning algorithm, which is used to process the pictures taken by the mobile phone camera. Step 5. When an electrical equipment failure occurs, the staff arrives in time, and then makes a preliminary judgment on the fault location based on the staff's work experience, takes a picture of the fault location with the camera on the mobile phone they carry with them, and then uploads the captured image information to the regional power accident emergency response system. The uploaded image information is analyzed using the deep learning algorithm in the system, and the features on the image information are extracted. The type of fault that has occurred is then identified through feature comparison. The regional power accident emergency response system then combines the relevant information of the electrical equipment and the surrounding environmental information to match the fault with the accident type in the fault information database, selects 5 potential power accidents with a high probability of occurrence, and provides targeted warnings and prompts to the staff based on the selected potential power accidents, prompting the staff to take preventive measures.
2. A safety early warning method for emergency handling of power accidents according to claim 1, characterized in that: The designated areas in step one refer to schools, office buildings, factories, and residential areas.
3. The method for early warning of power accident emergency response according to claim 1, characterized in that: In the electrical equipment map network in step 2, by selecting an electrical equipment at one of the coordinate points, you can see the locations of other electrical equipment associated with it, as well as relevant information of the electrical equipment associated with it.
4. The method for early warning of power accident emergency response according to claim 1, characterized in that: The fault information database in step three also stores solutions to related electrical equipment faults, potential safety accidents, and effective measures to prevent the safety accidents.
5. The method for safety early warning of power accident emergency response according to claim 1 is characterized by: The deep learning algorithm in step 4 includes a convolutional neural network. A convolutional neural network is a feedforward neural network whose artificial neurons can respond to surrounding units within a part of the coverage area and perform well in large-scale image processing. The basic structure of a convolutional neural network includes two layers. One is a feature extraction layer. The input of each neuron is connected to the local receptive field of the previous layer and extracts the local feature. Once the local feature is extracted, its positional relationship with other features is also determined. The second is a feature mapping layer. Each computing layer of the network is composed of multiple feature maps. Each feature map is a plane. The weights of all neurons on the plane are equal. The feature mapping structure uses a sigmoid function with a small influence function kernel as the activation function of the convolutional network, so that the feature map has displacement invariance.
6. The method for safety early warning of power accident emergency response according to claim 1, characterized in that: The five potential power accidents selected in step five are arranged in order of probability from high to low, and displayed to the staff through the mobile phone display screen, among which the potential power accident with the highest probability is highlighted.
7. The method for safety early warning of power accident emergency response according to claim 1, characterized in that: The regional power accident emergency handling system in step four also includes an animation simulation demonstration module, which is used to simulate and demonstrate power accidents that may be caused by faults identified in the system. The content of the simulation demonstration includes the degree of direct harm caused by the power accident to the staff who operate incorrectly, the degree of damage to the surrounding environment, the degree of impact on other electrical equipment associated with the electrical equipment, and the scope of impact of the accident.
Citation Information
Patent Citations
Power equipment fault detection and positioning method based on artificial intelligence reasoning fusion
CN110334740A
Electric power emergency command system
CN112531899A
Unmanned aerial vehicle intelligent electric power inspection system and method
CN113359826A
