CN113672859A - Switch point machine fault acoustic diagnosis system - Google Patents
Switch point machine fault acoustic diagnosis system Download PDFInfo
- Publication number
- CN113672859A CN113672859A CN202110944630.4A CN202110944630A CN113672859A CN 113672859 A CN113672859 A CN 113672859A CN 202110944630 A CN202110944630 A CN 202110944630A CN 113672859 A CN113672859 A CN 113672859A
- Authority
- CN
- China
- Prior art keywords
- module
- acoustic
- signal
- acquisition time
- information
- 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.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 13
- 230000007613 environmental effect Effects 0.000 claims abstract description 86
- 238000001514 detection method Methods 0.000 claims abstract description 74
- 238000007781 pre-processing Methods 0.000 claims abstract description 68
- 238000007405 data analysis Methods 0.000 claims abstract description 44
- 238000011156 evaluation Methods 0.000 claims abstract description 31
- 230000009467 reduction Effects 0.000 claims description 47
- 238000004458 analytical method Methods 0.000 claims description 41
- 239000013598 vector Substances 0.000 claims description 32
- 238000000034 method Methods 0.000 claims description 27
- 230000008569 process Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 17
- 238000012423 maintenance Methods 0.000 claims description 12
- 238000003672 processing method Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000000513 principal component analysis Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 241000283707 Capra Species 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000011946 reduction process Methods 0.000 description 3
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Computing Systems (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a turnout switch machine fault acoustic diagnosis system, which comprises a signal acquisition module, a storage module, a data analysis module, a signal preprocessing module, an acoustic detection module and an evaluation module, wherein the signal acquisition module is used for acquiring and storing detection data information in the storage module, the evaluation module analyzes the existing environmental information and fault detection results to obtain main influence factors, then the signal preprocessing module preprocesses the main influence factors to obtain preprocessing results, the data analysis module analyzes the preprocessing results of the signal preprocessing module to obtain noise influence parameters, then the environmental information in an acquisition time period is analyzed to obtain environmental influence parameters, finally a threshold value is obtained by the preprocessing results, the noise influence parameters and the environmental influence parameters, and a characteristic subset of the acoustic signals is selected through the threshold value, the selection of the characteristics of the acoustic signal by the threshold improves the accuracy of the detection of the acoustic signal.
Description
Technical Field
The invention relates to the technical field of acoustic diagnosis, in particular to a turnout point switch fault acoustic diagnosis system.
Background
The turnout switch machine is used for converting different running directions of a train, the turnout switch machine, a signal machine and a track circuit are three most critical outdoor parts in a railway signal system, and as the turnout switch machine is placed outdoors for a long time, the working state of the turnout switch machine is easily influenced by factors such as external environment (foreign matters clamped between point and base rails and the like) and extreme weather (rain, snow, ice and the like), and the fault problem of the turnout switch machine is one of main reasons influencing the running efficiency and running safety of the train; when the switch machine has mechanical failure, the physical structure of the switch machine can be changed, from the acoustic angle, on the premise of no change of acquisition equipment, the characteristics of an acoustic signal are jointly determined by a signal source and a propagation medium, and the change of the physical structure of the switch machine can certainly cause the change of the signal source or the propagation medium, so that the characteristics of the acoustic signal are changed, and as long as the acoustic signal characteristic points which are changed along with the change of the physical structure can be found and detected, the switch machine can be judged to be in normal operation or in failure; but there can be the noise elimination thoroughly in the time of handling acoustic signal, excessive noise elimination, the characteristic subset of acoustic signal selects inaccurate, the various scheduling problem of fault type for acoustic signal that can not accurate differentiation normal goat and the acoustic signal of unusual goat, so that discover the mechanical fault of switch goat in time, in order to improve the accuracy to switch goat acoustics detected signal, can in time take measures to reduce train operation risk, improve train operating efficiency, this system provides a switch goat trouble acoustics detection diagnostic system.
Disclosure of Invention
In view of the above situation and in order to overcome the defects of the prior art, an object of the present invention is to provide a switch machine failure acoustic diagnosis system, wherein an evaluation module analyzes environmental information when acquiring acoustic signals and compares the environmental information with the acoustic signals when detecting the failure type, a data analysis module combines the noise reduction process and the detection process of the acoustic signals with the analysis result of the environmental information to obtain a threshold value when detecting the acoustic signals, and selects a feature subset of the acoustic signals of different acquisition time periods according to the threshold value, thereby improving the accuracy of detecting the acoustic signals of the switch machine.
The technical scheme for solving the problem is that the turnout switch machine fault acoustic diagnosis system comprises a signal acquisition module, a storage module, a data analysis module, a signal preprocessing module, an acoustic detection module and an evaluation module, wherein the signal acquisition module is used for acquiring detection data information of the turnout switch machine, and the data analysis module is used for analyzing the detection data information to obtain an environmental influence parameter and a threshold value; the system management process is as follows:
(1) the signal acquisition module uploads the acquired detection data information for detecting the turnout switch machine to the storage module;
(2) the data analysis module can analyze the detected data information, firstly, the environmental information in the detected data information is analyzed to obtain a noise influence parameter and an environmental influence parameter, and then, a selection threshold value when the characteristics of the acoustic signal in the detected data information are selected is obtained through the analysis of the environmental influence parameter and the noise influence parameter, wherein the specific analysis process is as follows:
step one, a data analysis module calls all detection data information of a turnout switch machine, calls acquisition time information in the detection data information, and records an acquisition time period in the acquisition time information as t1,t2,t3...tnN represents the collection times, and the signal preprocessing module preprocesses the acoustic signals collected in different collection time periods to obtain preprocessing results according to the main influence factors obtained by the evaluation module on the evaluation analysis results of the detection data information of the collection time periodsProcessing the result, and sending the pre-processing result to a data analysis module, wherein the data analysis module analyzes the filtered noise in the pre-processing result to obtain a noise influence parameter;
step two, the data analysis module extracts the environment characteristic vector (X) of the acquisition time period from the environment information1,X2,X3...Xs) And s represents the number of the environment characteristic variables, the environment characteristic vector of each acquisition time period is analyzed by a principal component analysis method to obtain main environment characteristics, and the formula of the specific process is as follows:
Fi=a1iX1+a2iX2+…+asiXs;
wherein a is1i、a2i、asiFor the influence coefficients of elements in the environmental feature vector, i ∈ [1, n ]]I denotes the subscript of the acquisition time period, analysis F by principal component analysisiObtaining the main environmental characteristics in n corresponding to all the acquisition time periods, wherein each main environmental characteristic represents the environmental characteristic with the largest influence in the corresponding acquisition time period, and obtaining an environmental characteristic matrix according to the influence degree of the maximum environmental characteristics on the acoustic signals in all the acquisition time periodsCalculating a trace of the environment characteristic matrix X and recording the trace as an environment influence parameter T;
step three, the data analysis module further analyzes the preprocessing result, the environment characteristic matrix X, the noise influence parameter H and the environment influence parameter of the signal preprocessing module to obtain a threshold value G when the characteristics of the acoustic signal are selected, the detected data information also comprises the noise intensity, the signal-to-noise ratio and the acoustic signal of each acquisition time period, and the calculation formula is as follows:
wherein G represents a vector, each element in G represents a threshold value of a corresponding acquisition time period, i represents a label of the acquisition time period, and i belongs to [1, n ];
(3) the acoustic detection module selects a proper feature subset according to a threshold value obtained by analysis of the data analysis module, the acoustic detection module performs joint detection on acoustic signals to obtain a detection result, when the detection result indicates that the turnout switch machine is in fault, the detection module sends maintenance information to maintenance personnel, and the maintenance personnel perform timely inspection and maintenance on the turnout switch machine.
The evaluation module evaluates and analyzes environmental information in the detection data information and the detected fault information to obtain main influence factors, the signal preprocessing module preprocesses acoustic signals of different collected time periods according to the main influence factors to obtain preprocessing results, and the specific analysis process is as follows:
step 1, an evaluation analysis module evaluates and analyzes environmental information in the detection data information and detected fault information to obtain main influence factors corresponding to each acquisition time period;
step 2, collecting time period t in the first time1Iteration is carried out as a starting point, n acquisition time periods are divided into n-1 acquisition tuples, and two adjacent acquisition time periods are one acquisition tuple;
step 3, when the main influence factors corresponding to one acquisition tuple are the same, the signal preprocessing module calls different noise reduction processing methods of the acoustic signals from the storage module, processes the acoustic signals in two acquisition time periods in one acquisition tuple by using the different noise reduction processing methods to obtain two noise reduction processing results, wherein the two noise reduction processing results are the noise reduction acoustic signals subjected to noise reduction processing, and calculates the correlation coefficient of the two noise reduction acoustic signals;
step 4, when the main influence factors corresponding to one acquisition tuple are different, two noise reduction processing results are obtained by adopting the same noise reduction processing method, and calculation is also carried outObtaining correlation coefficient of two noise reduction processing results, and obtaining correlation vector R ═ (R) according to the correlation coefficient1,r2,r3...rn-1) The calculation equation of the correlation coefficient is as follows:
n is the number of the characteristics in the characteristic set of the noise-reduced acoustic signals after noise reduction, X, Y are characteristic vectors of the signals, X (j), Y (j) represents parameter values of j-th characteristics, and the preprocessing results obtained by the signal preprocessing module through analysis comprise correlation relation vectors, filtered noise and filtered acoustic signals and are sent to the data analysis module.
The evaluation analysis module evaluates and analyzes the environmental information in the detection data information and the detected fault information to obtain the main influence factors corresponding to each acquisition time period, the fault information comprises acoustic signals corresponding to faults, acquisition time periods, a noise reduction processing method, environmental information and fault types, analyzing the environmental information in the fault information of the same fault type, calculating the influence degree of all environmental influence factors on the fault, and calculating fixed ratio of influence degrees of different environmental influence factors on the fault to make the fixed ratio correspond to the fault type, analyzing the ratio of each acquisition time period by the evaluation module when analyzing different acquisition time periods, and comparing the data with a fixed ratio, determining the environmental influence factor with the largest ratio in the ratio as a main influence factor, and sending the main influence factor in each acquisition time period to the signal preprocessing module.
The data analysis module analyzes the filtered noise and the correlation vector in the preprocessing result to obtain noise influence parameters, firstly calculates the difference of signal-to-noise ratios of the acoustic signals in each acquisition time period before and after filtering, and then weights each element in the correlation vector according to the difference of the signal-to-noise ratios to obtain the noise influence parameters, the data acquisition module monitors each part of the turnout switch machine, and acquires the acoustic signals of the turnout switch machine operation once every other time period.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages;
1. an evaluation module of the system obtains an environmental influence factor ratio through analysis of existing detection results of environmental information and faults, then obtains a main influence factor by utilizing the environmental influence factor ratio, and then sends the main influence factor to a signal preprocessing module, the signal preprocessing module judges the environmental information in each acquisition time period by utilizing the main influence factor, selects different noise reduction methods to preprocess acoustic signals according to the judgment result, obtains a correlation coefficient by comparing preprocessing results of the acoustic signals in the acquisition time periods in the acquisition tuples with the same main influence factor through comparing different methods in one acquisition tuple, and reflects the generation of noise reduction errors of different signals in the noise reduction process by utilizing the correlation coefficient.
2. The data analysis module analyzes the evaluation result of the evaluation module, the preprocessing result of the signal preprocessing module and the environmental signal, firstly analyzes the preprocessing result of the signal preprocessing module to obtain a noise influence parameter, analyzes the environmental information in the acquisition time period to obtain an environmental influence parameter, then obtains a threshold value through the preprocessing result, the noise influence parameter and the environmental influence parameter, selects the characteristic subset of the acoustic signal through the threshold value, can correspond to different characteristic subsets under the selection of different threshold values, improves the accuracy of the detection of the fault acoustic signal of the turnout switch machine through the selection of the threshold value, and solves the error caused by the characteristic selection of the acoustic signal.
Drawings
FIG. 1 is an overall block diagram of the system;
FIG. 2 is a flow chart of the overall calculation of the present system;
FIG. 3 is an analysis flow diagram of a signal pre-processing module;
FIG. 4 is an analysis flow diagram of the data analysis module.
Detailed Description
The foregoing and other aspects, features and advantages of the invention will be apparent from the following more particular description of embodiments of the invention, as illustrated in the accompanying drawings in which reference is made to figures 1 to 4. The structural contents mentioned in the following embodiments are all referred to the attached drawings of the specification.
A turnout switch machine fault acoustic diagnosis system comprises a signal acquisition module, a storage module, a data analysis module, a signal preprocessing module, an acoustic detection module and an evaluation module, wherein the signal acquisition module is used for acquiring detection data information of a turnout switch machine, and the data analysis module is used for analyzing the detection data information to obtain environmental influence parameters and threshold values; in the acoustic detection, the accuracy of the fault detection of the turnout switch machine is influenced between the accuracy of the acoustic signal detection, but each stage of the acquisition, transmission, pretreatment and detection of the acoustic signal can be influenced by a plurality of external factors, the accuracy of the acoustic signal detection can be improved by reducing the noise and selecting the characteristics of the acoustic signal according to the environmental information when the acoustic signal is acquired and the detected information, and the system management process is specifically as follows:
(1) the signal acquisition module uploads the acquired detection data information for detecting the turnout switch machine to the storage module;
(2) the data analysis module can analyze the detected data information, firstly, the environmental information in the detected data information is analyzed to obtain a noise influence parameter and an environmental influence parameter, and then, a selection threshold value when the characteristics of the acoustic signal in the detected data information are selected is obtained through the analysis of the environmental influence parameter and the noise influence parameter, wherein the specific analysis process is as follows:
step one, a data analysis module calls all detection data information of a turnout switch machine, calls acquisition time information in the detection data information, and records an acquisition time period in the acquisition time information as t1,t2,t3...tnN represents the collection times, and the signal preprocessing module obtains different main influence factor pairs according to the evaluation analysis result of the evaluation module on the detection data information of the collection time periodThe method comprises the steps that acoustic signals acquired in an acquisition time period are preprocessed to obtain a preprocessing result, the preprocessing result is sent to a data analysis module, the data analysis module analyzes filtered noise in the preprocessing result to obtain noise influence parameters, the noise in the acoustic signals cannot be completely eliminated, abnormal signals in the acoustic signals when a turnout switch machine is abnormal in fault can be detected more accurately by improving the signal-to-noise ratio of the acoustic signals, the noise of the acoustic signals is influenced by environmental information, and the environment during acquisition also has certain influence on the fault of the turnout switch machine;
step two, the data analysis module extracts the environment characteristic vector (X) of the acquisition time period from the environment information1,X2,X3...Xs) And s represents the number of the environment characteristic variables, the environment characteristic vector of each acquisition time period is analyzed by a principal component analysis method to obtain main environment characteristics, and the formula of the specific process is as follows:
Fi=a1iX1+a2iX2+…+asiXs;
wherein a is11For each element's influence coefficient in the environmental feature vector, i ∈ [1, n ∈ ]]I is a subscript of the acquisition time period, the formula is one of the formulas corresponding to one environmental feature vector, and principal component analysis is performed through s corresponding formulas of one environmental feature vector to obtain corresponding FiAnalysis of F by principal component analysisiObtaining main environmental characteristics in n corresponding to all acquisition time periods, wherein each main environmental characteristic represents the environmental characteristic with the largest influence in the corresponding acquisition time period, the determined influence degrees of the maximum environmental characteristics on the acoustic signals are different, the influence degree of the environmental characteristic with the largest influence on each acoustic characteristic of the acoustic signals is calculated to obtain an environmental influence vector, an environmental characteristic matrix is obtained according to the environmental influence vector of each acquisition time period, and an environmental characteristic matrix is obtained according to the influence degrees of the main environmental characteristics on the acoustic signals in all acquisition time periodsCalculating a trace of the environment characteristic matrix X and recording the trace as an environment influence parameter T;
step three, the data analysis module further analyzes the preprocessing result, the environment characteristic matrix X, the noise influence parameter H and the environment influence parameter of the signal preprocessing module to obtain a threshold value G when the characteristics of the acoustic signal are selected, the detected data information also comprises the noise intensity, the signal-to-noise ratio and the acoustic signal of each acquisition time period, and the calculation formula is as follows:
wherein G represents a vector, each element in G represents a threshold corresponding to an acquisition time period, T represents an environmental impact parameter, H represents a noise impact parameter, C represents a weighting number of the environment, i represents a label of the acquisition time period, and i belongs to [1, n ];
(3) the acoustic detection module selects a proper feature subset according to a threshold value obtained by analysis of the data analysis module, the acoustic detection module performs joint detection on acoustic signals to obtain a detection result, when the detection result indicates that the turnout switch machine is in fault, the detection module sends maintenance information to maintenance personnel, and the maintenance personnel perform timely inspection and maintenance on the turnout switch machine.
The evaluation module evaluates and analyzes environmental information in the detection data information and detected fault information to obtain main influence factors, the signal preprocessing module preprocesses acoustic signals of different acquired time periods to obtain preprocessing results according to the main influence factors, the signal preprocessing module performs noise reduction processing on the acoustic signals acquired by the signal acquisition module, the adopted noise reduction mode is a noise reduction method stored in the storage module, different acoustic signals are subjected to noise reduction by adopting different noise reduction methods, so that the noise reduction degree of the acoustic signals cannot damage the acoustic signals by adopting dynamic noise reduction processes of the different noise reduction methods, and the specific analysis process is as follows:
step 1, an evaluation analysis module evaluates and analyzes environmental information in the detection data information and detected fault information to obtain main influence factors corresponding to each acquisition time period;
step 2, collecting time period t in the first time1Iteration is carried out as a starting point, n acquisition time periods are divided into n-1 acquisition tuples, and two adjacent acquisition time periods are one acquisition tuple;
step 3, when the main influence factors corresponding to one acquisition tuple are the same, the signal preprocessing module calls different noise reduction processing methods of the acoustic signals from the storage module, processes the acoustic signals in two acquisition time periods in one acquisition tuple by using the different noise reduction processing methods to obtain two noise reduction processing results, wherein the two noise reduction processing results are the noise reduction acoustic signals subjected to noise reduction processing, and calculates the correlation coefficient of the two noise reduction acoustic signals;
and 4, when the main influence factors corresponding to one acquisition tuple are different, obtaining two noise reduction processing results by adopting the same noise reduction processing method, calculating a correlation coefficient of the two noise reduction processing results, and obtaining a correlation vector R ═ according to the correlation coefficient1,r2,r3...rn-1) The calculation equation of the correlation coefficient is as follows:
n is the number of the characteristics in the characteristic set of the noise-reduced acoustic signals after noise reduction, X, Y are characteristic vectors of the signals, X (j), Y (j) represents parameter values of j-th characteristics, and the preprocessing results obtained by the signal preprocessing module through analysis comprise correlation relation vectors, filtered noise and filtered acoustic signals and are sent to the data analysis module.
The evaluation analysis module evaluates and analyzes environmental information in the detection data information and detected fault information to obtain main influence factors corresponding to each acquisition time period, the fault information comprises acoustic signals corresponding to faults, acquisition time periods, a noise reduction processing method, environmental information and fault types, the evaluation module analyzes the detection information comprising detection results stored in the storage module, the detection information comprises fault information, the fault information corresponds to the environmental information through the analysis of the fault information and the environmental information, analyzes the environmental information in the fault information of the same fault type, calculates the influence degrees of all the environmental influence factors on the faults, calculates the influence coefficient corresponding to each environmental influence factor by using a logistic regression method, and calculates the fixed ratio of the influence degrees of different environmental influence factors on the faults by using the influence coefficients, the fixed ratio is made to correspond to the fault type, when the evaluation module analyzes different acquisition time periods, the ratio of each acquisition time period is analyzed and compared with the fixed ratio, the environmental influence factor with the largest ratio in the ratio is determined as a main influence factor, and the main influence factor in each acquisition time period is sent to the signal preprocessing module.
The data analysis module analyzes the filtered noise and the correlation vector in the preprocessing result to obtain noise influence parameters, firstly calculates the difference of signal-to-noise ratios of the acoustic signals in each acquisition time period before and after filtering, and then weights each element in the correlation vector according to the difference of the signal-to-noise ratios to obtain the noise influence parameters, the data acquisition module monitors each part of the turnout switch machine, and acquires the acoustic signals of the turnout switch machine operation once every other time period.
The acoustic detection module performs joint detection on acoustic signals subjected to noise reduction processing by the signal preprocessing module according to the analysis result of the data analysis module, selects different acoustic signal feature subsets according to the threshold value analyzed and processed by the data analysis module, performs detection and analysis on the acoustic signals by using the acoustic signal feature subsets and an analysis method in machine learning, judges the acoustic signals, trains the feature subsets of the acoustic signals by using the analysis method in machine learning, detects and processes the acoustic signals, and detects abnormal signals with faults of the turnout switch.
When the system is used specifically, the system mainly comprises a signal acquisition module, a storage module, a data analysis module, a signal preprocessing module, an acoustic detection module and an evaluation module, wherein the signal acquisition module is used for acquiring detection data information of a turnout switch machine and storing the detection data information in the storage module, the evaluation module obtains an environmental influence factor ratio by analyzing the existing environmental information and a fault detection result, then obtains a main influence factor by utilizing the environmental influence factor ratio, and then sends the main influence factor to the signal preprocessing module, the signal preprocessing module judges the environmental information in each acquisition time period by utilizing the main influence factor, selects different noise reduction methods to preprocess the acoustic signal according to the judgment result, and obtains the preprocessing results of the acoustic signal in the acquisition time periods in the acquisition tuple with the same main influence factor by comparing different methods in one acquisition tuple The data analysis module analyzes the correlation vector of the signal preprocessing module preprocessing result to obtain a noise influence parameter, analyzes the environment information in the acquisition time period to obtain an environment influence parameter, and finally obtains a threshold value through the preprocessing result, the noise influence parameter and the environment influence parameter, selects the feature subset of the acoustic signal through the threshold value, the threshold values of the selected feature subset of the acoustic signal in different acquisition time periods can be different, the different feature subsets can be corresponding to different selection of the threshold value, the accuracy of the detection of the fault acoustic signal of the turnout switch machine is improved through the selection of the threshold value, the error caused by the feature selection of the acoustic signal is solved, and the problems of model complexity and popularization capability reduction caused by the long time required by feature analysis and model training when the selected feature parameters are excessive are solved, and the problem that different abnormal switch machine sound types are difficult to cover when the characteristic parameters are too few and the accuracy of classification is obviously reduced is also solved.
While the invention has been described in further detail with reference to specific embodiments thereof, it is not intended that the invention be limited to the specific embodiments thereof; for those skilled in the art to which the present invention pertains and related technologies, the extension, operation method and data replacement should fall within the protection scope of the present invention based on the technical solution of the present invention.
Claims (5)
1. The acoustic diagnosis system for the turnout switch machine fault is characterized by comprising a signal acquisition module, a storage module, a data analysis module, a signal preprocessing module, an acoustic detection module and an evaluation module, wherein the signal acquisition module is used for acquiring detection data information of the turnout switch machine, and the data analysis module is used for analyzing the detection data information to obtain an environmental influence parameter and a threshold value; the system management process is as follows:
(1) the signal acquisition module uploads the acquired detection data information for detecting the turnout switch machine to the storage module;
(2) the data analysis module can analyze the detected data information, firstly, the environmental information in the detected data information is analyzed to obtain a noise influence parameter and an environmental influence parameter, and then, a selection threshold value when the characteristics of the acoustic signal in the detected data information are selected is obtained through the analysis of the environmental influence parameter and the noise influence parameter, wherein the specific analysis process is as follows:
step one, a data analysis module calls all detection data information of a turnout switch machine, calls acquisition time information in the detection data information, and records an acquisition time period in the acquisition time information as t1,t2,t3…tnN represents the acquisition times, the signal preprocessing module obtains main influence factors according to the evaluation and analysis results of the evaluation module on the detection data information of the acquisition time period, preprocessing acoustic signals acquired in different acquisition time periods to obtain preprocessing results, and sends the preprocessing results to the data analysis module, and the data analysis module analyzes the noise according to the filtered noise in the preprocessing results to obtain noise influence parameters;
step two, the data analysis module extracts the environment characteristic vector (X) of the acquisition time period from the environment information1,X2,X3...Xs) And s represents the number of the environment characteristic variables, the environment characteristic vector of each acquisition time period is analyzed by a principal component analysis method to obtain main environment characteristics, and the formula of the specific process is as follows:
Fi=a1iX1+a2iX2+…+asiXs;
wherein a is1i、a2i、asiFor the influence coefficients of elements in the environmental feature vector, i ∈ [1, n ]]I denotes the subscript of the acquisition time period, analysis F by principal component analysisiObtaining main environmental characteristics in n corresponding to all the acquisition time periods, wherein each main environmental characteristic represents the environmental characteristic with the largest influence in the corresponding acquisition time period, and obtaining an environmental characteristic matrix according to the influence degree of the main environmental characteristics and the analysis result of the evaluation module on the acoustic signals in all the acquisition time periodsCalculating a trace of the environment characteristic matrix X and recording the trace as an environment influence parameter T;
step three, the data analysis module further analyzes the preprocessing result, the environment characteristic matrix X, the noise influence parameter H and the environment influence parameter of the signal preprocessing module to obtain a threshold value G when the characteristics of the acoustic signal are selected, the detected data information also comprises the noise intensity, the signal-to-noise ratio and the acoustic signal of each acquisition time period, and the calculation formula is as follows:
wherein G represents a vector, each element in G represents a threshold value of a corresponding acquisition time period, i represents a label of the acquisition time period, and i belongs to [1, n ];
(3) the acoustic detection module selects a proper feature subset according to a threshold value obtained by analysis of the data analysis module, the acoustic detection module performs joint detection on acoustic signals to obtain a detection result, when the detection result indicates that the turnout switch machine is in fault, the detection module sends maintenance information to maintenance personnel, and the maintenance personnel perform timely inspection and maintenance on the turnout switch machine.
2. The switch machine fault acoustic diagnosis system of claim 1, wherein the evaluation module evaluates and analyzes environmental information in the detection data information and fault information that has been detected to obtain main influence factors, and the signal preprocessing module preprocesses the acoustic signals of different collected time periods according to the main influence factors to obtain preprocessing results, wherein the specific analysis process is as follows:
step 1, an evaluation analysis module evaluates and analyzes environmental information in the detection data information and detected fault information to obtain main influence factors corresponding to each acquisition time period;
step 2, collecting time period t in the first time1Iteration is carried out as a starting point, n acquisition time periods are divided into n-1 acquisition tuples, and two adjacent acquisition time periods are one acquisition tuple;
step 3, when the main influence factors corresponding to one acquisition tuple are the same, the signal preprocessing module calls different noise reduction processing methods of the acoustic signals from the storage module, processes the acoustic signals in two acquisition time periods in one acquisition tuple by using the different noise reduction processing methods to obtain two noise reduction processing results, wherein the two noise reduction processing results are the noise reduction acoustic signals subjected to noise reduction processing, and calculates the correlation coefficient of the two noise reduction acoustic signals;
step 4, when the main influence factors corresponding to one acquisition tuple are different, obtaining the data by adopting the same denoising processing methodCalculating correlation coefficient of two noise reduction results, and obtaining correlation vector R (R) according to the correlation coefficient1,r2,r3...rn-1) The calculation equation of the correlation coefficient is as follows:
n is the number of the characteristics in the characteristic set of the noise-reduced acoustic signals after noise reduction, X, Y are characteristic vectors of the signals, X (j), Y (j) represents parameter values of j-th characteristics, and the preprocessing results obtained by the signal preprocessing module through analysis comprise correlation relation vectors, filtered noise and filtered acoustic signals and are sent to the data analysis module.
3. The acoustic diagnosis system for a switch machine fault according to claim 2, wherein the evaluation and analysis module evaluates and analyzes environmental information in the detected data information and the detected fault information to obtain main influence factors corresponding to each acquisition time period, the fault information includes acoustic signals, acquisition time periods, noise reduction processing methods, environmental information, and fault types corresponding to the fault, analyzes the environmental information in the fault information of the same fault type, calculates the influence degrees of all the environmental influence factors on the fault, and calculates the fixed ratio of the influence degrees of different environmental influence factors on the fault so that the fixed ratio corresponds to the fault type, when the evaluation module analyzes different acquisition time periods, the ratio of each acquisition time period is analyzed and compared with the fixed ratio, and determining the environmental influence factor with the largest ratio in the ratio as a main influence factor, and sending the main influence factor in each acquisition time period to the signal preprocessing module.
4. The switch machine fault acoustic diagnosis system of claim 1, wherein the data analysis module analyzes the filtered noise and the correlation vector in the preprocessing result to obtain the noise influence parameter, first calculates the difference between the signal-to-noise ratios of the acoustic signals in each acquisition time period before and after filtering, and then weights each element in the correlation vector according to the difference between the signal-to-noise ratios to obtain the noise influence parameter, the data acquisition module monitors each part of the switch machine, and acquires the acoustic signals of the switch machine operation every other time period.
5. The switch machine fault acoustic diagnosis system of claim 1, wherein the acoustic signal detection module performs joint detection on the acoustic signals subjected to noise reduction processing by the signal preprocessing module according to the analysis result of the data analysis module, selects different acoustic signal feature subsets according to the threshold values analyzed and processed by the data analysis module, and then performs detection and analysis on the acoustic signals by using the acoustic signal feature subsets and an analysis method in machine learning to judge the acoustic signals.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110944630.4A CN113672859B (en) | 2021-08-17 | 2021-08-17 | Fault acoustic diagnosis system for switch machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110944630.4A CN113672859B (en) | 2021-08-17 | 2021-08-17 | Fault acoustic diagnosis system for switch machine |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113672859A true CN113672859A (en) | 2021-11-19 |
CN113672859B CN113672859B (en) | 2024-03-29 |
Family
ID=78543433
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110944630.4A Active CN113672859B (en) | 2021-08-17 | 2021-08-17 | Fault acoustic diagnosis system for switch machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113672859B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114820544A (en) * | 2022-05-09 | 2022-07-29 | 西安得眠堂健康管理工作部 | Production monitoring management system of throat-moistening candy |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106017954A (en) * | 2016-05-13 | 2016-10-12 | 南京雅信科技集团有限公司 | Turnout point machine fault early warning system and method based on audio analysis |
CN106596123A (en) * | 2016-11-22 | 2017-04-26 | 东软集团股份有限公司 | Device fault diagnosis method, device fault diagnosis device, and device fault diagnosis system |
CN108540330A (en) * | 2018-04-24 | 2018-09-14 | 南京邮电大学 | A kind of network fault diagnosis method based on deep learning under heterogeneous network environment |
CN110132598A (en) * | 2019-05-13 | 2019-08-16 | 中国矿业大学 | Slewing rolling bearing fault noise diagnostics algorithm |
CN110596490A (en) * | 2019-09-11 | 2019-12-20 | 天津科技大学 | Intelligent detection method for railway turnout fault |
US20200012944A1 (en) * | 2018-07-05 | 2020-01-09 | Alstom Transport Technologies | Method and system for detecting switch degradation and failures |
CN112697272A (en) * | 2021-02-09 | 2021-04-23 | 郑州铁路职业技术学院 | Point switch fault detection device based on acoustics |
CN112801367A (en) * | 2021-01-27 | 2021-05-14 | 长沙理工大学 | Fault prediction method based on ARMret model considering rare variables |
CN113155504A (en) * | 2021-04-30 | 2021-07-23 | 苏州通汇轨道交通技术有限公司 | Intelligent testing system for point switch for rail transit |
-
2021
- 2021-08-17 CN CN202110944630.4A patent/CN113672859B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106017954A (en) * | 2016-05-13 | 2016-10-12 | 南京雅信科技集团有限公司 | Turnout point machine fault early warning system and method based on audio analysis |
CN106596123A (en) * | 2016-11-22 | 2017-04-26 | 东软集团股份有限公司 | Device fault diagnosis method, device fault diagnosis device, and device fault diagnosis system |
CN108540330A (en) * | 2018-04-24 | 2018-09-14 | 南京邮电大学 | A kind of network fault diagnosis method based on deep learning under heterogeneous network environment |
US20200012944A1 (en) * | 2018-07-05 | 2020-01-09 | Alstom Transport Technologies | Method and system for detecting switch degradation and failures |
CN110132598A (en) * | 2019-05-13 | 2019-08-16 | 中国矿业大学 | Slewing rolling bearing fault noise diagnostics algorithm |
CN110596490A (en) * | 2019-09-11 | 2019-12-20 | 天津科技大学 | Intelligent detection method for railway turnout fault |
CN112801367A (en) * | 2021-01-27 | 2021-05-14 | 长沙理工大学 | Fault prediction method based on ARMret model considering rare variables |
CN112697272A (en) * | 2021-02-09 | 2021-04-23 | 郑州铁路职业技术学院 | Point switch fault detection device based on acoustics |
CN113155504A (en) * | 2021-04-30 | 2021-07-23 | 苏州通汇轨道交通技术有限公司 | Intelligent testing system for point switch for rail transit |
Non-Patent Citations (1)
Title |
---|
洪腾蛟等: "深度学习在轴承故障诊断领域的应用研究", 《科学技术与工程》, vol. 21, no. 22, 8 August 2021 (2021-08-08), pages 9203 - 9211 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114820544A (en) * | 2022-05-09 | 2022-07-29 | 西安得眠堂健康管理工作部 | Production monitoring management system of throat-moistening candy |
CN114820544B (en) * | 2022-05-09 | 2023-06-20 | 西安得眠堂健康管理工作部 | Production monitoring management system of throat-moistening candy |
Also Published As
Publication number | Publication date |
---|---|
CN113672859B (en) | 2024-03-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112660745B (en) | Intelligent diagnosis method and system for carrier roller fault and readable storage medium | |
CN109324604B (en) | Intelligent train comprehensive fault analysis method based on multi-source signals | |
CN112504673B (en) | Carrier roller fault diagnosis method, system and storage medium based on machine learning | |
CN110405537B (en) | Method for establishing guide rail precision prediction model based on deep learning | |
CN111695598A (en) | Monitoring data abnormity diagnosis method based on generation countermeasure network | |
CN111914883A (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
CN111948487A (en) | High-voltage power equipment fault diagnosis method and system based on artificial intelligence | |
CN109139390B (en) | Fan blade fault identification method based on acoustic signal feature library | |
CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
CN112487890A (en) | Bearing acoustic signal fault diagnosis method based on parallel sparse filtering | |
CN112393906A (en) | Method for diagnosing, classifying and evaluating health of weak signal fault of bogie bearing of metro vehicle | |
CN116778964A (en) | Power transformation equipment fault monitoring system and method based on voiceprint recognition | |
CN115060491A (en) | Fan bearing operation health degree assessment method and system based on multi-source data | |
CN113672859B (en) | Fault acoustic diagnosis system for switch machine | |
CN114118219A (en) | Data-driven real-time abnormal detection method for health state of long-term power-on equipment | |
CN114799610A (en) | Welding quality real-time detection method and system based on inverse Fourier transform and self-encoder | |
CN115618205A (en) | Portable voiceprint fault detection system and method | |
Madain et al. | Fault diagnosis in vehicle engines using sound recognition techniques | |
CN113392874B (en) | Abnormal state diagnosis method and device for rail vehicle and terminal equipment | |
CN114330430A (en) | Elevator fault judgment method and system based on big data characteristic analysis | |
CN207992717U (en) | A kind of gate of hydropower station on-line condition monitoring system | |
CN111456915A (en) | Fault diagnosis device and method for internal components of fan engine room | |
CN110956112B (en) | Novel high-reliability slewing bearing service life assessment method | |
CN112362214A (en) | Method and system for online identification of belt tension | |
CN114997749B (en) | Intelligent scheduling method and system for power personnel |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |