Electrified cleaning scene monitoring system applying intelligent analysis

Abstract

The invention relates to a live-line cleaning scene monitoring system applying intelligent analysis, and the system comprises a mode detection mechanism which is disposed in a pedestal below a tower of a power transmission network, and is used for transmitting a first detection signal when detecting that the power transmission network is in a working mode of live-line cleaning of a suspension insulator at present, and otherwise, transmitting a second detection signal; and the intelligent analysis equipment is used for intelligently analyzing whether the constructors are in contact with the wire or not by adopting an intelligent analysis model. The electrified cleaning scene monitoring system applying intelligent analysis is stable in operation and intelligent in control. Various basic data used for subsequent intelligent analysis can be screened out, and the intelligent analysis model is adopted to intelligently analyze whether the constructors are in contact with the wires, so that intelligent analysis of construction dangerous scenes based on various visual data screened in a targeted manner is completed, and the requirements of the power transmission network for cleaning the suspension insulators in an electrified manner can be met. And a constructor needs to keep a safe distance from an adjacent wire.

Description

Technical Field

[0001] The present invention relates to the field of power transmission networks, and in particular to a live cleaning scene monitoring system using intelligent analysis. Background Art

[0002] The transmission network is a power transmission network that connects power plants, substations or substations, and is mainly responsible for the transmission of electric energy. According to the different transmission voltages, it can be divided into high-voltage transmission networks (110~220kv), ultra-high-voltage transmission networks (330~750kv) and ultra-high-voltage transmission networks (1000kv and above). The transmission network is composed of transmission equipment and substation equipment. The transmission equipment mainly includes transmission lines, towers, insulator strings, empty lines, etc.; the substation equipment mainly includes transformers, reactors, capacitors, circuit breakers, grounding switches, lightning arresters, voltage transformers, current transformers, and power protection, monitoring, control, and communication systems. The power system is getting larger and larger, and the structure is becoming more and more complex. Among the various forms of energy consumed by humans, the proportion of electric energy supplied by the power system is increasing.

[0003] In the prior art, during the operation of the transmission network, it is necessary to monitor whether there is contact between construction workers and conductors, so as to complete the intelligent analysis of construction danger scenarios and meet the safety construction requirements that construction workers should maintain a safe distance from adjacent conductors when cleaning suspension insulators under power. Obviously, there is a lack of corresponding solutions in the prior art. Summary of the invention

[0004] In order to solve the technical problems in the related fields, the present invention provides a live cleaning scene monitoring system using intelligent analysis. By obtaining the edge pixel points in the third processed image of the on-site image of the construction personnel after targeted optimization processing and obtaining the edge pixel points of the wire in the third processed image, the total number of edge pixel points of the construction personnel in the third processed image and the total number of edge pixel points of the wire in the third processed image are accumulated, thereby screening out various basic data for subsequent intelligent analysis. An intelligent analysis model is also used to intelligently analyze whether there is contact between the construction personnel and the wire based on the depth of field value of each edge pixel point of the construction personnel in the third processed image, the depth of field value of each edge pixel point of the wire in the third processed image, the grayscale value and coordinate value of each edge pixel point of the wire in the third processed image, the total number of edge pixel points of the construction personnel in the third processed image and the total number of edge pixel points of the wire in the third processed image, thereby completing the intelligent analysis of the construction danger scene based on the targeted screened visual data, and meeting the safety construction requirement that the construction personnel and the adjacent wires should maintain a safe distance when the transmission network is live cleaning the suspension insulator.

[0005] According to the present invention, a live cleaning scene monitoring system using intelligent analysis is provided, the system comprising: A mode detection mechanism is arranged in a base below a tower of a power transmission network, and is used to send a first detection signal when it is detected that the power transmission network is currently in a working mode of live cleaning suspension insulators, and is also used to send a second detection signal when it is detected that the power transmission network is currently not in the working mode of live cleaning suspension insulators; A signal capturing mechanism, connected to the mode detecting mechanism, for triggering an image signal capturing operation on the power transmission network site upon receiving the first detection signal, so as to obtain and output a captured image of the site; a first processing device, disposed in the base and connected to the signal capture mechanism, for performing image content enhancement processing by applying logarithmic transformation on the received live captured image to obtain and output a first processed image; a second processing device, connected to the first processing device, configured to perform image content SVD enhancement processing on the received first processed image to obtain and output a second processed image; a third processing device, connected to the second processing device, configured to perform image content enhancement processing of harmonic mean filtering on the received second processed image to obtain and output a third processed image; an intelligent analysis device, arranged in the base and connected to the third processing device, for obtaining each edge pixel point of the construction personnel in the third processed image and each edge pixel point of the wire in the third processed image, accumulating the total number of edge pixel points of the construction personnel in the third processed image and the total number of edge pixel points of the wire in the third processed image, and using an intelligent analysis model to intelligently analyze whether there is contact between the construction personnel and the wire based on the depth of field value of each edge pixel point of the construction personnel in the third processed image, the depth of field value of each edge pixel point of the wire in the third processed image, the grayscale value and coordinate value of each edge pixel point of the construction personnel in the third processed image, the grayscale value and coordinate value of each edge pixel point of the wire in the third processed image, the total number of edge pixel points of the construction personnel in the third processed image and the total number of edge pixel points of the wire in the third processed image; Among them, an intelligent analysis model is used to intelligently analyze whether there is contact between the construction workers and the wires based on the depth of field values ​​of each edge pixel points of the construction workers in the third processed image, the depth of field values ​​of each edge pixel points of the wires in the third processed image, the grayscale values ​​and coordinate values ​​of each edge pixel points of the construction workers in the third processed image, the grayscale values ​​and coordinate values ​​of each edge pixel points of the wires in the third processed image, the total number of edge pixels of the construction workers in the third processed image, and the total number of edge pixels of the wires in the third processed image. The intelligent analysis model includes: the intelligent analysis model is a convolutional neural network that has been trained multiple times and the number of training times is inversely correlated with the signal-to-noise ratio of the third processed image.

[0006] It can be seen that the present invention has at least the following three significant substantive features: Substantive feature A: Obtaining each edge pixel point in the third processed image, i.e., the on-site image of the construction personnel after targeted optimization processing, and obtaining each edge pixel point of the wire in the third processed image, accumulating the total number of edge pixel points of the construction personnel in the third processed image and the total number of edge pixel points of the wire in the third processed image, thereby screening out various basic data for subsequent intelligent analysis; Substantive feature B: An intelligent analysis model is used to intelligently analyze whether there is contact between the construction workers and the wires based on the depth of field value of each edge pixel point of the construction workers in the third processed image, the depth of field value of each edge pixel point of the wire in the third processed image, the grayscale value and coordinate value of each edge pixel point of the construction workers in the third processed image, the grayscale value and coordinate value of each edge pixel point of the wire in the third processed image, the total number of edge pixels of the construction workers in the third processed image, and the total number of edge pixels of the wire in the third processed image, thereby completing the intelligent analysis of construction hazard scenes based on targeted screened visual data, meeting the safety construction requirements of the transmission network that the construction workers should maintain a safe distance from the adjacent wires when cleaning the suspension insulators under power; Substantive Feature C: The intelligent analysis model structure for performing intelligent analysis of whether construction workers and wires are in contact is customized. It is a convolutional neural network that has been trained multiple times, and the number of training times is inversely correlated with the signal-to-noise ratio of the third processed image, thereby ensuring the stability and reliability of the intelligent analysis results.

[0007] The live cleaning scene monitoring system using intelligent analysis of the present invention is stable in operation and intelligent in control. Since it can screen out various basic data for subsequent intelligent analysis, it also uses an intelligent analysis model to intelligently analyze whether there is contact between construction personnel and wires, thereby completing the intelligent analysis of construction danger scenes based on various visual data screened in a targeted manner, meeting the safety construction requirements of the transmission network that construction personnel should maintain a safe distance from adjacent wires when live cleaning suspension insulators. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0009] Figure 1 It is an internal structure diagram of the live cleaning scene monitoring system using intelligent analysis according to the first embodiment of the present invention.

[0010] Figure 2 It is an internal structure diagram of a live cleaning scene monitoring system applying intelligent analysis according to a second embodiment of the present invention.

[0011] Figure 3 It is an internal structure diagram of a live cleaning scene monitoring system applying intelligent analysis according to a third embodiment of the present invention. DETAILED DESCRIPTION

[0012] The implementation scheme of the live cleaning scene monitoring system using intelligent analysis of the present invention will be described in detail below with reference to the accompanying drawings.

[0013] Figure 1 The internal structure diagram of the live cleaning scene monitoring system using intelligent analysis according to the first embodiment of the present invention is shown, and the system includes: A mode detection mechanism is arranged in a base below a tower of a power transmission network, and is used to send a first detection signal when it is detected that the power transmission network is currently in a working mode of live cleaning suspension insulators, and is also used to send a second detection signal when it is detected that the power transmission network is currently not in the working mode of live cleaning suspension insulators; Specifically, a numerical simulation mode can be used to implement the testing and simulation of the data processing process of the mode detection mechanism for sending a first detection signal when detecting that the power transmission network is currently in the working mode of live cleaning suspension insulators, and for sending a second detection signal when detecting that the power transmission network is currently not in the working mode of live cleaning suspension insulators; A signal capturing mechanism, connected to the mode detecting mechanism, for triggering an image signal capturing operation on the power transmission network site upon receiving the first detection signal, so as to obtain and output a captured image of the site; a first processing device, disposed in the base and connected to the signal capture mechanism, for performing image content enhancement processing by applying logarithmic transformation on the received live captured image to obtain and output a first processed image; a second processing device, connected to the first processing device, configured to perform image content SVD enhancement processing on the received first processed image to obtain and output a second processed image; a third processing device, connected to the second processing device, configured to perform image content enhancement processing of harmonic mean filtering on the received second processed image to obtain and output a third processed image; an intelligent analysis device, arranged in the base and connected to the third processing device, for obtaining each edge pixel point of the construction personnel in the third processed image and each edge pixel point of the wire in the third processed image, accumulating the total number of edge pixel points of the construction personnel in the third processed image and the total number of edge pixel points of the wire in the third processed image, and using an intelligent analysis model to intelligently analyze whether there is contact between the construction personnel and the wire based on the depth of field value of each edge pixel point of the construction personnel in the third processed image, the depth of field value of each edge pixel point of the wire in the third processed image, the grayscale value and coordinate value of each edge pixel point of the construction personnel in the third processed image, the grayscale value and coordinate value of each edge pixel point of the wire in the third processed image, the total number of edge pixel points of the construction personnel in the third processed image and the total number of edge pixel points of the wire in the third processed image; Wherein, using an intelligent analysis model to intelligently analyze whether there is contact between the construction personnel and the wire based on the depth of field value of each edge pixel point of the construction personnel in the third processed image, the depth of field value of each edge pixel point of the wire in the third processed image, the grayscale value and coordinate value of each edge pixel point of the construction personnel in the third processed image, the grayscale value and coordinate value of each edge pixel point of the wire in the third processed image, the total number of edge pixels of the construction personnel in the third processed image, and the total number of edge pixels of the wire in the third processed image includes: the intelligent analysis model is a convolutional neural network that has been trained multiple times, and the number of training times is inversely correlated with the signal-to-noise ratio of the third processed image; The intelligent analysis model is a convolutional neural network that has been trained multiple times and the number of training times is inversely correlated with the signal-to-noise ratio of the third processed image, including: using a numerical conversion function to represent the numerical conversion relationship of the inverse correlation between the number of training times and the signal-to-noise ratio of the third processed image; The use of a numerical conversion function to represent the numerical conversion relationship of the inverse correlation between the number of training times and the signal-to-noise ratio of the third processed image comprises: in the numerical conversion function, the signal-to-noise ratio of the third processed image is an input value, and the number of training times corresponding to the signal-to-noise ratio of the third processed image is an output value; And wherein, the signal capturing mechanism is further used to temporarily suspend triggering the image signal capturing operation on the power transmission network site when receiving the second detection signal.

[0014] Figure 2 It is an internal structure diagram of a live cleaning scene monitoring system applying intelligent analysis according to a second embodiment of the present invention.

[0015] exist Figure 2 In, with Figure 1 Differently, the live cleaning scene monitoring system using intelligent analysis shown in the second embodiment of the present invention may also include: The liquid crystal display mechanism is used to receive user input information for the first processing device, the second processing device, the third processing device and the intelligent analysis device respectively according to the user's operation.

[0016] Figure 3 It is an internal structure diagram of a live cleaning scene monitoring system applying intelligent analysis according to a third embodiment of the present invention.

[0017] exist Figure 3 In, with Figure 1 Differently, the live cleaning scene monitoring system using intelligent analysis shown in the third embodiment of the present invention may also include: a data analysis mechanism, arranged on the housings of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and used to measure the instantaneous pressure currently borne by the housing of any of the first processing device, the second processing device, the third processing device and the intelligent analysis device; Wherein, the data analysis mechanism is arranged on the housing of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and is used to measure the instantaneous pressure currently borne by the housing of any of the first processing device, the second processing device, the third processing device and the intelligent analysis device, including: the data analysis mechanism has a built-in pressure analysis device, which is used to issue a pressure alarm instruction when the instantaneous pressure currently borne by the housing of any of the first processing device, the second processing device, the third processing device and the intelligent analysis device exceeds the limit; Wherein, the data analysis mechanism is arranged on the housing of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and is used to measure the instantaneous pressure currently borne by the housing of any of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and further includes: the data analysis mechanism has a built-in pressure analysis device, and is used to issue a pressure safety instruction when the instantaneous pressure currently borne by the housing of each of the first processing device, the second processing device, the third processing device and the intelligent analysis device is within the limit; The data analysis mechanism is arranged on the housings of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and is used to measure the instantaneous pressure currently borne by the housings of any of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and further comprises: the data analysis mechanism uses a plurality of pressure detection units, and is used to respectively measure the instantaneous pressure currently borne by the housings of the first processing device, the second processing device, the third processing device and the intelligent analysis device; The data analysis mechanism uses a plurality of pressure detection units for respectively measuring the instantaneous pressure currently borne by the housings of the first processing device, the second processing device, the third processing device and the intelligent analysis device, including: the internal structures of the plurality of pressure detection units are the same; The data analysis mechanism uses a plurality of pressure detection units for respectively measuring the instantaneous pressure currently borne by the housings of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and further comprises: the pressure measurement upper limit values ​​and the pressure measurement lower limit values ​​of the plurality of pressure detection units are respectively equal; The pressure measurement upper limit values ​​and the pressure measurement lower limit values ​​of the plurality of pressure detection units being equal respectively include: the pressure measurement upper limit value is greater than the pressure measurement lower limit value; And wherein, the data analysis mechanism adopts multiple pressure detection units for respectively measuring the instantaneous pressure currently borne by the shells of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and also includes: the multiple pressure detection units are respectively installed at the bottom position of the top of the shells of the first processing device, the second processing device, the third processing device and the intelligent analysis device and are located in the center of the bottom.

[0018] In addition, in the live cleaning scene monitoring system using intelligent analysis, an intelligent analysis model is used to intelligently analyze whether there is contact between the construction workers and the wires based on the depth of field value of each edge pixel point of the construction workers in the third processed image, the depth of field value of each edge pixel point of the wire in the third processed image, the grayscale value and coordinate value of each edge pixel point of the construction workers in the third processed image, the grayscale value and coordinate value of each edge pixel point of the wire in the third processed image, the total number of edge pixels of the construction workers in the third processed image, and the total number of edge pixels of the wire in the third processed image. It also includes: using different numerical values ​​as the analysis results of the intelligent analysis model to respectively indicate whether there is contact between the construction workers and the wires.

[0019] Although the present invention has been described in conjunction with preferred embodiments, it will be appreciated that other similar embodiments may be used, or modifications and additions may be made to the described embodiments, to perform the same functions of the present invention without departing from the present invention. For example, although exemplary embodiments of the present invention have been described in the context of a digital device that emulates the functions of a personal computer, those skilled in the art will recognize that the present invention is not limited to such digital devices, and as described in this application, the present invention may be applied to any number of existing or emerging computing devices or environments. Therefore, the present invention should not be limited to any single embodiment, but rather should be interpreted in accordance with the breadth and scope of the appended claims.

Claims

1. A live cleaning scene monitoring system using intelligent analysis, characterized in that: The system comprises: A mode detection mechanism is arranged in a base below a tower of a power transmission network, and is used to send a first detection signal when it is detected that the power transmission network is currently in a working mode of live cleaning suspension insulators, and is also used to send a second detection signal when it is detected that the power transmission network is currently not in the working mode of live cleaning suspension insulators; A signal capturing mechanism, connected to the mode detecting mechanism, for triggering an image signal capturing operation on the power transmission network site upon receiving the first detection signal, so as to obtain and output a captured image of the site; a first processing device, disposed in the base and connected to the signal capture mechanism, for performing image content enhancement processing by applying logarithmic transformation on the received live captured image to obtain and output a first processed image; a second processing device, connected to the first processing device, configured to perform image content SVD enhancement processing on the received first processed image to obtain and output a second processed image; a third processing device, connected to the second processing device, configured to perform image content enhancement processing of harmonic mean filtering on the received second processed image to obtain and output a third processed image; An intelligent analysis device is arranged in the base and connected to the third processing device, and is used to obtain each edge pixel point of the construction personnel in the third processing image and each edge pixel point of the wire in the third processing image, accumulate the total number of edge pixel points of the construction personnel in the third processing image and the total number of edge pixel points of the wire in the third processing image, and use an intelligent analysis model to intelligently analyze whether there is contact between the construction personnel and the wire based on the depth of field value of each edge pixel point of the construction personnel in the third processing image, the depth of field value of each edge pixel point of the wire in the third processing image, the grayscale value and coordinate value of each edge pixel point of the construction personnel in the third processing image, the grayscale value and coordinate value of each edge pixel point of the wire in the third processing image, the total number of edge pixel points of the construction personnel in the third processing image and the total number of edge pixel points of the wire in the third processing image, including: the intelligent analysis model is a convolutional neural network that has been trained multiple times and the number of training times is inversely correlated with the signal-to-noise ratio of the third processing image.

2. The live cleaning scene monitoring system using intelligent analysis as claimed in claim 1, characterized in that: The intelligent analysis model is a convolutional neural network that has been trained multiple times, and the number of training times is inversely correlated with the signal-to-noise ratio of the third processed image, including: using a numerical conversion function to represent the numerical conversion relationship of the inverse correlation between the number of training times and the signal-to-noise ratio of the third processed image; The use of a numerical conversion function to represent the numerical conversion relationship of the inverse correlation between the number of training times and the signal-to-noise ratio of the third processed image comprises: in the numerical conversion function, the signal-to-noise ratio of the third processed image is an input value, and the number of training times corresponding to the signal-to-noise ratio of the third processed image is an output value; Wherein, the signal capturing mechanism is further used to temporarily suspend triggering the image signal capturing operation on the power transmission network site when receiving the second detection signal.

3. The live cleaning scene monitoring system using intelligent analysis as claimed in claim 2 is characterized in that: The system further comprises: The liquid crystal display mechanism is used to receive user input information for the first processing device, the second processing device, the third processing device and the intelligent analysis device respectively according to the user's operation.

4. The live cleaning scene monitoring system using intelligent analysis as claimed in claim 2, characterized in that: The system further comprises: The data analysis mechanism is arranged on the outer shell of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and is used to measure the instantaneous pressure currently borne by the outer shell of any one of the first processing device, the second processing device, the third processing device and the intelligent analysis device.

5. The live cleaning scene monitoring system using intelligent analysis as claimed in claim 4 is characterized by: A data analysis mechanism is arranged on the outer shell of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and is used to measure the instantaneous pressure currently borne by the outer shell of any of the first processing device, the second processing device, the third processing device and the intelligent analysis device, including: the data analysis mechanism has a built-in pressure analysis device, which is used to issue a pressure alarm instruction when the received instantaneous pressure currently borne by the outer shell of any of the first processing device, the second processing device, the third processing device and the intelligent analysis device exceeds the limit.

6. The live cleaning scene monitoring system using intelligent analysis as claimed in claim 5, characterized in that: A data analysis mechanism is arranged on the outer shell of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and is used to measure the instantaneous pressure currently borne by the outer shell of any one of the first processing device, the second processing device, the third processing device and the intelligent analysis device. It also includes: the data analysis mechanism has a built-in pressure analysis device, which is used to issue a pressure safety instruction when the received instantaneous pressure currently borne by the outer shell of each of the first processing device, the second processing device, the third processing device and the intelligent analysis device is within the limit.

7. The live cleaning scene monitoring system using intelligent analysis as claimed in claim 6, characterized in that: A data analysis mechanism is arranged on the outer shell of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and is used to measure the instantaneous pressure currently borne by the outer shell of any one of the first processing device, the second processing device, the third processing device and the intelligent analysis device. It also includes: the data analysis mechanism uses multiple pressure detection units to measure the instantaneous pressure currently borne by the outer shell of the first processing device, the second processing device, the third processing device and the intelligent analysis device respectively.

8. The live cleaning scene monitoring system using intelligent analysis as claimed in claim 7, characterized in that: The data analysis mechanism uses multiple pressure detection units to respectively measure the instantaneous pressure currently borne by the shells of the first processing device, the second processing device, the third processing device and the intelligent analysis device, including: the internal structures of the multiple pressure detection units are the same.

9. The live cleaning scene monitoring system using intelligent analysis as claimed in claim 8, characterized in that: The data analysis mechanism uses a plurality of pressure detection units for respectively measuring the instantaneous pressure currently borne by the housings of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and further includes: the pressure measurement upper limit values ​​and the pressure measurement lower limit values ​​of the plurality of pressure detection units are respectively equal; The pressure measurement upper limit values ​​and the pressure measurement lower limit values ​​of the plurality of pressure detection units being equal respectively include: the pressure measurement upper limit value is greater than the pressure measurement lower limit value; Among them, the data analysis mechanism adopts multiple pressure detection units to respectively measure the instantaneous pressure currently borne by the shells of the first processing device, the second processing device, the third processing device and the intelligent analysis device, and also includes: the multiple pressure detection units are respectively installed at the bottom position of the top of the shells of the first processing device, the second processing device, the third processing device and the intelligent analysis device and are located in the center of the bottom.

Images