Monitoring Method for Belt Conveyor Mechanisms Based on Fiber Optic Distributed Sensing

Abstract

This invention discloses a monitoring method for a belt conveyor mechanism based on distributed fiber optic sensing. The belt conveyor mechanism is equipped with distributed fiber optic sensors. The monitoring method includes the following steps: 1) acquiring distributed fiber optic acoustic signals x(n) to form a test dataset; uniformly extracting ψ samples from the test dataset for each sample x(n) to form a corresponding training set ψ(n); 2) performing a discrete Fourier transform on x(n) to obtain the frequency domain signal X(k); 3) calculating the bandpass filter spectral coefficients H. m (k); 4) Calculate the signal energy spectrum E(m); 5) Take the logarithm of E(m) and perform a discrete cosine transform to obtain the optimized signal y(n); 6) Calculate the path length P(n) of each sample x(n) in the test dataset; 7) Calculate the anomaly score s(y(n),n) of the optimized signal y(n); 8) Fault diagnosis. The monitoring method of this invention realizes online real-time monitoring of belt conveyor mechanisms, with accurate detection, timely discovery of safety hazards, ensuring the safe operation of belt conveyor mechanisms, eliminating the need for downtime, and improving operational efficiency.

Description

Technical Field

[0001] This invention relates to the field of equipment monitoring technology, and in particular to a monitoring method for a belt conveyor mechanism based on fiber optic distributed sensing. Background Technology

[0002] Belt conveyors are essential for loading, unloading, and transporting dry bulk cargo at docks. During operation, these conveyors require regular inspections to check for belt breakage and roller derailment, ensuring the safety of dry bulk cargo transport. Shorter inspection cycles result in more downtime, impacting operational efficiency; conversely, longer cycles often fail to detect conveyor abnormalities promptly, leading to higher safety hazards. Therefore, a monitoring method for belt conveyors based on fiber optic distributed sensing is designed. This method enables online real-time monitoring of belt conveyors, providing accurate detection, timely identification of safety hazards, ensuring safe operation without downtime, and improving operational efficiency. Summary of the Invention

[0003] In view of the above-mentioned defects or deficiencies in the existing technology, it is desirable to provide a monitoring method for belt conveyor mechanisms based on fiber optic distributed sensing, which realizes online real-time monitoring of belt conveyor mechanisms, with accurate detection, timely detection of safety hazards, ensuring the safety of belt conveyor operation, eliminating the need for downtime, and improving work efficiency.

[0004] This invention provides a monitoring method for a belt conveyor mechanism based on distributed fiber optic sensing. The belt conveyor mechanism is equipped with distributed fiber optic sensors, and the monitoring method includes the following steps:

[0005] 1) Collect distributed fiber acoustic signals x(n) at preset time intervals T to form a test dataset with N samples; for each sample x(n), uniformly extract ψ samples from the test dataset to form the corresponding training set ψ(n); where n=1,2,...,N;

[0006] 2) Perform a discrete Fourier transform on x(n) to obtain the frequency domain signal X(k);

[0007] 3) Calculate the bandpass filter spectral coefficients H m (k);

[0008] 4) Calculate the signal energy spectrum E(m);

[0009] 5) After taking the logarithm of E(m), perform a discrete cosine transform to obtain the optimized signal y(n);

[0010] 6) Calculate the path length P(n) of each sample x(n) in the test dataset;

[0011] 7) Calculate the anomaly score s(y(n),n) of the optimized signal y(n);

[0012] The formula for calculating s(y(n),n) is:

[0013] ;

[0014] ;

[0015] Where s(y(n),n) is the anomaly score of y(n) calculated from the training set ψ(n) for the nth sample, and its range is [0,1].

[0016] h(y(n)) is the path length of the optimized signal y(n);

[0017] E(h(y(n))) is the expected value of the path length h(y(n));

[0018] T L (n) represents the left-hand value of the optimized signal y(n) corresponding to the nth sample in the training set ψ(n);

[0019] T R (n) represents the right-hand side value of the optimized signal y(n) corresponding to the nth sample in the training set ψ(n);

[0020] 8) Fault diagnosis;

[0021] The closer s(y(n),n) is to 0, the lower the risk of abnormality in the belt conveyor mechanism; if s(y(n),n)=0, then the optimized signal y(n) has no outliers, and the belt conveyor mechanism has no abnormalities.

[0022] The closer s(y(n),n) is to 1.0, the higher the risk of abnormality in the belt conveyor mechanism; if s(y(n),n)=1.0, then there is an outlier in the optimized signal y(n), and the belt conveyor mechanism is abnormal.

[0023] Furthermore, in step 2), the formula for calculating X(k) is:

[0024] .

[0025] Furthermore, in step 3), H m The formula for calculating (k) is:

[0026] ;

[0027] ;

[0028] ;

[0029] ;

[0030] Among them, H m (k) represents the m-th bandpass filter at frequency f. k Spectral coefficients on;

[0031] f(m) is the linear frequency of the m-th bandpass filter. l f is the lowest frequency in the bandpass filter frequency range. h The highest frequency within the bandpass filter's frequency range;

[0032] M is the number of bandpass filters;

[0033] The frequency Mel(f(m)) after bandpass filter optimization satisfies:

[0034] ;

[0035] .

[0036] Furthermore, in step 4), the formula for calculating E(m) is:

[0037] .

[0038] Furthermore, in step 5), the formula for calculating y(n) is:

[0039] ;

[0040] .

[0041] Furthermore, in step 6), the formula for calculating P(n) is:

[0042] ;

[0043] ;

[0044] Where n = 1, 2, ..., N;

[0045] H(n-1) is the harmonic number;

[0046] e is Euler's constant.

[0047] Compared with the prior art, the beneficial effects of the present invention are:

[0048] The monitoring method of this invention acquires the operating data of the belt conveyor mechanism through distributed fiber optic sensors. By calculating the anomaly score s(y(n),n), a diagnostic result for the belt conveyor mechanism is obtained based on the anomaly score s(y(n),n). When the anomaly risk of the belt conveyor mechanism is high, timely maintenance and repair are carried out to avoid accidents. This monitoring method achieves continuous online real-time monitoring of the belt conveyor mechanism along the conveyor belt direction. The detection is accurate and can promptly identify safety hazards such as idler roller breakage during the conveying process, ensuring the safe operation of the belt conveyor mechanism. It accurately measures the fault point without stopping the machine, making the monitoring of the belt conveyor mechanism more intelligent and improving the automation management level of the entire conveying system.

[0049] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of the present invention, nor is it intended to restrict the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0050] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0051] Figure 1 This is a flowchart of a monitoring method for a belt conveyor mechanism based on fiber optic distributed sensing. Detailed Implementation

[0052] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0053] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0054] Please refer to Figure 1 The present invention provides a monitoring method for a belt conveyor mechanism based on distributed fiber optic sensing. The belt conveyor mechanism is equipped with distributed fiber optic sensors, and the monitoring method includes the following steps:

[0055] 1) Collect distributed fiber acoustic signals x(n) at preset time intervals T to form a test dataset with N samples; for each sample x(n), uniformly extract ψ samples from the test dataset to form the corresponding training set ψ(n); where n=1,2,...,N;

[0056] 2) Perform a discrete Fourier transform on x(n) to obtain the frequency domain signal X(k);

[0057] ;

[0058] 3) Calculate the bandpass filter spectral coefficients H m (k);

[0059] ;

[0060] ;

[0061] ;

[0062] ;

[0063] Among them, H m (k) represents the m-th bandpass filter at frequency f. k Spectral coefficients on;

[0064] f(m) is the linear frequency of the m-th bandpass filter. l f is the lowest frequency in the bandpass filter frequency range. h The highest frequency within the bandpass filter's frequency range;

[0065] M is the number of bandpass filters;

[0066] The frequency Mel(f(m)) after bandpass filter optimization satisfies:

[0067] ;

[0068] ;

[0069] 4) Calculate the signal energy spectrum E(m);

[0070] ;

[0071] 5) After taking the logarithm of E(m), perform a discrete cosine transform to obtain the optimized signal y(n);

[0072] ;

[0073] ;

[0074] 6) Calculate the path length P(n) of each sample x(n) in the test dataset;

[0075] ;

[0076] ;

[0077] Where n = 1, 2, ..., N;

[0078] H(n-1) is the harmonic number;

[0079] e is Euler's constant;

[0080] 7) Calculate the anomaly score s(y(n),n) of the optimized signal y(n);

[0081] ;

[0082] ;

[0083] Where s(y(n),n) is the anomaly score of y(n) calculated from the training set ψ(n) for the nth sample, and its range is [0,1].

[0084] h(y(n)) is the path length of the optimized signal y(n);

[0085] E(h(y(n))) is the expected value of the path length h(y(n));

[0086] T L (n) represents the left-hand value of the optimized signal y(n) corresponding to the nth sample in the training set ψ(n);

[0087] T R (n) represents the right-hand side value of the optimized signal y(n) corresponding to the nth sample in the training set ψ(n);

[0088] 8) Fault diagnosis;

[0089] The closer s(y(n),n) is to 0, the lower the risk of abnormality in the belt conveyor mechanism; if s(y(n),n)=0, then the optimized signal y(n) has no outliers, and the belt conveyor mechanism has no abnormalities.

[0090] The closer s(y(n),n) is to 1.0, the higher the risk of abnormality in the belt conveyor mechanism; if s(y(n),n)=1.0, then there is an outlier in the optimized signal y(n), and the belt conveyor mechanism is abnormal.

[0091] In this embodiment, the relevant data of the belt conveyor are obtained by the distributed optical fiber sensors on the belt conveyor, and the abnormal score s(y(n),n) is calculated from the obtained data. The diagnosis result of the belt conveyor is obtained based on the abnormal score s(y(n),n). When the abnormal risk of the belt conveyor is high, timely inspection and maintenance are carried out to avoid the occurrence of accidents.

[0092] By monitoring the operating status of the belt conveyor in real time, potential faults can be detected in a timely manner, and corresponding maintenance measures can be taken to avoid sudden equipment failures, improve equipment reliability and availability, reduce equipment downtime, and ensure the continuity of port production operations.

[0093] Traditional equipment maintenance methods mainly involve periodic inspections, which can lead to over-maintenance or under-maintenance. In contrast, the monitoring method proposed in this application is predictive maintenance based on monitoring and fault diagnosis technologies. It can develop reasonable maintenance plans based on the actual operating conditions of the equipment, enabling precise repairs and reducing maintenance costs.

[0094] The monitoring method proposed in this application can quickly locate the location of potential safety hazards in equipment, shorten the fault repair time, and improve the operating efficiency of equipment, thereby improving the loading, unloading and transportation efficiency of dry bulk cargo at the terminal and enhancing the terminal's competitiveness.

[0095] Timely detection and handling of equipment malfunctions can effectively prevent safety accidents caused by equipment failures and protect the lives and health of dock workers.

[0096] The monitoring method proposed in this application can effectively improve equipment management, optimize maintenance strategies, reduce operating costs, and improve production efficiency and economic benefits; enhance the automation and intelligence level of the terminal, strengthen the terminal's competitiveness in the market; provide strong protection for the safe production of the terminal, reduce the occurrence of safety accidents, and protect the reputation and assets of the enterprise.

[0097] The monitoring method proposed in this application can promote technological innovation and intelligent development in the dry bulk cargo transportation industry at ports, improve the overall equipment level and operational efficiency of the industry; provide new ideas and methods for equipment maintenance and management in the industry, and promote the transformation of equipment maintenance mode from traditional periodic inspection to predictive maintenance; provide practical basis for the formulation of industry standards and norms, and promote the standardization of the industry.

[0098] The monitoring method proposed in this application can ensure the efficient transportation of dry bulk cargo, meet the national economy's demand for energy, raw materials and other materials, and promote stable economic development; reduce logistics delays and economic losses caused by equipment failures, improve logistics efficiency and reduce logistics costs; enhance the safety production level of ports, reduce the negative impact of safety accidents on society, and promote social harmony and stability.

[0099] In the description of this specification, the terms "one embodiment," "some embodiments," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. 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.

[0100] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A monitoring method for a belt conveyor mechanism based on distributed fiber optic sensing, wherein the belt conveyor mechanism is equipped with distributed fiber optic sensors, characterized in that, The monitoring method includes the following steps: 1) Collect distributed fiber acoustic signals x(n) at preset time intervals T to form a test dataset with N samples; for each sample x(n), uniformly extract ψ samples from the test dataset to form the corresponding training set ψ(n); where n=1,2,...,N; 2) Perform a discrete Fourier transform on x(n) to obtain the frequency domain signal X(k); 3) Calculate the bandpass filter spectral coefficients H m (k); 4) Calculate the signal energy spectrum E(m); 5) After taking the logarithm of E(m), perform a discrete cosine transform to obtain the optimized signal y(n); 6) Calculate the path length P(n) of each sample x(n) in the test dataset; 7) Calculate the anomaly score s(y(n),n) of the optimized signal y(n); The formula for calculating s(y(n),n) is: ； ； Where s(y(n),n) is the anomaly score of y(n) calculated from the training set ψ(n) for the nth sample, and its range is [0,1]. h(y(n)) is the path length of the optimized signal y(n); E(h(y(n))) is the expected value of the path length h(y(n)); T L (n) represents the left-hand value of the optimized signal y(n) corresponding to the nth sample in the training set ψ(n); T R (n) represents the right-hand side value of the optimized signal y(n) corresponding to the nth sample in the training set ψ(n); 8) Fault diagnosis; The closer s(y(n),n) is to 0, the lower the risk of abnormality in the belt conveyor mechanism; if s(y(n),n)=0, then the optimized signal y(n) has no outliers, and the belt conveyor mechanism has no abnormalities. The closer s(y(n),n) is to 1.0, the higher the risk of abnormality in the belt conveyor mechanism; if s(y(n),n)=1.0, then there is an outlier in the optimized signal y(n), and the belt conveyor mechanism is abnormal.

2. The monitoring method for a belt conveyor mechanism based on fiber optic distributed sensing according to claim 1, characterized in that, In step 2), the formula for calculating X(k) is: 。 3. The monitoring method for a belt conveyor mechanism based on fiber optic distributed sensing according to claim 2, characterized in that, In step 3), H m The formula for calculating (k) is: ； ； ； ； Among them, H m (k) represents the m-th bandpass filter at frequency f. k Spectral coefficients on; f(m) is the linear frequency of the m-th bandpass filter. l f is the lowest frequency in the bandpass filter frequency range. h The highest frequency within the bandpass filter's frequency range; M is the number of bandpass filters; The frequency Mel(f(m)) after bandpass filter optimization satisfies: ； 。 4. The monitoring method for a belt conveyor mechanism based on fiber optic distributed sensing according to claim 3, characterized in that, In step 4), the formula for calculating E(m) is: 。 5. The monitoring method for a belt conveyor mechanism based on fiber optic distributed sensing according to claim 4, characterized in that, In step 5), the formula for calculating y(n) is: ； 。 6. The monitoring method for a belt conveyor mechanism based on fiber optic distributed sensing according to claim 5, characterized in that, In step 6), the formula for calculating P(n) is: ； ； Where n = 1, 2, ..., N; H(n-1) is the harmonic number; e is Euler's constant.

Images