CN115522995A - Method and system for detecting abnormal state of bucket wheel of door type bucket wheel machine based on audio signal - Google Patents

Method and system for detecting abnormal state of bucket wheel of door type bucket wheel machine based on audio signal Download PDF

Info

Publication number
CN115522995A
CN115522995A CN202211222212.5A CN202211222212A CN115522995A CN 115522995 A CN115522995 A CN 115522995A CN 202211222212 A CN202211222212 A CN 202211222212A CN 115522995 A CN115522995 A CN 115522995A
Authority
CN
China
Prior art keywords
bucket wheel
audio data
frequency domain
wheel machine
door type
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211222212.5A
Other languages
Chinese (zh)
Inventor
陈大明
邸大禹
孙智慧
王海彬
崔勇
曲小兵
朱旭
李全杰
刘庆杰
刘洪博
王冠迪
赵越
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changchun Thermal Power Plant Of Huaneng Jilin Power Generation Co ltd
Dalian Power Plant of Huaneng International Power Co Ltd
Original Assignee
Changchun Thermal Power Plant Of Huaneng Jilin Power Generation Co ltd
Dalian Power Plant of Huaneng International Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Changchun Thermal Power Plant Of Huaneng Jilin Power Generation Co ltd, Dalian Power Plant of Huaneng International Power Co Ltd filed Critical Changchun Thermal Power Plant Of Huaneng Jilin Power Generation Co ltd
Priority to CN202211222212.5A priority Critical patent/CN115522995A/en
Publication of CN115522995A publication Critical patent/CN115522995A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
    • F01D15/00—Adaptations of machines or engines for special use; Combinations of engines with devices driven thereby
    • F01D15/10—Adaptations for driving, or combinations with, electric generators
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
    • F01D21/00—Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for
    • F01D21/003—Arrangements for testing or measuring
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
    • F01D—NON-POSITIVE DISPLACEMENT MACHINES OR ENGINES, e.g. STEAM TURBINES
    • F01D25/00—Component parts, details, or accessories, not provided for in, or of interest apart from, other groups

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Abstract

The invention provides a method and a system for detecting abnormal states of a bucket wheel of a door type bucket wheel machine based on audio signals. According to the method, the field audio data are collected in real time in a mode that the sound sensor is arranged near the bucket wheel, abnormal operation conditions are found through processing modes of filtering, frequency domain transformation and the like on the audio signals, so that the operation state of the bucket wheel machine is alarmed, and the problem that operators can find the abnormal state of the bucket wheel in time after the bucket wheel machine is unattended is solved.

Description

Method and system for detecting abnormal state of bucket wheel of door type bucket wheel machine based on audio signal
Technical Field
The invention relates to the technical field of thermal power generation, in particular to a method and a system for detecting abnormal states of a bucket wheel of a gate-type bucket wheel machine based on audio signals.
Background
According to the operating requirements of cost reduction and efficiency improvement in the thermal power generation industry, most enterprises are carrying out or have completed unattended transformation of bucket wheel machines at present, and since unattended systems are put into operation, abnormal working conditions of the bucket wheel parts cannot be found by operators in the first time due to unattended operation on equipment, the integral function of the bucket wheel machines is easily disabled, and the equipment is stopped for a long time under severe conditions, so that serious economic loss is caused.
Disclosure of Invention
In light of the above-mentioned technical problems, a method and system for detecting abnormal state of a bucket wheel of a door type bucket wheel machine based on an audio signal are provided. The technical means adopted by the invention are as follows:
a door type bucket wheel machine bucket wheel abnormal state detection method based on audio signals comprises the following steps:
installing and deploying a sound sensor near a bucket wheel of the door type bucket wheel machine, and collecting field audio data;
preprocessing acquired audio data to convert continuous time signals into discrete time signals, wherein the preprocessing comprises signal discretization, original discrete audio data framing and Fourier frequency domain conversion, and further frequency domain characteristics of the audio signals are obtained;
and comparing the frequency domain features based on the preprocessing with a preset standard, and if the frequency domain features are abnormal, alarming to a control system.
Furthermore, the field audio data is connected with the main control system in an OPC ua communication mode, and the sound sensor records a section of audio data in a cycle of 3 seconds and generates a PCM format file.
Further, before the collected audio data is preprocessed, the following steps are provided:
detecting whether the bucket wheel is in a starting state, and if so, transmitting the field audio data to a master control system; if the audio data is in the non-starting state, the file generated by the sound sensor does not enter the main control system for analysis, and the recording of the next section of audio data is restarted.
Further, in the preprocessing process, the collection frequency of 16kHz is selected for discretization processing of signals.
Further, the original discrete audio data framing processing in the preprocessing process specifically includes the following steps:
framing original discrete audio data using a rectangular window:
x n [m]＝w(m)x[n+m] (1-1)
the rectangular window therein is represented as:
Figure BDA0003878682280000021
the short-time average amplitude is expressed as:
Figure BDA0003878682280000022
short time amplitude M n The value of (D) exceeding the predetermined value corresponds to a voiced sound segment, the short-term amplitude M n And when the number of the voiced sound segments is increased and the average amplitude value is overlarge, sending the preprocessed data to a Fourier transform module for secondary analysis.
Further, the comparing the frequency domain feature based on the preprocessing with the preset standard specifically comprises: performing statistical analysis on the discrete frequency domain characteristics, sampling and separating the frequency interval when the frequency interval is marked as effective data within 0-50000 HZ, intercepting 499 characteristics by taking 100Hz as a division unit, and screening the following rules again:
(1) Selecting a median M of the characteristic point amplitude values, and comparing the median M from a low frequency band to a high frequency band;
(2) Amplitude A i (0<i<500)；A i >M is a comparison result, A i <M is another alignment
(3) When the comparison result of one time is different from the comparison result of the last time, the comparison result is recorded as 1 time of change, the number n of times of change of the comparison result is counted after all comparisons are finished, and when n is larger than 30, the frequency of the response sound is greatly disturbed, and the abnormal sound is judged.
Furthermore, when an abnormality occurs to alarm the control system, the operator reads the abnormal sound signal, the system plays a real-time audio signal on site, and the operator confirms the fault.
The invention also discloses a system for detecting the abnormal state of the bucket wheel of the door type bucket wheel machine based on the audio signal, which comprises the following components:
the system comprises a sound sensor, a data processing module and a data processing module, wherein the sound sensor is used for collecting field audio data near a bucket wheel of the door type bucket wheel machine;
the sound signal processing unit is used for converting the collected field audio data into discrete time signals, and specifically comprises a signal discretization processing module, an original discrete audio data framing processing module and a Fourier frequency domain conversion processing module, so as to obtain the frequency domain characteristics of the audio signals;
and the sound signal judgment unit is used for comparing the frequency domain characteristics preprocessed by the sound signal processing unit with a preset standard and giving an alarm based on an abnormal judgment result.
According to the method, the field audio data are collected in real time in a mode of arranging the sound sensor near the bucket wheel, and the abnormal operation working condition is found by processing modes such as filtering and frequency domain transformation on the audio signal so as to give an alarm to the operation state of the bucket wheel machine, so that the problems of detection and diagnosis of the abnormal working condition of the bucket wheel after the existing bucket wheel machine is unattended are solved, manual regular inspection is not needed, whether the bucket wheel is in the normal working condition or not is judged remotely through the audio signal of the bucket wheel machine, and reliable technical support is provided for unattended operation of the bucket wheel machine.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a method for detecting abnormal conditions of a bucket wheel of a door type bucket wheel machine based on audio signals.
FIG. 2 is a frequency domain analysis diagram of the normal operation of the bucket wheel according to the embodiment of the present invention.
FIG. 3 is a frequency domain analysis diagram of bucket wheel anomalies (bucket wheel drop) in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention discloses a method for detecting an abnormal state of a bucket wheel of a gate-type bucket wheel machine based on an audio signal, including the following steps:
s00, mounting and deploying a sound sensor near a bucket wheel of the door type bucket wheel machine;
and S01, before use, the sound signal is checked to be output normally, and after network communication is normal, the detection process can be started.
And S02, the PC running the algorithm acquires a starting signal of the bucket wheel through an OPC ua communication mode, and the sound sensor records a section of audio data in a period of 3 seconds and generates a PCM format file.
And S03, when the current bucket wheel is detected to be in an un-started state, the data of the PCM file does not enter algorithm analysis, and recording of a next section of audio data is started again.
And S04, when a bucket wheel running signal is detected, the audio data file recorded at the moment enters an algorithm for processing and analysis. The processing and analysis through the algorithm in this embodiment is specifically a frequency domain feature analysis part of steps S05 to S07.
S05, in order to facilitate the computer to analyze and process the audio, in this embodiment, a certain rule needs to be set to perform sampling processing on the analog audio signal, and the function of the sampling processing is to change a continuous time signal into a discrete time signal.
According to the Nyquist theory, the sampling frequency is not lower than twice of the highest frequency of the sound signal, and the sampling frequency of 16kHz is selected for signal discretization processing by analyzing the audio signal actually acquired on site and comprehensively considering the actual audio restoration quality.
Quantization accuracy of sampling amplitude in this real-time example, 16 bytes occupying computer storage space for quantization are selected for considering both the calculation amount and the audio quality, and the analysis effect meets the use requirement through practical application. So far, the pre-processing of the audio data is completed.
Because the calculation amount of the fourier frequency domain conversion is very large, in consideration of saving the operation cost, the short-time average amplitude analysis is performed on the preprocessed audio data in the embodiment in advance.
Framing original discrete audio data using a rectangular window:
x n [m]＝w(m)x[n+m] (1-1)
the rectangular window therein is represented as:
Figure BDA0003878682280000051
the short-time average amplitude is expressed as:
Figure BDA0003878682280000052
short time amplitude M n The value of (D) exceeding the predetermined value corresponds to a voiced speech segment, the short-term amplitude M n If the numerical value of the data is smaller than the preset value, the data corresponds to unvoiced segments, and when the number of the voiced segments is increased and the average amplitude numerical value is overlarge, the preprocessed data are sent to a Fourier transform module for secondary analysis.
S06 is defined from the DFT of a finite-length discrete signal x (N), N =0,1,2.
Figure BDA0003878682280000053
Decomposition of x (n) into the sum of two sequences of even and odd numbers x (n) = x 1 (n)+x 2 (n)；x 1 (n) and x 2 (N) are each N/2, x in length 1 (n) is an odd number sequence, x 2 (n) is an even sequence, then:
Figure BDA0003878682280000054
due to the fact that
Figure BDA0003878682280000055
Then
Figure BDA0003878682280000056
Through the conversion, the calculation amount of Fourier transform is reduced, and the frequency domain characteristics of the audio signal are obtained.
S07, as shown in figures 2 and 3, performing statistical analysis on the discrete frequency domain characteristics, and when the frequency is 0-50000 HZ, marking as effective data, in the figures, obtaining a corresponding relation between the sound wave amplitude (the amplitude is subjected to normalization operation) corresponding to the frequency after Fourier transform and the frequency, wherein the abscissa is the frequency, and the ordinate is the sound wave amplitude.
The abnormality determination method includes:
(1) Selecting a median M of the characteristic point amplitude values, and comparing the median M from a low frequency band to a high frequency band;
(2) Amplitude A i (0<i<500)；A i >M is a comparison result, A i <M is another alignment
(3) When the comparison result of one time is different from the comparison result of the last time, the change is recorded as 1 time, the number n of times of the change of the comparison result is counted after all comparisons are finished, and when n is greater than 30, the frequency of the reaction sound is greatly disturbed, and the abnormal sound is judged.
And S08, sending an alarm to an upper computer of the control system through an OPC interface, and informing an operator of finding the abnormality of sound detection.
And S09, the operator clicks a confirmation button, and the system plays a real-time audio signal on site to confirm the fault of the operator.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and these modifications or substitutions do not depart from the spirit of the corresponding technical solutions of the embodiments of the present invention.

Claims (8)

1. A method for detecting abnormal state of a bucket wheel of a door type bucket wheel machine based on an audio signal is characterized by comprising the following steps:
installing and deploying a sound sensor near a bucket wheel of the door type bucket wheel machine, and collecting field audio data;
preprocessing acquired audio data to change continuous time signals into discrete time signals, wherein the preprocessing comprises signal discretization, original discrete audio data framing and Fourier frequency domain conversion, and then the frequency domain characteristics of the audio signals are obtained;
and comparing the frequency domain features based on the preprocessing with a preset standard, and if the frequency domain features are abnormal, alarming to a control system.
2. The method for detecting the abnormal state of the door-type bucket wheel of the bucket wheel machine based on the audio signal as claimed in claim 1, wherein field audio data are connected with a main control system in an OPC ua communication mode, and a sound sensor collects a piece of audio data in a period of 3 seconds and generates a file in a PCM format.
3. The method for detecting the abnormal state of the bucket wheel of the door type bucket wheel machine based on the audio signal as claimed in claim 1 or 2, wherein the method comprises the following steps before preprocessing collected audio data:
detecting whether the bucket wheel is in a starting state, and if so, transmitting the field audio data to a master control system; if the audio data is in the non-starting state, the file generated by the sound sensor does not enter the main control system for analysis, and the recording of the next section of audio data is restarted.
4. The method for detecting the abnormal state of the bucket wheel of the door type bucket wheel machine based on the audio signal as claimed in claim 1, wherein in the preprocessing process, the acquisition frequency of 16kHz is selected for discretization processing of the signal.
5. The method for detecting the abnormal state of the bucket wheel of the door type bucket wheel machine based on the audio signal according to claim 1 or 4, wherein the original discrete audio data in the preprocessing process are processed in a framing mode, and the method specifically comprises the following steps:
framing original discrete audio data using a rectangular window:
x n [m]＝w(m)x[n+m] (1-1)
the rectangular window therein is represented as:
Figure FDA0003878682270000021
the short-time average amplitude is expressed as:
Figure FDA0003878682270000022
short time amplitude M n The value of (D) exceeding the predetermined value corresponds to a voiced speech segment, the short-term amplitude M n And when the number of the voiced sound segments is increased and the average amplitude value is overlarge, sending the preprocessed data to a Fourier transform module for secondary analysis.
6. The method for detecting the abnormal state of the bucket wheel of the door type bucket wheel machine based on the audio signal according to claim 5, wherein the comparison between the frequency domain feature based on the preprocessing and the preset standard is specifically as follows: and (3) performing statistical analysis on the discrete frequency domain characteristics, sampling and separating the frequency interval when the frequency interval is marked as effective data within 0-50000 HZ, intercepting 499 characteristics by taking 100Hz as a division unit, and screening again according to the following rules:
(1) Selecting a median M of the characteristic point amplitude values, and comparing the median M from a low frequency band to a high frequency band;
(2) Amplitude A i (0<i<500)；A i >M is a comparison result, A i <M is another alignment
(3) When the comparison result of one time is different from the comparison result of the last time, the change is recorded as 1 time, the number n of times of the change of the comparison result is counted after all comparisons are finished, and when n is greater than 30, the frequency of the reaction sound is greatly disturbed, and the abnormal sound is judged.
7. The method for detecting the abnormal state of the bucket wheel of the door type bucket wheel machine based on the audio signal as claimed in claim 1, wherein when the abnormality occurs, an operator reads the abnormal sound signal and the system plays a real-time audio signal on site, and the operator confirms the fault.
8. A door-type bucket wheel abnormal state detecting system based on audio signals is characterized by comprising:
the sound sensor is used for collecting field audio data near the bucket wheel of the door type bucket wheel machine;
the sound signal processing unit is used for converting the collected field audio data into discrete time signals, and specifically comprises a signal discretization processing module, an original discrete audio data framing processing module and a Fourier frequency domain conversion processing module to obtain the frequency domain characteristics of the audio signals;
and the sound signal judging unit is used for comparing the frequency domain characteristics preprocessed by the sound signal processing unit with a preset standard and giving an alarm based on an abnormal judgment result.
CN202211222212.5A 2022-10-08 2022-10-08 Method and system for detecting abnormal state of bucket wheel of door type bucket wheel machine based on audio signal Pending CN115522995A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211222212.5A CN115522995A (en) 2022-10-08 2022-10-08 Method and system for detecting abnormal state of bucket wheel of door type bucket wheel machine based on audio signal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211222212.5A CN115522995A (en) 2022-10-08 2022-10-08 Method and system for detecting abnormal state of bucket wheel of door type bucket wheel machine based on audio signal

Publications (1)

Publication Number Publication Date
CN115522995A true CN115522995A (en) 2022-12-27

Family

ID=84701803

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211222212.5A Pending CN115522995A (en) 2022-10-08 2022-10-08 Method and system for detecting abnormal state of bucket wheel of door type bucket wheel machine based on audio signal

Country Status (1)

Country Link
CN (1) CN115522995A (en)

Similar Documents

Publication Publication Date Title
JP2002022617A (en) Apparatus for diagnosing bearing
CN111653291B (en) Intelligent health monitoring method for power equipment based on voiceprint
CN112903815A (en) Monitoring method and monitoring system for bridge expansion joint state
CN113670434B (en) Method and device for identifying sound abnormality of substation equipment and computer equipment
WO2023279382A1 (en) Motor bearing running state fault detection method and system
CN116626544B (en) Frequency domain trigger data acquisition system and method
CN113551765A (en) Sound spectrum analysis and diagnosis method for equipment fault
CN116383633A (en) Method and system for detecting faults of machine-made sand vibrating screen through multi-factor comprehensive analysis
CN113567162A (en) Fan fault intelligent diagnosis device and method based on acoustic sensor
CN113982850A (en) Fan comprehensive health analysis method and system fusing high-frequency and low-frequency signals
CN115687969A (en) Low-voltage transformer fault diagnosis method based on sound characteristic analysis
JP2002140090A (en) Abnormality monitor device
CN112666430B (en) Intelligent fault detection method and system for voiceprint of transformer
CN115522995A (en) Method and system for detecting abnormal state of bucket wheel of door type bucket wheel machine based on audio signal
CN117331790A (en) Machine room fault detection method and device for data center
CN114242085A (en) Fault diagnosis method and device for rotating equipment
CN110579657A (en) Transformer fault detection system based on vibration signal analysis and detection method thereof
CN111983295A (en) Equipment fault prediction method and system
CN112814890A (en) Method for detecting pump machine fault based on voiceprint and vibration
CN112345648A (en) High-voltage circuit breaker cam crack fault detection device and method
CN110907028A (en) Cable vibration signal type detection method and system
JP3952242B2 (en) Reactor structure monitoring device
CN113763679B (en) Method and device for monitoring abnormal sound of gas insulated enclosed type combined electrical apparatus
JP7202248B2 (en) PLANT CONDITION MONITORING SYSTEM AND PLANT CONDITION MONITORING METHOD
CN116705271B (en) Medical flushing equipment operation monitoring system based on big data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination