Intelligent inspection and fault early warning method for adhesive tape transportation corridor

Abstract

The invention provides an intelligent inspection and fault early warning method for an adhesive tape transportation corridor, and belongs to the technical field of inspection of adhesive tape transportation corridors. The method comprises the following steps of: acquiring multi-source heterogeneous data representing the running state of equipment in real time by utilizing various sensors deployed along a rubber belt conveying corridor and at key positions; preprocessing the multi-source heterogeneous data to obtain preprocessed data; performing feature extraction based on the preprocessed data; and judging the running state of the equipment based on the extracted features in combination with a preset threshold value. According to the method, the operation data of the adhesive tape and related equipment are comprehensively collected in combination with multiple sensors, manual participation is not needed, the labor intensity is reduced, the inspection efficiency is improved, manual inspection is completely replaced or greatly reduced, and all-weather and full-coverage automatic intelligent monitoring is achieved. And meanwhile, the safety risk of manual inspection is avoided.

Description

Technical Field

[0001] This invention relates to the field of belt conveyor corridor inspection technology, and in particular to an intelligent inspection and fault early warning method for belt conveyor corridors. Background Technology

[0002] In industrial sectors such as mining, metallurgy, and ports, belt conveyors serve as crucial facilities for the continuous transport of materials. Their stable and reliable operation is vital to the efficiency and safety of the entire production system. During long-term operation, belt conveyors may experience malfunctions such as belt misalignment, tearing, wear, and joint damage. Idler rollers may experience problems such as jamming, abnormal noise, and overheating. If these malfunctions are not detected and addressed in a timely manner, they can range from affecting transport efficiency to causing equipment damage, material spillage, and even safety accidents.

[0003] Currently, the inspection of conveyor belt conveyor corridors involves: inspectors periodically patrolling the corridor, judging the equipment's operating status through visual observation, listening, and touch. This method is labor-intensive, inefficient, heavily reliant on the inspectors' experience and sense of responsibility, and prone to missed or incorrect inspections. Furthermore, the safety of inspectors is difficult to guarantee in the dusty, noisy, and confined environment of the corridor. Installing sensors, such as belt misalignment switches and tear sensors, at key locations along the conveyor belt corridor allows for monitoring of specific faults. However, this method has a limited monitoring range, only able to monitor specific faults and unable to comprehensively assess the operating status of the conveyor belt and related equipment.

[0004] Therefore, a comprehensive intelligent inspection and fault early warning method for conveyor belt transport corridors is needed. Summary of the Invention

[0005] In view of this, the present invention provides an intelligent inspection and fault early warning method for conveyor belt transport corridors, which realizes automated, intelligent and continuous monitoring of the status of corridor equipment, improves inspection efficiency and safety, and solves the problems of high labor intensity, low efficiency, high safety risk and untimely and inaccurate fault early warning in the traditional inspection method. It provides early and accurate early warning of potential faults, reduces the risk of unplanned equipment downtime, and ensures safe and stable production operation.

[0006] Therefore, the present invention provides the following technical solution: A method for intelligent inspection and fault early warning of conveyor belt transport corridors includes: By utilizing a variety of sensors deployed along the conveyor belt transport corridor and at key locations, multi-source heterogeneous data characterizing the equipment's operating status are collected in real time. The multi-source heterogeneous data is preprocessed to obtain preprocessed data; Feature extraction based on preprocessed data; The operating status of the device is determined based on the extracted features and a preset threshold.

[0007] Furthermore, the multi-source heterogeneous data includes: Images, sounds, vibrations, and temperature.

[0008] Furthermore, the preprocessing includes: Gaussian filtering is used to denoise the image, removing dust and light spots. The temperature data acquired by the infrared thermal imager is filtered by a moving average to eliminate the influence of ambient temperature fluctuations. The sound signal collected by the sound sensor is subjected to Fourier transform to convert the time domain signal into a frequency domain signal.

[0009] Furthermore, the feature extraction based on preprocessed data includes: Edge detection is performed on the preprocessed image to obtain the edge contour of the tape, and the edge offset is calculated. Calculate the average and maximum temperatures of the idler rollers from the temperature data.

[0010] Furthermore, the step of determining the device operating status based on the extracted features and a preset threshold includes: When the offset exceeds the deviation threshold, it is judged as a tape deviation fault; When the maximum temperature exceeds the preset temperature threshold, it is determined to be a fault of excessively high roller temperature.

[0011] Furthermore, the various sensors deployed along the conveyor belt transport corridor and at key locations include: Multiple image sensors are deployed on supports along the corridor, covering the load-bearing section, return section, drive rollers and tension rollers, and are equipped with supplementary lighting to adapt to dark environments; Multiple sound sensors are deployed in areas with densely packed idler rollers; Multiple vibration sensors are installed on the idler roller bearing housing, drive roller, tension roller bearing housing, motor housing, and reducer housing; Multiple temperature sensors are installed in the bearing housing and motor windings.

[0012] Laser scanners are installed in critical locations for deviation detection and contour detection.

[0013] Advantages and positive effects of the present invention: By combining multiple sensors to comprehensively collect operational data of the tape and related equipment, no manual intervention is required, reducing labor intensity, improving inspection efficiency, completely replacing or significantly reducing manual inspections, and achieving all-weather, full-coverage automated intelligent monitoring. At the same time, it avoids the safety risks of manual inspections.

[0014] By integrating multi-source heterogeneous data, including images, sound, vibration, and temperature, it enables comprehensive perception of the operating status of key equipment such as conveyor belts, idlers, rollers, and drive units, and more accurate fault identification and location. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of the intelligent inspection and fault early warning method for conveyor belt transport corridors in an embodiment of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0018] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0019] This invention provides an intelligent inspection and fault early warning method for conveyor belt transport corridors, comprising the following steps: By utilizing a variety of sensors deployed along the conveyor belt corridor and at key locations, multi-source heterogeneous data characterizing the equipment's operating status are collected in real time.

[0020] The surface condition of the conveyor belt is acquired through image sensors, including tearing, scratches, foreign objects, and material accumulation; as well as the appearance condition of the idlers and rollers, including damage, jamming, missing parts, and deviation.

[0021] The noise data of the equipment is collected by sound sensors to identify abnormal noises from idlers, bearing damage, and belt slippage.

[0022] Vibration signals from key rotating components, including idlers, rollers, and drive units, are collected using vibration sensors to analyze mechanical faults such as bearing damage, imbalance, and misalignment.

[0023] Temperature sensors are used to monitor the temperature of bearings, motors, and gearboxes to prevent overheating failures.

[0024] The belt misalignment and material cross-sectional profile are measured using a laser scanning sensor.

[0025] Fire warnings are issued using smoke or flame sensors.

[0026] Multiple image sensor modules are deployed on supports along the corridor to cover key areas (such as the load-bearing section, return section, and drive / tensioning / redirection rollers), and supplementary lighting equipment is configured to adapt to dark environments.

[0027] Multiple sound sensors are deployed in areas with densely packed idlers or near critical equipment.

[0028] Multiple vibration sensors are installed on the idler roller bearing housing, drive / tension roller bearing housing, and motor / gearbox housing.

[0029] Multiple temperature sensors are installed at temperature measurement points such as bearing housings and motor windings.

[0030] Laser scanner, installed in critical locations for deviation detection and contour checking. Environmental sensor module (temperature, humidity, dust, smoke).

[0031] Sensor node: integrates sensors, signal conditioning circuits, local microprocessors, and communication modules (such as LoRa, NB-IoT, WiFi, and industrial Ethernet) and is responsible for data acquisition and preliminary processing.

[0032] Network Layer: Communication Network: Used to connect the sensing layer and the edge / cloud layer, and may include industrial Ethernet, fiber optic ring network, wireless mesh network, 4G / 5G, LoRa / NB-IoT, etc., to achieve reliable, low-latency data transmission.

[0033] The remote monitoring center sets the moving speed of the inspection device to 1m / s, the acquisition frequency of the sensing unit to 10 frames per second for the high-definition camera, temperature data every 2 seconds for the infrared thermal imager, 1000 vibration data points per second for the vibration sensor, 44100 sound data points per second for the sound sensor, and environmental data every 5 seconds for the temperature and humidity sensor.

[0034] The system calculates the average temperature, maximum temperature, and rate of temperature change from temperature data; extracts peak values ​​and root mean square values ​​from vibration signals; and extracts spectral features such as center frequency and bandwidth from sound signals. The fault identification module presets feature thresholds for various faults, such as the edge offset threshold for belt misalignment and the temperature threshold for idlers. When the extracted feature parameters exceed the corresponding thresholds, the corresponding fault is identified.

[0035] Data preprocessing: Gaussian filtering is used to denoise the images captured by the high-definition camera, removing noise such as dust and light spots; histogram equalization is used for image enhancement. The temperature data acquired by the infrared thermal imager is processed by moving average filtering to eliminate the influence of ambient temperature fluctuations. Wavelet transform is used to reduce noise in the vibration signals collected by the vibration sensor to extract the effective vibration signals; Perform a Fourier transform on the sound signal collected by the sound sensor to convert the time-domain signal into a frequency-domain signal; The vibration signal is denoised using wavelet transform.

[0036] Feature extraction: Edge detection is performed on the preprocessed image to obtain the edge contour of the tape, the edge offset is calculated, and it is determined whether the tape has deviated. The texture features of the tape surface are calculated by the gray-level co-occurrence matrix to identify the wear area of ​​the tape. Calculate the average and maximum temperatures of the idler rollers from the temperature data, and analyze the temperature change trend; The peak value and root mean square value of the vibration are extracted from the vibration signal to determine whether there is abnormal vibration of the idler roller; the abnormal noise signal of the idler roller is identified from the frequency domain characteristics of the sound signal.

[0037] Fault identification and early warning: The extracted tape edge offset is compared with a preset misalignment threshold. When the offset exceeds the misalignment threshold, it is judged as a tape misalignment fault. The preferred misalignment threshold is 50mm.

[0038] The maximum temperature of the idler roller is compared with the preset temperature threshold. If the temperature exceeds the preset temperature threshold, it is determined that the idler roller temperature is too high. The preferred temperature threshold is 80℃.

[0039] Other types of faults can be identified based on the extracted feature parameters.

[0040] For minor faults, such as slight wear on the tape, a yellow warning signal is issued; for serious faults, such as tearing of the tape, a red warning signal is issued, and the fault location and fault type are displayed in the remote monitoring center.

[0041] Remote monitoring: The display screen at the remote monitoring center shows real-time data such as images, temperature, and vibration transmitted by the inspection device. When a warning signal is received, it automatically issues an audible and visual alarm. After reviewing the fault information, staff can send instructions to the inspection device through the remote monitoring center to stop it at the fault location for focused image capture and data collection, further confirming the fault situation so that maintenance personnel can be promptly dispatched to handle it.

[0042] The hardware implementation for this method includes: a high-definition camera using a 20-megapixel industrial camera with a zoom lens, capable of capturing clear images of the tape surface; mounted on a rotatable pan-tilt unit, allowing for 360° horizontal and 90° vertical rotation for omnidirectional image acquisition; an infrared thermal imager with a resolution of 640×512 and a temperature range of -20℃ to 300℃, used to detect the temperature of the tape and idler rollers; a piezoelectric accelerometer with a sensitivity of 100mV / g, mounted on the idler roller support, with a sampling frequency of 10kHz; a microphone array for sound acquisition, capable of collecting sound information within a 360° range, with a sampling frequency of 44.1kHz; and a temperature and humidity sensor with a measurement range of 0-50℃ for temperature and 20%-90%RH for humidity, with accuracies of ±0.5℃ and ±3%RH, respectively.

[0043] It uses an embedded processor, model NVIDIA Jetson AGX Xavier, which has powerful computing capabilities and can process the acquired data in real time.

[0044] The communication system utilizes a 5G wireless communication module, supporting high-speed data transmission. It can transmit processed results and raw data to a remote monitoring center in real time, while simultaneously receiving control commands from the remote monitoring center. The communication distance can exceed 5km. The power supply unit uses a 100Ah lithium battery pack with a voltage of 24V, supporting continuous operation of the inspection device for over 8 hours. The charging module employs wireless charging; when the inspection device returns to the charging base station, it automatically begins charging, with a full charge taking approximately 2 hours.

[0045] This method significantly improves inspection efficiency, reduces labor costs and intensity, prevents personnel from entering hazardous areas, and enhances operational safety. Its modular design facilitates the addition of new sensor types or analysis algorithms to adapt to different scenario requirements. It reduces unplanned downtime, optimizes maintenance plans, extends equipment lifespan, and significantly lowers overall operation and maintenance costs.

[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent inspection and fault early warning of conveyor belt transport corridors, characterized in that, include: By utilizing a variety of sensors deployed along the conveyor belt transport corridor and at key locations, multi-source heterogeneous data characterizing the equipment's operating status are collected in real time. The multi-source heterogeneous data is preprocessed to obtain preprocessed data; Feature extraction based on preprocessed data; The operating status of the device is determined based on the extracted features and a preset threshold.

2. The method according to claim 1, characterized in that, The multi-source heterogeneous data includes: Images, sounds, vibrations, and temperature.

3. The method according to claim 1, characterized in that, The preprocessing includes: Gaussian filtering is used to denoise the image, removing dust and light spots. The temperature data acquired by the infrared thermal imager is filtered by a moving average to eliminate the influence of ambient temperature fluctuations. The sound signal collected by the sound sensor is subjected to Fourier transform to convert the time domain signal into a frequency domain signal.

4. The method according to claim 1, characterized in that, The feature extraction based on preprocessed data includes: Edge detection is performed on the preprocessed image to obtain the edge contour of the tape, and the edge offset is calculated. Calculate the average and maximum temperatures of the idler rollers from the temperature data.

5. The method according to claim 1, characterized in that, The step of determining the device operating status based on the extracted features and a preset threshold includes: When the offset exceeds the deviation threshold, it is judged as a tape deviation fault; When the maximum temperature exceeds the preset temperature threshold, it is determined to be a fault of excessively high roller temperature.

6. The method according to claim 1, characterized in that, The various sensors deployed along the conveyor belt transport corridor and at key locations include: Multiple image sensors are deployed on supports along the corridor, covering the load-bearing section, return section, drive rollers and tension rollers, and are equipped with supplementary lighting to adapt to dark environments; Multiple sound sensors are deployed in areas with densely packed idler rollers; Multiple vibration sensors are installed on the idler roller bearing housing, drive roller, tension roller bearing housing, motor housing, and reducer housing; Multiple temperature sensors are installed in the bearing housing and motor windings. Laser scanners are installed in critical locations for deviation detection and contour detection.

Images