An intelligent electric anti-vibration hammer state identification system

Abstract

The present invention relates to an intelligent electric anti-vibration hammer state identification system, comprising: a component application device, which is used to use an AI recognition model to intelligently analyze the probability of the existence of a standard image corresponding to a complete hammer body based on various visual data of the anti-vibration hammer; a numerical analysis device, which is used to wirelessly send a hammer body defect alarm signal to a remote power implementation server when the probability value obtained by the intelligent analysis is less than or equal to a set probability threshold. Through the present invention, the various visual data of the anti-vibration hammer collected can be input into the AI ​​recognition model in parallel to intelligently analyze the probability of the existence of a standard image corresponding to a complete hammer body, and when the probability value of the existence of the standard image is less than or equal to the set probability threshold, a hammer body defect alarm signal is wirelessly sent to the remote power implementation server, otherwise, a hammer body complete notification information is wirelessly sent to the remote power implementation server, thereby improving the intelligent level of anti-vibration hammer state identification.

Description

Technical Field

[0001] The invention relates to the field of electric power, and in particular to an intelligent electric anti-vibration hammer state identification system. Background Art

[0002] The anti-vibration hammer is designed to reduce the vibration of the conductor caused by wind. The pole position of the high-voltage overhead line is high and the span is large. When the conductor is affected by wind, it will vibrate. When the conductor vibrates, the working conditions at the place where the conductor is suspended are the most unfavorable. Due to multiple vibrations, the conductor will suffer fatigue damage due to periodic bending, so it is necessary to use anti-vibration devices for anti-vibration treatment. When the span of the overhead line is greater than 120 meters, anti-vibration hammers are generally used for anti-vibration.

[0003] However, since the anti-vibration hammer is generally in a field environment and is a fragile object, it is easy for the hammer body to be damaged after long-term use. At this time, it is necessary to wirelessly send a hammer damage alarm signal to a remote power implementation server. Otherwise, it is necessary to wirelessly send a hammer integrity notification information to the remote power implementation server. However, the prior art lacks a targeted high-precision identification mechanism for the anti-vibration hammer's hammer damage, which makes it difficult to effectively identify the on-site integrity status of the anti-vibration hammer. Summary of the invention

[0004] In order to solve the above problems, the present invention provides an intelligent electric anti-vibration hammer state identification system, which inputs the contrast of the foreground area in the multi-layer mapping picture, the cyan component, magenta component, yellow component and black component of each pixel point in the multi-layer mapping picture in the CMYK color space, and the cyan component, magenta component, yellow component and black component of each pixel point in the standard image corresponding to the anti-vibration hammer in the CMYK color space into an AI recognition model in parallel, and executes the AI ​​recognition model to obtain the probability value of the standard image corresponding to the anti-vibration hammer in the multi-layer mapping picture output by it, and when the probability value of the standard image in the multi-layer mapping picture is less than or equal to the set probability threshold, wirelessly sends a hammer defect alarm signal to a remote electric power implementation server, and when the probability value of the standard image in the multi-layer mapping picture is greater than the set probability threshold, wirelessly sends hammer complete notification information to the remote electric power implementation server, thereby improving the intelligence level of anti-vibration hammer state identification.

[0005] According to the present invention, an intelligent electric anti-vibration hammer state identification system is provided, the system comprising:

[0006] A positioning shooting device is arranged on the patrol drone and has a built-in real-time positioning component and a shooting execution component connected to the real-time positioning component, and is used to execute a shooting operation on the overhead line where the target anti-vibration hammer is located when the target anti-vibration hammer is reached, so as to obtain and output a corresponding positioning shooting picture;

[0007] A multi-layer mapping device, connected to the positioning shooting device and comprising a data enrichment device, a content enhancement device and an image rendering device, for continuously performing bilinear interpolation processing, image spatial domain enhancement processing and image rendering processing on the received positioning shooting picture to obtain and output a corresponding multi-layer mapping picture;

[0008] A component application device, comprising a component extraction device, a numerical analysis device and an intelligent identification device, wherein the numerical analysis device is connected to the component extraction device and the intelligent identification device respectively, and the component application device is used to extract the cyan component, magenta component, yellow component and black component of each pixel point in the received multi-layer mapping picture in the CMYK color space, and input the contrast of the foreground area in the multi-layer mapping picture, the cyan component, magenta component, yellow component and black component of each pixel point in the multi-layer mapping picture in the CMYK color space, and the cyan component, magenta component, yellow component and black component of each pixel point in the standard image corresponding to the anti-vibration hammer in the CMYK color space into an AI recognition model in parallel, and execute the AI ​​recognition model to obtain the probability value of the existence of the standard image in the multi-layer mapping picture outputted by the AI ​​recognition model, wherein the AI ​​recognition model is a radial basis neural network after completing multiple trainings;

[0009] A numerical analysis device, connected to the component application device, is used to wirelessly send a hammer defect alarm signal to a remote power implementation server when the probability value of the standard image existing in the multi-layer mapping screen is less than or equal to a set probability threshold;

[0010] The numerical analysis device is further used to wirelessly send hammer integrity notification information to a remote power implementation server when the probability value of the standard image existing in the multi-layer mapping screen is greater than the set probability threshold;

[0011] The AI ​​recognition model is a radial basis neural network that has completed multiple trainings, including: the number of times the radial basis neural network is trained is monotonically positively correlated with the content complexity of the standard image corresponding to the anti-vibration hammer;

[0012] Among them, the number of times the radial basis neural network is trained is monotonically positively correlated with the content complexity of the standard image corresponding to the anti-vibration hammer, including: the more the number of pixel points with repeated pixel values ​​in the standard image corresponding to the anti-vibration hammer, the lower the content complexity of the standard image corresponding to the anti-vibration hammer.

[0013] The present invention has at least the following three important inventive features:

[0014] Firstly: using customized component application devices including component extraction equipment, numerical analysis equipment and intelligent identification equipment to provide reliable hardware resources for whether there is a standard image in the multi-layer mapping screen;

[0015] Secondly: the contrast of the foreground area in the multi-layer mapping picture, the cyan component, magenta component, yellow component and black component of each pixel point in the multi-layer mapping picture in the CMYK color space, and the cyan component, magenta component, yellow component and black component of each pixel point in the standard image corresponding to the anti-vibration hammer in the CMYK color space are input into the AI ​​recognition model in parallel, and the AI ​​recognition model is executed to obtain the probability value of the standard image corresponding to the anti-vibration hammer in the multi-layer mapping picture outputted by the AI ​​recognition model;

[0016] Again: the numerical analysis device is used to wirelessly send a hammer defect alarm signal to a remote power implementation server when the probability value of the standard image existing in the multi-layer mapping screen is less than or equal to the set probability threshold, and to wirelessly send a hammer complete notification information to the remote power implementation server when the probability value of the standard image existing in the multi-layer mapping screen is greater than the set probability threshold, thereby improving the intelligence level of anti-vibration hammer status identification. DETAILED DESCRIPTION

[0017] The following is a detailed description of an implementation scheme of an intelligent electric anti-vibration hammer state identification system of the present invention.

[0018] According to embodiment A of the present invention, an intelligent electric anti-vibration hammer state identification system includes:

[0019] A positioning shooting device is arranged on the patrol drone and has a built-in real-time positioning component and a shooting execution component connected to the real-time positioning component, and is used to execute a shooting operation on the overhead line where the target anti-vibration hammer is located when the target anti-vibration hammer is reached, so as to obtain and output a corresponding positioning shooting picture;

[0020] A multi-layer mapping device, connected to the positioning shooting device and comprising a data enrichment device, a content enhancement device and an image rendering device, for continuously performing bilinear interpolation processing, image spatial domain enhancement processing and image rendering processing on the received positioning shooting picture to obtain and output a corresponding multi-layer mapping picture;

[0021] Specifically, the multi-layer mapping device is connected to the positioning shooting device and includes a data enrichment device, a content enhancement device and an image rendering device, and is used to continuously perform bilinear interpolation processing, image spatial domain enhancement processing and image rendering processing on the received positioning shooting picture to obtain and output the corresponding multi-layer mapping picture, including: selecting and using MATLAB toolbox to simulate and implement the data processing process of continuously performing bilinear interpolation processing, image spatial domain enhancement processing and image rendering processing on the received positioning shooting picture to obtain and output the corresponding multi-layer mapping picture;

[0022] A component application device, comprising a component extraction device, a numerical analysis device and an intelligent identification device, wherein the numerical analysis device is connected to the component extraction device and the intelligent identification device respectively, and the component application device is used to extract the cyan component, magenta component, yellow component and black component of each pixel point in the received multi-layer mapping picture in the CMYK color space, and input the contrast of the foreground area in the multi-layer mapping picture, the cyan component, magenta component, yellow component and black component of each pixel point in the multi-layer mapping picture in the CMYK color space, and the cyan component, magenta component, yellow component and black component of each pixel point in the standard image corresponding to the anti-vibration hammer in the CMYK color space into an AI recognition model in parallel, and execute the AI ​​recognition model to obtain the probability value of the existence of the standard image in the multi-layer mapping picture outputted by the AI ​​recognition model, wherein the AI ​​recognition model is a radial basis neural network after completing multiple trainings;

[0023] A numerical analysis device, connected to the component application device, is used to wirelessly send a hammer defect alarm signal to a remote power implementation server when the probability value of the standard image existing in the multi-layer mapping screen is less than or equal to a set probability threshold;

[0024] The numerical analysis device is further used to wirelessly send hammer integrity notification information to a remote power implementation server when the probability value of the standard image existing in the multi-layer mapping screen is greater than the set probability threshold;

[0025] The AI ​​recognition model is a radial basis neural network that has completed multiple trainings, including: the number of times the radial basis neural network is trained is monotonically positively correlated with the content complexity of the standard image corresponding to the anti-vibration hammer;

[0026] The number of times the radial basis neural network is trained is monotonically positively correlated with the content complexity of the standard image corresponding to the anti-vibration hammer, including: the more the number of pixel points with repeated pixel values ​​in the standard image corresponding to the anti-vibration hammer, the lower the content complexity of the standard image corresponding to the anti-vibration hammer;

[0027] Among them, the contrast of the foreground area in the multi-layer mapping picture, the cyan component, magenta component, yellow component and black component of each pixel point in the multi-layer mapping picture in the CMYK color space, and the cyan component, magenta component, yellow component and black component of each pixel point in the standard image corresponding to the anti-vibration hammer in the CMYK color space are input into the AI ​​recognition model in parallel, and the AI ​​recognition model is executed to obtain the probability value of the existence of the standard image in the multi-layer mapping picture outputted by it, including: the standard image corresponding to the anti-vibration hammer is an imaging pattern of only a single anti-vibration hammer taken when the anti-vibration hammer leaves the factory.

[0028] Compared with implementation scheme A of the present invention, an intelligent electric anti-vibration hammer state identification system shown in implementation scheme B of the present invention may also include the following components:

[0029] A decibel measuring mechanism is connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, respectively, and is used to measure the decibel of noise near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively;

[0030] Wherein, the decibel measurement mechanism is respectively connected with the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to respectively measure the decibel of the noise near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, including: the decibel measurement mechanism includes a plurality of decibel measurement units, which are respectively connected with the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, so as to complete the respective measurement of the decibel of the noise near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device;

[0031] Wherein, the decibel measurement mechanism includes a plurality of decibel measurement units, which are used to be connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, so as to complete the respective measurement of the decibel of the noise near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, including: the plurality of decibel measurement units are a plurality of decibel sensor circuits, which are used to be connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, so as to complete the respective measurement of the decibel of the noise near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively;

[0032] Wherein, the plurality of decibel measurement units are a plurality of decibel sensing circuits, which are used to be connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, so as to complete the respective measurement of the decibel of the nearby noise of the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, including: the structures of the plurality of decibel sensing circuits are the same;

[0033] Among them, the multiple decibel measurement units are multiple decibel sensor circuits, which are used to be connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, so as to complete the separate measurement of the decibels of the nearby noise of the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, and also include: the multiple decibel sensor circuits have the same decibel measurement upper limit value and decibel measurement lower limit value.

[0034] Compared with implementation scheme A of the present invention, an intelligent electric anti-vibration hammer state identification system shown in implementation scheme C of the present invention may also include the following components:

[0035] A voice control processing device is arranged near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to provide the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device with the voice control services they need respectively;

[0036] The voice control processing device is arranged near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to provide the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device with the voice control services required by each device. The voice control processing device includes a sound collection unit, a numerical conversion unit and a signal sending unit.

[0037] The voice control processing device is arranged near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to provide the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device with the required voice control services respectively, and further comprises: the numerical conversion unit is connected to the sound collection unit and the signal sending unit respectively;

[0038] Among them, the voice control processing device is arranged near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to provide the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device with the voice control services they need respectively. It also includes: the sound collection unit is used to collect sound signals near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and determine whether the collected sound signals belong to sound control signals, so as to only send the sound control signals to the numerical conversion unit for analysis of the control signals.

[0039] In addition, in the intelligent electric anti-vibration hammer state identification system, the contrast of the foreground area in the multi-layer mapping picture, the cyan component, magenta component, yellow component and black component of each pixel point in the multi-layer mapping picture in the CMYK color space, and the cyan component, magenta component, yellow component and black component of each pixel point in the standard image corresponding to the anti-vibration hammer in the CMYK color space are input into the AI ​​recognition model in parallel, and the AI ​​recognition model is executed to obtain the probability value of the existence of the standard image in the multi-layer mapping picture output by it, which also includes: the value of any color component of the cyan component, magenta component, yellow component and black component of each pixel point in the multi-layer mapping picture in the CMYK color space is between 0-255.

[0040] An intelligent electric anti-vibration hammer state identification system of the present invention is used to address the technical problem in the prior art that the integrity of the hammer body of the anti-vibration hammer in the field environment is difficult to be analyzed in a targeted and high-precision manner. The system inputs the collected visual data of the anti-vibration hammer into the AI ​​recognition model in parallel to intelligently analyze the probability of the existence of a standard image corresponding to a complete hammer body, and when the probability value of the existence of the standard image is less than or equal to a set probability threshold, a hammer body defect alarm signal is wirelessly sent to a remote electric power implementation server; otherwise, a hammer body complete notification information is wirelessly sent to the remote electric power implementation server, thereby improving the intelligence level of anti-vibration hammer state identification.

[0041] The present invention has been described with reference to its typical embodiments, but those skilled in the art will be able to make various modifications to the described embodiments without departing from its purpose and scope. The terms and descriptions used herein are set forth by way of example only and are not intended to be limiting. In particular, although the method has been described by way of example, the steps of the method may be performed in a different order than that illustrated or simultaneously. Those skilled in the art will recognize that these and other changes may be made within the purpose and scope defined by the following claims and their equivalents.

Claims

1. An intelligent electric anti-vibration hammer state identification system, characterized in that: The system comprises: A positioning shooting device is arranged on the patrol drone and has a built-in real-time positioning component and a shooting execution component connected to the real-time positioning component, and is used to execute a shooting operation on the overhead line where the target anti-vibration hammer is located when the target anti-vibration hammer is reached, so as to obtain and output a corresponding positioning shooting picture; A multi-layer mapping device, connected to the positioning shooting device and comprising a data enrichment device, a content enhancement device and an image rendering device, for continuously performing bilinear interpolation processing, image spatial domain enhancement processing and image rendering processing on the received positioning shooting picture to obtain and output a corresponding multi-layer mapping picture; A component application device, comprising a component extraction device, a numerical analysis device and an intelligent identification device, wherein the numerical analysis device is connected to the component extraction device and the intelligent identification device respectively, and the component application device is used to extract the cyan component, magenta component, yellow component and black component of each pixel point in the received multi-layer mapping picture in the CMYK color space, and input the contrast of the foreground area in the multi-layer mapping picture, the cyan component, magenta component, yellow component and black component of each pixel point in the multi-layer mapping picture in the CMYK color space, and the cyan component, magenta component, yellow component and black component of each pixel point in the standard image corresponding to the anti-vibration hammer in the CMYK color space into an AI recognition model in parallel, and execute the AI ​​recognition model to obtain the probability value of the existence of the standard image in the multi-layer mapping picture outputted by the AI ​​recognition model, wherein the AI ​​recognition model is a radial basis neural network after completing multiple trainings; The standard image corresponding to the anti-vibration hammer is an imaging pattern including only a single anti-vibration hammer taken when the anti-vibration hammer leaves the factory; A numerical analysis device, connected to the component application device, is used to wirelessly send a hammer defect alarm signal to a remote power implementation server when the probability value of the standard image existing in the multi-layer mapping screen is less than or equal to a set probability threshold; The numerical analysis device is further used to wirelessly send hammer integrity notification information to a remote power implementation server when the probability value of the standard image existing in the multi-layer mapping screen is greater than the set probability threshold; The AI ​​recognition model is a radial basis neural network that has completed multiple trainings, including: the number of times the radial basis neural network is trained is monotonically positively correlated with the content complexity of the standard image corresponding to the anti-vibration hammer; Among them, the number of times the radial basis neural network is trained is monotonically positively correlated with the content complexity of the standard image corresponding to the anti-vibration hammer, including: the more the number of pixel points with repeated pixel values ​​in the standard image corresponding to the anti-vibration hammer, the lower the content complexity of the standard image corresponding to the anti-vibration hammer.

2. The intelligent electric anti-vibration hammer state identification system according to claim 1, characterized in that: The system further comprises: A decibel measuring mechanism is connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, respectively, and is used to measure the decibel of noise near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively; Among them, the decibel measuring mechanism is respectively connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to respectively measure the decibels of noise near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device. The decibel measuring mechanism includes multiple decibel measuring units, which are respectively connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device to complete the respective measurements of the decibels of noise near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device.

3. The intelligent electric anti-vibration hammer state identification system according to claim 2, characterized in that: The decibel measurement mechanism includes a plurality of decibel measurement units, which are used to be respectively connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device to complete the respective measurements of the decibels of noise in the vicinity of the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device. The plurality of decibel measurement units are a plurality of decibel sensor circuits, which are used to be respectively connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device to complete the respective measurements of the decibels of noise in the vicinity of the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device.

4. The intelligent electric anti-vibration hammer state identification system according to claim 3, characterized in that: The multiple decibel measurement units are multiple decibel sensor circuits, which are used to be connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, so as to complete the separate measurement of the decibels of nearby noise of the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, including: the structures of the multiple decibel sensor circuits are the same.

5. The intelligent electric anti-vibration hammer state identification system according to claim 4, characterized in that: The multiple decibel measurement units are multiple decibel sensor circuits, which are used to be connected to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively to complete the separate measurement of the decibels of nearby noise of the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively, and also include: the multiple decibel sensor circuits have the same decibel measurement upper limit value and decibel measurement lower limit value.

6. The intelligent electric anti-vibration hammer state identification system according to any one of claims 2 to 5, characterized in that: The system further comprises: The voice control processing device is arranged near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to provide the required voice control services to the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device respectively.

7. The intelligent electric anti-vibration hammer state identification system according to claim 6, characterized in that: The voice control processing device is arranged near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to provide the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device with the required voice control services respectively, including: the voice control processing device includes a sound collection unit, a numerical conversion unit and a signal sending unit.

8. The intelligent electric anti-vibration hammer state identification system according to claim 7, characterized in that: The voice control processing device is arranged near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to provide the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device with the required voice control services respectively, and further includes: the numerical conversion unit is connected to the sound collection unit and the signal sending unit respectively; Among them, the voice control processing device is arranged near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and is used to provide the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device with the voice control services they need respectively. It also includes: the sound collection unit is used to collect sound signals near the numerical analysis device, the component extraction device, the numerical analysis device and the intelligent identification device, and determine whether the collected sound signals belong to sound control signals, so as to only send the sound control signals to the numerical conversion unit for analysis of the control signals.