Conveyor fault detection method and system based on machine learning

Abstract

A conveyor fault detection system based on machine learning, comprising a signal acquisition unit (2), which is mounted on a conveyor body to acquire real-time state information of the conveyor, and to output, on the basis of an acquisition signal, a response signal; a central processing unit (1), an output end of the signal acquisition unit (2) being electrically connected to an input end of the central processing unit (1) to input the response signal into the central processing unit (1); and a power supply assembly (3), an output end of the central processing unit (1) being electrically connected to an input end of the power supply assembly (3), and the central processing unit (1) outputting, on the basis of the response signal, a control signal to the power supply assembly (3) to control same to be turned on or off, and an output end of the power supply assembly (3) being electrically connected to a drive motor of the conveyor to provide same with electric energy. Accordingly, the problem of difficulties in performing fault detection on the conveyor and controlling same to be started and stopped in real time during operation is solved. The present invention further relates to a conveyor fault detection method using the detection system.

Description

Machine Learning-Based Conveyor Fault Detection System and Method Technical Field

[0001] This invention relates to the technical field of conveyor fault detection, and specifically to a conveyor fault detection system and method based on machine learning. Background Technology

[0002] A conveyor is a material handling machine that continuously transports materials along a defined route. Also known as a continuous conveyor, it is now widely used in a variety of industries for material transport.

[0003] Conveyors come in many different types, with belt conveyors being a common one. Belt conveyors use a drive unit to rotate rollers, which in turn drive the belt, thus conveying materials. However, due to constantly changing conveying conditions, conveyors are prone to malfunctions during operation, such as belt misalignment, belt pressure exceeding thresholds, and belt slippage. If a conveyor malfunctions, it can easily cause irreparable damage and may even injure operators. Therefore, there is an urgent need for a system that can monitor conveyors in real time and control their start and stop in a timely manner.

[0004] Summary of the Invention

[0005] This invention proposes a machine learning-based conveyor fault detection system, which includes:

[0006] The signal acquisition unit is installed on the conveyor body to acquire real-time status information of the conveyor and output a response signal based on the acquired signal.

[0007] A central processing unit, wherein the output terminal of the signal acquisition unit is electrically connected to the input terminal of the central processing unit, for inputting the response signal into the central processing unit;

[0008] The power supply component has its output terminal electrically connected to the input terminal of the central processing unit. The central processing unit outputs a control signal to the power supply component based on the response signal to control its on / off state. The output terminal of the power supply component is electrically connected to the drive motor of the conveyor to provide it with electrical energy.

[0009] A further provision of the present invention includes an adjustment unit, wherein the output terminal of the central processing unit is electrically connected to the input terminal of the adjustment unit for outputting a response signal to the adjustment unit, and the adjustment unit starts to adjust the conveyor based on the response signal.

[0010] A further provision of the present invention is that the adjustment unit includes a vibrating feeder and a correction device, and the output terminal of the central processing unit is electrically connected to the input terminals of the vibrating feeder and the correction device, respectively, for controlling the operation of the vibrating feeder and the correction device.

[0011] A further provision of the present invention includes a display unit and an alarm unit, wherein the output terminal of the central processing unit is electrically connected to the input terminals of the display unit and the alarm unit, respectively, so as to output response signals to the display unit and the alarm unit, so that the display unit displays the corresponding fault condition and the alarm unit issues a corresponding warning.

[0012] A further provision of the present invention includes a storage unit electrically connected to the central processing unit for storing data within the central processing unit.

[0013] A further configuration of the present invention is as follows: the signal acquisition unit includes a pressure sensor, a limit sensor, and a color mark sensor; the output terminals of the pressure sensor, the limit sensor, and the color mark sensor are electrically connected to the input terminal of the central processing unit, respectively, for outputting corresponding signals to the central processing unit; the pressure sensor is used to detect the pressure on the conveyor belt, the limit sensor is used to detect the belt deviation signal, and the color mark sensor is used to detect the belt's vertical vibration signal.

[0014] This invention proposes a machine learning-based method for conveyor fault detection, comprising: using the system described in any one of claims 1-7 for detection, including the following steps:

[0015] S1: The signal acquisition unit detects the pressure, deviation, and vibration of the conveyor belt;

[0016] S2: The signal acquired by the signal acquisition unit is transmitted to the central processing unit, which performs calculations on the signal and outputs a corresponding control signal based on the calculation results.

[0017] S3: The central processing unit transmits the control signals to the corresponding display unit, alarm unit, adjustment unit, and power supply component based on the control signal status;

[0018] S4: The display unit displays corresponding information based on the control signal, the alarm unit performs alarm processing based on the control signal, the adjustment unit makes adaptive adjustments to the material and belt on the conveyor based on the control signal, and the power supply component controls the on / off state based on the control signal.

[0019] The beneficial effects of this invention are as follows: through the signal acquisition unit, the condition of the conveyor belt can be detected in real time, that is, the belt pressure, the degree of deviation and the vibration of the belt can be detected. Then, the response signal is converted into a control signal by the central processing unit and sent to the corresponding control unit or power supply component to realize the adjustment of the belt and timely shutdown, thereby avoiding irreparable damage to the conveyor belt or injury to the operator. Attached Figure Description

[0020] Figure 1 shows a schematic diagram of the system of the present invention.

[0021] Figure 2 shows a flowchart of the method of the present invention.

[0022] Reference numerals in the attached diagram: 1. Central processing unit; 2. Signal acquisition unit; 21. Pressure sensor; 22. Limit sensor; 23. Color mark sensor; 3. Power supply assembly; 4. Adjustment unit; 41. Vibrating feeder; 42. Correction device; 5. Display unit; 6. Alarm unit; 7. Storage unit. Detailed Implementation

[0023] Those skilled in the art can refer to the content of this document and appropriately improve the process parameters to achieve the desired results. It should be particularly noted that all similar substitutions and modifications are obvious to those skilled in the art and are considered to be included in this invention. The methods and applications of this invention have been described through preferred embodiments. Those skilled in the art can make modifications or appropriate alterations and combinations to the methods and applications described herein without departing from the content, spirit, and scope of this invention to implement and apply the technology of this invention.

[0024] Example 1

[0025] This invention proposes a machine learning-based fault detection system for a dredging machine, which includes a signal acquisition unit 2 installed on the conveyor body to collect real-time status information of the conveyor and output a response signal based on the collected signal. The information detected by the signal acquisition unit 2 includes the pressure of the conveyor belt, the degree of belt deviation, and the vertical vibration of the belt.

[0026] The output of the signal acquisition unit 2 is electrically connected to the central processing unit 1. The central processing unit 1 is a PLC programmable controller. The output of the signal acquisition unit 2 is electrically connected to the input of the central processing unit 1 so as to input the response signal into the central processing unit 1, which processes it and converts it into an electrical control signal.

[0027] The output terminal of the power supply assembly 3 is electrically connected to the input terminal of the control board of the power supply assembly 3 to input control signals into the power supply assembly 3, thereby controlling the on / off state of the power supply assembly 3. The output terminal of the power supply assembly 3 is electrically connected to the drive motor of the conveyor to provide power for the drive motor. By controlling the on / off state of the power supply assembly 3, the central processing unit 1 further controls the start and stop of the drive motor, and thus controls the start and stop of the conveyor.

[0028] It also includes an adjustment unit 4. The output end of the central processing unit 1 is electrically connected to the input end of the adjustment unit 4. The central processing unit 1 outputs a control signal to the adjustment unit 4 based on the response signal. The adjustment unit 4 can make adaptive adjustments to the conveyor belt based on the control signal.

[0029] The regulating unit 4 includes a vibrating feeder 41 and a deviation correction device 42. The output end of the central processing unit 1 is electrically connected to the input ends of the vibrating feeder 41 and the deviation correction device 42, respectively, so as to input control signals to the vibrating feeder 41 and the deviation correction device 42, control the vibration frequency of the vibrating feeder 41 and the operation of the deviation correction device 42, and further control the amount of material on the conveyor belt and the belt deviation.

[0030] It also includes a display unit 5 and an alarm unit 6, wherein the display unit 5 is an LED display screen, and the alarm unit 6 can be a warning light or a buzzer. The output terminal of the central processing unit 1 is electrically connected to the input terminals of the display unit 5 and the alarm unit 6 respectively, so as to output response signals to the display unit 5 and the alarm unit 6 respectively, so that the display unit 5 displays the corresponding fault condition and the alarm unit 6 issues the corresponding alarm warning.

[0031] It also includes a storage unit 7, which is electrically connected to the central processing unit 1, thereby achieving the purpose of storing the data processed in the central processing unit 1.

[0032] The signal acquisition unit 2 includes a pressure sensor 21, a limit sensor 22, and a color mark sensor 23. The pressure sensor 21 is installed below the belt and abuts against it to collect the pressure exerted on the belt by the conveyed material. The limit sensors 22 are installed on both sides of the belt, with at least two sensors 22 positioned on each side. When the belt deviates from its designated path, it will contact the limit sensor 22, thus detecting the belt deviation signal. The color mark sensor 23 is located at one end of the belt, with its detection end higher than the belt. When the belt vibrates up and down, it will be detected by the color mark sensor 23, thus detecting the up and down vibration signal of the belt.

[0033] It should be noted that when pressure sensor 21 detects excessive pressure on the belt, it outputs a pressure signal to central processing unit 1. Central processing unit 1 then outputs a control signal to vibrating feeder 41 based on this pressure signal, controlling the vibration frequency of vibrating feeder 41 and reducing its feeding rate. When limit sensor 22 detects belt misalignment, it outputs a misalignment signal to central processing unit 1. Central processing unit 1 then outputs a control signal to correction device 42, controlling it to adjust the belt and return it to the correct track. If the signals detected by pressure sensor 21 and limit sensor 22 exceed the threshold, central processing unit 1 transmits a control signal to power supply component 3, stopping the conveyor to prevent damage. Color mark sensor 23 detects belt vibration. If it detects belt vibration, it indicates a significant problem with belt operation. In this case, central processing unit 1 directly controls power supply component 3 to disconnect based on the signal from color mark sensor 23.

[0034] Example 2

[0035] This embodiment proposes a machine learning-based fault detection method for dredging machines, using the detection system described in Embodiment 1, and includes the following steps:

[0036] S1: The signal acquisition unit 2 is used to detect the pressure, deviation and vibration of the conveyor belt;

[0037] S2: The signal acquired by the signal acquisition unit 2 is transmitted to the central processing unit 1, where the central processing unit 1 performs calculations on the signal and outputs a corresponding control signal based on the calculation results.

[0038] S3: The central processing unit 1 transmits the control signal to the corresponding display unit 5, alarm unit 6, adjustment unit 4 and power supply component 3 based on the control signal situation;

[0039] S4: The display unit 5 displays corresponding information based on the control signal, the alarm unit 6 performs alarm processing based on the control signal, the adjustment unit 4 makes adaptive adjustments to the material and belt on the conveyor based on the control signal, and the power supply component 3 controls the on / off state based on the control signal.

[0040] In summary, this invention enables real-time detection of the conveyor belt condition through signal acquisition by the signal acquisition unit 2, namely, detection of belt pressure, belt deviation, and belt vibration. Then, the central processing unit 1 converts the response signal into a control signal and sends it to the corresponding control unit or power supply component 3 to adjust the belt and stop the machine in time, thereby avoiding irreparable damage to the conveyor belt or injury to the operators.

[0041] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be within the scope of protection of the present invention.

Claims

1. A conveyor fault detection system based on machine learning, characterized in that: Including: The signal acquisition unit (2) is installed on the conveyor body to acquire real-time status information of the conveyor and output a response signal based on the acquired signal. The output terminal of the signal acquisition unit (2) is electrically connected to the input terminal of the central processing unit (1) to input the response signal into the central processing unit (1); The power supply assembly (3) is electrically connected to the input terminal of the central processing unit (1). The central processing unit (1) outputs a control signal to the power supply assembly (3) based on the response signal to control its on / off state. The output terminal of the power supply assembly (3) is electrically connected to the drive motor of the conveyor to provide it with power.

2. The machine learning-based conveyor fault detection system according to claim 1, characterized in that: It also includes an adjustment unit (4), the output terminal of the central processing unit (1) is electrically connected to the input terminal of the adjustment unit (4) for outputting a response signal to the adjustment unit, and the adjustment unit (4) starts to adjust the conveyor based on the response signal.

3. The machine learning-based conveyor fault detection system according to claim 2, characterized in that: The adjustment unit (4) includes a vibrating feeder (41) and a correction device (42). The output end of the central processing unit (1) is electrically connected to the input ends of the vibrating feeder (41) and the correction device (42) respectively, so as to control the operation of the vibrating feeder (41) and the correction device (42).

4. The machine learning-based conveyor fault detection system according to claim 1, characterized in that: It also includes a display unit (5) and an alarm unit (6). The output terminal of the central processing unit (1) is electrically connected to the input terminals of the display unit (5) and the alarm unit (6) respectively, so as to output response signals to the display unit (5) and the alarm unit (6) respectively, so that the display unit (5) displays the corresponding fault condition and the alarm unit (6) issues a corresponding warning.

5. The machine learning-based conveyor fault detection system according to claim 1, characterized in that: It also includes a storage unit (7) electrically connected to the central processing unit (1) for storing data within the central processing unit (1).

6. The machine learning-based conveyor fault detection system according to claim 1, characterized in that: The signal acquisition unit (2) includes a pressure sensor (21), a limit sensor (22), and a color mark sensor (23). The output terminals of the pressure sensor (21), the limit sensor (22), and the color mark sensor (23) are electrically connected to the input terminal of the central processing unit (1) to output corresponding signals to the central processing unit (1). The pressure sensor (21) is used to detect the pressure on the conveyor belt, the limit sensor (22) is used to detect the belt deviation signal, and the color mark sensor (23) is used to detect the belt up-and-down vibration signal.

7. A machine learning-based method for conveyor fault detection, characterized in that: The detection using the system described in any one of claims 1-7 includes the following steps: S1: The signal acquisition unit (2) is used to detect the pressure, deviation and vibration of the conveyor belt; S2: The signal acquired by the signal acquisition unit (2) is transmitted to the central processing unit (1), whereby the central processing unit (1) performs calculations on the signal and outputs a corresponding control signal based on the calculation results. S3: The central processing unit (1) transmits the control signal to the corresponding display unit (5), alarm unit (6), adjustment unit (4) and power supply assembly (3) based on the control signal situation; S4: The display unit (5) displays corresponding information based on the control signal, the alarm unit (6) performs alarm processing based on the control signal, the adjustment unit (4) makes adaptive adjustments to the material and belt on the conveyor based on the control signal, and the power supply component (3) controls the on / off state based on the control signal.

Images