Carrier roller anomaly detection method of belt conveyor, related device and related system

Abstract

The invention discloses a carrier roller anomaly detection method of a belt conveyor, a related device and a related system, and relates to the technical field of anomaly detection.The method comprises the steps that a sensing optical fiber arranged on the carrier roller rack side of the belt conveyor is used for obtaining multi-dimensional carrier roller operation data at the current detection moment; according to the carrier roller operation data of each dimension at the current detection moment, carrying out abnormity diagnosis on the carrier roller of the belt conveyor so as to obtain carrier roller abnormity diagnosis results corresponding to the multiple dimensions respectively; according to the carrier roller abnormity diagnosis results corresponding to the multiple dimensions, a final carrier roller abnormity diagnosis result is determined; if the final carrier roller abnormity diagnosis result indicates that the carrier roller is abnormal, carrier roller abnormity early warning is sent out. According to the carrier roller anomaly detection method of the belt conveyor, carrier roller anomaly detection of the belt conveyor can be automatically achieved, the carrier roller does not need to be transformed, the implementation complexity and the later maintenance complexity are low, and the detection effect is good.

Description

Technical Field

[0001] The present application relates to the technical field of abnormality detection, and in particular to a method for detecting abnormality of rollers of a belt conveyor, a related device and a related system. Background Art

[0002] Belt conveyors are typical equipment that uses rotation as the main form of motion. They include motors, reducers, redirecting rollers, drive rollers, and thousands of rollers. As the most commonly used rotating parts of belt conveyors, rollers are prone to frictional heating and ignition and tearing of the conveyor belts if they are abnormal and not replaced in time, which can cause equipment damage and production suspension, resulting in significant economic losses and even casualties. It can be seen that it is very important to detect abnormalities in the rollers of belt conveyors.

[0003] At present, the main method for abnormal detection of belt conveyor rollers is manual inspection. That is, during the operation of the belt conveyor, the inspection personnel rely on their personal work experience to check whether the rollers are abnormal by knocking, checking, etc.

[0004] Since the manual inspection method mainly relies on the personal quality, work attitude and experience of the inspectors, the manual inspection method is highly subjective and prone to missed inspections or wrong inspections. Summary of the invention

[0005] In view of this, the present application provides a belt conveyor roller abnormality detection method, related device and related system to solve the problem that the manual inspection method is highly subjective, which easily leads to missed detection or wrong detection. The technical solution is as follows:

[0006] The first aspect of the present application provides a method for detecting an abnormality of a roller of a belt conveyor, comprising:

[0007] Using a sensing optical fiber disposed on the roller frame side of the belt conveyor, the multi-dimensional roller operation data at the current detection moment is obtained;

[0008] According to the roller operation data of each dimension at the current detection moment, abnormality diagnosis is performed on the roller of the belt conveyor to obtain roller abnormality diagnosis results corresponding to multiple dimensions respectively;

[0009] Determine a final roller abnormality diagnosis result according to the roller abnormality diagnosis results corresponding to the multiple dimensions;

[0010] If the final roller abnormality diagnosis result indicates that the roller is abnormal, a roller abnormality warning is issued.

[0011] In a possible implementation, the multi-dimensional roller operation data includes roller operation data in any two or all of the following dimensions: vibration dimension, sound dimension, and temperature dimension.

[0012] In a possible implementation, the method of obtaining multi-dimensional roller operation data at the current detection moment by using a sensing optical fiber disposed on the roller frame side of the belt conveyor includes:

[0013] Sending an optical signal to a sensing optical fiber disposed on the roller frame side of the belt conveyor at a current detection moment;

[0014] receiving the optical signal reflected back by the sensing optical fiber and carrying the roller vibration information, roller sound information and roller temperature information;

[0015] The received optical signal is demodulated to obtain the multi-dimensional roller operation data at the current detection moment.

[0016] In a possible implementation, the roller abnormality diagnosis result corresponding to any dimension can indicate whether the roller is abnormal and the specific abnormality category when it is abnormal;

[0017] The belt conveyor roller abnormality detection method also includes:

[0018] If the final roller abnormality diagnosis result indicates that the roller is abnormal, determining a risk priority number according to the roller abnormality diagnosis results corresponding to the multiple dimensions respectively;

[0019] According to the risk priority number, the roller maintenance strategy is determined.

[0020] In a possible implementation, the method of obtaining multi-dimensional roller operation data at the current detection moment by using a sensing optical fiber disposed on the roller frame side of the belt conveyor includes:

[0021] Using multiple optical fiber acquisition units of the sensing optical fiber arranged on the roller frame side of the belt conveyor, multi-dimensional roller operation data of multiple measuring points at the current detection time are obtained;

[0022] According to the roller operation data of each dimension at the current detection moment, abnormality diagnosis is performed on the roller of the belt conveyor to obtain roller abnormality diagnosis results corresponding to multiple dimensions, including:

[0023] For each measuring point, according to the roller operation data of each dimension at the current detection moment of the measuring point, the roller abnormality diagnosis within the measuring range of the measuring point is performed to obtain the roller abnormality diagnosis results corresponding to the measuring point in multiple dimensions.

[0024] In a possible implementation, the multi-dimensional roller operation data includes roller operation data in a vibration dimension;

[0025] According to the roller operation data of the measuring point in the vibration dimension at the current detection time, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension, including:

[0026] Acquire the roller operation data of the measuring point sequence corresponding to the measuring point in the vibration dimension from the roller operation data at the previous detection moment, and obtain the historical roller vibration data of the measuring point, wherein the measuring point sequence corresponding to the measuring point includes the measuring point and the adjacent measuring points of the measuring point;

[0027] Perform fast Fourier transform on the historical roller vibration data of the measuring point and the current roller vibration data of the measuring point respectively, to obtain the historical spectrum line amplitude feature set of the measuring point and the current spectrum line amplitude feature set of the measuring point, wherein the current roller vibration data of the measuring point is the roller operation data in the vibration dimension at the current detection moment of the measuring point sequence corresponding to the measuring point;

[0028] According to the historical spectrum line amplitude feature set of the measuring point and the current spectrum line amplitude feature set of the measuring point, a feature distribution difference value between the current roller vibration data of the measuring point and the historical roller vibration data of the measuring point is determined to obtain a feature distribution difference value corresponding to the measuring point;

[0029] According to the characteristic distribution difference value corresponding to the measuring point, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension.

[0030] In a possible implementation, the abnormality diagnosis of the roller within the measuring range of the measuring point is performed according to the characteristic distribution difference value corresponding to the measuring point to obtain the abnormality diagnosis result of the roller corresponding to the measuring point in the vibration dimension, including:

[0031] Inputting the characteristic distribution difference value corresponding to the measuring point into a pre-trained first abnormality diagnosis model, and obtaining the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension output by the first abnormality diagnosis model;

[0032] The first abnormality diagnosis model is trained by using first training samples marked with abnormalities and first training samples marked with specific abnormality categories, and the first training samples are feature distribution difference values ​​corresponding to the measurement points.

[0033] In a possible implementation, the multi-dimensional roller operation data includes roller operation data in a sound dimension;

[0034] According to the roller operation data of the measuring point in the sound dimension at the current detection time, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the sound dimension, including:

[0035] Inputting the roller operation data of the measuring point in the sound dimension at the current detection moment into the pre-trained second abnormality diagnosis model, obtaining the roller abnormality diagnosis result corresponding to the measuring point in the sound dimension output by the second abnormality diagnosis model;

[0036] The second abnormality diagnosis model is trained by using second training samples marked with or without abnormalities and second training samples marked with specific abnormality categories, and the second training samples are roller operation data of the measuring points in the sound dimension.

[0037] In a possible implementation, the multi-dimensional roller operation data includes roller operation data in a temperature dimension;

[0038] According to the roller operation data of the measuring point in the temperature dimension at the current detection time, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the temperature dimension, including:

[0039] By comparing the roller operation data of the current detection moment of the measuring point in the temperature dimension with the preset temperature threshold, the roller abnormality diagnosis result corresponding to the measuring point in the temperature dimension is determined.

[0040] In a possible implementation, determining the roller maintenance strategy according to the risk priority number includes:

[0041] Determining the risk priority number range to which the risk priority number belongs from the risk priority number ranges respectively corresponding to several preset risk assessment levels, wherein the several risk assessment levels also respectively correspond to maintenance strategies;

[0042] Determine the risk assessment level corresponding to the risk priority number range to which the risk priority number belongs as the target risk assessment level;

[0043] The maintenance strategy corresponding to the target risk assessment level is determined as the maintenance strategy for the abnormal roller.

[0044] A second aspect of the present application provides a roller abnormality detection device for a belt conveyor, comprising: a roller operation data acquisition module, a roller abnormality diagnosis module and a roller abnormality early warning module;

[0045] The roller operation data acquisition module is used to acquire multi-dimensional roller operation data at the current detection moment by using a sensing optical fiber arranged on the roller frame side of the belt conveyor;

[0046] The roller abnormality diagnosis module is used to perform abnormality diagnosis on the roller of the belt conveyor according to the roller operation data of each dimension at the current detection moment, so as to obtain roller abnormality diagnosis results corresponding to multiple dimensions respectively, and determine the final roller abnormality diagnosis result according to the roller abnormality diagnosis results corresponding to the multiple dimensions respectively;

[0047] The roller abnormality warning module is used to issue a roller abnormality warning when the final roller abnormality diagnosis result indicates that the roller is abnormal.

[0048] The third aspect of the present application provides an optical fiber signal processing device, comprising at least one processor and a memory connected to the processor, wherein:

[0049] The memory is used to store computer programs;

[0050] The processor is used to execute the computer program so that the optical fiber signal processing device can implement the steps of any one of the above-mentioned methods for detecting roller abnormalities of a belt conveyor.

[0051] A fourth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of any of the above-mentioned methods for detecting roller abnormalities of a belt conveyor.

[0052] A fifth aspect of the present application provides a computer program product, comprising computer-readable instructions, which, when executed on an electronic device, enables the electronic device to implement the steps of any one of the above-mentioned methods for detecting abnormalities in belt conveyor rollers.

[0053] A sixth aspect of the present application provides a belt conveyor roller abnormality detection system, comprising: a sensing optical fiber, and an optical fiber signal processing device connected to the sensing optical fiber, wherein the sensing optical fiber is arranged on the roller frame side of the belt conveyor;

[0054] The optical fiber signal processing device is used to perform abnormality detection on the rollers of the belt conveyor using any of the above-mentioned belt conveyor roller abnormality detection methods.

[0055] By means of the above technical scheme, the belt conveyor roller abnormality detection method provided in the present application first utilizes the sensing optical fiber arranged on the roller frame side of the belt conveyor to obtain the multi-dimensional roller operation number at the current detection moment, and then performs abnormal diagnosis on the rollers of the belt conveyor according to the roller operation data of each dimension at the current detection moment to obtain roller abnormality diagnosis results corresponding to multiple dimensions, and then determines the final roller abnormality diagnosis result according to the roller abnormality diagnosis results corresponding to multiple dimensions. If the final roller abnormality diagnosis result indicates that the roller is abnormal, a roller abnormality warning is issued. The belt conveyor roller abnormality detection method provided in the present application, on the one hand, automatically realizes the belt conveyor roller abnormality detection. Since the detection process does not require human participation, it avoids the problems caused by manual detection (such as the problem of human subjective factors affecting the detection effect). On the other hand, the roller operation data is obtained by using sensor optical fiber. Since the sensor optical fiber is arranged on the roller frame side of the belt conveyor, there is no need to modify the roller, and the implementation complexity and subsequent maintenance complexity are low, and the cost is not high. On the other hand, multi-dimensional roller operation data is obtained, and then the roller abnormality diagnosis is performed based on the multi-dimensional roller operation data. The abnormality diagnosis based on the multi-dimensional roller operation data can obtain a more accurate abnormality diagnosis result. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0057] Figure 1 A schematic flow chart of a method for detecting abnormality of a belt conveyor roller provided in an embodiment of the present application;

[0058] Figure 2 A schematic diagram of deploying a sensing optical fiber on the roller frame side of a belt conveyor provided in an embodiment of the present application;

[0059] Figure 3 A schematic diagram of a three-core sensing optical fiber provided in an embodiment of the present application;

[0060] Figure 4 According to the measurement point P provided in the embodiment of the present application k The roller operation data in the vibration dimension at the current detection time, for the measuring point P k The rollers within the measured range are diagnosed abnormally to obtain the measuring point P. k Flow chart of abnormal diagnosis results corresponding to the vibration dimension;

[0061] Figure 5 A schematic flow chart of another method for detecting abnormality of a belt conveyor roller provided in an embodiment of the present application;

[0062] Figure 6 A schematic diagram of the structure of a belt conveyor roller abnormality detection device provided in an embodiment of the present application;

[0063] Figure 7 A schematic structural diagram of a belt conveyor roller abnormality detection system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0065] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0066] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0067] In view of the fact that the existing manual inspection method is highly subjective and prone to missed or wrong detection, research was conducted. The initial idea was to use a microphone to collect the sound signal of the belt conveyor roller, obtain the signal characteristic component of the collected roller sound signal, and determine whether the belt conveyor roller is abnormal by comparing the signal characteristic component with the set threshold.

[0068] The above idea does not require manual inspection, thus avoiding the influence of human subjective factors. However, the detection effect of the above idea is not good (false detection is prone to occur), and the pickup range of the microphone is limited. When the length of the belt conveyor is large, a large number of microphones need to be deployed along the line (for example, for a 10km belt conveyor, even if one is deployed every 10m, 1,000 microphones need to be deployed), so the cost is high.

[0069] In view of the poor detection effect and high detection cost of the above ideas, further research was carried out. During the research process, a roller abnormality detection scheme based on a temperature velocity sensor was conceived, that is, a temperature velocity sensor is deployed in contact on the roller of the belt conveyor, and the temperature signal and speed signal of the roller are collected by the temperature velocity sensor deployed on the roller. By comparing the collected temperature signal with the preset temperature threshold and comparing the collected speed signal with the preset speed threshold, it is determined whether the roller of the belt conveyor is abnormal.

[0070] Research on the above-mentioned roller abnormality detection scheme based on temperature velocity sensors found that, on the one hand, the contact deployment of temperature velocity sensors on the rollers of the belt conveyor requires simple modification of the rollers, which means that the belt conveyor transportation operation process needs to be stopped, which is unacceptable to the production unit. On the other hand, since a temperature velocity sensor needs to be installed on each roller, the cost is very high, and the subsequent electricity costs and maintenance complexity are also high.

[0071] In view of the many problems with the above-mentioned roller abnormality detection scheme based on temperature speed sensor, further research was carried out. Through continuous research, a roller abnormality detection method for belt conveyor with better effect was finally proposed.

[0072] Next, the belt conveyor roller abnormality detection method provided by the present application is introduced through the following embodiments.

[0073] See also Figure 1 , shows a schematic flow chart of a method for detecting an abnormality of a belt conveyor roller provided in an embodiment of the present application, and the method for detecting an abnormality of a belt conveyor roller may include:

[0074] Step S101: using the sensing optical fiber disposed on the roller frame side of the belt conveyor to obtain the multi-dimensional roller operation data at the current detection moment.

[0075] In order to avoid modifying the rollers of the belt conveyor, reduce costs, and reduce the complexity of implementation and subsequent maintenance, this embodiment proposes to deploy a sensing optical fiber on the roller frame side of the belt conveyor, such as Figure 2 As shown, the sensing optical fiber is used to obtain the roller operation data of the belt conveyor. In order to obtain a better detection effect, this embodiment obtains the roller operation data of multiple dimensions.

[0076] The multi-dimensional roller operation data in this embodiment may include roller operation data of any two or all of the following dimensions: vibration dimension, sound dimension, and temperature dimension. Preferably, the multi-dimensional roller operation data includes roller operation data of vibration dimension, roller operation data of sound dimension, and roller operation data of temperature dimension. It should be noted that the roller operation data of vibration dimension is roller vibration data, the roller operation data of sound dimension is roller sound data, and the roller operation data of temperature dimension is roller temperature data.

[0077] In one possible implementation, the process of obtaining multi-dimensional roller operation data at the current detection moment using the sensing optical fiber disposed on the roller frame side of the belt conveyor may include: transmitting an optical signal to the sensing optical fiber disposed on the roller frame side of the belt conveyor at the current detection moment; receiving an optical signal reflected back by the sensing optical fiber containing roller vibration information, roller sound information, and roller temperature information; and demodulating the received optical signal to obtain multi-dimensional roller operation data at the current detection moment.

[0078] The sensing optical fiber in this embodiment can be a single-core sensing optical fiber or a multi-core sensing optical fiber. If the sensing optical fiber in this embodiment is a single-core sensing optical fiber, multi-dimensional roller operation data can be demodulated from the optical signal reflected back from the single-core sensing optical fiber, such as roller operation data in vibration dimension, roller operation data in sound dimension, and roller operation data in temperature dimension. If the sensing optical fiber in this embodiment is a multi-core sensing optical fiber, roller operation data in different dimensions can be demodulated from the optical signals reflected back from different cores of the multi-core sensing optical fiber. For example, the sensing optical fiber is a three-core sensing optical fiber, such as Figure 3 As shown, the roller operation data in the vibration dimension can be demodulated from the light signal reflected from core 1, the roller operation data in the sound dimension can be demodulated from the light signal reflected from core 2, and the roller operation data in the temperature dimension can be demodulated from the light signal reflected from core 3. It should be noted that Figure 3 The multi-core sensing optical fiber shown is only an example. The present embodiment does not limit the sensing optical fiber to a three-core sensing optical fiber. For example, the sensing optical fiber may also be a four-core sensing optical fiber (for example, the roller operation data in the vibration dimension is demodulated from the optical signal reflected from core 1 and core 2, the roller operation data in the sound dimension is demodulated from the optical signal reflected from core 3, and the roller operation data in the temperature dimension is demodulated from the optical signal reflected from core 4), a five-core sensing optical fiber (for example, the roller operation data in the vibration dimension is demodulated from the optical signal reflected from core 1 and core 2, the roller operation data in the sound dimension is demodulated from the optical signal reflected from core 3 and core 4, and the roller operation data in the temperature dimension is demodulated from the optical signal reflected from core 5), etc.

[0079] Step S102: performing abnormality diagnosis on the rollers of the belt conveyor according to the roller operation data of each dimension at the current detection moment, so as to obtain roller abnormality diagnosis results corresponding to multiple dimensions.

[0080] Taking into account that the accuracy of abnormality diagnosis of the belt conveyor rollers based on the roller operation data of a single dimension is not high, in order to obtain higher abnormality diagnosis accuracy, this embodiment obtains roller operation data of multiple dimensions, and then performs abnormality diagnosis on the belt conveyor rollers based on the roller operation data of each dimension, so as to obtain roller abnormality diagnosis results corresponding to multiple dimensions.

[0081] Exemplarily, the multi-dimensional roller operation data includes roller operation data in vibration dimension, roller operation data in sound dimension and roller operation data in temperature dimension. The roller of the belt conveyor can be diagnosed for abnormality according to the roller operation data in vibration dimension at the current detection moment to obtain the roller abnormality diagnosis result corresponding to the vibration dimension. The roller of the belt conveyor can be diagnosed for abnormality according to the roller operation data in sound dimension at the current detection moment to obtain the roller abnormality diagnosis result corresponding to the sound dimension. The roller of the belt conveyor can be diagnosed for abnormality according to the roller operation data in temperature dimension at the current detection moment to obtain the roller abnormality diagnosis result corresponding to the temperature dimension. Among them, the roller abnormality diagnosis result can indicate whether the roller of the belt conveyor is abnormal.

[0082] Step S103: determining a final roller abnormality diagnosis result according to the roller abnormality diagnosis results corresponding to the multiple dimensions.

[0083] In order to obtain a more accurate roller abnormality diagnosis result, this embodiment combines the roller abnormality diagnosis results corresponding to multiple dimensions to determine the final roller abnormality diagnosis result.

[0084] There are many ways to determine the final roller abnormality diagnosis result based on the roller abnormality diagnosis results corresponding to multiple dimensions. For example, if the roller abnormality diagnosis result of the vibration dimension indicates that the roller is abnormal, and the roller abnormality diagnosis result of the sound dimension indicates that the roller is abnormal, then the roller abnormality is determined. For another example, if the roller abnormality diagnosis result of the vibration dimension indicates that the roller is abnormal, the roller abnormality diagnosis result of the sound dimension indicates that the roller is abnormal, and the roller abnormality diagnosis result corresponding to the temperature dimension indicates that the roller is abnormal, then the roller abnormality is determined. The specific strategy for determining the final roller abnormality diagnosis result based on the roller abnormality diagnosis results corresponding to multiple dimensions can be determined according to the actual application scenario.

[0085] Step S104: If the final roller abnormality diagnosis result indicates that the roller of the belt conveyor is abnormal, a roller abnormality warning is issued.

[0086] If the final roller abnormality diagnosis result indicates that the roller of the belt conveyor is abnormal, a roller abnormality warning is issued to the equipment management personnel.

[0087] The belt conveyor roller abnormality detection method provided in the embodiment of the present application first utilizes the sensing optical fiber arranged on the roller frame side of the belt conveyor to obtain the multi-dimensional roller operation number at the current detection moment, and then performs abnormal diagnosis on the roller of the belt conveyor based on the roller operation data of each dimension at the current detection moment to obtain roller abnormality diagnosis results corresponding to multiple dimensions, and then determines the final roller abnormality diagnosis result based on the roller abnormality diagnosis results corresponding to the multiple dimensions. If the final roller abnormality diagnosis result indicates that the roller is abnormal, a roller abnormality warning is issued. The belt conveyor roller abnormality detection method provided in the embodiment of the present application, on the one hand, automatically realizes the belt conveyor roller abnormality detection. Since the detection process does not require human participation, it avoids the problems caused by manual detection (such as the problem of human subjective factors affecting the detection effect). On the other hand, the roller operation data is obtained by using sensor optical fiber. Since the sensor optical fiber is arranged on the roller frame side of the belt conveyor, there is no need to modify the roller, and the implementation complexity and subsequent maintenance complexity are low, and the cost is not high. On the other hand, multi-dimensional roller operation data is obtained, and then the roller abnormality diagnosis is performed based on the multi-dimensional roller operation data. The abnormality diagnosis based on the multi-dimensional roller operation data can obtain a more accurate roller abnormality diagnosis result.

[0088] In another embodiment of the present application, the specific implementation process of "step S101: using the sensing optical fiber arranged on the roller frame side of the belt conveyor to obtain the multi-dimensional roller operation data at the current detection moment" and "step S102: based on the roller operation data of each dimension at the current detection moment, performing abnormal diagnosis on the rollers of the belt conveyor to obtain roller abnormality diagnosis results corresponding to multiple dimensions" in the above embodiment is introduced.

[0089] The process of obtaining multi-dimensional roller operation data at the current detection moment using the sensing optical fiber arranged on the roller frame side of the belt conveyor may include: obtaining multi-dimensional roller operation data at multiple measuring points at the current detection moment using multiple optical fiber acquisition units of the sensing optical fiber arranged on the roller frame side of the belt conveyor.

[0090] like Figure 2 As shown, the sensing optical fiber in this embodiment includes multiple optical fiber collection units, and the multiple optical fiber collection units are obtained by winding a sensing optical fiber multiple times at different positions on the side of the roller frame. The position of each optical fiber collection unit is a measuring point. The multiple optical fiber collection units of the sensing optical fiber can obtain multi-dimensional roller operation data of multiple measuring points at the current detection moment.

[0091] The process of performing abnormal diagnosis on the rollers of the belt conveyor according to the roller operation data in each dimension at the current detection moment to obtain the roller abnormal diagnosis results corresponding to multiple dimensions may include: for each measuring point, performing abnormal diagnosis on the rollers within the measuring range of the measuring point according to the roller operation data in each dimension at the current detection moment of the measuring point to obtain the roller abnormal diagnosis results corresponding to the measuring point in multiple dimensions.

[0092] Next, we take the multi-dimensional operation data including the roller operation data in vibration dimension, the roller operation data in sound dimension and the roller operation data in temperature dimension as an example to analyze the roller operation data according to a measuring point P. k (kth measuring point) The roller operation data in each dimension at the current detection time, for measuring point P k The rollers within the measured range are diagnosed abnormally to obtain the measuring point P. k The specific implementation process of the roller abnormality diagnosis results corresponding to multiple dimensions is introduced.

[0093] First, according to the measuring point P k The roller operation data in the vibration dimension at the current detection time, for the measuring point P k The rollers within the measured range are diagnosed abnormally to obtain the measuring point P. k The specific implementation process of the roller abnormality diagnosis results corresponding to the vibration dimension is introduced, such as Figure 4 As shown, this may include:

[0094] Step S401: Obtain the measuring point P from the multi-dimensional roller operation data at the previous detection moment k The corresponding measuring point sequence in the vibration dimension of the roller running data, get the measuring point P k Historical roller vibration data.

[0095] Among them, the measuring point P k The corresponding measurement point sequence includes measurement point P k And the measuring point P k The adjacent measuring point, measuring point P k The adjacent measuring points may include measuring point P k The forward adjacent measuring point and / or the backward adjacent measuring point of, for example, measuring point P k The adjacent measuring points can include P k-1 , P k+1 For example, the measuring point P k The adjacent measuring points can include P k-1 , P k-2 , P k+1 , P k+2 .

[0096] In this embodiment, the measuring point P is obtained from the multi-dimensional roller operation data at the previous detection moment. kThe corresponding measuring point sequence in the vibration dimension of the roller running data, thus obtaining the measuring point P k Historical roller vibration data.

[0097] Step S402: For measuring point P k Historical roller vibration data and measuring point P k The current roller vibration data are respectively subjected to fast Fourier transform to obtain the measuring point P k The historical spectral line amplitude feature set and the measurement point P k The current spectral line amplitude feature set.

[0098] Among them, the measuring point P k The current roller vibration data is the measuring point P k The corresponding measuring point sequence is the roller operation data in the vibration dimension at the current detection moment.

[0099] Step S403: According to the measuring point P k The historical spectral line amplitude characteristics and the measurement point P k The current spectral line amplitude characteristics determine the measurement point P k The current roller vibration data and the measuring point P k The characteristic distribution difference value of the historical roller vibration data is obtained by measuring point P k The corresponding feature distribution difference value.

[0100] Specifically, measuring point P k The corresponding feature distribution difference value D k It can be calculated according to the following formula:

[0101] (1)

[0102] Where A is the adjustment matrix, which takes the identity matrix, tr() represents the trace of the matrix, M is the maximum mean difference matrix, X k ={X h , X t k}, X h Indicates measuring point P k The historical spectral line amplitude feature set, X t k Indicates measuring point P k The current spectral line amplitude characteristic set, x i Represents X h The i-th feature in n h Represents X h The number of features in x j Represents X t k The jth feature in n t Represents X t k The number of features in .

[0103] Step S404: According to the measuring point P k The corresponding feature distribution difference value, for the measurement point P k The rollers within the measured range are diagnosed abnormally to obtain the measuring point P. k The abnormal diagnosis results of the roller corresponding to the vibration dimension.

[0104] In a possible implementation, according to the measuring point P k The corresponding feature distribution difference value, for the measurement point P k The rollers within the measured range are diagnosed abnormally to obtain the measuring point P. k The process of abnormal diagnosis results corresponding to the vibration dimension may include: k The corresponding feature distribution difference value is input into the first abnormality diagnosis model obtained by pre-training, and the measurement point P output by the first abnormality diagnosis model is obtained. k The abnormal diagnosis results of the roller corresponding to the vibration dimension.

[0105] Among them, the first abnormality diagnosis model is trained using the constructed first training data set, and the first training data set may include several first training samples marked with or without abnormalities and several first training samples marked with specific abnormality categories. When constructing the first training data set, multiple categories can be preset, such as no abnormality, mild abnormality, moderate abnormality, and severe abnormality, so as to obtain several first training samples marked with or without abnormalities, several first training samples marked with mild abnormalities, several first training samples marked with moderate abnormalities, and several first training samples marked with severe abnormalities, so as to form the first training data set with the above-mentioned first training samples of each category. The first training sample in the first training data set is the feature distribution difference value corresponding to the measuring point, and the first training sample in the first training data set can cover all measuring points.

[0106] It should be noted that the above-mentioned no abnormality, mild abnormality, moderate abnormality, and severe abnormality are only examples. This embodiment does not limit the preset multiple categories to include no abnormality, mild abnormality, moderate abnormality, and severe abnormality. For example, the preset multiple categories may also include no abnormality, mild abnormality, and severe abnormality. The preset multiple categories can be set according to the actual application scenario.

[0107] The first abnormality diagnosis model in this embodiment can be an abnormality diagnosis model based on SVM. Of course, this embodiment is not limited to this, and the first abnormality diagnosis model can also be an abnormality diagnosis model based on a neural network. If the first abnormality diagnosis model is an abnormality diagnosis model based on SVM, a suitable kernel function can be selected first, and then parameter optimization can be performed to obtain the optimal C parameter and kernel parameter. After obtaining the appropriate kernel function and the optimal parameters, an abnormality diagnosis model based on SVM can be constructed based on the appropriate kernel function and the optimal parameters, and then the training data in the first training data set can be used to train the abnormality diagnosis model based on SVM. It should be noted that when constructing the first training data set, a test data set can be constructed at the same time. After the training is completed, the trained model can be tested with the test data set. If the performance of the model meets the requirements after testing, the training is terminated, otherwise the model is continued to be trained until the model meets the requirements.

[0108] Next, according to the measuring point P k The roller operation data in the sound dimension at the current detection time, for the measuring point P k The rollers within the measured range are diagnosed abnormally to obtain the measuring point P. k The specific implementation process of the roller abnormality diagnosis results corresponding to the sound dimension is introduced.

[0109] In a possible implementation, according to the measuring point P k The roller operation data in the sound dimension at the current detection time, for the measuring point P k The rollers within the measured range are diagnosed abnormally to obtain the measuring point P. k The process of diagnosing the abnormal roller results corresponding to the sound dimension may include: k The roller operation data in the sound dimension at the current detection time is input into the pre-trained second abnormality diagnosis model to obtain the measurement point P output by the second abnormality diagnosis model. k The abnormal roller diagnosis results corresponding to the sound dimension.

[0110] Among them, the second abnormality diagnosis model is trained using the constructed second training data set, and the second training data set may include several second training samples marked with or without abnormalities and several second training samples marked with specific abnormality categories. When constructing the second training data set, multiple categories can be preset (consistent with the categories preset when constructing the first training data set mentioned above), such as no abnormality, mild abnormality, moderate abnormality, and severe abnormality, so as to obtain several second training samples marked with or without abnormalities, several second training samples marked with mild abnormalities, several second training samples marked with moderate abnormalities, and several second training samples marked with severe abnormalities, so as to form the second training data set composed of the second training samples marked in each category. The second training samples in the second training data set are the roller operation data of the measuring points in the sound dimension, and the second training samples in the second training data set can cover all measuring points.

[0111] When training the second abnormality diagnosis model with the second training samples in the second training data set, the training goal is to make the category predicted by the second abnormality diagnosis model for the second training sample and the category labeled by the second training sample tend to be consistent.

[0112] After the second abnormality diagnosis model is obtained through training, the second abnormality diagnosis model can be obtained through training, and the second abnormality diagnosis model can be obtained through training, according to the measurement point P k The roller operation data in the sound dimension at the current detection time for the measuring point P k The abnormality diagnosis of the rollers within the measured range is carried out, that is, the measuring point P k The second abnormality diagnosis model is trained by inputting the roller operation data in the sound dimension at the current detection moment. The second abnormality diagnosis model determines the target category from multiple preset categories (such as no abnormality, slight abnormality, moderate abnormality, and severe abnormality) as the measurement point P k Abnormal diagnostic results corresponding to the sound dimension.

[0113] Next, according to the measuring point P k The roller operation data in the temperature dimension at the current detection time, for the measuring point P k The rollers within the measured range are diagnosed abnormally to obtain the measuring point P. k The specific implementation process of the roller abnormality diagnosis results corresponding to the temperature dimension is introduced.

[0114] In a possible implementation, according to the measuring point P k The roller operation data in the temperature dimension at the current detection time, for the measuring point P k The rollers within the measured range are diagnosed abnormally to obtain the measuring point P. k The process of diagnosing the abnormal roller results corresponding to the temperature dimension may include: kThe roller operation data in the temperature dimension at the current detection moment is compared with the preset temperature threshold to determine the roller abnormality diagnosis result corresponding to the temperature dimension of the measuring point.

[0115] Among them, the measuring point P k The roller operation data in the temperature dimension at the current detection time is the roller temperature value, which can be obtained by setting the measuring point P k The roller temperature value at the current detection moment is compared with the preset temperature threshold to determine the measuring point P. k Abnormal diagnosis results corresponding to the temperature dimension.

[0116] For example, the following categories are preset: no abnormality, mild abnormality, moderate abnormality, severe abnormality, and the temperature threshold T is preset. th1 、T th2 、T th3 , T th1 <T th2 <T th3 , if the measuring point P k The roller temperature value at the current detection time is less than T th1 , then the abnormal diagnosis result of the roller corresponding to the temperature dimension of the measuring point is determined to be no abnormality. If the measuring point P k The roller temperature value at the current detection time is greater than or equal to T th1 and less than T th2 , then the abnormal diagnosis result of the roller corresponding to the temperature dimension of the measuring point is determined to be a slight abnormality. If the measuring point P k The roller temperature value at the current detection time is greater than or equal to T th2 and less than T th3 , then determine the measuring point P k The abnormal diagnosis result of the roller in the temperature dimension is moderate abnormality. k The roller temperature value at the current detection time is greater than or equal to T th3 , it is determined that the roller abnormality diagnosis result corresponding to the measuring point in the temperature dimension is a severe abnormality.

[0117] Through the above process, the measuring point P can be determined k The roller abnormality diagnosis results corresponding to multiple dimensions. The roller abnormality diagnosis results corresponding to other measuring points in multiple dimensions can be obtained in the same way. The roller abnormality diagnosis result corresponding to a measuring point in a dimension is the abnormality diagnosis result of the roller in the measuring range of the measuring point in the dimension.

[0118] For each measuring point, after obtaining the roller abnormality diagnosis results corresponding to the measuring point in multiple dimensions, the roller abnormality diagnosis result finally corresponding to the measuring point can be determined according to the roller abnormality diagnosis results corresponding to the measuring point in multiple dimensions, that is, the final abnormality diagnosis result of the roller within the measuring range of the measuring point.

[0119] In another embodiment of the present application, Figure 5 As shown, the belt conveyor roller abnormality detection method may further include the following steps in addition to the above steps S101 to S104:

[0120] Step S105: If the final roller abnormality diagnosis result indicates that the roller is abnormal, a risk priority number is determined according to the roller abnormality diagnosis results corresponding to the multiple dimensions.

[0121] The above-mentioned embodiment mentioned that multiple optical fiber acquisition units of the sensor optical fiber arranged on the roller frame side of the belt conveyor can be used to obtain multi-dimensional roller operation data of multiple measuring points at the current detection moment. Then, for each measuring point, the roller abnormality diagnosis can be performed on the rollers within the measuring range of the measuring point based on the roller operation data of each dimension at the current detection moment of the measuring point to obtain the roller abnormality diagnosis results corresponding to the measuring point in multiple dimensions. After obtaining the roller abnormality diagnosis results corresponding to the measuring point in multiple dimensions, the roller abnormality diagnosis result finally corresponding to the measuring point can be determined based on the roller abnormality diagnosis results corresponding to the measuring point in multiple dimensions.

[0122] For each measuring point, after obtaining the roller abnormality diagnosis result corresponding to the measuring point, if the roller abnormality diagnosis result corresponding to the measuring point indicates a roller abnormality, the risk priority number can be determined according to the roller abnormality diagnosis results (i.e., abnormality categories) corresponding to the measuring point in multiple dimensions.

[0123] It should be noted that the risk priority number is determined based on three influencing parameters, namely severity S, occurrence rate O and difficulty in detection D. Severity S reflects the impact of the anomaly (1-10 points). The higher the score, the more serious the result. The occurrence rate O reflects the probability of the anomaly occurring (1-10 points). The higher the score, the greater the probability of a certain type of anomaly occurring. The difficulty in detection D reflects the possibility of the anomaly being detected (1-10 points). The higher the score, the more difficult it is to be detected.

[0124] The calculation formula of risk priority number RPN is:

[0125] RPN=S×O×D (2)

[0126] For each measuring point, when determining the risk priority number according to the roller abnormality diagnosis results (i.e., abnormality categories) corresponding to the measuring point in multiple dimensions, the specific values ​​of the severity S, occurrence rate O, and difficulty of detection D of the three influencing parameters can be determined according to the roller abnormality diagnosis results (i.e., abnormality categories) corresponding to the measuring point in multiple dimensions, and then the risk priority number RPN corresponding to the measuring point can be obtained according to the above formula. A determination rule for determining the parameter values ​​of the three influencing parameters according to the abnormality category can be preset, and then, according to the roller abnormality diagnosis results (i.e., abnormality categories) corresponding to the measuring point in multiple dimensions, the parameter values ​​of the three influencing parameters can be determined according to the preset determination rule.

[0127] Step S106: Determine the roller maintenance strategy according to the risk priority number.

[0128] Specifically, the process of determining the roller maintenance strategy based on the risk priority number may include: determining the risk priority number range to which the risk priority number belongs from the risk priority number ranges corresponding to several preset risk assessment levels, wherein the several risk assessment levels also correspond to maintenance strategies respectively; determining the risk assessment level corresponding to the risk priority number range to which the risk priority number belongs as the target risk assessment level; and determining the maintenance strategy corresponding to the target risk assessment level as the maintenance strategy for abnormal rollers.

[0129] For each measuring point, the risk priority number range to which the risk priority number corresponding to the measuring point belongs is determined from the risk priority number ranges corresponding to several preset risk assessment levels, and the risk assessment level corresponding to the risk priority number range to which the risk priority number corresponding to the measuring point belongs is determined as the target risk assessment level corresponding to the measuring point, and the maintenance strategy corresponding to the target risk assessment level corresponding to the measuring point is determined as the maintenance strategy for the roller within the measured range of the measuring point.

[0130] The following table shows an example of several preset risk assessment levels, risk priority number ranges corresponding to the several risk assessment levels, and maintenance strategies corresponding to the several risk assessment levels:

[0131] Table 1 Examples of several risk assessment levels and corresponding risk priority ranges and maintenance strategies

[0132]

[0133] It should be noted that the RPN in the above table th1 >RPN th2 .

[0134] For example, the risk priority number corresponding to a measurement point is greater than the RPN th1According to the above table, the risk assessment level corresponding to the measuring point can be determined as level one maintenance, and the maintenance strategy corresponding to level one maintenance is immediate shutdown maintenance. It can be determined that the maintenance strategy for the rollers within the measuring range of the measuring point is immediate shutdown maintenance.

[0135] After the maintenance strategy is determined, it can be output to the equipment management personnel.

[0136] The above describes the belt conveyor roller abnormality detection method provided in the embodiment of the present application. The following describes the device corresponding to the belt conveyor roller abnormality detection method.

[0137] See also Figure 6 , Figure 6 A structural schematic diagram of a roller abnormality detection device for a belt conveyor provided in an embodiment of the present application, the roller abnormality detection device for the belt conveyor may include: a roller operation data acquisition module 601, a roller abnormality diagnosis module 602 and a roller abnormality warning module 603.

[0138] The roller operation data acquisition module 601 is used to obtain the multi-dimensional roller operation data at the current detection moment using the sensor optical fiber arranged on the roller frame side of the belt conveyor.

[0139] The roller abnormality diagnosis module 602 is used to perform abnormality diagnosis on the rollers of the belt conveyor according to the roller operation data of each dimension at the current detection moment, so as to obtain roller abnormality diagnosis results corresponding to multiple dimensions, and determine the final roller abnormality diagnosis result according to the roller abnormality diagnosis results corresponding to the multiple dimensions.

[0140] The roller abnormality warning module 603 is used to issue a roller abnormality warning when the final roller abnormality diagnosis result indicates that the roller is abnormal.

[0141] In a possible implementation, the multi-dimensional roller operation data includes roller operation data in any two or all of the following dimensions: vibration dimension, sound dimension, and temperature dimension.

[0142] In a possible implementation, the roller operation data acquisition module 601 is specifically used to:

[0143] At the current detection moment, an optical signal is sent to a sensing optical fiber disposed on the roller frame side of the belt conveyor;

[0144] Receive the optical signal reflected by the sensing optical fiber, which contains the roller vibration information, roller sound information and roller temperature information;

[0145] The received optical signal is demodulated to obtain the multi-dimensional roller operation data at the current detection moment.

[0146] In a possible implementation, the roller abnormality diagnosis result corresponding to any dimension can indicate whether the roller is abnormal and the specific abnormality category when it is abnormal.

[0147] The belt conveyor roller abnormality detection device may further include: a maintenance strategy determination module 604 .

[0148] The maintenance strategy determination module 604 is used to determine the risk priority number according to the roller abnormality diagnosis results corresponding to multiple dimensions when the final roller abnormality diagnosis result indicates that the roller is abnormal, and determine the roller maintenance strategy according to the risk priority number.

[0149] In a possible implementation, the roller operation data acquisition module 601 is specifically used to:

[0150] By using a plurality of optical fiber acquisition units of the sensing optical fiber arranged on the roller frame side of the belt conveyor, multi-dimensional roller operation data of a plurality of measuring points at the current detection moment are acquired.

[0151] The roller abnormality diagnosis module 602 performs abnormality diagnosis on the rollers of the belt conveyor according to the roller operation data of each dimension at the current detection moment to obtain roller abnormality diagnosis results corresponding to multiple dimensions, which is specifically used for:

[0152] For each measuring point, according to the roller operation data of each dimension at the current detection moment of the measuring point, the roller abnormality diagnosis within the measuring range of the measuring point is performed to obtain the roller abnormality diagnosis results corresponding to the measuring point in multiple dimensions.

[0153] In a possible implementation, the multi-dimensional roller operation data includes roller operation data in the vibration dimension. The roller abnormality diagnosis module 602 performs abnormality diagnosis on the rollers within the measurement range of the measurement point according to the roller operation data in the vibration dimension at the current detection moment of the measurement point to obtain the roller abnormality diagnosis result corresponding to the measurement point in the vibration dimension, specifically for:

[0154] Acquire the roller operation data of the measuring point sequence corresponding to the measuring point in the vibration dimension from the roller operation data at the previous detection moment, and obtain the historical roller vibration data of the measuring point, wherein the measuring point sequence corresponding to the measuring point includes the measuring point and the adjacent measuring points of the measuring point;

[0155] Perform fast Fourier transform on the historical roller vibration data of the measuring point and the current roller vibration data of the measuring point respectively, to obtain the historical spectrum line amplitude feature set of the measuring point and the current spectrum line amplitude feature set of the measuring point, wherein the current roller vibration data of the measuring point is the roller operation data in the vibration dimension at the current detection moment of the measuring point sequence corresponding to the measuring point;

[0156] According to the historical spectrum line amplitude feature set of the measuring point and the current spectrum line amplitude feature set of the measuring point, a feature distribution difference value between the current roller vibration data of the measuring point and the historical roller vibration data of the measuring point is determined to obtain a feature distribution difference value corresponding to the measuring point;

[0157] According to the characteristic distribution difference value corresponding to the measuring point, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension.

[0158] In a possible implementation, the roller abnormality diagnosis module 602 performs abnormality diagnosis on the roller within the measured range of the measuring point according to the characteristic distribution difference value corresponding to the measuring point to obtain the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension, specifically for:

[0159] The characteristic distribution difference value corresponding to the measuring point is input into a pre-trained first abnormality diagnosis model to obtain the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension output by the first abnormality diagnosis model.

[0160] The first abnormality diagnosis model is trained by using first training samples marked with abnormalities and first training samples marked with specific abnormality categories, and the first training samples are feature distribution difference values ​​corresponding to the measurement points.

[0161] In a possible implementation, the multi-dimensional roller operation data includes roller operation data in the sound dimension. The roller abnormality diagnosis module 602 performs abnormality diagnosis on the rollers within the measurement range of the measurement point according to the roller operation data in the sound dimension at the current detection moment of the measurement point to obtain the roller abnormality diagnosis result corresponding to the measurement point in the sound dimension, specifically for:

[0162] The roller operation data of the measuring point in the sound dimension at the current detection moment is input into the pre-trained second abnormality diagnosis model to obtain the roller abnormality diagnosis result of the measuring point in the sound dimension output by the second abnormality diagnosis model.

[0163] The second abnormality diagnosis model is trained by using second training samples marked with or without abnormalities and second training samples marked with specific abnormality categories, and the second training samples are roller operation data of the measuring points in the sound dimension.

[0164] In a possible implementation, the multi-dimensional roller operation data includes roller operation data in the temperature dimension. The roller abnormality diagnosis module 602 performs abnormality diagnosis on the rollers within the measurement range of the measurement point according to the roller operation data in the temperature dimension at the current detection moment of the measurement point to obtain the roller abnormality diagnosis result corresponding to the measurement point in the temperature dimension, specifically for:

[0165] By comparing the roller operation data of the current detection moment of the measuring point in the temperature dimension with the preset temperature threshold, the roller abnormality diagnosis result corresponding to the measuring point in the temperature dimension is determined.

[0166] In a possible implementation, when the maintenance strategy determining module 604 determines the roller maintenance strategy according to the risk priority number, it is specifically used to:

[0167] Determining the risk priority number range to which the risk priority number belongs from the risk priority number ranges respectively corresponding to several preset risk assessment levels, wherein the several risk assessment levels also respectively correspond to maintenance strategies;

[0168] Determine the risk assessment level corresponding to the risk priority number range to which the risk priority number belongs as the target risk assessment level;

[0169] The maintenance strategy corresponding to the target risk assessment level is determined as the maintenance strategy for the abnormal roller.

[0170] The roller abnormality detection device for a belt conveyor provided in an embodiment of the present application first utilizes a sensing optical fiber arranged on the roller frame side of the belt conveyor to obtain the multi-dimensional roller operation number at the current detection moment, and then performs abnormal diagnosis on the rollers of the belt conveyor based on the roller operation data of each dimension at the current detection moment to obtain roller abnormality diagnosis results corresponding to the multiple dimensions, and then determines the final roller abnormality diagnosis result based on the roller abnormality diagnosis results corresponding to the multiple dimensions. If the final roller abnormality diagnosis result indicates that the roller is abnormal, a roller abnormality warning is issued. The belt conveyor roller abnormality detection device provided in the embodiment of the present application, on the one hand, automatically realizes the belt conveyor roller abnormality detection. Since the detection process does not require human participation, it avoids the problems caused by manual detection (such as the problem of human subjective factors affecting the detection effect). On the other hand, the roller operation data is obtained by using sensor optical fiber. Since the sensor optical fiber is arranged on the roller frame side of the belt conveyor, there is no need to modify the roller, and the implementation complexity and subsequent maintenance complexity are low, and the cost is not high. On the other hand, multi-dimensional roller operation data is obtained, and then the roller abnormality diagnosis is performed based on the multi-dimensional roller operation data. The abnormality diagnosis based on the multi-dimensional roller operation data can obtain a more accurate abnormality diagnosis result.

[0171] An embodiment of the present application also provides a fiber optic signal processing device, which may include: at least one processor, at least one communication interface, at least one memory and at least one communication bus.

[0172] In the embodiment of the present application, the number of the processor, the communication interface, the memory, and the communication bus is at least one, and the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0173] The processor may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application;

[0174] The memory may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0175] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to implement the steps of the belt conveyor roller abnormality detection method provided in the above embodiment.

[0176] An embodiment of the present application also provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of the belt conveyor roller abnormality detection method provided in the above embodiment.

[0177] An embodiment of the present application also provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the steps of the belt conveyor roller abnormality detection method provided in the above embodiment.

[0178] The present application also provides a belt conveyor roller abnormality detection system, such as Figure 7 As shown, it may include a sensing optical fiber 701 and an optical fiber signal processing device 702 connected to the sensing optical fiber 701, wherein the sensing optical fiber 701 is arranged on the roller frame side of the belt conveyor.

[0179] The optical fiber signal processing device 702 is used to detect abnormalities on the rollers of the belt conveyor using the belt conveyor roller abnormality detection method provided in the above embodiment.

[0180] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0181] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0182] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0183] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A method for detecting abnormality of rollers of a belt conveyor, characterized in that: include: Using a sensing optical fiber disposed on the roller frame side of the belt conveyor, the multi-dimensional roller operation data at the current detection moment is obtained; According to the roller operation data of each dimension at the current detection moment, abnormality diagnosis is performed on the roller of the belt conveyor to obtain roller abnormality diagnosis results corresponding to multiple dimensions respectively; Determine a final roller abnormality diagnosis result according to the roller abnormality diagnosis results corresponding to the multiple dimensions; If the final roller abnormality diagnosis result indicates that the roller is abnormal, a roller abnormality warning is issued.

2. The belt conveyor roller abnormality detection method according to claim 1, characterized in that: The multi-dimensional roller operation data includes roller operation data in any two or all of the following dimensions: vibration dimension, sound dimension, and temperature dimension.

3. The belt conveyor roller abnormality detection method according to claim 1, characterized in that: The method uses a sensing optical fiber disposed on the roller frame side of the belt conveyor to obtain multi-dimensional roller operation data at the current detection time, including: Sending an optical signal to a sensing optical fiber disposed on the roller frame side of the belt conveyor at a current detection moment; receiving the optical signal reflected back by the sensing optical fiber and carrying the roller vibration information, roller sound information and roller temperature information; The received optical signal is demodulated to obtain the multi-dimensional roller operation data at the current detection moment.

4. The belt conveyor roller abnormality detection method according to claim 1, characterized in that: The roller abnormality diagnosis result corresponding to any dimension can indicate whether the roller is abnormal and the specific abnormality category when it is abnormal; The belt conveyor roller abnormality detection method also includes: If the final roller abnormality diagnosis result indicates that the roller is abnormal, determining a risk priority number according to the roller abnormality diagnosis results corresponding to the multiple dimensions respectively; According to the risk priority number, the roller maintenance strategy is determined.

5. The belt conveyor roller abnormality detection method according to claim 1, characterized in that: The method uses a sensing optical fiber disposed on the roller frame side of the belt conveyor to obtain multi-dimensional roller operation data at the current detection time, including: Using multiple optical fiber acquisition units of the sensing optical fiber arranged on the roller frame side of the belt conveyor, multi-dimensional roller operation data of multiple measuring points at the current detection time are obtained; According to the roller operation data of each dimension at the current detection moment, abnormality diagnosis is performed on the roller of the belt conveyor to obtain roller abnormality diagnosis results corresponding to multiple dimensions, including: For each measuring point, according to the roller operation data of each dimension at the current detection moment of the measuring point, the roller abnormality diagnosis within the measuring range of the measuring point is performed to obtain the roller abnormality diagnosis results corresponding to the measuring point in multiple dimensions.

6. The belt conveyor roller abnormality detection method according to claim 5, characterized in that: The multi-dimensional roller operation data includes roller operation data in a vibration dimension; According to the roller operation data of the measuring point in the vibration dimension at the current detection time, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension, including: Acquire the roller operation data of the measuring point sequence corresponding to the measuring point in the vibration dimension from the roller operation data at the previous detection moment, and obtain the historical roller vibration data of the measuring point, wherein the measuring point sequence corresponding to the measuring point includes the measuring point and the adjacent measuring points of the measuring point; Performing fast Fourier transform on the historical roller vibration data of the measuring point and the current roller vibration data of the measuring point respectively, so as to obtain the historical spectrum line amplitude feature set of the measuring point and the current spectrum line amplitude feature set of the measuring point, wherein the current roller vibration data of the measuring point is the roller operation data in the vibration dimension at the current detection moment of the measuring point sequence corresponding to the measuring point; According to the historical spectrum line amplitude feature set of the measuring point and the current spectrum line amplitude feature set of the measuring point, a feature distribution difference value between the current roller vibration data of the measuring point and the historical roller vibration data of the measuring point is determined to obtain a feature distribution difference value corresponding to the measuring point; According to the characteristic distribution difference value corresponding to the measuring point, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension.

7. The belt conveyor roller abnormality detection method according to claim 6, characterized in that: According to the characteristic distribution difference value corresponding to the measuring point, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension, including: Inputting the characteristic distribution difference value corresponding to the measuring point into a pre-trained first abnormality diagnosis model, and obtaining the roller abnormality diagnosis result corresponding to the measuring point in the vibration dimension output by the first abnormality diagnosis model; The first abnormality diagnosis model is trained by using first training samples marked with abnormalities and first training samples marked with specific abnormality categories, and the first training samples are feature distribution difference values ​​corresponding to the measurement points.

8. The belt conveyor roller abnormality detection method according to claim 5, characterized in that: The multi-dimensional roller operation data includes roller operation data in the sound dimension; According to the roller operation data of the measuring point in the sound dimension at the current detection time, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the sound dimension, including: Inputting the roller operation data of the measuring point in the sound dimension at the current detection moment into the pre-trained second abnormality diagnosis model, obtaining the roller abnormality diagnosis result corresponding to the measuring point in the sound dimension output by the second abnormality diagnosis model; The second abnormality diagnosis model is trained by using second training samples marked with or without abnormalities and second training samples marked with specific abnormality categories, and the second training samples are roller operation data of the measuring points in the sound dimension.

9. The belt conveyor roller abnormality detection method according to claim 5, characterized in that: The multi-dimensional roller operation data includes roller operation data in a temperature dimension; According to the roller operation data of the measuring point in the temperature dimension at the current detection time, the roller within the measuring range of the measuring point is diagnosed abnormally to obtain the roller abnormality diagnosis result corresponding to the measuring point in the temperature dimension, including: By comparing the roller operation data of the current detection moment of the measuring point in the temperature dimension with the preset temperature threshold, the roller abnormality diagnosis result corresponding to the measuring point in the temperature dimension is determined.

10. The belt conveyor roller abnormality detection method according to claim 4, characterized in that: Determining the roller maintenance strategy according to the risk priority number includes: Determining the risk priority number range to which the risk priority number belongs from the risk priority number ranges respectively corresponding to several preset risk assessment levels, wherein the several risk assessment levels also respectively correspond to maintenance strategies; Determine the risk assessment level corresponding to the risk priority number range to which the risk priority number belongs as the target risk assessment level; The maintenance strategy corresponding to the target risk assessment level is determined as the maintenance strategy for the abnormal roller.

11. A belt conveyor roller abnormality detection device, characterized in that: include: Roller operation data acquisition module, roller abnormality diagnosis module and roller abnormality early warning module; The roller operation data acquisition module is used to acquire multi-dimensional roller operation data at the current detection moment by using a sensing optical fiber arranged on the roller frame side of the belt conveyor; The roller abnormality diagnosis module is used to perform abnormality diagnosis on the roller of the belt conveyor according to the roller operation data of each dimension at the current detection moment, so as to obtain roller abnormality diagnosis results corresponding to multiple dimensions respectively, and determine the final roller abnormality diagnosis result according to the roller abnormality diagnosis results corresponding to the multiple dimensions respectively; The roller abnormality warning module is used to issue a roller abnormality warning when the final roller abnormality diagnosis result indicates that the roller is abnormal.

12. An optical fiber signal processing device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the optical fiber signal processing device can implement the steps of the belt conveyor roller abnormality detection method as described in any one of claims 1 to 10.

13. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of the belt conveyor roller abnormality detection method as described in any one of claims 1 to 10.

14. A computer program product, characterized in that It includes computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the steps of the belt conveyor roller abnormality detection method as described in any one of claims 1 to 10.

15. A belt conveyor roller abnormality detection system, characterized in that: include: A sensing optical fiber, and an optical fiber signal processing device connected to the sensing optical fiber, wherein the sensing optical fiber is arranged on the roller frame side of the belt conveyor; The optical fiber signal processing device is used to perform abnormality detection on the rollers of the belt conveyor using the belt conveyor roller abnormality detection method as described in any one of claims 1 to 10.

Images