Belt conveyor idler abnormal detection method, related device and related system

Abstract

The present application discloses a method for detecting abnormal idlers of a belt conveyor, related devices and related systems, which relates to the technical field of abnormal detection. The method includes: obtaining multi-dimensional idler operation data at the current detection moment by using a sensing optical fiber arranged on the side of the idler rack of the belt conveyor; performing abnormal diagnosis on the idlers of the belt conveyor according to the idler operation data of each dimension at the current detection moment to obtain idler abnormal diagnosis results respectively corresponding to multiple dimensions; determining the final idler abnormal diagnosis result according to the idler abnormal diagnosis results respectively corresponding to multiple dimensions; and if the final idler abnormal diagnosis result indicates that the idler is abnormal, an idler abnormal warning is issued. The method for detecting abnormal idlers of the belt conveyor disclosed in the present application can automatically detect abnormal idlers of the belt conveyor, without the need to transform the idlers, and has relatively low implementation complexity and later maintenance complexity, and good detection effect.

Description

Technical Field

[0001] The present application relates to the technical field of anomaly detection, and in particular, to a method for detecting anomalies of idlers of a belt conveyor, related devices, and related systems. Background Art

[0002] A belt conveyor is a typical device with rotation as the main form of motion, which includes a motor, a reducer, a redirecting roller, a driving roller, and thousands of groups of idlers, etc. As the most widely used rotating component of a belt conveyor, once an idler has an anomaly and is not replaced in time, it is easy to generate heat by friction, ignite, and tear the conveyor belt, thereby causing equipment damage and production stoppage, resulting in significant economic losses, and even possible casualties. It can be seen that it is crucial to detect anomalies of the idlers of a belt conveyor.

[0003] Currently, the main method for detecting anomalies of the idlers of a belt conveyor is manual inspection, that is, during the operation of the belt conveyor, the inspection personnel rely on personal work experience to check whether the idlers are abnormal by means of knocking, visual inspection, etc.

[0004] Since the manual inspection method mainly relies on the personal qualities, work attitudes, and experience of the inspection personnel, the subjectivity of the manual inspection method is relatively strong, and it is easy to miss or misdetect. Summary of the Invention

[0005] In view of this, the present application provides a method for detecting anomalies of idlers of a belt conveyor, related devices, and related systems, which is used to solve the problem that the subjectivity of the manual inspection method is relatively strong, resulting in easy omission or misdetection. The technical solutions are as follows:

[0006] The first aspect of the present application provides a method for detecting anomalies of idlers of a belt conveyor, including:

[0007] Obtaining multi-dimensional idler operation data at the current detection moment by using a sensing optical fiber arranged on the side of the idler rack of the belt conveyor;

[0008] Performing anomaly diagnosis on the idlers of the belt conveyor according to the idler operation data of each dimension at the current detection moment to obtain idler anomaly diagnosis results corresponding to multiple dimensions respectively;

[0009] Determining the final idler anomaly diagnosis result according to the idler anomaly diagnosis results corresponding to the multiple dimensions respectively;

[0010] If the final idler anomaly diagnosis result indicates that the idler is abnormal, an idler anomaly warning is issued.

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

[0012] In a possible implementation, obtaining the multi-dimensional idler running data at the current detection moment by using the sensing optical fiber arranged on the idler rack side of the belt conveyor includes:

[0013] Sending an optical signal to the sensing optical fiber arranged on the idler rack side of the belt conveyor at the current detection moment;

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

[0015] Demodulating the received optical signal to obtain the multi-dimensional idler running data at the current detection moment.

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

[0017] The method for detecting idler abnormalities of the belt conveyor further includes:

[0018] If the final idler abnormal diagnosis result indicates that the idler is abnormal, then determine the risk priority number according to the idler abnormal diagnosis results corresponding to the multiple dimensions;

[0019] Determine the idler maintenance strategy according to the risk priority number.

[0020] In a possible implementation, obtaining the multi-dimensional idler running data at the current detection moment by using the sensing optical fiber arranged on the idler rack side of the belt conveyor includes:

[0021] Using multiple optical fiber acquisition units of the sensing optical fiber arranged on the idler rack side of the belt conveyor to obtain the multi-dimensional idler running data of multiple measurement points at the current detection moment;

[0022] The abnormal diagnosis of the idlers of the belt conveyor according to the idler running data of each dimension at the current detection moment to obtain the idler abnormal diagnosis results corresponding to multiple dimensions respectively includes:

[0023] For each measurement point, perform abnormal diagnosis on the idlers within the measured range of the measurement point according to the idler running data of each dimension at the current detection moment of the measurement point, so as to obtain the idler abnormal diagnosis results corresponding to the measurement point in multiple dimensions respectively.

[0024] In a possible implementation, the multi-dimensional idler running data includes the idler running data of the vibration dimension;

[0025] Based on the running data of the idler at the current detection time of this measurement point in the vibration dimension, perform abnormal diagnosis on the idlers within the range measured by this measurement point to obtain the abnormal diagnosis result of the idlers corresponding to this measurement point in the vibration dimension, including:

[0026] Obtain the running data of the idler in the vibration dimension of the measurement point sequence corresponding to this measurement point from the running data of the idler at the previous detection time to obtain the historical idler vibration data of this measurement point, where the measurement point sequence corresponding to this measurement point includes this measurement point and its adjacent measurement points;

[0027] Perform fast Fourier transform on the historical idler vibration data of this measurement point and the current idler vibration data of this measurement point respectively to obtain the historical spectral line amplitude feature set of this measurement point and the current spectral line amplitude feature set of this measurement point, where the current idler vibration data of this measurement point is the running data of the idler at the current detection time of the measurement point sequence corresponding to this measurement point in the vibration dimension;

[0028] According to the historical spectral line amplitude feature set of this measurement point and the current spectral line amplitude feature set of this measurement point, determine the characteristic distribution difference value between the current idler vibration data of this measurement point and the historical idler vibration data of this measurement point to obtain the characteristic distribution difference value corresponding to this measurement point;

[0029] According to the characteristic distribution difference value corresponding to this measurement point, perform abnormal diagnosis on the idlers within the range measured by this measurement point to obtain the abnormal diagnosis result of the idlers corresponding to this measurement point in the vibration dimension.

[0030] In a possible implementation manner, the performing abnormal diagnosis on the idlers within the range measured by this measurement point according to the characteristic distribution difference value corresponding to this measurement point to obtain the abnormal diagnosis result of the idlers corresponding to this measurement point in the vibration dimension includes:

[0031] Input the characteristic distribution difference value corresponding to this measurement point into a pre-trained first abnormal diagnosis model to obtain the abnormal diagnosis result of the idlers corresponding to this measurement point in the vibration dimension output by the first abnormal diagnosis model;

[0032] Wherein, the first abnormal diagnosis model is trained using a first training sample labeled with whether there is an abnormality and a first training sample labeled with a specific abnormality category, and the first training sample is the characteristic distribution difference value corresponding to the measurement point.

[0033] In a possible implementation manner, the multi-dimensional idler running data includes the running data of the idler in the sound dimension;

[0034] Based on the running data of the idler at the current detection time of this measurement point in the sound dimension, perform abnormal diagnosis on the idlers within the range measured by this measurement point to obtain the abnormal diagnosis result of the idlers corresponding to this measurement point in the sound dimension, including:

[0035] Input the idler running data of the measuring point at the current detection moment in the sound dimension into the pre-trained second anomaly diagnosis model to obtain the idler anomaly diagnosis result corresponding to the measuring point in the sound dimension output by the second anomaly diagnosis model;

[0036] Among them, the second anomaly diagnosis model is trained using the second training samples labeled with whether there is an anomaly and the second training samples labeled with specific anomaly categories, and the second training samples are the idler running data of the measuring point in the sound dimension.

[0037] In a possible implementation manner, the multi-dimensional idler running data includes the idler running data in the temperature dimension;

[0038] According to the idler running data of the measuring point at the current detection moment in the temperature dimension, perform anomaly diagnosis on the idlers within the range measured by the measuring point to obtain the idler anomaly diagnosis result corresponding to the measuring point in the temperature dimension, including:

[0039] Determine the idler anomaly diagnosis result corresponding to the measuring point in the temperature dimension by comparing the idler running data of the measuring point at the current detection moment in the temperature dimension with a preset temperature threshold.

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

[0041] Determine 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, where 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] Determine the maintenance strategy corresponding to the target risk assessment level as the maintenance strategy for the abnormal idlers.

[0044] The second aspect of the present application provides an idler anomaly detection device for a belt conveyor, including: an idler running data acquisition module, an idler anomaly diagnosis module, and an idler anomaly warning module;

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

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

[0047] The idler abnormal warning module is used to issue an idler abnormal warning when the final idler abnormal diagnosis result indicates idler abnormality.

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

[0049] The memory is used to store a computer program;

[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 idler abnormal detection methods for the 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 one of the above-mentioned idler abnormal detection methods for the belt conveyor.

[0052] A fifth aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions run on an electronic device, the electronic device can implement the steps of any one of the above-mentioned idler abnormal detection methods for the belt conveyor.

[0053] A sixth aspect of the present application provides an idler abnormal detection system for a belt conveyor, including: 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 side of the idler rack of the belt conveyor;

[0054] The optical fiber signal processing device is used to perform abnormal detection on the idlers of the belt conveyor by using any one of the above-mentioned idler abnormal detection methods for the belt conveyor.

[0055] With the above technical solution, the method for detecting abnormal idlers of a belt conveyor provided by this application first uses a sensing optical fiber arranged on the side of the idler rack of the belt conveyor to obtain multi-dimensional idler operation data at the current detection moment. Then, based on the idler operation data of each dimension at the current detection moment, an abnormal diagnosis is performed on the idlers of the belt conveyor to obtain abnormal diagnosis results corresponding to multiple dimensions respectively. Next, based on the abnormal diagnosis results corresponding to multiple dimensions respectively, the final abnormal diagnosis result of the idlers is determined. If the final abnormal diagnosis result indicates that the idlers are abnormal, an abnormal idler warning is issued. For the method for detecting abnormal idlers of a belt conveyor provided by this application, on the one hand, it automatically realizes the detection of abnormal idlers of the belt conveyor. Since the detection process does not require manual participation, it avoids the problems brought by manual detection (such as the problem of the influence of human subjective factors on the detection effect). On the other hand, the sensing optical fiber is used to obtain idler operation data. Since the sensing optical fiber is arranged on the side of the idler rack of the belt conveyor, there is no need to modify the idlers, and the implementation complexity and the later maintenance complexity are relatively low, and the cost is not high. On the other hand, multi-dimensional idler operation data is obtained, and then an abnormal diagnosis is performed on the idlers based on the multi-dimensional idler operation data. Performing an abnormal diagnosis based on the multi-dimensional idler operation data can obtain a relatively accurate abnormal diagnosis result. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the provided drawings without creative efforts.

[0057] Figure 1 It is a schematic flowchart of a method for detecting abnormal idlers of a belt conveyor provided by an embodiment of this application;

[0058] Figure 2 It is a schematic diagram of deploying a sensing optical fiber on the side of the idler rack of a belt conveyor provided by an embodiment of this application;

[0059] Figure 3 It is a schematic diagram of a three-core sensing optical fiber provided by an embodiment of this application;

[0060] Figure 4 For an embodiment of this application, according to the idler operation data of the vibration dimension at the current detection moment at measurement point P k to perform an abnormal diagnosis on the idlers within the measured range of measurement point P k to obtain a schematic flowchart of the abnormal diagnosis result corresponding to the vibration dimension at measurement point P k ;

[0061] Figure 5 Schematic flowchart of another method for detecting abnormal idlers of a belt conveyor provided by an embodiment of the present application;

[0062] Figure 6 Schematic structural diagram of an idler abnormal detection device for a belt conveyor provided by an embodiment of the present application;

[0063] Figure 7 Schematic structural diagram of an idler abnormal detection system for a belt conveyor provided by an embodiment of the present application. Detailed implementation manners

[0064] The embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. The terms used in the embodiments of the present application are only for explaining the specific embodiments of the present application, rather than aiming to limit the present application.

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

[0066] The terms "first", "second", etc. in the description and claims of the present application and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, which is only a way of distinguishing objects with the same attributes when describing the embodiments of the present application. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product or device including a series of units does not have to be limited to those units, but may include other units not clearly listed or inherent to these processes, methods, products or devices.

[0067] In view of the strong subjectivity of the existing manual inspection method, which is prone to missed inspections or misjudgments, research has been carried out. The initial idea was to use a pickup to collect the idler sound signals of the belt conveyor, obtain the signal feature components of the collected idler sound signals, and determine whether the idlers of the belt conveyor are abnormal by comparing the signal feature components with a set threshold.

[0068] Since the above idea does not require manual inspection, it avoids the influence of human subjective factors. However, the detection effect of the above idea is not good (prone to false alarms), and moreover, the pickup range of the pickup is limited. When the length of the belt conveyor is large, a large number of pickups need to be deployed along the line (for example, for a 10 km belt conveyor, even if one pickup is deployed every 10 m, 1000 pickups need to be deployed), so the cost is relatively high.

[0069] In view of the poor detection effect and high detection cost of the above-mentioned idea, research was continued, and during the research process, a roller abnormal detection scheme based on temperature and speed sensors was conceived. That is, temperature and speed sensors are deployed in a contact manner on the rollers of the belt conveyor, and the temperature signal and rotation speed signal of the rollers are collected by the temperature and speed sensors deployed on the rollers. By comparing the collected temperature signal with a preset temperature threshold and comparing the collected rotation speed signal with a preset rotation speed threshold, it is determined whether the rollers of the belt conveyor are abnormal.

[0070] Research on the above-mentioned roller abnormal detection scheme based on temperature and speed sensors found that, on the one hand, deploying temperature and speed sensors in a contact manner on the rollers of the belt conveyor requires simple modification of the rollers, which means that the transportation operation process of the belt conveyor needs to be stopped, and this is unacceptable to the production unit. On the other hand, since temperature and speed sensors need to be installed on each roller, the cost is very high, and moreover, the subsequent electricity consumption and maintenance complexity are also relatively high.

[0071] In view of the many problems existing in the above-mentioned roller abnormal detection scheme based on temperature and speed sensors, research was continued, and through continuous research, a roller abnormal detection method for belt conveyors with better effects was finally proposed.

[0072] Next, the roller abnormal detection method provided by this application will be introduced through the following embodiments.

[0073] Please refer to Figure 1 , which shows a schematic flowchart of the roller abnormal detection method for belt conveyors provided by the embodiments of this application. The roller abnormal detection method may include:

[0074] Step S101: Use the sensing optical fiber provided on the side of the roller rack of the belt conveyor to obtain 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 sensing optical fibers on the side of the roller rack of the belt conveyor. As Figure 2 shown, use the sensing optical fiber to obtain the roller operation data of the belt conveyor. In order to obtain a better detection effect, this embodiment obtains multi-dimensional roller operation data.

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

[0077] In a possible implementation manner, the process of obtaining the multi-dimensional idler running data at the current detection moment by using the sensing optical fiber arranged on the idler rack side of the belt conveyor may include: transmitting an optical signal to the sensing optical fiber arranged on the idler rack side of the belt conveyor at the current detection moment; receiving the optical signal reflected back by the sensing optical fiber and carrying the idler vibration information, idler sound information, and idler temperature information; and demodulating the received optical signal to obtain the multi-dimensional idler running data at the current detection moment.

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

[0079] Step S102: Based on the running data of the idlers in each dimension at the current detection moment, perform abnormal diagnosis on the idlers of the belt conveyor to obtain the idler abnormal diagnosis results corresponding to each dimension respectively.

[0080] Considering that the accuracy of abnormal diagnosis of the idlers of the belt conveyor based on the running data of the idlers in a single dimension is not high, in order to obtain a higher accuracy of abnormal diagnosis, in this embodiment, the running data of the idlers in multiple dimensions are obtained, and then the idlers of the belt conveyor are abnormally diagnosed according to the running data of the idlers in each dimension, so as to obtain the idler abnormal diagnosis results corresponding to each dimension respectively.

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

[0082] Step S103: Determine the final idler abnormal diagnosis result according to the idler abnormal diagnosis results corresponding to each dimension respectively.

[0083] In order to obtain a relatively accurate idler abnormal diagnosis result, in this embodiment, the final idler abnormal diagnosis result is determined by combining the idler abnormal diagnosis results corresponding to each dimension respectively.

[0084] There are various implementation methods for determining the final idler abnormal diagnosis result according to the idler abnormal diagnosis results corresponding to each dimension respectively. For example, if the idler abnormal diagnosis result in the vibration dimension indicates that the idler is abnormal, and the idler abnormal diagnosis result in the sound dimension indicates that the idler is abnormal, then it is determined that the idler is abnormal. Another example is that if the idler abnormal diagnosis result in the vibration dimension indicates that the idler is abnormal, the idler abnormal diagnosis result in the sound dimension indicates that the idler is abnormal, and the idler abnormal diagnosis result corresponding to the temperature dimension indicates that the idler is abnormal, then it is determined that the idler is abnormal. The specific strategy for determining the final idler abnormal diagnosis result according to the idler abnormal diagnosis results corresponding to each dimension respectively can be determined according to the actual application scenario.

[0085] Step S104: If the final idler abnormal diagnosis result indicates that the idlers of the belt conveyor are abnormal, then issue an idler abnormal warning.

[0086] If the abnormal diagnosis result of the idler indicates that the idler of the belt conveyor is abnormal, an idler abnormal warning is sent to the equipment management personnel.

[0087] The idler abnormal detection method of the belt conveyor provided by the embodiment of the present application first uses the sensing optical fiber arranged on the side of the idler frame of the belt conveyor to obtain the multi-dimensional idler operation data at the current detection moment, and then diagnoses the abnormality of the idler of the belt conveyor according to the idler operation data of each dimension at the current detection moment to obtain the idler abnormal diagnosis results corresponding to multiple dimensions respectively. Then, according to the idler abnormal diagnosis results corresponding to multiple dimensions respectively, the final idler abnormal diagnosis result is determined. If the final idler abnormal diagnosis result indicates that the idler is abnormal, an idler abnormal warning is sent. For the idler abnormal detection method of the belt conveyor provided by the embodiment of the present application, on the one hand, the automatic detection of the idler abnormality of the belt conveyor is realized. Since the detection process does not require manual participation, the problems brought by manual detection (such as the problem that the detection effect is affected by subjective factors) are avoided. On the other hand, the sensing optical fiber is used to obtain the idler operation data. Since the sensing optical fiber is arranged on the side of the idler frame of the belt conveyor, there is no need to transform the idler, and the implementation complexity and the later maintenance complexity are relatively low, and the cost is not high. On the other hand, multi-dimensional idler operation data is obtained, and then the idler is diagnosed for abnormality according to the multi-dimensional idler operation data. The abnormal diagnosis based on the multi-dimensional idler operation data can obtain a relatively accurate idler abnormal diagnosis result.

[0088] In another embodiment of the present application, the specific implementation processes of "Step S101: Use the sensing optical fiber arranged on the side of the idler frame of the belt conveyor to obtain the multi-dimensional idler operation data at the current detection moment" and "Step S102: According to the idler operation data of each dimension at the current detection moment, diagnose the abnormality of the idler of the belt conveyor to obtain the idler abnormal diagnosis results corresponding to multiple dimensions respectively" in the above embodiment are introduced.

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

[0090] As Figure 2 shown, the sensing optical fiber in this embodiment includes multiple optical fiber acquisition units, which are obtained by winding a sensing optical fiber multiple times at different positions on the side of the idler frame. The position where each optical fiber acquisition unit is located is a measurement point. The multi-dimensional idler operation data of multiple measurement points at the current detection moment can be obtained by using the multiple optical fiber acquisition units of the sensing optical fiber.

[0091] The process of performing abnormal diagnosis on the idlers of a belt conveyor based on the idler operation data of each dimension at the current detection moment to obtain the idler abnormal diagnosis results corresponding to multiple dimensions may include: for each measuring point, performing abnormal diagnosis on the idlers within the range measured by the measuring point according to the idler operation data of each dimension at the current detection moment of the measuring point, so as to obtain the idler abnormal diagnosis results corresponding to the measuring point in multiple dimensions.

[0092] Next, taking the idler operation data including the vibration dimension, the sound dimension, and the temperature dimension as an example of the multi-dimensional operation data, according to the idler operation data of a measuring point P k (the k-th measuring point) at the current detection moment in each dimension, the process of performing abnormal diagnosis on the idlers within the range measured by the measuring point P k to obtain the idler abnormal diagnosis results corresponding to the measuring point P k in multiple dimensions will be introduced.

[0093] First, the specific implementation process of performing abnormal diagnosis on the idlers within the range measured by the measuring point P k according to the idler operation data at the current detection moment in the vibration dimension will be introduced to obtain the idler abnormal diagnosis result corresponding to the measuring point P k in the vibration dimension. As k shown, it may include: Figure 4 shown, it may include:

[0094] Step S401: Obtain the idler operation data of the measuring point sequence corresponding to the measuring point P k in the vibration dimension from the multi-dimensional idler operation data of the previous detection moment to obtain the historical idler vibration data of the measuring point P k .

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

[0096] In this embodiment, the idler operation data of the measuring point P kThe running data of the idler at the corresponding measuring point sequence in the vibration dimension, so as to obtain the measuring point P k 's historical idler vibration data.

[0097] Step S402: Perform fast Fourier transform on the historical idler vibration data of the measuring point P k and the current idler vibration data of the measuring point P k respectively, to obtain the historical spectral line amplitude feature set of the measuring point P k and the current spectral line amplitude feature set of the measuring point P k .

[0098] Among them, the current idler vibration data of the measuring point P k is the running data of the idler at the current detection moment of the measuring point sequence corresponding to the measuring point P k in the vibration dimension.

[0099] Step S403: Determine the characteristic distribution difference value between the current idler vibration data of the measuring point P k and the historical idler vibration data of the measuring point P k according to the historical spectral line amplitude feature and the current spectral line amplitude feature of the measuring point P k , to obtain the characteristic distribution difference value corresponding to the measuring point P k k .

[0100] Specifically, the characteristic distribution difference value D k corresponding to the measuring point Pcan be calculated according to the following formula: k (1)

[0101] (1)

[0102] Among them, A is an 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 represents the historical spectral line amplitude feature set of the measuring point P k , X t k represents the current spectral line amplitude feature set of the measuring point P k , x i represents the i-th feature in X h , n h represents the number of features in X h , x j represents the j-th feature in X t k , n t represents the number of features in X t k .

[0103] Step S404: Based on the characteristic distribution difference value corresponding to the measuring point P k perform anomaly diagnosis on the idlers within the measured range of the measuring point P k to obtain the idler anomaly diagnosis result corresponding to the measuring point P k in the vibration dimension.

[0104] In a possible implementation, the process of performing anomaly diagnosis on the idlers within the measured range of the measuring point P k based on the characteristic distribution difference value corresponding to the measuring point P k to obtain the anomaly diagnosis result corresponding to the measuring point P k in the vibration dimension may include: inputting the characteristic distribution difference value corresponding to the measuring point P k into a pre-trained first anomaly diagnosis model to obtain the idler anomaly diagnosis result corresponding to the measuring point P k output by the first anomaly diagnosis model in the vibration dimension.

[0105] Among them, the first anomaly diagnosis model is trained using the constructed first training data set. The first training data set may include a number of first training samples labeled with normal or abnormal conditions and a number of first training samples labeled with specific abnormal categories. When constructing the first training data set, multiple categories can be preset, such as normal, mild anomaly, moderate anomaly, and severe anomaly, so as to obtain a number of first training samples labeled with normal or abnormal conditions, a number of first training samples labeled with mild anomaly, a number of first training samples labeled with moderate anomaly, and a number of first training samples labeled with severe anomaly, and the first training data set is composed of the above-mentioned first training samples labeled with various categories. The first training samples in the first training data set are the characteristic distribution difference values corresponding to the measuring points, and the first training samples in the first training data set can cover all measuring points.

[0106] It should be noted that the above normal, mild anomaly, moderate anomaly, and severe anomaly are only examples. This embodiment does not limit that the multiple preset categories include normal, mild anomaly, moderate anomaly, and severe anomaly. For example, the multiple preset categories can also include normal, mild anomaly, and severe anomaly, and the multiple preset categories can be set according to the actual application scenario.

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

[0108] Next, based on the running data of the idler at the current detection moment in the sound dimension of measuring point P k the idlers within the measured range of measuring point P k are subjected to anomaly diagnosis to obtain the anomaly diagnosis result of the idlers corresponding to measuring point P k in the sound dimension, and the specific implementation process will be introduced.

[0109] In a possible implementation manner, based on the running data of the idler at the current detection moment in the sound dimension of measuring point P k the idlers within the measured range of measuring point P k are subjected to anomaly diagnosis to obtain the anomaly diagnosis result of the idlers corresponding to measuring point P k in the sound dimension, and the process may include: inputting the running data of the idler at the current detection moment in the sound dimension of measuring point P k into the pre-trained second anomaly diagnosis model to obtain the anomaly diagnosis result of the idlers corresponding to measuring point P k output by the second anomaly diagnosis model in the sound dimension.

[0110] Among them, the second anomaly diagnosis model is trained using the constructed second training dataset, which may include a number of second training samples labeled with or without anomalies and a number of second training samples labeled with specific anomaly categories. When constructing the second training dataset, multiple categories can be preset (the same as those preset when constructing the first training dataset), such as no anomaly, mild anomaly, moderate anomaly, and severe anomaly, so as to obtain a number of second training samples labeled with or without anomalies, a number of second training samples labeled with mild anomalies, a number of second training samples labeled with moderate anomalies, and a number of second training samples labeled with severe anomalies, and the second training dataset is composed of the second training samples labeled with various categories above. The second training samples in the second training dataset are the idler running data of the measuring point in the sound dimension, and the second training samples in the second training dataset can cover all measuring points.

[0111] When training the second anomaly diagnosis model with the second training samples in the second training dataset, the training objective is to make the category predicted by the second anomaly diagnosis model for the second training samples tend to be consistent with the category labeled by the second training samples.

[0112] After training the second anomaly diagnosis model, the trained second anomaly diagnosis model can be used to diagnose anomalies of the idlers within the measured range of the measuring point P k at the current detection moment in the sound dimension of the idler running data. That is, the idler running data of the measuring point P k at the current detection moment in the sound dimension is input into the trained second anomaly diagnosis model. The second anomaly diagnosis model determines the target category from a preset multiple categories (such as no anomaly, mild anomaly, moderate anomaly, severe anomaly), and uses it as the anomaly diagnosis result corresponding to the measuring point P k in the sound dimension. k

[0113] Next, the specific implementation process of diagnosing anomalies of the idlers within the measured range of the measuring point P k at the current detection moment in the temperature dimension of the idler running data to obtain the idler anomaly diagnosis result corresponding to the measuring point P k in the temperature dimension will be introduced. k

[0114] In a possible implementation, the process of diagnosing anomalies of the idlers within the measured range of the measuring point P k at the current detection moment in the temperature dimension of the idler running data to obtain the idler anomaly diagnosis result corresponding to the measuring point P k in the temperature dimension may include: by inputting the idler running data of the measuring point P k at the current detection moment in the temperature dimension into k ​​Compare the running data of the idler at the current detection time in the temperature dimension with the preset temperature threshold to determine the abnormal diagnosis result of the idler corresponding to the measurement point in the temperature dimension.

[0115] Among them, the measurement point P k The running data of the idler at the current detection time in the temperature dimension is the idler temperature value, which can be obtained by measuring the idler temperature value of the measurement point P k at the current detection time and comparing it with the preset temperature threshold to determine the abnormal diagnosis result of the measurement point P k corresponding to the temperature dimension.

[0116] Exemplarily, the following categories are preset: no abnormality, mild abnormality, moderate abnormality, severe abnormality, and the temperature thresholds T th1 、T th2 、T th3 ,T th1 <T th2 <T th3 ,If the idler temperature value of the measurement point P k at the current detection time is less than T th1 ,it is determined that the abnormal diagnosis result of the idler corresponding to the measurement point in the temperature dimension is no abnormality. If the idler temperature value of the measurement point P k at the current detection time is greater than or equal to T th1 and less than T th2 ,it is determined that the abnormal diagnosis result of the idler corresponding to the measurement point in the temperature dimension is mild abnormality. If the idler temperature value of the measurement point P k at the current detection time is greater than or equal to T th2 and less than T th3 ,it is determined that the abnormal diagnosis result of the idler corresponding to the measurement point P k in the temperature dimension is moderate abnormality. If the idler temperature value of the measurement point P k at the current detection time is greater than or equal to T th3 ,it is determined that the abnormal diagnosis result of the idler corresponding to the measurement point in the temperature dimension is severe abnormality.

[0117] Through the above process, the abnormal diagnosis results of the idler corresponding to the measurement point P k in multiple dimensions can be determined respectively. In the same way, the abnormal diagnosis results of the idler corresponding to other measurement points in multiple dimensions can be obtained respectively. The abnormal diagnosis result of the idler corresponding to a measurement point in a dimension is the abnormal diagnosis result of the idler within the measured range of the measurement point in that dimension.

[0118] For each measurement point, after obtaining the abnormal diagnosis results of the idler corresponding to the measurement point in multiple dimensions respectively, the final abnormal diagnosis result of the idler corresponding to the measurement point can be determined according to the abnormal diagnosis results of the idler corresponding to the measurement point in multiple dimensions respectively, that is, the final abnormal diagnosis result of the idler within the measured range of the measurement point.

[0119] In another embodiment of the present application, as Figure 5 shown, in addition to the above steps S101 to S104, the method for detecting abnormal idlers of a belt conveyor may further include the following steps:

[0120] Step S105: If the final abnormal idler diagnosis result indicates that the idler is abnormal, determine the risk priority number according to the abnormal idler diagnosis results corresponding to multiple dimensions respectively.

[0121] As mentioned in the above embodiment, multiple optical fiber acquisition units of the sensing optical fiber arranged on the side of the idler frame of the belt conveyor can be used to obtain multi-dimensional idler operation data of multiple measurement points at the current detection moment. Furthermore, for each measurement point, abnormal diagnosis of the idlers within the range measured by this measurement point can be performed according to the idler operation data of each dimension at the current detection moment of this measurement point, so as to obtain the abnormal idler diagnosis results corresponding to this measurement point in multiple dimensions respectively. After obtaining the abnormal idler diagnosis results corresponding to this measurement point in multiple dimensions respectively, the final corresponding abnormal idler diagnosis result of this measurement point can be determined according to the abnormal idler diagnosis results corresponding to this measurement point in multiple dimensions respectively.

[0122] For each measurement point, after obtaining the final corresponding abnormal idler diagnosis result of this measurement point, if the final corresponding abnormal idler diagnosis result of this measurement point indicates that the idler is abnormal, the risk priority number can be determined according to the abnormal idler diagnosis results corresponding to this measurement point in multiple dimensions respectively (i.e., the abnormal categories).

[0123] It should be noted that the risk priority number is determined according to three impact parameters, namely severity S, occurrence rate O, and detectability D. Severity S reflects the impact degree of the abnormality (1 - 10 points), and the higher the score, the more serious the result. Occurrence rate O reflects the probability of the abnormality occurring (1 - 10 points), and the higher the score, the greater the probability of a certain abnormal category appearing. Detectability D reflects the possibility of the abnormality being detected (1 - 10 points), and the higher the score, the more difficult it is to be discovered.

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

[0125] RPN = S × O × D (2)

[0126] For each measurement point, when determining the Risk Priority Number (RPN) based on the abnormal diagnosis results (i.e., abnormal categories) of the idler corresponding to the measurement point in multiple dimensions, the specific values of the three impact parameters, severity S, occurrence rate O, and detectability D, can be determined according to the abnormal diagnosis results (i.e., abnormal categories) of the idler corresponding to the measurement point in multiple dimensions. Then, the RPN corresponding to the measurement point can be obtained according to the above formula. Rules for determining the parameter values of the three impact parameters based on the abnormal category can be preset. Furthermore, according to the abnormal diagnosis results (i.e., abnormal categories) of the idler corresponding to the measurement point in multiple dimensions, the parameter values of the three impact parameters are determined according to the preset rules.

[0127] Step S106: Determine the idler maintenance strategy according to the Risk Priority Number.

[0128] Specifically, the process of determining the idler maintenance strategy according to the Risk Priority Number may include: determining the range of the Risk Priority Number to which the Risk Priority Number belongs from the ranges of Risk Priority Numbers corresponding to several preset risk assessment levels, where several risk assessment levels also respectively correspond to maintenance strategies; determining the risk assessment level corresponding to the range of the Risk Priority Number 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 the abnormal idler.

[0129] For each measurement point, determine the range of the Risk Priority Number to which the Risk Priority Number corresponding to the measurement point belongs from the ranges of Risk Priority Numbers corresponding to several preset risk assessment levels, determine the risk assessment level corresponding to the range of the Risk Priority Number to which the Risk Priority Number corresponding to the measurement point belongs as the target risk assessment level corresponding to the measurement point, and determine the maintenance strategy corresponding to the target risk assessment level corresponding to the measurement point as the maintenance strategy for the idler within the range measured by the measurement point.

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

[0131] Table 1 Example of several risk assessment levels and the corresponding ranges of Risk Priority Numbers and maintenance strategies

[0132]

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

[0134] Exemplarily, the Risk Priority Number corresponding to a measurement point is greater than RPN th1, the risk assessment level corresponding to this measuring point can be determined as first-level maintenance according to the above table. The maintenance strategy corresponding to first-level maintenance is to stop the machine immediately for maintenance. Then, it can be determined that the maintenance strategy for the idlers within the range measured by this measuring point is to stop the machine immediately for maintenance.

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

[0136] The above introduced the idler abnormal detection method for the belt conveyor provided by the embodiments of the present application. Next, the device corresponding to the above idler abnormal detection method for the belt conveyor will be introduced.

[0137] Please refer to Figure 6 , Figure 6 , which is a schematic structural diagram of an idler abnormal detection device for a belt conveyor provided by the embodiments of the present application. The idler abnormal detection device for the belt conveyor may include: an idler operation data acquisition module 601, an idler abnormal diagnosis module 602, and an idler abnormal warning module 603.

[0138] The idler operation data acquisition module 601 is configured to acquire multi-dimensional idler operation data at the current detection moment by using a sensing optical fiber arranged on the side of the idler frame of the belt conveyor.

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

[0140] The idler abnormal warning module 603 is configured to issue an idler abnormal warning when the final idler abnormal diagnosis result indicates idler abnormality.

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

[0142] In a possible implementation manner, when the idler operation data acquisition module 601 acquires multi-dimensional idler operation data at the current detection moment by using a sensing optical fiber arranged on the side of the idler frame of the belt conveyor, it is specifically configured to:

[0143] Send an optical signal to the sensing optical fiber arranged on the side of the idler frame of the belt conveyor at the current detection moment;

[0144] Receive the optical signal reflected back by the sensing optical fiber and carrying idler vibration information, idler sound information, and idler temperature information;

[0145] Demodulate the received optical signal to obtain multi-dimensional idler running data at the current detection moment.

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

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

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

[0149] In a possible implementation, when the idler running data acquisition module 601 acquires multi-dimensional idler running data at the current detection moment by using the sensing optical fiber arranged on the idler rack side of the belt conveyor, it is specifically configured to:

[0150] Use multiple optical fiber acquisition units of the sensing optical fiber arranged on the idler rack side of the belt conveyor to acquire multi-dimensional idler running data of multiple measurement points at the current detection moment.

[0151] When the idler abnormality diagnosis module 602 performs an abnormality diagnosis on the idlers of the belt conveyor according to the idler running data of each dimension at the current detection moment to obtain idler abnormality diagnosis results corresponding to multiple dimensions respectively, it is specifically configured to:

[0152] For each measurement point, perform an abnormality diagnosis on the idlers within the range measured by the measurement point according to the idler running data of each dimension at the current detection moment of the measurement point, so as to obtain idler abnormality diagnosis results corresponding to multiple dimensions of the measurement point.

[0153] In a possible implementation, the multi-dimensional idler running data includes idler running data in the vibration dimension. When the idler abnormality diagnosis module 602 performs an abnormality diagnosis on the idlers within the range measured by the measurement point according to the idler running data in the vibration dimension at the current detection moment of the measurement point to obtain the idler abnormality diagnosis result corresponding to the measurement point in the vibration dimension, it is specifically configured to:

[0154] Obtain the idler running data in the vibration dimension of the measurement point sequence corresponding to the measurement point from the idler running data of the previous detection moment to obtain the historical idler vibration data of the measurement point, where the measurement point sequence corresponding to the measurement point includes the measurement point and its adjacent measurement points;

[0155] Perform fast Fourier transforms on the historical idler vibration data of the measurement point and the current idler vibration data of the measurement point respectively to obtain the historical spectral line amplitude feature set of the measurement point and the current spectral line amplitude feature set of the measurement point. Among them, the current idler vibration data of the measurement point is the idler operation data in the vibration dimension at the current detection moment of the measurement point sequence corresponding to the measurement point;

[0156] According to the historical spectral line amplitude feature set of the measurement point and the current spectral line amplitude feature set of the measurement point, determine the characteristic distribution difference value between the current idler vibration data of the measurement point and the historical idler vibration data of the measurement point, and obtain the characteristic distribution difference value corresponding to the measurement point;

[0157] According to the characteristic distribution difference value corresponding to the measurement point, perform abnormal diagnosis on the idlers within the measured range of the measurement point to obtain the idler abnormal diagnosis result corresponding to the measurement point in the vibration dimension.

[0158] In a possible implementation manner, when the idler abnormal diagnosis module 602 performs abnormal diagnosis on the idlers within the measured range of the measurement point according to the characteristic distribution difference value corresponding to the measurement point to obtain the idler abnormal diagnosis result corresponding to the measurement point in the vibration dimension, it is specifically used for:

[0159] Input the characteristic distribution difference value corresponding to the measurement point into a pre-trained first abnormal diagnosis model to obtain the idler abnormal diagnosis result corresponding to the measurement point in the vibration dimension output by the first abnormal diagnosis model.

[0160] Among them, the first abnormal diagnosis model is trained using a first training sample labeled with whether there is an abnormality and a first training sample labeled with a specific abnormal category, and the first training sample is the characteristic distribution difference value corresponding to the measurement point.

[0161] In a possible implementation manner, the multi-dimensional idler operation data includes the idler operation data in the sound dimension. When the idler abnormal diagnosis module 602 performs abnormal diagnosis on the idlers within the measured range of the measurement point according to the idler operation data of the measurement point at the current detection moment in the sound dimension to obtain the idler abnormal diagnosis result corresponding to the measurement point in the sound dimension, it is specifically used for:

[0162] Input the idler operation data of the measurement point at the current detection moment in the sound dimension into a pre-trained second abnormal diagnosis model to obtain the idler abnormal diagnosis result corresponding to the measurement point in the sound dimension output by the second abnormal diagnosis model.

[0163] Among them, the second abnormal diagnosis model is trained using a second training sample labeled with whether there is an abnormality and a second training sample labeled with a specific abnormal category, and the second training sample is the idler operation data of the measurement point in the sound dimension.

[0164] In a possible implementation, the multi-dimensional idler running data includes the idler running data in the temperature dimension. When the idler anomaly diagnosis module 602 performs an anomaly diagnosis on the idlers within the measured range of the measurement point according to the idler running data in the temperature dimension at the current detection moment of the measurement point to obtain the idler anomaly diagnosis result corresponding to the measurement point in the temperature dimension, it is specifically used for:

[0165] By comparing the idler running data in the temperature dimension at the current detection moment of the measurement point with a preset temperature threshold, to determine the idler anomaly diagnosis result corresponding to the measurement point in the temperature dimension.

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

[0167] To determine 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, where each of the several risk assessment levels also corresponds to a maintenance strategy;

[0168] To 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] To determine the maintenance strategy corresponding to the target risk assessment level as the maintenance strategy for the abnormal idlers.

[0170] The idler anomaly detection device of the belt conveyor provided by the embodiments of the present application first uses the sensing optical fiber arranged on the side of the idler rack of the belt conveyor to obtain the multi-dimensional idler running data at the current detection moment, and then performs an anomaly diagnosis on the idlers of the belt conveyor according to the idler running data in each dimension at the current detection moment to obtain the idler anomaly diagnosis results corresponding to multiple dimensions respectively. Then, according to the idler anomaly diagnosis results corresponding to multiple dimensions respectively, the final idler anomaly diagnosis result is determined. If the final idler anomaly diagnosis result indicates that the idler is abnormal, an idler anomaly warning is issued. For the idler anomaly detection device of the belt conveyor provided by the embodiments of the present application, on the one hand, it automatically realizes the idler anomaly detection of the belt conveyor. Since the detection process does not require manual participation, it avoids the problems brought by manual detection (such as the problem that the detection effect is affected by human subjective factors). On the other hand, the sensing optical fiber is used to obtain the idler running data. Since the sensing optical fiber is arranged on the side of the idler rack of the belt conveyor, there is no need to transform the idlers, and the implementation complexity and the later maintenance complexity are relatively low, and the cost is not high. On the third hand, multi-dimensional idler running data is obtained, and then an anomaly diagnosis is performed on the idlers according to the multi-dimensional idler running data. Performing an anomaly diagnosis according to the multi-dimensional idler running data can obtain a relatively accurate anomaly diagnosis result.

[0171] An embodiment of the present application also provides an optical fiber 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 complete mutual communication through the communication bus;

[0173] The processor may be a central processing unit (CPU), or a specific integrated circuit (ASIC) (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiment of the present application, etc.;

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

[0175] Among them, the memory stores a program, and the processor can call the program stored in the memory, and the program is used to implement the steps of the idler abnormal detection method of the belt conveyor 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, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of the idler abnormal detection method of the belt conveyor provided in the above embodiment.

[0177] An embodiment of the present application also provides a computer program product, including computer-readable instructions, and when the computer-readable instructions run on an electronic device, the electronic device can implement the steps of the idler abnormal detection method of the belt conveyor provided in the above embodiment.

[0178] An embodiment of the present application also provides an idler abnormal detection system for a belt conveyor, as Figure 7 shown, which 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 side of the idler rack of the belt conveyor.

[0179] The optical fiber signal processing device 702 is used to perform abnormal detection on the idlers of the belt conveyor by using the idler abnormal detection method of the belt conveyor provided in the above embodiment.

[0180] In addition, it should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines.

[0181] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general hardware. Of course, it can also be implemented by dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. Generally, functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits, or dedicated circuits. However, for this application, in more cases, software program implementation is a better implementation method. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disc of a computer, and includes several instructions to enable a computer device (which can be a personal computer, training device, or network device, etc.) to execute the methods described in various embodiments of this application.

[0182] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part 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 processes or functions described in the embodiments of the present application are 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. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center by wired (such as coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a training device or a data center that includes one or more integrated available media. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

Claims

1. A method for detecting abnormalities of idlers of a belt conveyor, characterized in that, Including: Utilize the sensing optical fiber arranged on the side of the idler frame of the belt conveyor to obtain multi-dimensional idler operation data at the current detection moment, wherein the multi-dimensional idler operation data at the current detection moment includes the idler operation data of multiple measurement points at the current detection moment in the vibration dimension; Perform abnormal diagnosis on the idlers of the belt conveyor according to the idler operation data of each dimension at the current detection moment to obtain idler abnormal diagnosis results corresponding to multiple dimensions respectively; Determine the final idler abnormal diagnosis result according to the idler abnormal diagnosis results corresponding to the multiple dimensions respectively; If the final idler abnormal diagnosis result indicates idler abnormality, issue an idler abnormality warning; Performing abnormal diagnosis on the idlers of the belt conveyor according to the idler operation data in the vibration dimension at the current detection moment includes: For each measurement point, obtain the historical idler vibration data of this measurement point from the idler operation data of the previous detection moment; Determine the spectral amplitude characteristic distribution difference value between the current idler vibration data of this measurement point and the historical idler vibration data of this measurement point to obtain the characteristic distribution difference value corresponding to this measurement point; Perform abnormal diagnosis on the idlers within the range measured by this measurement point according to the characteristic distribution difference value corresponding to this measurement point.

2. The abnormal detection method for the idler of the belt conveyor according to claim 1, characterized in that, The multi-dimensional idler operation data further includes idler operation data in the sound dimension and / or temperature dimension.

3. The abnormal detection method for the idler of the belt conveyor according to claim 1, characterized in that, The step of utilizing the sensing optical fiber arranged on the side of the idler frame of the belt conveyor to obtain multi-dimensional idler operation data at the current detection moment includes: Send an optical signal to the sensing optical fiber arranged on the side of the idler frame of the belt conveyor at the current detection moment; Receive the optical signal reflected back by the sensing optical fiber with idler vibration information, idler sound information, and idler temperature information; Demodulate the received optical signal to obtain multi-dimensional idler operation data at the current detection moment.

4. The abnormal detection method for the idler of the belt conveyor according to claim 1, characterized in that The idler abnormal diagnosis result corresponding to any dimension can indicate whether the idler is abnormal and the specific abnormal category during the abnormality; The idler abnormal detection method of the belt conveyor further includes: If the final idler abnormal diagnosis result indicates idler abnormality, determine the risk priority number according to the idler abnormal diagnosis results corresponding to the multiple dimensions respectively; Determine the idler maintenance strategy according to the risk priority number.

5. The abnormal detection method for the idler of the belt conveyor according to claim 1, characterized in that, The step of utilizing the sensing optical fiber arranged on the side of the idler frame of the belt conveyor to obtain multi-dimensional idler operation data at the current detection moment includes: Utilize multiple optical fiber acquisition units of the sensing optical fiber arranged on the side of the idler frame of the belt conveyor to obtain multi-dimensional idler operation data of multiple measurement points at the current detection moment; The step of performing abnormal diagnosis on the idlers of the belt conveyor according to the idler operation data of each dimension at the current detection moment to obtain idler abnormal diagnosis results corresponding to multiple dimensions respectively includes: For each measurement point, perform abnormal diagnosis on the idlers within the range measured by this measurement point according to the idler operation data of this measurement point at the current detection moment in each dimension to obtain idler abnormal diagnosis results corresponding to this measurement point in multiple dimensions respectively.

6. The abnormal detection method for the idler of the belt conveyor according to claim 1, characterized in that, The step of obtaining the historical idler vibration data of this measurement point from the idler operation data of the previous detection moment includes: Obtain the running data of the idler corresponding to the measuring point sequence at the vibration dimension from the running data of the idler at the previous detection moment, and obtain the historical idler vibration data of the measuring point. Among them, the measuring point sequence corresponding to the measuring point includes the measuring point and its adjacent measuring points; The determining the difference value of the spectral amplitude characteristic distribution between the current idler vibration data of the measuring point and the historical idler vibration data of the measuring point, and obtaining the characteristic distribution difference value corresponding to the measuring point includes: Perform fast Fourier transform on the historical idler vibration data of the measuring point and the current idler vibration data of the measuring point respectively to obtain the historical spectral amplitude characteristic set of the measuring point and the current spectral amplitude characteristic set of the measuring point. Among them, the current idler vibration data of the measuring point is the running data of the idler at the current detection moment of the measuring point sequence corresponding to the measuring point at the vibration dimension; According to the historical spectral amplitude characteristic set of the measuring point and the current spectral amplitude characteristic set of the measuring point, determine the difference value of the characteristic distribution between the current idler vibration data of the measuring point and the historical idler vibration data of the measuring point, and obtain the characteristic distribution difference value corresponding to the measuring point.

7. The abnormal detection method of the idler of the belt conveyor according to claim 1, characterized in that, The performing abnormal diagnosis on the idlers within the measuring range of the measuring point according to the characteristic distribution difference value corresponding to the measuring point includes: Input the characteristic distribution difference value corresponding to the measuring point into the pre-trained first abnormal diagnosis model to obtain the abnormal diagnosis result of the idler corresponding to the measuring point at the vibration dimension output by the first abnormal diagnosis model; Among them, the first abnormal diagnosis model is trained by using the first training samples marked with whether there is an abnormality and the first training samples marked with specific abnormal categories, and the first training sample is the characteristic distribution difference value corresponding to the measuring point.

8. The abnormal detection method for the idler of the belt conveyor according to claim 5, characterized in that, The multi-dimensional idler running data includes the running data of the idler at the sound dimension; Perform abnormal diagnosis on the idlers within the measuring range of the measuring point according to the running data of the idler at the current detection moment of the measuring point at the sound dimension to obtain the abnormal diagnosis result of the idler corresponding to the measuring point at the sound dimension, including: Input the running data of the idler at the current detection moment of the measuring point at the sound dimension into the pre-trained second abnormal diagnosis model to obtain the abnormal diagnosis result of the idler corresponding to the measuring point at the sound dimension output by the second abnormal diagnosis model; Among them, the second abnormal diagnosis model is trained by using the second training samples marked with whether there is an abnormality and the second training samples marked with specific abnormal categories, and the second training sample is the running data of the idler at the sound dimension of the measuring point.

9. The abnormal detection method of the idler of the belt conveyor according to claim 5, characterized in that, The multi-dimensional idler running data includes the running data of the idler at the temperature dimension; Perform abnormal diagnosis on the idlers within the measuring range of the measuring point according to the running data of the idler at the current detection moment of the measuring point at the temperature dimension to obtain the abnormal diagnosis result of the idler corresponding to the measuring point at the temperature dimension, including: Determine the abnormal diagnosis result of the idler corresponding to the measuring point at the temperature dimension by comparing the running data of the idler at the current detection moment of the measuring point at the temperature dimension with the preset temperature threshold.

10. The abnormal detection method of the idler of the belt conveyor according to claim 4, characterized in that, The determining the idler maintenance strategy according to the risk priority number includes: Determine the range of the risk priority number to which the risk priority number belongs from the ranges of risk priority numbers corresponding to a plurality of preset risk assessment levels, wherein each of the plurality of risk assessment levels also corresponds to a maintenance strategy; Determine the risk assessment level corresponding to the range of the risk priority number to which the risk priority number belongs as the target risk assessment level; Determine the maintenance strategy corresponding to the target risk assessment level as the maintenance strategy for the abnormal idler.

11. An abnormal detection device for idlers of a belt conveyor, characterized in that, Includes: An idler running data acquisition module, an idler abnormality diagnosis module, and an idler abnormality warning module; The idler running data acquisition module is configured to use a sensing optical fiber disposed on the side of the idler rack of the belt conveyor to acquire multi-dimensional idler running data at the current detection moment, wherein the multi-dimensional idler running data at the current detection moment includes the idler running data of multiple measurement points at the current detection moment in the vibration dimension; The idler abnormality diagnosis module is configured to perform an abnormality diagnosis on the idlers of the belt conveyor according to the idler running data of each dimension at the current detection moment to obtain idler abnormality diagnosis results corresponding to multiple dimensions respectively, and determine the final idler abnormality diagnosis result according to the idler abnormality diagnosis results corresponding to the multiple dimensions respectively; The idler abnormality warning module is configured to issue an idler abnormality warning when the final idler abnormality diagnosis result indicates idler abnormality; When the idler abnormality diagnosis module performs an abnormality diagnosis on the idlers of the belt conveyor according to the idler running data in the vibration dimension at the current detection moment, it specifically is configured to: For each measurement point, obtain the historical idler vibration data of the measurement point from the idler running data of the previous detection moment; determine the difference value of the spectral amplitude feature distribution between the current idler vibration data of the measurement point and the historical idler vibration data of the measurement point to obtain the feature distribution difference value corresponding to the measurement point; perform an abnormality diagnosis on the idlers within the range measured by the measurement point according to the feature distribution difference value corresponding to the measurement point.

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

14. A computer program product, characterized in that, Includes computer-readable instructions, and when the computer-readable instructions run on an electronic device, the electronic device can implement the steps of the method for detecting idler abnormalities of a belt conveyor as described in any one of claims 1 to 10.

15. A roller abnormal detection system for a belt conveyor, characterized in that, Includes: A sensing optical fiber and an optical fiber signal processing device connected to the sensing optical fiber, wherein the sensing optical fiber is disposed on the side of the idler rack of the belt conveyor; The optical fiber signal processing device is used to perform abnormal detection on the idlers of the belt conveyor by using the method for detecting abnormal idlers of the belt conveyor according to any one of claims 1 to 10.

Images