Carrier roller fault monitoring method, system and device based on sonar abnormal sound analysis
By using sonar anomaly analysis to monitor idler roller faults in real time, the problem of failure to detect faults in idler roller fault monitoring technology in a timely manner has been solved, thereby improving maintenance efficiency and reducing costs.
Patent Information
- Application Number
- CN202310580406.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-23
- Publication Date
- 2024-11-26
AI Technical Summary
Existing idler roller fault monitoring technology cannot detect faults in a timely manner in harsh environments, leading to further development of faults, increasing the cost and time of manual inspections, and reducing maintenance efficiency.
A sonar-based abnormal sound analysis method is adopted, which uses sonar sensors to collect noise audio data in real time, performs signal preprocessing and spectrum analysis, extracts abnormal sound signals, determines the location of roller faults, and provides early warning.
It enables real-time online monitoring of idler roller faults, preventing further development of faults, improving maintenance efficiency, and reducing equipment maintenance costs.
Smart Images

Figure CN119024341A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of electronic communications, and relates to a fault monitoring method, and in particular to a roller fault monitoring method, system and device based on sonar abnormal sound analysis. Background Art
[0002] Belt conveyor rollers are the most important part of belt conveyors and also the most common part of belt conveyors. Belt conveyor rollers are different from unpowered rollers used for material transportation, although they are similar in form and appearance. However, belt conveyor rollers have a larger load capacity and have corresponding restrictions on speed.
[0003] Belt conveyors operate continuously for a long time under high speed and heavy load conditions. The rollers that carry the conveyor belts are vulnerable parts. Belt conveyor rollers are a general term for rollers, including: various trough rollers, buffer rollers, parallel rollers, etc. The specifications range from 89 to 219, and they are selected and installed according to different belt conveyor models. Including iron rollers, ceramic rollers, rubber rollers, etc. It is one of the most used and most convenient parts of belt conveyors.
[0004] Common faults of rollers: abnormal friction noise of rollers, wear and tear on the outer surface of the roller, severe rust, water and dust entering the bearing seal, grease deterioration, accelerated damage, bearing jamming, bearing strength, stiffness, fatigue damage, etc.
[0005] In order to avoid the above-mentioned impacts caused by roller failure, an effective roller monitoring method is urgently needed. At present, roller failure is often determined by manual inspection, but this manual detection method has many problems:
[0006] First, it is inconvenient to conduct manual inspection when the inspection environment is bad, and manual inspection is likely to cause casualties;
[0007] Secondly, manual inspection has obvious defects such as high inspection cost, low efficiency, and serious impact on production and transportation work.
[0008] Therefore, monitoring the operating status of the roller can not only improve the maintenance efficiency, but also has important significance for the safe operation of the belt conveyor.
[0009] Therefore, in the existing roller fault monitoring technology, since the rollers may randomly fail when operating in harsh environments, and if the failure does not occur in time, it will cause the further development of the failure and cause more serious impact, resulting in large costs and operation time for manual inspections, which greatly reduces the work efficiency of roller maintenance. Summary of the invention
[0010] In view of the shortcomings of the prior art mentioned above, the purpose of the present application is to provide a roller fault monitoring method, system and device based on sonar abnormal sound analysis, which is used to solve the problem that in the process of implementing the roller fault monitoring technology in the prior art, the roller may randomly fail when operating in a harsh environment, and when the failure does not occur in time, it will cause the further development of the failure and cause more serious impact, thereby resulting in large costs and operation time for manual inspections, greatly reducing the work efficiency of roller maintenance.
[0011] To achieve the above-mentioned purpose and other related purposes, in a first aspect, the present application provides a roller fault monitoring method based on sonar abnormal sound analysis, comprising the following steps: acquiring noise audio monitoring data of each node in the target area; performing signal preprocessing on the noise audio monitoring data to obtain a noise audio signal; performing spectrum analysis based on the noise audio signal to obtain noise frequency distribution characteristics; extracting abnormal sound signals based on the noise frequency distribution characteristics, so as to obtain the fault location of the roller according to the warning information and issue a warning.
[0012] In an implementation of the first aspect, obtaining noise audio monitoring data in a target area includes the following steps: distributing and installing monitoring equipment on equipment in the target area; collecting audio monitoring data at each node in real time based on the monitoring equipment; the audio monitoring data includes audio feature data and historical data.
[0013] In an implementation of the first aspect, the audio feature data includes: sound pressure level, main frequency and impulse response; the historical data includes: data acquisition time, abnormal node number, and abnormal feature information.
[0014] In an implementation of the first aspect, performing signal preprocessing on the noise audio monitoring data to obtain a noise audio signal includes the following steps: performing filtering and signal amplification based on the audio monitoring data to obtain a noise audio signal.
[0015] In an implementation of the first aspect, performing spectrum analysis based on the noise audio signal to obtain noise frequency distribution characteristics includes the following steps: performing spectrum analysis on the noise audio signal based on a Fourier transform algorithm to obtain noise audio frequency domain information; obtaining frequency components and amplitudes of a noise audio spectrum based on the noise audio frequency domain information; performing amplitude calculation based on the noise audio spectrum to obtain noise audio intensity; and obtaining noise frequency distribution characteristics based on the noise audio spectrum.
[0016] In an implementation of the first aspect, an abnormal sound signal is extracted according to the noise frequency distribution characteristics, and an early warning is issued to determine the fault position of the roller according to the early warning information, including the following steps: based on the noise frequency distribution characteristics within a certain time period, determine whether the noise is an abnormal sound signal; when the noise is an abnormal sound signal, the node position corresponding to the noise is the fault position; when the noise is other signals, the node position corresponding to the noise is not the fault position.
[0017] In an implementation of the first aspect, judging whether the noise is an abnormal sound signal according to the noise frequency distribution characteristics within a certain time period includes the following steps: when the impact component of the working noise is greater than or equal to the impact component threshold, it is an abnormal sound signal; when the impact component of the working noise is less than the impact component threshold, it is a normal signal.
[0018] In the second aspect, the present application provides a roller fault monitoring system based on sonar abnormal sound analysis, including: an acquisition module, used to obtain noise audio monitoring data of each node in the target area; a data processing module, used to perform signal preprocessing on the noise audio monitoring data to obtain a noise audio signal; perform spectrum analysis based on the noise audio signal to obtain noise frequency distribution characteristics; a judgment module, used to extract the abnormal sound signal according to the noise frequency distribution characteristics, so as to determine the fault location of the roller according to the warning information and issue a warning.
[0019] In a third aspect, the present application provides a roller fault monitoring device based on sonar abnormal sound analysis, comprising: a processor and a memory. The memory is used to store a computer program; the processor is connected to the memory and is used to execute the computer program stored in the memory, so that the roller fault monitoring device based on sonar abnormal sound analysis executes the roller fault monitoring method based on sonar abnormal sound analysis.
[0020] On the last aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, characterized in that the program is executed by a processor to implement the roller fault monitoring method based on sonar abnormal sound analysis.
[0021] As described above, the roller fault monitoring method, system and device based on sonar abnormal sound analysis of the present invention have the following beneficial effects:
[0022] The present application performs roller abnormal sound analysis based on sonar sensors, and can collect audio in real time and perform real-time analysis based on the sonar sensors to realize the process of online monitoring; and the roller fault monitoring method based on sonar abnormal sound analysis provided by the present application can improve the work efficiency of roller maintenance and reduce the cost of equipment maintenance operations on the basis of avoiding further development of faults. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 Shown is a flow chart of a roller fault monitoring method based on sonar abnormal sound analysis in one embodiment of the present invention.
[0024] Figure 2 Shown is a schematic diagram of the audio signal processing flow in the roller fault monitoring method based on sonar abnormal sound analysis of the present invention.
[0025] Figure 3 It shows a flow chart of S11 in the roller fault monitoring method based on sonar abnormal sound analysis of the present invention.
[0026] Figure 4 It shows a flow chart of S13 in the roller fault monitoring method based on sonar abnormal sound analysis of the present invention.
[0027] Figure 5 It is a schematic diagram of the principle structure of a roller fault monitoring system based on sonar abnormal sound analysis in one embodiment of the present invention.
[0028] Figure 6 Shown is a schematic diagram of the principle structure of a roller fault monitoring device based on sonar abnormal sound analysis in one embodiment of the present invention.
[0029] Component number description
[0030] 51 Get Module
[0031] 52 Data processing module
[0032] 53 Judgment module
[0033] 61 Processor
[0034] 62 Memory
[0035] Steps S11 to S14 DETAILED DESCRIPTION
[0036] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.
[0037] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.
[0038] The following will describe in detail the roller fault monitoring method based on sonar abnormal sound analysis provided in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application.
[0039] See also Figure 1 and Figure 2 , respectively, show a flow chart of a roller fault monitoring method based on sonar abnormal sound analysis in one embodiment of the present invention and a flow chart of an audio signal processing in a roller fault monitoring method based on sonar abnormal sound analysis of the present invention. Figure 1 and Figure 2 As shown, this embodiment provides a roller fault monitoring method based on sonar abnormal sound analysis.
[0040] The roller fault monitoring method based on sonar abnormal sound analysis specifically comprises the following steps:
[0041] S11, obtaining noise audio monitoring data of each node in the target area.
[0042] See also Figure 3 , which is a flow chart of S11 in the roller fault monitoring method based on sonar abnormal sound analysis of the present invention. The specific steps are as follows:
[0043] S111, sonar monitoring equipment is distributed and installed on the equipment in the target area to build a distributed sonar system. A sonar system (same as "sonar system") is a general term for methods and equipment used to detect and locate objects using sound waves.
[0044] A sonar system usually consists of a transmitter, a receiver, and a signal processor. The transmitter sends out a series of sound wave pulses, which propagate through the medium and are reflected by objects. The receiver receives these reflected signals and converts them into electrical signals. The signal processor processes these electrical signals to determine the position and shape of underwater objects.
[0045] The detection range and resolution of a sonar system depends on the performance of the transmitter and receiver. The more powerful the transmitter, the longer the detection range, but it also increases noise and interference. The more sensitive the receiver, the better the resolution.
[0046] Sonar first uses a sound source (sonar transducer) to emit sound waves. The sound waves are then reflected back after hitting objects in the water. The intensity and spectrum information of the sound signals reflected by different objects are different. After receiving this information containing rich content, the sonar receiving device processes the data and compares it with the data in the database to determine what the irradiated object is.
[0047] In this embodiment, several nodes are set on the entire belt conveyor system in the target area, and corresponding monitoring equipment is configured on each node to realize the position positioning function of the faulty roller during the abnormal sound monitoring process. The monitoring equipment here adopts a sonar sensor. The node includes the location information of the sonar sensor installation.
[0048] Specifically, a sonar node is set every 10 meters on the entire belt conveyor system in the target area, and a sonar sensor for collecting audio at the end is set at the node.
[0049] S112, collecting audio monitoring data at each node in real time based on the monitoring device; the audio monitoring data includes audio feature data and historical data.
[0050] Establish an equipment structure form, break it down into the smallest maintenance unit, and use the smallest maintenance unit as a node to associate its collected data and historical information.
[0051] In this embodiment, audio monitoring data is collected in real time by sonar sensors installed at each node. Audio monitoring data includes: audio feature data and historical data. Among them, the audio feature data includes fields such as sound pressure level, main frequency and impulse response, etc., and an audio feature database is constructed based on the audio feature data. The historical data includes fields such as data acquisition time, abnormal node number, abnormal feature information, etc., and a historical database is constructed based on the historical data. Among them, the abnormal feature information is encoded to unify the semantics.
[0052] S12, performing signal preprocessing on the noise audio monitoring data to obtain a noise audio signal.
[0053] Filtering and signal amplification are performed based on the audio monitoring data to obtain a noise audio signal.
[0054] In this embodiment, a signal processing circuit is connected to the back end of each sonar sensor. The signal processing circuit performs signal processing on the microphone voltage signal (i.e., audio signal) used, including filtering and signal amplification enhancement of the electrical signal, which is used to solve the problem that the low-frequency noise interference of the belt conveyor equipment is large in the actual application environment, and the signal amplification is required to increase the dynamic range of the actual acquisition.
[0055] S13, performing spectrum analysis based on the noise audio signal to obtain noise frequency distribution characteristics. Figure 4 , which is a flow chart of S13 in the roller fault monitoring method based on sonar abnormal sound analysis of the present invention. Figure 4 As shown, the S13 comprises the following steps:
[0056] S131, performing spectrum analysis on the noise audio signal based on a Fourier transform algorithm to obtain noise audio frequency domain information. Based on the noise audio frequency domain information, frequency components and amplitudes of the noise audio spectrum are obtained.
[0057] In this embodiment, the audio signal is converted from the time domain to the frequency domain by using a fast Fourier transform (FFT) algorithm, thereby obtaining the frequency component and amplitude of the audio signal.
[0058] Fast Fourier Transform (FFT) is a method based on Fourier's theorem to greatly reduce the amount of calculation, quickly convert time domain signals to frequency domain signals, and minimize signal processing time. It uses a real-time digital signal processor and window technology to quickly convert time domain signals to frequency domain and improve signal processing efficiency.
[0059] In the distributed conveyor belt roller abnormal sound monitoring system of the present embodiment, the spectrum analysis algorithm is mainly used to extract the characteristics of the sound signal and compare it with the characteristics of the normal sound.
[0060] Specifically, the corresponding vibration data is determined according to the collected audio data, and a corresponding audio vibration file is generated; the data in the audio vibration file is separated into sound data and vibration data; the sound data is parsed to obtain the channel data in the sound data; and the vibration data is parsed at the same time to obtain the vibration characteristics after parsing. Then, the vibration characteristics after parsing are compared with the characteristics of normal sound to realize the spectrum analysis process of the audio data.
[0061] S132: Perform amplitude calculation based on the noise audio spectrum to obtain noise audio intensity.
[0062] In this embodiment, the sound pressure level feature can be obtained from the converted frequency domain information (ie, the audio spectrum) by amplitude calculation. The sound pressure level feature is used to represent the intensity of the sound and can be used to determine whether the sound exceeds the normal range.
[0063] Sound pressure level (SPL) refers to the size of effective sound pressure relative to a reference value measured on a logarithmic scale, and its relationship with the reference value is described in decibels (unit: dB). The human hearing threshold for 1KHz sound (i.e.: the lowest sound pressure that produces hearing) is 20Pa, which is usually used as the reference value of sound pressure level.
[0064] The maximum sound pressure level is an important indicator of microphone parameters. It refers to the maximum sound pressure level that the microphone can withstand to achieve a total harmonic distortion of 0.5, generally expressed in decibels. The larger the value, the better.
[0065] Specifically, a sonar sensor is set at a certain node in the belt conveyor system. The sonar sensor serves as a specific point sound source. The sound pressure level at this point is:
[0066] SPL = 20log(10)[p(e) / p(ref)]
[0067] Where p(ref) represents the reference sound pressure, which is generally 2*10E -5 Pa; p(e) represents the effective value of the sound pressure to be measured.
[0068] In this embodiment, Fourier transform, wavelet transform, discrete cosine transform and other formulas may be used to perform corresponding calculations.
[0069] S133: Acquire noise frequency distribution characteristics based on the noise audio spectrum.
[0070] In this embodiment, the frequency distribution characteristics are obtained by analyzing the audio spectrum and calculating the main frequency of the audio signal collected by the sonar sensor at the node. The main frequency can be used to distinguish different types of sounds, such as determining whether the audio signal is white noise, pure tone, or harmonics.
[0071] Sound can be divided into the following nine categories: pure tone, compound tone, fundamental tone, harmonic, single tone, consonant tone, noise, white noise, and black noise. Among them, pure tone refers to a single-frequency sine wave sound; compound tone refers to two or more pure tones; fundamental tone is A periodic composite sound is a sound with the same period or a sound with the lowest frequency in a non-periodic composite sound; harmonics, also called doublets, are sounds that are integer multiples of the fundamental sound in a periodic composite sound, except for the fundamental sound; noise refers to non-periodic sound; white noise refers to sound with uniform energy distribution over a wide frequency range, etc.
[0072] Specifically, when a main frequency is obtained by calculation, such as when the calculated main frequency is within 0 to 20 kHz, the audio can be determined to be white noise; or when the calculated main frequency is a single frequency of 1000, it is a pure tone.
[0073] For example: the calculation of the main frequency. The calculation of the main frequency is related to the speed. For the belt conveyor, since the process speed remains consistent, the speed is relatively stable and can be within a fixed range.
[0074] S14, extracting abnormal sound signals according to the noise frequency distribution characteristics, so as to obtain the fault position of the roller according to the early warning information and issue an early warning.
[0075] In the distributed sonar system, the audio data of all nodes are collected in real time, and the impact component of the belt conveyor's working noise in each cycle is extracted. The impact component is used to judge whether there is any obvious abnormality in the roller of the belt conveyor system.
[0076] When the belt conveyor is in normal working condition, the noise is mainly caused by friction between the roller and the belt when the roller rotates at high speed. The sound of this noise is relatively stable and will not be mixed with abnormal impact and extrusion components. When the belt conveyor has local faults, such as roller derailment, peeling, jamming, and lack of oil, the roller will also produce impact components caused by abnormalities during the friction and rotation of the roller. Among them, the characteristic strength of this sound component can be used as the main basis for early monitoring of whether the equipment is damaged.
[0077] In this embodiment, the impact component is determined by a threshold value. The impact response characterizes the size of the impact component in the signal and is used to evaluate the stability of the signal. The normal range is usually set between 0 and 1. Generally, when the belt conveyor is operating normally, this parameter is less than 0.2.
[0078] When an abnormal signal is detected through the monitoring of the distributed sonar system, the information of the historical record database is combined with the sonar sensor node information of the monitored signal to obtain the physical location of the fault point; at the same time, the fault history information is recorded in the system and an alarm message is issued through the system.
[0079] In this embodiment, when a fault occurs, the system generates an alarm to remind personnel to perform maintenance work, and the corresponding fault alarm information and maintenance work information are stored to form a device history. At the same time, the user can handle the fault problem of the node according to the prompt of the alarm information.
[0080] The roller fault monitoring method based on sonar abnormal sound analysis of the present application is used to analyze the roller abnormal sound based on the sonar sensor, and the audio can be collected in real time according to the sonar sensor and analyzed in real time to realize the process of online monitoring. The roller fault monitoring method based on sonar abnormal sound analysis provided by the present application can improve the work efficiency of roller maintenance and reduce the cost of equipment maintenance operations on the basis of avoiding further development of the fault.
[0081] The protection scope of the roller fault monitoring method based on sonar abnormal sound analysis described in the embodiment of the present application is not limited to the execution order of the steps listed in the present embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present application are included in the protection scope of the present application.
[0082] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the following is achieved: Figure 1 The roller fault monitoring method based on sonar abnormal sound analysis.
[0083] At any possible level of technical detail combination, the present application may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present application.
[0084] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, (but not limited to) an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.
[0085] The computer-readable program described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device through a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives a computer-readable program instruction from the network, and forwards the computer-readable program instruction for storage in the computer-readable storage medium in each computing / processing device. The computer program instruction for performing the operation of the present application can be an assembly instruction, an instruction set architecture (ISA) instruction, a machine instruction, a machine-related instruction, a microcode, a firmware instruction, a state setting data, an integrated circuit configuration data, or a source code or object code written in any combination of one or more programming languages, wherein the programming language includes an object-oriented programming language, such as Smalltalk, C++, etc., and a procedural programming language, such as "C" language or similar programming language. Computer readable program instructions can be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In certain embodiments, by using the state information of computer readable program instructions to personalize electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (PLAs), the electronic circuits can execute computer readable program instructions, thereby realizing various aspects of the present application.
[0086] The embodiment of the present application also provides a roller fault monitoring system based on sonar abnormal sound analysis. The roller fault monitoring system based on sonar abnormal sound analysis can implement the roller fault monitoring method based on sonar abnormal sound analysis described in the present application. However, the implementation device of the roller fault monitoring method based on sonar abnormal sound analysis described in the present application includes but is not limited to the structure of the roller fault monitoring system based on sonar abnormal sound analysis listed in the present embodiment. All structural deformations and replacements of the prior art made according to the principles of the present application are included in the protection scope of the present application.
[0087] The roller fault monitoring system based on sonar abnormal sound analysis provided by this embodiment will be described in detail below with reference to the drawings.
[0088] This embodiment provides a roller fault monitoring system based on sonar abnormal sound analysis, including:
[0089] See also Figure 5 , which is a schematic diagram of the principle structure of a roller fault monitoring system based on sonar abnormal sound analysis in one embodiment of the present invention. Figure 5 As shown, the roller fault monitoring system based on sonar abnormal sound analysis includes: an acquisition module 51, a data processing module 52 and a judgment module 53.
[0090] The acquisition module 81 is used to acquire the noise audio monitoring data of each node in the target area.
[0091] Sonar monitoring equipment is distributed and installed on the equipment in the target area to build a distributed sonar system. Sonar system (same as "sonar system") is a general term for the method and equipment used to detect and locate objects using sound waves.
[0092] In this embodiment, several nodes are set on the entire belt conveyor system in the target area, and corresponding monitoring equipment is configured on each node to realize the position positioning function of the faulty roller during the abnormal sound monitoring process. The monitoring equipment here adopts a sonar sensor. The node includes the location information of the sonar sensor installation.
[0093] Specifically, a sonar node is set every 10 meters on the entire belt conveyor system in the target area, and a sonar sensor for collecting audio at the end is set at the node.
[0094] The audio monitoring data at each node is collected in real time based on the monitoring device; the audio monitoring data includes audio feature data and historical data.
[0095] Establish an equipment structure form, break it down into the smallest maintenance unit, and use the smallest maintenance unit as a node to associate its collected data and historical information.
[0096] In this embodiment, audio monitoring data is collected in real time by sonar sensors installed at each node. Audio monitoring data includes: audio feature data and historical data. Among them, the audio feature data includes fields such as sound pressure level, main frequency and impulse response, etc., and an audio feature database is constructed based on the audio feature data. The historical data includes fields such as data acquisition time, abnormal node number, abnormal feature information, etc., and a historical database is constructed based on the historical data. Among them, the abnormal feature information is encoded to unify the semantics.
[0097] The data processing module 52 is connected to the acquisition module 51 and is used to perform signal preprocessing on the noise audio monitoring data to obtain a noise audio signal; and perform spectrum analysis based on the noise audio signal to obtain noise frequency distribution characteristics.
[0098] The noise audio monitoring data is subjected to signal preprocessing to obtain a noise audio signal.
[0099] Filtering and signal amplification are performed based on the audio monitoring data to obtain a noise audio signal.
[0100] In this embodiment, a signal processing circuit is connected to the back end of each sonar sensor. The signal processing circuit performs signal processing on the microphone voltage signal (i.e., audio signal) used, including filtering and signal amplification enhancement of the electrical signal, which is used to solve the problem that the low-frequency noise interference of the belt conveyor equipment is large in the actual application environment, and the signal amplification is required to increase the dynamic range of the actual acquisition.
[0101] A frequency spectrum analysis is performed based on the noise audio signal to obtain noise frequency distribution characteristics.
[0102] The noise audio signal is subjected to spectrum analysis based on a Fourier transform algorithm to obtain frequency domain information of the noise audio signal. Based on the frequency domain information of the noise audio signal, the frequency components and amplitudes of the noise audio spectrum are obtained.
[0103] In this embodiment, the above audio signal is converted from the time domain to the frequency domain by using a fast Fourier transform (FFT) algorithm, thereby obtaining the frequency component and amplitude of the audio signal.
[0104] In the distributed conveyor belt roller abnormal sound monitoring system of the present embodiment, the spectrum analysis algorithm is mainly used to extract the characteristics of the sound signal and compare it with the characteristics of the normal sound.
[0105] Specifically, the corresponding vibration data is determined according to the collected audio data, and a corresponding audio vibration file is generated; the data in the audio vibration file is separated into sound data and vibration data; the sound data is parsed to obtain the channel data in the sound data; and the vibration data is parsed at the same time to obtain the vibration characteristics after parsing. Then, the vibration characteristics after parsing are compared with the characteristics of normal sound to realize the spectrum analysis process of the audio data.
[0106] Amplitude calculation is performed based on the noise audio spectrum to obtain noise audio intensity.
[0107] In this embodiment, the sound pressure level feature can be obtained from the converted frequency domain information (ie, the audio spectrum) by amplitude calculation. The sound pressure level feature is used to represent the intensity of the sound and can be used to determine whether the sound exceeds the normal range.
[0108] In this embodiment, Fourier transform, wavelet transform, discrete cosine transform and other formulas may be used to perform corresponding calculations.
[0109] A noise frequency distribution feature is obtained based on the noise audio spectrum.
[0110] In this embodiment, the frequency distribution characteristics are obtained by analyzing the audio spectrum and calculating the main frequency of the audio signal collected by the sonar sensor at the node. The main frequency can be used to distinguish different types of sounds, such as determining whether the audio signal is white noise, pure tone, or harmonics.
[0111] Specifically, when a main frequency is obtained by calculation, such as when the calculated main frequency is within 0 to 20 kHz, the audio can be determined to be white noise; or when the calculated main frequency is a single frequency of 1000, it is a pure tone.
[0112] The judgment module 53 is used to extract the abnormal sound signal according to the noise frequency distribution characteristics, so as to determine the fault position of the roller according to the early warning information and issue an early warning.
[0113] The abnormal sound signal is extracted according to the noise frequency distribution characteristics, so as to obtain the fault position of the roller according to the early warning information and issue an early warning.
[0114] In the distributed sonar system, the audio data of all nodes are collected in real time, and the impact component of the belt conveyor's working noise in each cycle is extracted. The impact component is used to judge whether there is any obvious abnormality in the roller of the belt conveyor system.
[0115] When the belt conveyor is in normal working condition, the noise is mainly caused by friction between the roller and the belt when the roller rotates at high speed. The sound of this noise is relatively stable and will not be mixed with abnormal impact and extrusion components. When the belt conveyor has local faults, such as roller derailment, peeling, jamming, and lack of oil, the roller will also produce impact components caused by abnormalities during the friction and rotation of the roller. Among them, the characteristic strength of this sound component can be used as the main basis for early monitoring of whether the equipment is damaged.
[0116] In this embodiment, the impact component is determined by a threshold value. The impact response characterizes the size of the impact component in the signal and is used to evaluate the stability of the signal. The normal range is usually set between 0 and 1. Generally, when the belt conveyor is operating normally, this parameter is less than 0.2.
[0117] When an abnormal signal is detected through the monitoring of the distributed sonar system, the information of the historical record database is combined with the sonar sensor node information of the monitored signal to obtain the physical location of the fault point; at the same time, the fault history information is recorded in the system and an alarm message is issued through the system.
[0118] In this embodiment, when a fault occurs, the system generates an alarm to remind personnel to perform maintenance work, and the corresponding fault alarm information and maintenance work information are stored to form a device history. At the same time, the user can handle the fault problem of the node according to the prompt of the alarm information.
[0119] Roller fault monitoring model based on sonar abnormal sound analysis The roller fault monitoring system based on sonar abnormal sound analysis can collect audio in real time according to the sonar sensor and perform real-time analysis to realize the process of online monitoring. The roller fault monitoring method based on sonar abnormal sound analysis provided in this application can improve the efficiency of roller maintenance and reduce the cost of equipment maintenance operations on the basis of avoiding further development of faults.
[0120] It should be noted that it should be understood that the division of the various modules of the above system is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the x module can be a separately established processing element, or it can be integrated in a certain chip of the above system for implementation. In addition, it can also be stored in the memory of the above system in the form of program code, and called and executed by a certain processing element of the above system. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.
[0121] The above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASIC), or one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
[0122] See also Figure 6 , which is a schematic diagram of the principle structure of a roller fault monitoring device based on sonar abnormal sound analysis in one embodiment of the present invention. Figure 6 As shown, this embodiment provides a roller fault monitoring device based on sonar abnormal sound analysis, and the roller fault monitoring device based on sonar abnormal sound analysis includes: a processor 61 and a memory 62; the memory 62 is used to store computer programs; the processor 61 is connected to the memory 62, and is used to execute the computer program stored in the memory 62, so that the roller fault monitoring device based on sonar abnormal sound analysis performs the various steps of the roller fault monitoring method based on sonar abnormal sound analysis as described above.
[0123] Preferably, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.
[0124] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0125] In summary, the roller fault monitoring method, system and device based on sonar abnormal sound analysis provided by the present application have the following features:
[0126] Beneficial effects:
[0127] This application analyzes roller abnormal sound based on sonar sensors, can collect audio in real time and perform real-time analysis based on sonar sensors, realize the process of online monitoring, and reduce the safety hazards caused by regular inspections by on-site personnel. The roller fault monitoring method based on sonar abnormal sound analysis provided by this application can improve the efficiency of roller maintenance and reduce the cost of equipment maintenance operations on the basis of avoiding further development of faults.
[0128] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.
Claims
1. A roller fault monitoring method based on sonar abnormal sound analysis, characterized in that: The following steps are involved: Obtain noise audio monitoring data of each node in the target area; Performing signal preprocessing on the noise audio monitoring data to obtain a noise audio signal; Performing spectrum analysis based on the noise audio signal to obtain noise frequency distribution characteristics; The abnormal sound signal is extracted according to the noise frequency distribution characteristics, so as to obtain the fault position of the roller according to the early warning information and issue an early warning.
2. The roller fault monitoring method based on sonar abnormal sound analysis according to claim 1 is characterized in that: Acquiring noise audio monitoring data in the target area includes the following steps: Distribute and install monitoring equipment on the equipment in the target area; The audio monitoring data at each node is collected in real time based on the monitoring device; the audio monitoring data includes audio feature data and historical data.
3. The roller fault monitoring method based on sonar abnormal sound analysis according to claim 2 is characterized in that: The audio feature data includes: sound pressure level, main frequency and impulse response; The historical data includes: data acquisition time, abnormal node number, and abnormal feature information.
4. The roller fault monitoring method based on sonar abnormal sound analysis according to claim 1 is characterized in that: Performing signal preprocessing on the noise audio monitoring data to obtain a noise audio signal comprises the following steps: Filtering and signal amplification are performed based on the audio monitoring data to obtain a noise audio signal.
5. The roller fault monitoring method based on sonar abnormal sound analysis according to claim 1 is characterized in that: Performing spectrum analysis based on the noise audio signal to obtain noise frequency distribution characteristics includes the following steps: Performing spectrum analysis on the noise audio signal based on a Fourier transform algorithm to obtain frequency domain information of the noise audio; Based on the noise audio frequency domain information, obtaining the frequency components and amplitudes of the noise audio spectrum; Performing amplitude calculation based on the noise audio spectrum to obtain noise audio intensity; A noise frequency distribution feature is obtained based on the noise audio spectrum.
6. The roller fault monitoring method based on sonar abnormal sound analysis according to claim 1 is characterized in that: Extracting abnormal sound signals according to the noise frequency distribution characteristics and issuing early warnings to determine the fault location of the roller according to the early warning information includes the following steps: Determine whether the noise is an abnormal sound signal according to the frequency distribution characteristics of the noise in a certain time period; When the noise is an abnormal sound signal, the node position corresponding to the noise is the fault position; when the noise is other signals, the node position corresponding to the noise is not the fault position.
7. The roller fault monitoring method based on sonar abnormal sound analysis according to claim 5 is characterized in that: According to the noise frequency distribution characteristics in a certain time period, determining whether the noise is an abnormal sound signal includes the following steps: When the impact component of the working noise is greater than or equal to the impact component threshold, it is an abnormal sound signal; When the impact component of the working noise is less than the impact component threshold, it is a normal signal.
8. A roller fault monitoring system based on sonar abnormal sound analysis, characterized in that: include: An acquisition module is used to acquire noise audio monitoring data of each node in the target area; A data processing module is used to perform signal preprocessing on the noise audio monitoring data to obtain a noise audio signal; perform spectrum analysis based on the noise audio signal to obtain noise frequency distribution characteristics; The judgment module is used to extract the abnormal sound signal according to the noise frequency distribution characteristics, so as to determine the fault position of the roller according to the early warning information and issue an early warning.
9. A roller fault monitoring device based on sonar abnormal sound analysis, characterized in that: include: Processor and memory; The memory is used to store computer programs; The processor is connected to the memory and is used to execute the computer program stored in the memory so that the roller fault monitoring device based on sonar abnormal sound analysis executes the roller fault monitoring method based on sonar abnormal sound analysis as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the roller fault monitoring method based on sonar abnormal sound analysis as described in any one of claims 1 to 7 is implemented.
