Intelligent rolling element distributed detection method and system based on end-edge cooperative diagnosis

Abstract

The application belongs to the technical field of mechanical fault diagnosis, and specifically discloses an intelligent rolling body distributed detection method and system based on end-edge cooperative diagnosis, which comprises the following steps: S1, collecting vibration and temperature data of multiple rolling bodies on a belt conveyor device; S2, uniformly decomposing vibration signals of each rolling body and calculating kurtosis values to obtain a characteristic distribution vector; S3, respectively performing mutual detection on the characteristic distribution vector and the temperature characteristic value of each rolling body, finding an outlier as a fault candidate point by using a K nearest neighbor algorithm; S4, collecting vibration data of the fault candidate point of the rolling body, performing SVMD decomposition to obtain a sub-signal, performing frequency spectrum analysis and envelope spectrum analysis on the sub-signal, and judging whether a fault frequency of the rolling body really exists, and if so, outputting corresponding fault information and performing fault cause analysis. By using the technical scheme, a distributed outlier detection is used to locate a fault rolling body and obtain fault information.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of mechanical fault diagnosis, and relates to an intelligent rolling body distributed detection method and system based on end-edge cooperative diagnosis. BACKGROUND

[0002] Long-distance belt conveyors have the characteristics of long conveying distance, large transport capacity and uniform distribution of multiple rolling bodies, and are widely used in coal mines, metallurgy and construction industries. However, due to the fact that long-distance belt conveyors often work in harsh environments such as high speed, heavy load and vibration impact, key components such as the belt, the roller and the motor are prone to failure during operation. Therefore, in order to ensure the stability of the long-distance belt conveyor, it is of great significance to monitor the fault of the long-distance belt conveyor and timely find the health status problem, so as to realize the safe and reliable operation of the belt conveyor and gradually realize unattended operation.

[0003] At present, the fault diagnosis method for long-distance belt conveyors mainly detects the fault of single component in the belt conveyor, such as collecting and analyzing the vibration signals of the drum and the motor, so as to diagnose the fault of these components. However, these methods have the disadvantages of not being able to fully utilize the fault information of the belt conveyor and single detection object. In addition, the multiple rolling bodies of the belt conveyor have different running characteristics and service conditions in space, and have similar characteristics in signals. Therefore, how to utilize the characteristics to detect the fault of multiple rolling bodies of the long-distance belt conveyor with large span and wide coverage is a problem to be solved. SUMMARY

[0004] The application aims to provide an intelligent rolling body distributed detection method and system based on end-edge cooperative diagnosis, which adopts distributed outlier detection to locate the fault rolling body and obtain fault information.

[0005] In order to achieve the above-mentioned purpose, the basic scheme of the application is as follows: an intelligent rolling body distributed detection method based on end-edge cooperative diagnosis, comprising the following steps:

[0006] S1, collecting vibration and temperature data of multiple rolling bodies on the belt conveyor device;

[0007] S2, based on wavelet packet transform, uniformly scaling the vibration signals of each rolling body, calculating the kurtosis value of each scale signal of each rolling body after decomposition, and obtaining a feature distribution vector;

[0008] S3, respectively checking the feature distribution vector and the temperature data of each rolling body, finding outliers as fault candidate points by using K-neighbor algorithm;

[0009] S4, collect the vibration data of the fault candidate point of the rolling body, and decompose to obtain a sub-signal, perform spectrum analysis and envelope spectrum analysis on the sub-signal, judge whether the fault frequency of the rolling body really exists, and if so, output the corresponding fault information and perform fault cause analysis.

[0010] The working principle and beneficial effects of the basic scheme are that, based on the characteristics of the rolling body signal, the vibration and temperature data of multiple rolling bodies on the belt conveyor device are collected, the distributed outlier detection method is used to locate the fault rolling body, and accurate fault information is obtained.

[0011] Further, based on wavelet packet transform, the vibration signals of the rolling bodies are uniformly scaled and decomposed, and the kurtosis values of the decomposed signals of the rolling bodies are calculated to obtain a characteristic distribution vector, and the specific steps are as follows:

[0012] At a certain time t i , the vibration signal collected by the wireless vibration and temperature sensor of the N rolling bodies is f k (t), k = 1, 2, …, N; the WPT is used to decompose the vibration signals to obtain m sub-signals of each vibration signal;

[0013] Based on the kurtosis value, the characteristic distribution vector M k =(ξ1,ξ2,…,ξ m ) of the sub-signals of the decomposed vibration signals is calculated, and ξ m is the kurtosis value of the sub-signal m, and the kurtosis value is:

[0014]

[0015] Wherein, kurt is the kurtosis value, E represents the expectation, μ represents the sequence mean, σ represents the sequence standard deviation, and x represents the signal sequence.

[0016] Based on the kurtosis value, the characteristic distribution vector of the sub-signals of the decomposed vibration signals is calculated, which is simple to operate.

[0017] Further, the characteristic distribution vectors and temperature characteristic values of the rolling bodies are respectively checked, and the method for finding outliers by using K-neighbor algorithm is:

[0018] For a sample set X = [x1, x2, …, x m ];

[0019] The Euclidean distance d i,j between x i and x j in the sample set is:

[0020] d i,j = ||xi -x j || 2

[0021] wherein, i = 1, 2, … m, j = 1, 2, … m;

[0022] According to the Euclidean distance difference, find the first K neighbors of each sample point x i x oj , j = 1, 2, … K, and then calculate the average distance D i between each sample point and its K nearest neighbor samples:

[0023]

[0024] D i is the K-neighbor distance of x i , set the K-neighbor distance threshold of the feature distribution vector and the temperature feature value, and the sample points exceeding the K-neighbor distance threshold are judged as outlier sample points;

[0025] Calculate the outlier sample points of the feature distribution vector sample set and the temperature feature sample set by the K-neighbor algorithm respectively, and these outlier sample points are the fault candidate points.

[0026] Mutual inspection is performed on the feature distribution vector and the temperature feature value of each intelligent rolling body wireless acquisition and transmission node to obtain the fault candidate points, which is beneficial to screening faults.

[0027] Further, in step S4, the vibration and temperature data of the rolling body at consecutive L time points are collected, steps S2 and S3 are executed, and the outlier points of the wireless vibration and temperature sensor acquisition and transmission nodes at each time point are found. If a wireless vibration and temperature sensor acquisition and transmission node is continuously an abnormal outlier point, the vibration data signal of the wireless vibration and temperature sensor acquisition and transmission node is obtained, the optimal penalty coefficient a of SVMD is set, and SVMD is used to adaptively decompose and diagnose the vibration data signal;

[0028] The sub-signals of the signal after SVMD decomposition are subjected to frequency spectrum analysis and envelope spectrum analysis to determine whether a fault truly exists and to perform fault diagnosis analysis.

[0029] If the characteristic frequency of the rolling body exists in the frequency spectrum analysis and envelope spectrum of the sub-signals, it means that a fault truly exists, and the cause of the fault is analyzed and other operations are performed.

[0030] Further, the method for setting the optimal penalty coefficient a of SVMD is:

[0031] When the vibration signal f(t) is subjected to SVMD decomposition, the initial parameter a group and epsilon are input, the modes and modal center frequencies are obtained by SVMD decomposition, and iterative updating is performed until the convergence condition is met:

[0032]

[0033] Wherein, alpha group is a penalty coefficient, epsilon is a convergence threshold, The nth modal, The n+1th modal;

[0034] After iteration is stopped, the kurtosis value kurt of the signal reconstructed by SVMD decomposition under the alpha parameter is calculated, the alpha value is updated, and the next SVMD decomposition iteration is carried out until the alpha group is traversed;

[0035] The kurtosis values of the signals reconstructed by decomposition under each alpha value are compared, the decomposition parameter alpha with the maximum kurtosis value is selected, and the corresponding filter parameter group is output;

[0036] For the optimal decomposition parameter, a group of modal components IMF and corresponding center frequencies omega are obtained by SVMD decomposition k The upper and lower frequency cutoff points [f 下 ,f 上 ] corresponding to 0.1 times of the spectral center frequency amplitude of each modal component are calculated, and the bandwidth B is f 上 -f 下 .

[0037] The parameters of SVMD are only the penalty coefficient alpha and the convergence coefficient epsilon, and the number of decomposition modes does not need to be set in advance in the decomposition process, so that good decomposition effect can be obtained only by setting the penalty coefficient alpha.

[0038] Further, the method for performing spectrum analysis and envelope spectrum analysis on the sub-signals after the signal is decomposed by SVMD is as follows:

[0039] The pitch diameter of the rolling body, the roller diameter, the number of rollers, the rotation speed and the contact angle parameters are obtained, and the fault frequency of the rolling body is calculated;

[0040] The characteristic frequency is the multiple of the fault frequency, and if the characteristic frequency of the rolling body exists in the spectrum and envelope spectrum of the sub-signal, it indicates that the fault really exists.

[0041] Simple operation, easy to use.

[0042] The application also provides an intelligent rolling body distributed detection system based on end-side collaborative diagnosis, which comprises a device layer, a wireless acquisition and transmission node layer, a relay module layer and an upper computer layer which are connected in sequence, the wireless acquisition and transmission node layer is used for collecting vibration and temperature data of a plurality of rolling bodies on a belt conveyor device in the device layer, and the upper computer layer executes the method and performs fault analysis on the intelligent rolling body.

[0043] The system utilizes the cooperation of each layer to perform fault analysis on the intelligent rolling body.

[0044] Further, the wireless acquisition and transmission node layer includes a plurality of wireless vibration and temperature sensors, which are arranged at corresponding rolling bodies of the belt conveyor device of the device layer.

[0045] Simple structure, convenient to use. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 It is the flowchart of feature distribution vector obtained by the intelligent rolling body distributed detection method based on end-side collaborative diagnosis of the application;

[0047] Figure 2 It is the flowchart of finding outliers of the intelligent rolling body distributed detection method based on end-side collaborative diagnosis of the application;

[0048] Figure 3 It is the flowchart of setting the optimal penalty coefficient of SVMD of the intelligent rolling body distributed detection method based on end-side collaborative diagnosis of the application;

[0049] Figure 4 It is the flowchart of the intelligent rolling body distributed detection method based on end-side collaborative diagnosis of the application;

[0050] Figure 5 It is the structural schematic diagram of the intelligent rolling body distributed detection system based on end-side collaborative diagnosis of the application;

[0051] Figure 6 It is the structural schematic diagram of the intelligent rolling body distributed detection method based on end-side collaborative diagnosis of the application, which uses WPT to decompose each vibration signal. DETAILED DESCRIPTION

[0052] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary, only for explaining the present application, and cannot be understood as a limitation of the present application.

[0053] In the description of the present application, it should be understood that the terms "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0054] In the description of the present application, unless otherwise specified and limited, it is necessary to explain that the terms "mounting", "connection", "connection" should be understood broadly, for example, it can be mechanical connection or electrical connection, it can be the communication inside two elements, it can be direct connection or indirect connection through intermediate medium, and the specific meaning of the above terms can be understood by the person skilled in the art according to the specific situation.

[0055] The number of roller rolling bodies of the long-distance belt conveyor is large, and because the service conditions are consistent, the signals collected by each rolling body are similar. These rolling bodies rotate stably in normal work, and if a fault occurs, periodic vibration pulses are generated at the fault point. Based on the characteristics of the above rolling body signals, the present application is based on the difference between normal rolling body and fault rolling body signals, and adopts a distributed outlier detection method to locate the fault rolling body.

[0056] The present application discloses an intelligent rolling body distributed detection method based on end-edge collaborative diagnosis, as shown in Figure 4 The present application discloses an intelligent rolling body distributed detection method based on end-edge collaborative diagnosis, as shown in

[0057] S1, collecting vibration and temperature data of a plurality of rolling bodies on the belt conveyor device;

[0058] S2, based on wavelet packet transformation (WPT), uniformly scale decomposition is performed on the vibration signals of each rolling body, the kurtosis value of each scale signal after decomposition of each rolling body is calculated, the feature distribution vector is obtained and uploaded to the relay module layer (i.e. relay layer);

[0059] S3, in the relay module layer, the feature distribution vector and temperature data of each rolling body (the temperature data collected by different rolling bodies are the temperature characteristic values thereof) are respectively checked, the K nearest neighbor algorithm is used to find the outlier point as the fault candidate point, and is sent to the upper computer layer; because each position works under the same working condition, theoretically the sensitive modal characteristic value of the vibration signal should be similar, for the position corresponding to the outlier point, it is indicated that a fault may exist.

[0060] S4, collecting vibration data of the fault candidate point of the rolling body and performing decomposition (such as SVMD decomposition, which can continuously extract sub-signals and does not need to set the number of IMF, and the calculation complexity is low) to obtain a sub-signal, performing frequency spectrum analysis and envelope spectrum analysis on the sub-signal, judging whether the fault frequency of the rolling body really exists, and if it exists, outputting the corresponding fault information and performing fault reason analysis (reason analysis is performed on the phenomenon of the fault).

[0061] In a preferred scheme of the present application, as Figure 1As shown, based on wavelet packet transform, the vibration signals of each rolling element are decomposed at a uniform scale. The kurtosis values ​​of the decomposed signals at each scale are then calculated to obtain the feature distribution vector. The specific steps are as follows:

[0062] At a certain moment t i Let f be the vibration signal collected by the wireless vibration and temperature sensor transmission nodes of N rolling elements. k (t), k = 1, 2, ..., N; The vibration signals are decomposed using WPT (e.g., Figure 6 As shown, it is divided into low-frequency components and high-frequency components, and m sub-signals of each vibration signal are obtained;

[0063] Based on the kurtosis value, the characteristic distribution vector M of each vibration signal after decomposition is calculated. k =(ξ1,ξ2,…,ξ) m ), ξ m Let m be the kurtosis value of the sub-signal.

[0064]

[0065] Where kurt is the kurtosis value, E represents the expectation, μ represents the sequence mean, σ represents the sequence standard deviation, and x represents the signal sequence.

[0066] In a preferred embodiment of the present invention, such as Figure 2 As shown, the characteristic distribution vectors and temperature characteristic values ​​of each rolling element are cross-checked, and the K-Nearest Neighbor (KNN) algorithm is used to find outliers.

[0067] For a sample set X = [x1, x2, ..., x...] m ];

[0068] Sample sets x i With x j The Euclidean distance d between them i,j for:

[0069] d i,j =||x i -x j || 2

[0070] Where i = 1, 2, ..., m, j = 1, 2, ..., m;

[0071] Based on the Euclidean distance difference, find the x of each sample point. i The first K nearest neighbors x oj Let j = 1, 2, ..., K, then calculate the average distance D between each sample point and its K nearest neighbors. i :

[0072]

[0073] D i the K-nearest neighbor distance of x i The K-nearest neighbor distance of x is set as the K-nearest neighbor distance threshold of the feature distribution vector and the temperature feature value, and the sample points exceeding the K-nearest neighbor distance threshold are judged as outlier sample points.

[0074] The outlier sample points of the feature distribution vector sample set and the temperature feature sample set are calculated respectively through the K-nearest neighbor algorithm, and these outlier sample points are the fault candidate points.

[0075] In a preferred scheme of the present application, in step S4, the vibration and temperature data of the rolling body at consecutive L time points are collected, steps S2 and S3 are executed to find outlier points of the wireless vibration and temperature sensor sampling and transmission nodes at each time point, if a wireless vibration and temperature sensor sampling and transmission node is continuously an abnormal outlier point, the vibration data signal of the wireless vibration and temperature sensor sampling and transmission node is acquired, the optimal penalty coefficient a of SVMD is set, and the vibration data signal is adaptively decomposed and diagnosed by using SVMD.

[0076] The sub-signals of the signal after SVMD decomposition are subjected to frequency spectrum analysis and envelope spectrum analysis to determine whether a fault truly exists (if the characteristic frequency of the rolling body exists in the frequency spectrum analysis and envelope spectrum of the sub-signal, it is indicated that a fault truly exists) and to perform fault diagnosis analysis. The signal is subjected to SVMD decomposition to obtain sub-signals, and these sub-signals have different frequency components. By analyzing the sub-signals of specific frequency components (such as the characteristic frequency of the rolling body), it is determined whether the rolling body has a fault.

[0077] In a preferred scheme of the present application, as shown in Figure 3 The method for setting the optimal penalty coefficient a of SVMD is as follows:

[0078] When the vibration signal f(t) is subjected to SVMD decomposition, the initial parameter a group and ε are input, each mode and mode center frequency are acquired through SVMD decomposition and are iteratively updated until the convergence condition is met:

[0079]

[0080] Wherein, a group is the penalty coefficient, ε is the convergence threshold, is the n th mode, is the n+1 th mode;

[0081] After the iteration is stopped, the kurtosis value kurt of the signal obtained by reconstructing the SVMD decomposition under the α parameter is calculated, the α value is updated, and the next SVMD decomposition iteration is performed until the a group is traversed;

[0082] Compare the kurtosis values ​​of the signals obtained from decomposition and reconstruction under different α values, select the decomposition parameter α with the largest kurtosis value, and output the corresponding filter parameter set;

[0083] For the optimal decomposition parameters, a set of modal components (IMFs) and their corresponding center frequencies (ω) are obtained through SVMD decomposition. k Calculate the upper and lower frequency cutoff points [f] corresponding to 0.1 times the amplitude of the center frequency of each modal component spectrum. 下 ,f 上 The bandwidth we are looking for is B = f 上 -f 下 .

[0084] In a preferred embodiment of the present invention, the method for performing spectral analysis and envelope spectrum analysis on the sub-signals after SVMD decomposition of the signal is as follows:

[0085] Obtain the rolling element pitch diameter, roller diameter, number of rollers, rotational speed and contact angle parameters, and calculate the rolling element failure frequency;

[0086] The characteristic frequency is a multiple of the fault frequency. If the characteristic frequency of the rolling body exists in the spectrum and envelope spectrum of the sub-signal, it indicates that a real fault exists.

[0087] This invention also provides an intelligent rolling element distributed detection system based on end-edge collaborative diagnostics, such as... Figure 5 As shown, the system includes a device layer, a wireless data acquisition and transmission node layer, a relay module layer, and a host computer layer connected in sequence. The wireless data acquisition and transmission node layer is used to collect vibration and temperature data of multiple rolling elements on the belt conveyor device in the device layer, and uploads the data to the host computer layer through the relay module layer. The host computer layer executes the method described in this invention to perform fault analysis on the intelligent rolling elements.

[0088] In a preferred embodiment of the present invention, the wireless data acquisition node layer includes multiple wireless vibration and temperature sensors, which are disposed at the corresponding rolling elements of the belt conveyor device in the equipment layer.

[0089] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0090] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely divergences of the principles and application of the present application and that numerous modifications, changes, substitutions, and alterations can be made thereto without departing from the spirit and scope of the present application, which is defined by the following claims and their equivalents.

Claims

1. An intelligent rolling body distributed detection method based on end-side collaborative diagnosis, characterized in that, Includes the following steps: S1 collects vibration and temperature data of multiple rolling elements on the belt conveyor device; S2, based on wavelet packet transform, decompose the vibration signal of each rolling element at a uniform scale, calculate the kurtosis value of each scale signal after decomposition of each rolling element, and obtain the feature distribution vector; S3, perform mutual inspection on the feature distribution vectors and temperature data of each rolling element, and use the K-nearest neighbor algorithm to find outliers as candidate fault points; S4. Collect vibration data of candidate fault points of the rolling element, decompose them to obtain sub-signals, perform spectrum analysis and envelope spectrum analysis on the sub-signals to determine whether the fault frequency of the rolling element actually exists. If it exists, output the corresponding fault information and perform fault cause analysis. The method of cross-checking the feature distribution vectors and temperature feature values ​​of each rolling element, and using the K-nearest neighbor algorithm to find outliers is as follows: For a sample set ; between the respective sample sets and the euclidean distance between is: ， wherein , ; Find each sample point based on the Euclidean distance difference. The first K nearest neighbors , Then calculate the average distance between each sample point and its K nearest neighbors. : ， wherein, is K-neighbor distance, set the K-neighbor distance threshold of the feature distribution vector and the temperature feature value, and the sample points exceeding the K-neighbor distance threshold are judged as outlier sample points; The K-nearest neighbor algorithm is used to calculate the outlier sample points in the feature distribution vector sample set and the temperature feature sample set, respectively. These outlier sample points are the fault candidate points. In step S4, vibration and temperature data of the rolling body are collected for L consecutive time periods. Steps S2 and S3 are executed to find outliers at each time period of the wireless vibration and temperature sensor data acquisition node. If a wireless vibration and temperature sensor data acquisition node is continuously an outlier, the vibration data signal of that wireless vibration and temperature sensor data acquisition node is acquired, and the optimal penalty coefficient of SVMD is set. The vibration data signal was adaptively decomposed and diagnosed using SVMD. The sub-signals after SVMD decomposition are subjected to spectrum analysis and envelope spectrum analysis to determine whether a fault actually exists and to perform fault diagnosis analysis. The method for performing spectral and envelope spectrum analysis on the sub-signals after SVMD decomposition of the signal is as follows: Obtain the rolling element pitch diameter, roller diameter, number of rollers, rotational speed, and contact angle parameters, and calculate the rolling element fault frequency. The characteristic frequency is a multiple of the fault frequency. If the characteristic frequency of the rolling element exists in the spectrum and envelope spectrum of the sub-signal, it indicates that a fault actually exists.

2. The intelligent rolling element distributed detection method based on end-edge collaborative diagnosis as described in claim 1, characterized in that, Based on wavelet packet transform, the vibration signals of each rolling element are decomposed at a uniform scale. The kurtosis values ​​of the decomposed signals at each scale are then calculated to obtain the feature distribution vector. The specific steps are as follows: At some point ,set up The vibration signal collected by the wireless vibration temperature sensor transmission node of each rolling element is k=1,2,...,N; The vibration signals are decomposed using WPT to obtain the values ​​of each vibration signal. Individual signals; Based on the kurtosis value, calculate the characteristic distribution vector of each vibration signal after decomposition into sub-signals. , Let m be the kurtosis value of the sub-signal. ， Where kurt is the kurtosis value, and E represents the expectation. Let σ represent the mean of the sequence, σ represent the standard deviation of the sequence, and x represent the signal sequence.

3. The intelligent rolling element distributed detection method based on end-edge collaborative diagnosis as described in claim 1, characterized in that, Set the optimal penalty coefficient for SVMD The method is as follows: When performing SVMD decomposition on the vibration signal f(t), the initial parameters are input. The group and ε are obtained by SVMD decomposition to obtain each mode and its center frequency, and iteratively updated until the convergence condition is met: || u k n+1 - u k n || 2 2 || u k n || 2 2 <ε, in, The group is the penalty coefficient, ε is the convergence threshold, and u k n For the nth mode, u k n+1 This is the (n+1)th mode; After the iteration stops, the calculation is performed. The kurt value of the signal obtained from SVMD decomposition and reconstruction under the specified parameters is updated. The value is used to proceed to the next SVMD decomposition iteration until the traversal is complete. Group; Compare each The kurtosis values ​​of the reconstructed signals are selected from the kurtosis values, and the decomposition parameter with the largest kurtosis value is chosen. and output the corresponding filter parameter set; For the optimal decomposition parameters, a set of modal components IMF and the corresponding center frequency ω are obtained by SVMD decomposition k , the upper and lower frequency cutoff points [f 下 , f 上 ] corresponding to 0.1 times the amplitude of the center frequency of the spectrum of each modal component are calculated, and the bandwidth B is f 上 -f 下 .

4. A distributed intelligent rolling element detection system based on end-edge collaborative diagnosis, characterized in that, It includes a device layer, a wireless data acquisition node layer, a relay module layer and a host computer layer connected in sequence. The wireless data acquisition node layer is used to collect vibration and temperature data of multiple rolling elements on the belt conveyor device in the device layer. The host computer layer executes the method described in any one of claims 1-3 to perform fault analysis on the intelligent rolling elements.

5. The intelligent rolling element distributed detection system based on end-edge collaborative diagnosis as described in claim 4, characterized in that, The wireless data acquisition node layer includes multiple wireless vibration and temperature sensors, which are installed at the corresponding rolling elements of the belt conveyor device in the equipment layer.

Images