CN114935451A - Coal conveying belt carrier roller fault detection system and method based on inspection robot - Google Patents
Coal conveying belt carrier roller fault detection system and method based on inspection robot Download PDFInfo
- Publication number
- CN114935451A CN114935451A CN202210545937.1A CN202210545937A CN114935451A CN 114935451 A CN114935451 A CN 114935451A CN 202210545937 A CN202210545937 A CN 202210545937A CN 114935451 A CN114935451 A CN 114935451A
- Authority
- CN
- China
- Prior art keywords
- carrier roller
- roller
- fault
- noise
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Manipulator (AREA)
Abstract
The invention belongs to the technical field of inspection robots, and discloses a coal conveying belt carrier roller fault detection system and method based on an inspection robot, wherein the method comprises the following steps: establishing a carrier roller fault image detection model and a carrier roller fault noise detection model; acquiring real-time carrier roller video data and real-time carrier roller noise data; respectively carrying out corresponding preprocessing on real-time carrier roller video data and real-time carrier roller noise data to obtain preprocessed carrier roller image data of continuous frames and preprocessed noise frequency band data of the continuous frames; inputting the preprocessed carrier roller image data of the continuous frames into a carrier roller fault image detection model to perform dominant carrier roller fault detection to obtain a dominant fault detection result; and inputting the preprocessed noise frequency band data of the continuous frames into a roller fault noise detection model to perform hidden roller fault detection to obtain a hidden fault detection result. The invention solves the problems of large workload, high labor cost and poor automatic detection effect of manual inspection in the prior art.
Description
Technical Field
The invention belongs to the technical field of inspection robots, and particularly relates to a coal conveying belt carrier roller fault detection system and method based on an inspection robot.
Background
The carrier roller is one of the main components of a belt type coal conveyor, the cost of the carrier roller is high, the carrier roller is also a vulnerable part, the quality of the carrier roller directly affects the stability of the conveyor, the damaged carrier roller can scratch a belt even to cause belt spontaneous combustion to cause greater economic loss, therefore, fault detection is carried out on the carrier roller, timely replacement and maintenance are carried out on the carrier roller which has faults, the carrier roller becomes one of the main research key points, in the prior art, manual inspection is mainly adopted, the workload is high, the labor cost is high, even if partial automatic detection technology exists, the obvious damage of the carrier roller can only be detected, the latent faults cannot be found, and the detection effect is poor.
Disclosure of Invention
The invention aims to provide a coal conveying belt carrier roller fault detection system and method based on an inspection robot, and aims to solve the problems of large workload of manual inspection, high labor cost and poor automatic detection effect in the prior art.
The technical scheme adopted by the invention is as follows:
the utility model provides a coal conveying belt bearing roller fault detection system based on robot patrols and examines, is including patrolling and examining the robot, patrols and examines the track, edge calculation gateway and surveillance center, patrols and examines the track and sets up under the bearing roller, patrols and examines the robot and patrol and examine track sliding connection, and patrols and examines the robot and be provided with bearing roller video acquisition unit and bearing roller noise acquisition unit, bearing roller video acquisition unit and bearing roller noise acquisition unit all set up towards the bearing roller, edge calculation gateway respectively with patrol and examine robot and surveillance center communication connection.
Further, the inspection robot comprises a robot body, a moving unit, a carrier roller video collecting unit, a carrier roller noise collecting unit, an operation detecting unit, a robot main control unit and a rechargeable battery, wherein the moving unit is arranged at the bottom end of the robot body and is in sliding connection with the inspection track, the carrier roller video collecting unit and the carrier roller noise collecting unit are arranged outside the robot body and are arranged facing the carrier roller, the operation detecting unit and the rechargeable battery are arranged inside the robot body, the robot main control unit is respectively electrically connected with the moving unit, the carrier roller video collecting unit, the carrier roller noise collecting unit and the operation detecting unit, the robot main control unit is in communication connection with the edge computing gateway, and the rechargeable battery is respectively in communication connection with the robot main control unit, the moving unit, the rechargeable battery, the operation detecting unit, the inspection robot main control unit, the carrier roller video collecting unit and the operation detecting unit, The carrier roller video acquisition unit, the carrier roller noise acquisition unit and the operation detection unit are electrically connected.
Furthermore, the edge computing gateway comprises an edge computing unit and a network unit, the edge computing unit is electrically connected with the network unit, and the network unit is respectively in communication connection with the wireless communication module of the inspection robot and the monitoring center.
Furthermore, the monitoring center is provided with a data server, the data server is in communication connection with the edge computing gateway, and the data server is in communication connection with an external cloud data center.
A coal conveying belt carrier roller fault detection method based on an inspection robot is based on a coal conveying belt carrier roller fault detection system and comprises the following steps:
establishing a carrier roller fault image detection model and a carrier roller fault noise detection model;
acquiring real-time carrier roller video data and real-time carrier roller noise data;
respectively carrying out corresponding preprocessing on real-time carrier roller video data and real-time carrier roller noise data to obtain preprocessed carrier roller image data of continuous frames and preprocessed noise frequency band data of the continuous frames;
inputting the preprocessed carrier roller image data of the continuous frames into a carrier roller fault image detection model to perform dominant carrier roller fault detection to obtain a dominant fault detection result;
and inputting the preprocessed noise frequency band data of the continuous frames into a roller fault noise detection model to perform hidden roller fault detection to obtain a hidden fault detection result.
Further, a roller fault image detection model is established based on a TPH-YOLOv5 algorithm, and a roller fault noise detection model is established based on a GRU-FICN algorithm.
Further, the network structure of the carrier roller fault image detection model comprises an input end, a Backbone module, a detectionNeck module, a TPH module and a Prediction module;
the network structure of the carrier roller fault noise detection model comprises an input end, a DimensionShoffle module, a double-layer GRU module, a double-layer inclusion module, a global pooling layer, a Concat module and a Softmax module.
Further, the corresponding preprocessing of the real-time carrier roller video data comprises frame interception, Gaussian denoising, gray level and normalization which are sequentially carried out;
and carrying out corresponding preprocessing on the real-time carrier roller noise data, wherein the preprocessing comprises filtering, pre-emphasis, frame interception and windowing which are sequentially carried out.
Further, inputting the preprocessed carrier roller image data of the continuous frames into a carrier roller fault image detection model for dominant carrier roller fault detection, and the method comprises the following steps:
carrying out mesh division on the preprocessed carrier roller image data of all frames, and acquiring a prior frame of each mesh;
acquiring an initial prediction frame corresponding to each prior frame according to the offset of the prior frame and a preset prediction frame;
carrying out non-maximum suppression screening on the initial prediction frame according to a preset intersection ratio and a preset confidence coefficient to obtain a final prediction frame of the preprocessed carrier roller image data of all frames;
tracking and marking the same carrier roller target in the final prediction frame by using a target tracking algorithm;
and carrying out dominant roller fault detection on the roller target in the final prediction frame to obtain a dominant fault detection result.
Further, inputting the preprocessed noise frequency band data of the continuous frames into a roller fault noise detection model for carrying out hidden roller fault detection, and the method comprises the following steps:
inputting the preprocessed noise frequency band data of the continuous frames into a roller fault and noise detection model to carry out fuzzy roller fault diagnosis, and obtaining noise characteristic data of the current roller and a corresponding fuzzy fault diagnosis result;
if the fuzzy fault diagnosis result indicates that the current carrier roller has a fault, extracting an explicit fault detection result of the current carrier roller;
if the dominant fault detection result indicates that the current carrier roller has no dominant fault, carrier roller temperature data of the current carrier roller are extracted;
and performing fusion weighted fault diagnosis according to the temperature data and the noise characteristic data of the carrier roller to obtain a hidden fault detection result.
The invention has the beneficial effects that:
1) according to the coal conveying belt carrier roller fault detection system based on the inspection robot, the inspection robot and the inspection track are adopted to automatically detect the coal conveying belt carrier roller, a manual inspection mode is avoided, the workload and the labor cost are reduced, the carrier roller video acquisition unit and the carrier roller noise acquisition unit are adopted to simultaneously detect the carrier roller fault, the fault detection accuracy and efficiency are improved, finally, the edge computing gateway and the monitoring center are adopted to carry out remote data transmission and control, and the system practicability is improved.
2) According to the coal conveying belt carrier roller fault detection method based on the inspection robot, the carrier roller fault image detection model and the carrier roller fault noise detection model are established based on machine learning, the accuracy and the efficiency of fault detection are further improved, the carrier roller is subjected to dominant fault detection and recessive fault detection, latent faults of the carrier roller can be found, serious faults or complete damage of the carrier roller due to further development are avoided, and the practicability and the timeliness of the method are improved.
Other advantageous effects of the present invention will be further described in the detailed description.
Drawings
Fig. 1 is a structural block diagram of a coal conveying belt roller fault detection system based on an inspection robot in the invention.
Fig. 2 is a front sectional view showing the construction of the inspection robot in the present invention.
FIG. 3 is a flow chart of a coal conveying belt roller fault detection method based on an inspection robot in the invention.
In the figure, 1, a robot body; 2. a mobile unit; 3. a carrier roller video acquisition unit; 4. a carrier roller noise acquisition unit; 5. a robot main control unit; 6. a rechargeable battery; 7. a track body; 8. a track support.
Detailed Description
The invention is further explained below with reference to the drawings and the specific embodiments.
Example 1:
as shown in fig. 1, this embodiment provides a coal conveying belt bearing roller fault detection system based on robot patrols and examines, including patrolling and examining the robot, patrol and examine the track, edge calculation gateway and surveillance center, patrol and examine the track and set up under the bearing roller, patrol and examine the robot and patrol and examine track sliding connection, and patrol and examine the robot and be provided with bearing roller video acquisition unit 3 and bearing roller noise acquisition unit 4, bearing roller video acquisition unit 3 and bearing roller noise acquisition unit 4 all set up towards the bearing roller, edge calculation gateway respectively with patrol and examine robot and surveillance center communication connection.
The inspection robot and the inspection track are matched to collect carrier roller video data and carrier roller noise data below the coal conveying belt, the carrier roller video data and the carrier roller noise data are input into the edge computing gateway to perform related fault detection, and the edge computing gateway can process a large amount of edge computing and send a detection result to the monitoring center to be displayed and analyzed.
Preferably, as shown in fig. 2, the inspection robot includes a robot body 1, a moving unit 2, a roller video collecting unit 3, a roller noise collecting unit 4, an operation detecting unit, a robot main control unit 5 and a rechargeable battery 6, the moving unit 2 is disposed at the bottom end of the robot body 1, the moving unit 2 is slidably connected with the inspection rail, the roller video collecting unit 3 and the roller noise collecting unit 4 are both disposed outside the robot body 1, the roller video collecting unit 3 and the roller noise collecting unit 4 are both disposed facing the roller, the operation detecting unit and the rechargeable battery 6 are both disposed inside the robot body 1, the robot main control unit 5 is respectively electrically connected with the moving unit 2, the roller video collecting unit 3, the roller noise collecting unit 4 and the operation detecting unit, and the robot main control unit 5 is in communication connection with an edge computing gateway, the rechargeable battery 6 is respectively electrically connected with the robot main control unit 5, the mobile unit 2, the carrier roller video acquisition unit 3, the carrier roller noise acquisition unit 4 and the operation detection unit;
the carrier roller video acquisition unit 3 comprises two thermal imaging cameras arranged on two sides of the top end of the robot and a high-speed camera arranged in the center of the top end of the robot, and the thermal imaging cameras and the high-speed camera are respectively and electrically connected with the robot main control unit 5 and the rechargeable battery 6; the thermal imaging camera is used for acquiring a thermal imaging image of the carrier roller, temperature data of each position of the carrier roller can be acquired according to the thermal imaging image, the thermal imaging camera is used for detecting latent faults of the carrier roller in a follow-up mode, and the high-speed camera is used for acquiring video data of the carrier roller;
the carrier roller noise acquisition unit 4 is a digital pickup which is respectively and electrically connected with the robot main control unit 5 and the rechargeable battery 6; the digital sound pick-up can extract digital audio data which can be identified by the robot main control unit 5;
the robot main control unit 5 comprises a robot main control module, a first storage module, a motor driving module and a wireless communication module, wherein the robot main control module is respectively electrically connected with the first storage module, the motor driving module and the wireless communication module, the motor driving module is electrically connected with the mobile unit 2, and the wireless communication module is in communication connection with the edge computing gateway;
the mobile unit 2 comprises a mobile motor and a mobile assembly which are arranged at the bottom of the outer side of the robot body 1, the mobile motor is connected with a mobile assembly bearing, and the mobile motor is respectively electrically connected with the motor driving module and the rechargeable battery 6; the moving unit 2 is used for supporting the moving task of the inspection robot, namely moving back and forth on the inspection track body 7 and acquiring data of each carrier roller;
the operation detection unit comprises a temperature sensor, a humidity sensor, an electric quantity sensor, a speed sensor, a vibration sensor, a position sensor and an A/D converter which are all arranged inside the robot body 1, the A/D converter is respectively and electrically connected with the robot main control module, the temperature sensor, the humidity sensor, the electric quantity sensor, the speed sensor, the vibration sensor and the position sensor, the temperature sensor and the humidity sensor are all arranged at the position of the rechargeable battery 6, and the electric quantity sensor is electrically connected with the output end of the rechargeable battery 6; the operation detection unit is used for detecting the normal operation state of the inspection robot, including temperature, humidity, speed, vibration, position, electric quantity of the rechargeable battery 6 and the like, and detecting whether the inspection robot breaks down;
the patrol rail comprises a rail body 7 and a rail support 8, the rail support 8 is arranged under the carrier roller, the rail support 8 is fixedly connected with the bottom end of the coal conveying belt rack, the rail body 7 is arranged in the rail support 8, and the rail body 7 is an I-shaped rail.
Preferably, the edge computing gateway comprises an edge computing unit and a network unit, the edge computing unit is electrically connected with the network unit, and the network unit is respectively in communication connection with the wireless communication module of the inspection robot and the monitoring center;
the edge calculation unit comprises an edge calculation main control module, a second storage module, a preprocessing module, a carrier roller fault image detection module, a carrier roller fault noise detection module and an encryption module, wherein the edge calculation main control module is respectively connected with the second storage module, the preprocessing module, the carrier roller fault image detection module, the carrier roller fault noise detection module, the encryption module and the network unit; the carrier roller fault image detection module is provided with a carrier roller fault image detection model, and the carrier roller fault noise detection module is provided with a carrier roller fault noise detection model;
the edge computing gateway bears most of computing and remote data transmission functions, can realize the control task of the inspection robot in the environment with poor signals, meanwhile, the preprocessing, the roller fault image detection and the roller fault noise detection are carried out in the edge computing unit, the data processing pressure of the monitoring center can be reduced, the storage space of the second storage module can be saved, the monitoring center broadcasts a public key to all the edge computing units, a corresponding private key is locally kept, the encryption module encrypts and uploads the data which needs to be uploaded by the edge computing unit according to the public key, and the encrypted data is decrypted by the private key in the monitoring center, so that the safety of data transmission is ensured.
Preferably, the monitoring center is provided with a data server, the data server is in communication connection with the edge computing gateway, and the data server is in communication connection with an external cloud data center;
the data server comprises a data parallel receiving module, a decryption module, a cache database module and a data parallel uploading module, the data parallel receiving module is in communication connection with the edge computing gateway, the data parallel receiving module, the decryption module, the cache database module and the data parallel uploading module are sequentially connected, and the data parallel uploading module is in communication connection with an external cloud data center.
According to the coal conveying belt carrier roller fault detection system based on the inspection robot, the inspection robot and the inspection track are adopted to automatically detect the coal conveying belt carrier roller, a manual inspection mode is avoided, the workload and the labor cost are reduced, the carrier roller video acquisition unit and the carrier roller noise acquisition unit are adopted to simultaneously detect the carrier roller fault, the fault detection accuracy and efficiency are improved, finally, the edge calculation gateway and the monitoring center are adopted to carry out remote data transmission and control, and the system practicability is improved.
Example 2:
as shown in fig. 3, the present embodiment provides a coal conveying belt roller fault detection method based on an inspection robot, and a coal conveying belt roller fault detection system based on the inspection robot includes the following steps:
establishing a carrier roller fault image detection model and a carrier roller fault noise detection model;
the method comprises the steps that a carrier roller fault image detection model is established based on a TPH-YOLOv5 algorithm, and a network structure of the carrier roller fault image detection model comprises an input end, a backhaul module, a detective neutral module, a TPH module and a Prediction module; the first input end processes an input image by using a Mosaic data enhancement method; the Backbone module comprises a Focus structure and a CSP structure; the structure of the first detectionNeck module is an FPN + PAN structure; the first Prediction module uses a GIOU _ Loss function to perform Loss calculation; a TPH module is added on the basis of YOLOv5 to detect roller fault targets with different sizes;
the method comprises the steps that a carrier roller fault noise detection model is established based on a GRU-FICN algorithm, and the network structure of the carrier roller fault noise detection model comprises an input end, a DimensionShuffle module, a double-layer GRU module, a double-layer inclusion module, a global pooling layer, a Concat module and a Softmax module; the convolution layer in the GRU-FICN algorithm can well extract the local features of the sound signal, the GRU in the model structure is a variant of the LSTM, a forgetting gate and an input gate of the LSTM are integrated into a single updating gate, the structure of the GRU also comprises a resetting gate, wherein the updating gate determines the degree of the information of the previous state transmitted into the current state, and the resetting gate determines how much information of the previous state is written into a candidate set of the current state, a double-layer GRU network structure is adopted in the embodiment, the GRU network reduces the calculation complexity of the LSTM by introducing a gating unit with fewer parameters, the local feature extraction of the sound signal adopts two one-dimensional extended Inceprtion modules and a global pooling layer, the two inclusion modules can well extract the sound local features, the use of the global pooling layer greatly reduces the feature value output by the network, the global pooling operation is to average each feature map into an output value, compared with a common full-connection layer, the global pooling has the advantages of few parameters, comprehensive receptive field, spatial information and the like;
acquiring real-time carrier roller video data and real-time carrier roller noise data;
carrying out corresponding pretreatment on real-time carrier roller video data and real-time carrier roller noise data respectively to obtain continuous frames of pretreated carrier roller image data and continuous frames of pretreated noise frequency band data;
carrying out corresponding preprocessing on real-time carrier roller video data, including frame interception, Gaussian denoising, gray level and normalization which are sequentially carried out; removing image noise in the carrier roller image by Gaussian denoising, converting the carrier roller image into a gray image, and normalizing the gray image into the carrier roller image with the same size, so as to facilitate subsequent fault detection;
carrying out corresponding preprocessing on the real-time carrier roller noise data, including filtering, pre-emphasis, frame interception and windowing in sequence; the low-frequency low-amplitude noise data are filtered, the influence of the superposition of the noise of adjacent carrier rollers on the noise of the current carrier roller on the detection accuracy is avoided, and the high-frequency part is pre-emphasized and enhanced, so that the frequency spectrum of the signal is relatively flat and balanced; the selected frame length is 10ms-30ms, the sound signal is considered to be approximately stable, and in order to ensure continuity and correlation, a Hamming window is selected for windowing, namely, each frame of sound signal is multiplied by a window function, so that two sections of the sound signal of the frame gradually tend to zero;
inputting the preprocessed carrier roller image data of continuous frames into a carrier roller fault image detection model for dominant carrier roller fault detection to obtain a dominant fault detection result, and the method comprises the following steps:
carrying out grid division on the preprocessed carrier roller image data of all frames, and acquiring a priori frame of each grid;
acquiring an initial prediction frame corresponding to each prior frame according to the offset of the prior frame and a preset prediction frame;
carrying out non-maximum suppression screening on the initial prediction frame according to a preset intersection ratio and a preset confidence coefficient to obtain a final prediction frame of the preprocessed carrier roller image data of all frames;
tracking and marking the same carrier roller target in the final prediction frame by using a target tracking algorithm; because the video data of the carrier rollers are collected by videos of the carrier rollers in the inspection process, and each carrier roller rotates, tracking and numbering are carried out on different fault parts of different carrier rollers and the same carrier roller, and the efficiency and the accuracy of fault detection are improved;
carrying out dominant roller fault detection on the roller target in the final prediction frame to obtain a dominant fault detection result; the dominant fault detection result is whether the current carrier roller has dominant faults or not and the categories of the dominant faults, including carrier roller cracks, carrier roller scars, carrier roller disconnection and other faults which are easy to distinguish and need to be maintained and replaced, and the dominant faults can have great influence on the normal work of the coal conveying belt;
inputting the preprocessed noise frequency band data of continuous frames into a roller fault and noise detection model to perform hidden roller fault detection to obtain a hidden fault detection result, and the method comprises the following steps:
inputting the preprocessed noise frequency band data of the continuous frames into a roller fault and noise detection model to carry out fuzzy roller fault diagnosis, and obtaining noise characteristic data of the current roller and a corresponding fuzzy fault diagnosis result;
the fuzzy fault diagnosis can analyze dominant faults and recessive faults of the carrier roller according to noise frequency band data, wherein the dominant faults are detected according to a carrier roller fault image detection model, the remaining abnormal conditions are recessive faults and comprise latent faults such as carrier roller inclination and carrier roller deformation, although the faults can not cause major safety and generation accidents temporarily, the faults can gradually develop into serious faults affecting normal work of the carrier roller and a coal conveying belt, and the detection and the processing need to be carried out in advance;
if the fuzzy fault diagnosis result indicates that the current carrier roller has a fault, extracting an explicit fault detection result of the current carrier roller;
if the dominant fault detection result indicates that the current carrier roller has no dominant fault, carrier roller temperature data of the current carrier roller are extracted;
a thermal imaging camera is adopted to collect a thermal imaging image of the carrier roller, and temperature data of each position of the carrier roller can be obtained according to the thermal imaging image;
carrying out fusion weighted fault diagnosis according to the carrier roller temperature data and the noise characteristic data to obtain a hidden fault detection result;
according to the temperature data distribution of each part of the carrier roller, fault probability is obtained, for example, if the temperature data of a non-bearing point of the carrier roller is high, the carrier roller is likely to incline, the fault probability is high, or if the temperature data of the middle position of the carrier roller is too large in difference, the carrier roller is likely to deform to be broken, the fault probability is high, the fault probability can be obtained according to noise characteristic data, the fault probability and the non-bearing point of the carrier roller are fused and weighted, and finally classification is carried out, so that corresponding hidden faults are obtained.
According to the coal conveying belt carrier roller fault detection method based on the inspection robot, a carrier roller fault image detection model and a carrier roller fault noise detection model are established based on machine learning, the accuracy and the efficiency of fault detection are further improved, explicit fault detection and implicit fault detection are carried out on the carrier roller, latent faults of the carrier roller can be found, serious faults or complete damage of the carrier roller due to further development are avoided, and the practicability and the timeliness of the method are improved.
The present invention is not limited to the above-described alternative embodiments, and various other forms of products can be obtained by anyone in light of the present invention. The above detailed description should not be taken as limiting the scope of the invention, which is defined in the claims, and which the description is intended to be interpreted accordingly.
Claims (10)
1. The utility model provides a coal conveyor belt bearing roller fault detection system based on robot patrols and examines which characterized in that: including patrolling and examining the robot, patrolling and examining track, edge calculation gateway and surveillance center, patrol and examine the track and set up under the bearing roller, patrol and examine the robot and patrol and examine track sliding connection, and patrol and examine the robot and be provided with bearing roller video acquisition unit (3) and bearing roller noise acquisition unit (4), bearing roller video acquisition unit (3) and bearing roller noise acquisition unit (4) all set up towards the bearing roller, edge calculation gateway respectively with patrol and examine robot and surveillance center communication connection.
2. The inspection robot-based coal conveying belt roller fault detection system according to claim 1, wherein: patrol and examine robot include robot (1), mobile unit (2), bearing roller video acquisition unit (3), bearing roller noise acquisition unit (4), operation detecting element, robot main control unit (5) and rechargeable battery (6), mobile unit (2) set up in the bottom of robot (1), and mobile unit (2) and patrol and examine track sliding connection, bearing roller video acquisition unit (3) and bearing roller noise acquisition unit (4) all set up in the outside of robot (1), and bearing roller video acquisition unit (3) and bearing roller noise acquisition unit (4) all set up towards the bearing roller, operation detecting element and rechargeable battery (6) all set up in the inside of robot (1), robot main control unit (5) respectively with mobile unit (2), bearing roller video acquisition unit (3), Bearing roller noise acquisition unit (4) and operation detecting element electric connection, and robot main control unit (5) and edge calculation gateway communication connection, rechargeable battery (6) respectively with robot main control unit (5), mobile unit (2), bearing roller video acquisition unit (3), bearing roller noise acquisition unit (4) and operation detecting element electric connection.
3. The inspection robot-based coal conveying belt roller fault detection system according to claim 2, wherein: the edge computing gateway comprises an edge computing unit and a network unit, wherein the edge computing unit is electrically connected with the network unit, and the network unit is respectively in communication connection with a wireless communication module and a monitoring center of the inspection robot.
4. The inspection robot-based coal conveying belt roller fault detection system according to claim 3, wherein: the monitoring center is provided with a data server, the data server is in communication connection with the edge computing gateway, and the data server is in communication connection with an external cloud data center.
5. A coal conveying belt roller fault detection method based on an inspection robot is based on the coal conveying belt roller fault detection system of claim 4, and is characterized in that: the method comprises the following steps:
establishing a carrier roller fault image detection model and a carrier roller fault noise detection model;
acquiring real-time carrier roller video data and real-time carrier roller noise data;
respectively carrying out corresponding preprocessing on real-time carrier roller video data and real-time carrier roller noise data to obtain preprocessed carrier roller image data of continuous frames and preprocessed noise frequency band data of the continuous frames;
inputting the preprocessed carrier roller image data of the continuous frames into a carrier roller fault image detection model to perform dominant carrier roller fault detection to obtain a dominant fault detection result;
and inputting the preprocessed noise frequency band data of the continuous frames into a roller fault noise detection model to perform hidden roller fault detection to obtain a hidden fault detection result.
6. The inspection robot-based fault detection method for the coal conveying belt carrier roller according to claim 5, characterized in that: the method comprises the steps of establishing a carrier roller fault image detection model based on a TPH-YOLOv5 algorithm, and establishing a carrier roller fault noise detection model based on a GRU-FICN algorithm.
7. The inspection robot-based fault detection method for the coal conveying belt carrier roller according to claim 6, wherein: the network structure of the carrier roller fault image detection model comprises an input end, a Backbone module, a detectionNeck module, a TPH module and a Prediction module;
the network structure of the carrier roller fault noise detection model comprises an input end, a DimensionShoffle module, a double-layer GRU module, a double-layer inclusion module, a global pooling layer, a Concat module and a Softmax module.
8. The inspection robot-based fault detection method for the coal conveying belt carrier roller according to claim 7, characterized in that: carrying out corresponding preprocessing on real-time carrier roller video data, including frame interception, Gaussian denoising, gray level and normalization which are sequentially carried out;
and carrying out corresponding preprocessing on the real-time carrier roller noise data, wherein the preprocessing comprises filtering, pre-emphasis, frame interception and windowing which are sequentially carried out.
9. The inspection robot-based fault detection method for the coal conveying belt carrier roller according to claim 8, wherein: inputting the preprocessed carrier roller image data of continuous frames into a carrier roller fault image detection model for dominant carrier roller fault detection, and the method comprises the following steps:
carrying out grid division on the preprocessed carrier roller image data of all frames, and acquiring a priori frame of each grid;
acquiring an initial prediction frame corresponding to each prior frame according to the offset of the prior frame and a preset prediction frame;
performing non-maximum suppression screening on the initial prediction frame according to the preset intersection ratio and the preset confidence coefficient to obtain a final prediction frame of the preprocessed carrier roller image data of all frames;
tracking and marking the same roller target in the final prediction frame by using a target tracking algorithm;
and carrying out dominant roller fault detection on the roller target in the final prediction frame to obtain a dominant fault detection result.
10. The inspection robot-based fault detection method for the coal conveying belt carrier roller according to claim 9, wherein: inputting the preprocessed noise frequency band data of continuous frames into a roller fault noise detection model for hidden roller fault detection, and the method comprises the following steps:
inputting the preprocessed noise frequency band data of the continuous frames into a roller fault and noise detection model to carry out fuzzy roller fault diagnosis to obtain noise characteristic data of the current roller and a corresponding fuzzy fault diagnosis result;
if the fuzzy fault diagnosis result indicates that the current carrier roller has a fault, extracting an explicit fault detection result of the current carrier roller;
if the dominant fault detection result indicates that the current carrier roller has no dominant fault, carrier roller temperature data of the current carrier roller are extracted;
and performing fusion weighted fault diagnosis according to the temperature data and the noise characteristic data of the carrier roller to obtain a hidden fault detection result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210545937.1A CN114935451A (en) | 2022-05-19 | 2022-05-19 | Coal conveying belt carrier roller fault detection system and method based on inspection robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210545937.1A CN114935451A (en) | 2022-05-19 | 2022-05-19 | Coal conveying belt carrier roller fault detection system and method based on inspection robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114935451A true CN114935451A (en) | 2022-08-23 |
Family
ID=82864928
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210545937.1A Pending CN114935451A (en) | 2022-05-19 | 2022-05-19 | Coal conveying belt carrier roller fault detection system and method based on inspection robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114935451A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115285621A (en) * | 2022-09-28 | 2022-11-04 | 常州海图信息科技股份有限公司 | Belt bearing roller fault monitoring system based on artificial intelligence |
-
2022
- 2022-05-19 CN CN202210545937.1A patent/CN114935451A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115285621A (en) * | 2022-09-28 | 2022-11-04 | 常州海图信息科技股份有限公司 | Belt bearing roller fault monitoring system based on artificial intelligence |
CN115285621B (en) * | 2022-09-28 | 2023-01-24 | 常州海图信息科技股份有限公司 | Belt bearing roller fault monitoring system based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108109385B (en) | System and method for identifying and judging dangerous behaviors of power transmission line anti-external damage vehicle | |
CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
CN103413150A (en) | Power line defect diagnosis method based on visible light image | |
CN109716108A (en) | A kind of Asphalt Pavement Damage detection system based on binocular image analysis | |
CN102759347B (en) | Online in-process quality control device and method for high-speed rail contact networks and composed high-speed rail contact network detection system thereof | |
CN112149522A (en) | Intelligent visual external-damage-prevention monitoring system and method for cable channel | |
CN206074832U (en) | A kind of railcar roof pantograph foreign matter detection system | |
CN105931246A (en) | Fabric flaw detection method based on wavelet transformation and genetic algorithm | |
CN111695512B (en) | Unattended cultural relic monitoring method and unattended cultural relic monitoring device | |
Chen et al. | An intelligent sewer defect detection method based on convolutional neural network | |
CN114998244A (en) | Intelligent track beam finger-shaped plate inspection system and method based on computer vision | |
CN112332541B (en) | Monitoring system and method for transformer substation | |
CN114935451A (en) | Coal conveying belt carrier roller fault detection system and method based on inspection robot | |
CN110631832A (en) | Subway vehicle bearing fault on-line detection method | |
CN112964180A (en) | Urban rail vehicle collector shoe detection system | |
CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
CN110019060B (en) | Method and device for automatically synchronizing locomotive video file and operation record file | |
CN105447463B (en) | Across the camera to automatically track system that substation is identified based on characteristics of human body | |
CN116168019B (en) | Power grid fault detection method and system based on machine vision technology | |
CN112883836A (en) | Video detection method for deformation of underground coal mine roadway | |
Daogang et al. | Anomaly identification of critical power plant facilities based on YOLOX-CBAM | |
CN116086547B (en) | Contact net icing detection method based on infrared imaging and meteorological monitoring | |
CN115359399A (en) | Underground drainage pipeline defect detection and identification method based on improved YOLOX | |
CN114973694B (en) | Tunnel traffic flow monitoring system and method based on inspection robot | |
CN114353880A (en) | Strain insulator string wind-induced vibration online monitoring system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |