Environment detection method and system for power distribution room

Abstract

The invention provides an environment detection method and system for a power distribution room, and the method comprises the steps: configuring at least one infrared sensor and a camera in pairs at different positions of the power distribution room, detecting and obtaining an infrared image and a visible light image of the corresponding position of the power distribution room, and constructing paired binding samples through the infrared image and the visible light image; constructing a neural network model, configuring a network layer and weight parameters of the neural network model, and inputting binding sample data of the infrared image and the visible light image into the neural network model for training; obtaining a trained living organism state recognition model, and recognizing the type of a living organism in the power distribution room and the state of the living organism according to the living organism state recognition model; and alarm information is generated according to the type and the state of the living organism, and the infrared sensor and the camera are positioned according to the infrared image and the visible light image corresponding to the alarm information for safe emergency treatment or small animal expelling at the corresponding position of the power distribution room.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental detection, and in particular to an environmental detection method and system for a power distribution room. Background Art

[0002] The traditional distribution room environment is complex. There may be problems such as dangerous gas leakage, condensation accumulation, invasion of small animals nearby, water accumulation in cable trenches, fire extinguisher leakage, and people falling to the ground due to oxygen depletion. Dangerous gas leakage includes but is not limited to sulfur hexafluoride gas leakage, and the traditional distribution network does not detect the above gases. The distribution room environment monitoring system is usually composed of an intelligent environmental control host, an automatic alarm, a front-end sensor, and management software or a cloud platform. However, the traditional distribution room has no unified solution for the dangers brought by the above complex environment. Summary of the invention

[0003] One of the inventive purposes of the present invention is to provide an environmental detection method and system for a distribution room, wherein the method and system are configured with an infrared sensor and a camera, wherein the infrared sensor is used to detect temperature image data including animals and related equipment in the distribution room, and is combined with the camera to perform inspections and alarms on images of related animal intrusions and human falls. Therefore, the present invention can use dual image data input into an AI model for effective identification of living organisms in the above-mentioned environment, and provide an effective living organism status alarm method, thereby avoiding damage to related equipment of the power system due to the invasion of small animals. At the same time, the falling status of on-duty personnel can also be effectively monitored to avoid danger to on-duty personnel in the distribution room due to electric shock or other reasons. The use of dual image data samples in the present invention can effectively reduce the impact of densely distributed cables in the distribution room on the image recognition of living organisms.

[0004] Another object of the present invention is to provide an environmental detection method and system for a distribution room. Compared with traditional technical solutions, the present invention also utilizes the dual image data collected by the infrared sensor and the camera to input into the AI ​​model to identify the relevant lines and the temperature of the lines, so that the power system lines with abnormal temperatures can be quickly identified, and the corresponding power system line faults can be quickly checked. The present invention uses the AI ​​model with the dual image data as samples to simultaneously perform identification of different risk types, thereby improving the centralized processing efficiency of risk detection and troubleshooting.

[0005] Another inventive object of the present invention is to provide an environmental detection method and system for a distribution room, wherein the method and system pre-configure a humidity sensor in the distribution room, and the humidity sensor is combined with a camera to identify and judge the condensation conditions of the cables in the corresponding distribution room, and perform dehumidification operations in the corresponding distribution room according to the condensation conditions to improve the safety of the distribution room.

[0006] Another object of the present invention is to provide an environmental detection method and system for a distribution room, wherein the method and system also configure a water immersion sensor in the cable trench, wherein the water immersion sensor is used to detect water immersion data in the cable trench in the distribution room, and upload the water immersion data to a central controller for generating water immersion alarm information.

[0007] In order to achieve at least one of the above-mentioned invention objects, the present invention further provides an environment detection method for a power distribution room, the method comprising: At least one infrared sensor and camera are configured in pairs at different positions in the power distribution room to detect and obtain infrared images and visible light images of corresponding positions in the power distribution room, and the infrared images and visible light images are constructed into paired binding samples; Constructing a neural network model, configuring the network layers and weight parameters of the neural network model, and inputting the bound sample data of the infrared image and the visible light image into the neural network model for training; Obtaining a trained living organism state recognition model, and identifying the type of living organisms and the state of the living organisms in the power distribution room according to the living organism state recognition model; Alarm information is generated according to the type and state of the living organism, and the infrared sensor and camera are positioned according to the infrared image and visible light image corresponding to the alarm information, so as to provide safety first aid or drive away small animals at the corresponding position of the power distribution room.

[0008] According to another preferred embodiment of the present invention, the living biological state recognition model is used to identify small animals of different types and human body information, wherein when the living biological state recognition model uses the infrared image and the visible light image to identify the target human body in the distribution room, it further identifies the posture information of the target human body, and determines whether the current target human body is at risk of falling down according to the posture information, and generates corresponding falling down risk alarm information according to the posture information of the target human body, wherein the falling down risk alarm information includes the positioning information of the target human body in the distribution room; when the living biological state recognition model uses the infrared image and the visible light image to identify the type of small animals in the distribution room, it generates small animal invasion alarm information, wherein the small animal invasion alarm information includes the positioning information of the corresponding small animals.

[0009] According to one of the preferred embodiments of the present invention, a humidity sensor and a dehumidifier are provided in the distribution room, and the camera is also used to obtain cable images at corresponding positions in the distribution room, and the cable images are input into a trained neural network model for cable condensation recognition, wherein a mapping relationship between cable condensation recognition data of the image sensor at the corresponding cable position and the start-up mapping relationship of the dehumidifier is established, and the dehumidifier is started in combination with the humidity sensor and the recognized cable condensation recognition data.

[0010] According to another preferred embodiment of the present invention, the power distribution room is equipped with a sulfur hexafluoride gas sensor and a heptafluoropropane gas sensor, and the sulfur hexafluoride gas sensor and the heptafluoropropane gas sensor are communicatively connected to a power distribution room control center, and the power distribution room control center is pre-configured with the sulfur hexafluoride gas concentration threshold and the heptafluoropropane gas concentration threshold, respectively. When the corresponding gas concentrations detected by the corresponding sulfur hexafluoride gas sensors and the heptafluoropropane gas sensors in the power distribution room are greater than the preset concentration thresholds, an alarm message of dangerous gas leakage is issued.

[0011] According to another preferred embodiment of the present invention, an oxygen sensor, a carbon monoxide sensor and a carbon dioxide sensor are further arranged in the bathroom of the distribution room, and the oxygen sensor, the carbon monoxide sensor and the carbon dioxide sensor respectively establish communication connections with the distribution room control center, and the distribution room control center is respectively configured with oxygen concentration thresholds, carbon monoxide concentration thresholds and carbon dioxide concentration thresholds, and the distribution room control center issues corresponding alarm information after comparing the detection concentrations of different types of gases with the corresponding thresholds.

[0012] According to another preferred embodiment of the present invention, the infrared sensors and cameras bound to the distribution room collect infrared temperature images and conductor type images of conductors at corresponding positions in the distribution room, and input the infrared temperature images and conductor type images into a neural network model for training to obtain a trained temperature anomaly recognition model for the conductor type of the distribution room, identify the conductor type and conductor position of abnormal temperature in the distribution room according to the temperature anomaly recognition model for the conductor type, and send conductor temperature anomaly alarm information through the distribution room control center.

[0013] According to another preferred embodiment of the present invention, the distribution room is equipped with a smoke sensor, and a smoke type alarm strategy is pre-configured in the distribution room control center. When the smoke sensor in the distribution room detects the corresponding smoke type and the corresponding smoke type reaches a preset concentration, the distribution room control center generates smoke alarm information for the distribution room and locates the smoke position.

[0014] According to another preferred embodiment of the present invention, the distribution room is also equipped with a temperature sensor and a water immersion detection device, wherein the temperature sensor is used to detect the ambient temperature in the distribution room, and perform a cooling operation of the distribution room according to the ambient temperature; the water immersion detection device is installed in the cable trench of the distribution room, and is used to detect whether there is water immersion information in the cable trench of the distribution room, and if so, issue a water immersion alarm information.

[0015] In order to achieve at least one of the above-mentioned invention purposes, the present invention further provides an environment detection system for a power distribution room, wherein the system executes the above-mentioned environment detection method for a power distribution room.

[0016] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the above-mentioned method for environmental detection of a power distribution room. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Shown is a flow chart of an environmental detection method for a power distribution room according to the present invention. DETAILED DESCRIPTION

[0018] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0019] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0020] Please combine Figure 1The present invention discloses a method and system for detecting the environment of a power distribution room. The method mainly includes the following steps: first, infrared sensors and cameras need to be configured in advance at different positions in the power distribution room, wherein the infrared sensors and cameras at each position are bound, and the bound infrared sensors and cameras are configured with corresponding position labeling information. The infrared sensor is used to obtain thermal imaging data including but not limited to small animals, human thermal imaging data and thermal imaging data of conductors of corresponding power system equipment in the power distribution room. Since single thermal imaging data is greatly affected by the environment, there are many cables and heating devices in the power distribution room, wherein the cables have a greater impact on the recognition of camera occlusion, and the heating devices have a greater impact on the recognition of living organisms with a certain body temperature. Therefore, it is difficult to effectively distinguish the above-mentioned small animals, human bodies and conductors of power equipment through single thermal imaging data or visible images. Therefore, the present invention inputs the infrared image of thermal imaging obtained by the infrared sensor into a neural network model for training and analysis in combination with the visible light image collected by the camera for visible light, which is used for recognition and analysis of different types of small animals, target human bodies and conductors of power system equipment. The image data acquired by the infrared sensor and the camera are dual images of the same detection position at the same detection time as an input sample of the neural network model binding data. The above-mentioned bound dual image samples can effectively solve the problem of insufficient accuracy of a single detection method in the power distribution scenario. It should be noted that the above-mentioned thermal imaging and image combination recognition and analysis method for conductors of small animals, human bodies and power equipment can be implemented based on a neural network model; neural network models including but not limited to CNN and DNN can be used. Of course, in another feasible and preferred embodiment of the present invention, different neural network models can be used to respectively recognize the thermal imaging and image combination of the conductors of the above-mentioned small animals, human bodies and power equipment, and the present invention will not repeat them in detail. The construction and training method of the neural network model includes but is not limited to: configuring the network layers such as the input layer, convolution layer, pooling layer and output layer of the neural network, and setting weight parameters between each network layer, training and outputting through the corresponding activation function, and obtaining the corresponding trained neural network model. The above-mentioned model training method can refer to the prior art, and the present invention will not repeat them in detail. The present invention uses the above-mentioned small animals invading the power distribution room and the infrared images and visible light images of the human body in the power distribution room as sample sets to construct and train a living organism state recognition model, wherein the living organism state recognition model is used to identify different types of living organisms, and the states of the corresponding living organisms (such as the target human body falling posture), etc. Further, the power distribution room control center configures corresponding alarm information according to the corresponding living organism type and state.

[0021] Specifically, when the infrared sensor and image sensor at the corresponding position of the distribution room acquire the infrared image and visible light image of the same position, the living biological state recognition model uses the infrared image and visible light image to recognize the target human body in the distribution room, further recognizes the posture information of the target human body, and judges whether the current target human body has a risk of falling down according to the posture information. When the target human body is recognized by the neural network model, the posture state of the target human body can be further judged, and corresponding falling down risk warning information is generated according to the posture information of the target human body, wherein the falling down risk warning information includes the positioning information of the target human body in the distribution room; when the living biological state recognition model uses the infrared image and visible light image to recognize the type of small animals in the distribution room, it generates small animal invasion warning information, wherein the small animal invasion warning information includes the positioning information of the corresponding small animals; wherein the positioning information of the small animals will be obtained according to the position annotation information of the infrared sensor and image sensor for identifying the presence of small animals, and the present invention will not elaborate on this.

[0022] Furthermore, since there are many cables in the distribution room, and condensation is easily generated in the cables when the temperature and humidity in the distribution room environment change, the generation of cable condensation may cause circuit breaking or short circuit. The above condensation is one of the important factors affecting the safety of the distribution room. Therefore, the present invention combines the configured camera to perform image recognition on the cable condensation in the distribution room and execute the operation after recognition. The specific method includes the following steps: the camera is also used to obtain the cable image of the corresponding position of the distribution room, and the cable image is input into the trained neural network model for cable condensation recognition, wherein a mapping relationship between the cable condensation recognition data of the image sensor at the corresponding cable position and the startup mapping relationship of the dehumidifier is established, and the dehumidifier is started in combination with the humidity sensor and the recognized cable condensation recognition data, wherein the dehumidifier may include but is not limited to air conditioners and other equipment.

[0023] In one of the preferred embodiments of the present invention, the power distribution room is also equipped with a sulfur hexafluoride gas sensor and a heptafluoropropane gas sensor, and the sulfur hexafluoride gas sensor and the heptafluoropropane gas sensor are communicatively connected to the power distribution room control center, and the power distribution room control center is pre-configured with the sulfur hexafluoride gas concentration threshold and the heptafluoropropane gas concentration threshold, respectively. When the corresponding gas concentration detected by the corresponding sulfur hexafluoride gas sensor and the heptafluoropropane gas sensor in the power distribution room is greater than the preset concentration threshold, an alarm message of dangerous gas leakage is issued. The above-mentioned corresponding gas sensors can effectively reduce or avoid the damage caused by the leakage of related dangerous gases.

[0024] Furthermore, since the conductors such as the related cables in the distribution room may generate heat due to faults, etc., the traditional cable faults need to be detected by means of contact temperature sensors installed in specific positions. Therefore, the present invention uses the infrared sensor combined with the image sensor to input dual image samples into the corresponding AI model for training, which is used to identify the corresponding cable faults by means of dual image thermodynamic imaging and visible light imaging. In this embodiment, non-contact cable heating fault identification can be performed, which has a faster and more accurate identification effect compared to the traditional fixed position installation method. The specific method includes the following steps: the infrared sensor and camera bound to the distribution room collect the infrared temperature image and conductor type image of the conductor at the corresponding position of the distribution room, and input the infrared temperature image and conductor type image of the conductor into the neural network model for training to obtain a trained temperature anomaly recognition model for the conductor type of the distribution room, identify the conductor type and conductor position of the abnormal temperature of the distribution room according to the temperature anomaly recognition model of the conductor type, and send the conductor temperature anomaly alarm information through the control center of the distribution room.

[0025] Furthermore, the present invention is also configured with different other sensors and temperature and humidity sensors to detect different environmental conditions in the distribution room, and upload different types of sensor data to the distribution room control center for comprehensive analysis, and give different types of alarm information, specifically including: the bathroom of the distribution room is also configured with an oxygen sensor, a carbon monoxide sensor and a carbon dioxide sensor, the oxygen sensor, the carbon monoxide sensor and the carbon dioxide sensor respectively establish communication connections with the distribution room control center, the distribution room control center is respectively configured with an oxygen concentration threshold, a carbon monoxide concentration threshold and a carbon dioxide concentration threshold, and the distribution room control center issues corresponding alarm information after comparing the detection concentration of different types of gas with the corresponding threshold. The distribution room control center is pre-configured with a smoke type alarm strategy, when the smoke sensor in the distribution room detects the corresponding smoke type, and the corresponding smoke type reaches a preset concentration, the distribution room control center generates the smoke alarm information of the distribution room and locates the smoke position. The distribution room is also equipped with a temperature sensor and a water immersion detection device, wherein the temperature sensor is used to detect the ambient temperature in the distribution room and perform a cooling operation of the distribution room according to the ambient temperature; the water immersion detection device is installed in the cable trench of the distribution room, and is used to detect whether there is water immersion information in the cable trench of the distribution room, and if so, a water immersion alarm information is issued.

[0026] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0027] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0028] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A method for detecting the environment of a power distribution room, characterized in that: The method comprises: At least one infrared sensor and camera are configured in pairs at different positions in the power distribution room to detect and obtain infrared images and visible light images of corresponding positions in the power distribution room, and the infrared images and visible light images are constructed into paired binding samples; Constructing a neural network model, configuring the network layers and weight parameters of the neural network model, and inputting the bound sample data of the infrared image and the visible light image into the neural network model for training; Obtaining a trained living organism state recognition model, and identifying the type of living organisms and the state of the living organisms in the power distribution room according to the living organism state recognition model; Alarm information is generated according to the type and state of the living organism, and the infrared sensor and camera are positioned according to the infrared image and visible light image corresponding to the alarm information, so as to provide safety first aid or drive away small animals at the corresponding position of the power distribution room.

2. The method for detecting the environment of a power distribution room according to claim 1, characterized in that: The living organism state recognition model is used to recognize small animals of different types and human body information. When the living organism state recognition model uses the infrared image and the visible light image to recognize the target human body in the distribution room, it further recognizes the posture information of the target human body, and determines whether the current target human body is at risk of falling down according to the posture information, and generates corresponding falling down risk warning information according to the posture information of the target human body, wherein the falling down risk warning information includes the positioning information of the target human body in the distribution room; when the living organism state recognition model uses the infrared image and the visible light image to recognize the type of small animal in the distribution room, it generates small animal invasion warning information, wherein the small animal invasion warning information includes the positioning information of the corresponding small animal.

3. The method for detecting the environment of a power distribution room according to claim 1, characterized in that: The distribution room is provided with a humidity sensor and a dehumidifier. The camera is also used to obtain cable images at corresponding positions in the distribution room, and the cable images are input into a trained neural network model for cable condensation recognition. A mapping relationship between the cable condensation recognition data of the image sensor at the corresponding cable position and the start-up mapping relationship of the dehumidifier is established, and the dehumidifier is started in combination with the humidity sensor and the recognized cable condensation recognition data.

4. The method for detecting the environment of a power distribution room according to claim 1, characterized in that: The power distribution room is equipped with a sulfur hexafluoride gas sensor and a heptafluoropropane gas sensor, and the sulfur hexafluoride gas sensor and the heptafluoropropane gas sensor are communicatively connected to the power distribution room control center, and the power distribution room control center is pre-configured with the sulfur hexafluoride gas concentration threshold and the heptafluoropropane gas concentration threshold, respectively. When the corresponding gas concentrations detected by the corresponding sulfur hexafluoride gas sensors and the heptafluoropropane gas sensors in the power distribution room are greater than the preset concentration threshold, an alarm message of dangerous gas leakage is issued.

5. The method for detecting the environment of a power distribution room according to claim 1, characterized in that: The bathroom of the distribution room is also equipped with an oxygen sensor, a carbon monoxide sensor and a carbon dioxide sensor. The oxygen sensor, the carbon monoxide sensor and the carbon dioxide sensor respectively establish communication connections with the distribution room control center. The distribution room control center is respectively equipped with oxygen concentration thresholds, carbon monoxide concentration thresholds and carbon dioxide concentration thresholds. The distribution room control center issues corresponding alarm information after comparing the detection concentrations of different types of gases with the corresponding thresholds.

6. The method for detecting the environment of a power distribution room according to claim 1, characterized in that: The infrared sensors and cameras bound to the distribution room collect infrared temperature images and conductor type images of conductors at corresponding positions in the distribution room, and input the infrared temperature images and conductor type images into a neural network model for training to obtain a trained temperature anomaly recognition model for the conductor type of the distribution room, identify the conductor type and conductor position of abnormal temperature in the distribution room according to the conductor type temperature anomaly recognition model, and send conductor temperature anomaly alarm information through the distribution room control center.

7. The method for detecting the environment of a power distribution room according to claim 1, characterized in that: The distribution room is equipped with a smoke sensor, and a smoke type alarm strategy is pre-configured in the distribution room control center. When the smoke sensor in the distribution room detects the corresponding smoke type and the corresponding smoke type reaches a preset concentration, the distribution room control center generates smoke alarm information for the distribution room and locates the smoke position.

8. The method for detecting the environment of a power distribution room according to claim 1, characterized in that: The distribution room is also equipped with a temperature sensor and a water immersion detection device, wherein the temperature sensor is used to detect the ambient temperature in the distribution room and perform a cooling operation of the distribution room according to the ambient temperature; the water immersion detection device is installed in the cable trench of the distribution room, and is used to detect whether there is water immersion information in the cable trench of the distribution room, and if so, a water immersion alarm information is issued.

9. An environmental detection system for a power distribution room, characterized in that: The system executes the method for detecting the environment of a power distribution room as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for detecting an environment of a power distribution room as described in any one of claims 1 to 8.

Images