CN117565807B - Mining flameproof crawler-type transport vehicle - Google Patents
Mining flameproof crawler-type transport vehicle Download PDFInfo
- Publication number
- CN117565807B CN117565807B CN202410063896.1A CN202410063896A CN117565807B CN 117565807 B CN117565807 B CN 117565807B CN 202410063896 A CN202410063896 A CN 202410063896A CN 117565807 B CN117565807 B CN 117565807B
- Authority
- CN
- China
- Prior art keywords
- independent
- matching
- components
- independent component
- crawler
- 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.)
- Active
Links
- 238000005065 mining Methods 0.000 title claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 66
- 230000005856 abnormality Effects 0.000 claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 18
- 238000012880 independent component analysis Methods 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims description 50
- 239000011159 matrix material Substances 0.000 claims description 42
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 description 19
- 238000004364 calculation method Methods 0.000 description 4
- 238000000354 decomposition reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 239000000383 hazardous chemical Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
- B60R16/0231—Circuits relating to the driving or the functioning of the vehicle
- B60R16/0232—Circuits relating to the driving or the functioning of the vehicle for measuring vehicle parameters and indicating critical, abnormal or dangerous conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D55/00—Endless track vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Transportation (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of crawler-type transport vehicles, in particular to a mining flameproof crawler-type transport vehicle. The crawler-type transport vehicle comprises an abnormality monitoring and analyzing module. The abnormality monitoring and analyzing module comprises: the system comprises a vibration sensor module and an abnormal data processor, wherein the abnormal data processor is used for determining and monitoring abnormal conditions and corresponding abnormal positions of the crawler-type transport vehicle by performing independent component analysis on vibration data obtained by the vibration sensor module. According to the invention, independent component analysis is carried out on vibration data, so that the problem that vibration of other parts can affect judgment of fault parts is avoided, and the accuracy in judging fault positions is improved.
Description
Technical Field
The invention relates to the technical field of crawler-type transport vehicles, in particular to a mining flameproof crawler-type transport vehicle.
Background
The mining flameproof crawler-type transport vehicle is a special vehicle working in an explosive gas environment and is generally used in dangerous environments such as underground mines. Due to the severe mining environment, mechanical components in the mining flameproof crawler carrier vehicle are easily worn, such as a crawler, a steering system, a transmission system and the like, and can be severely worn and corroded, so that faults are caused. Since mines are a potential hazard area, there are hazardous gases, dust and other hazardous materials. If the flameproof crawler carrier vehicle malfunctions due to the abrasion of mechanical parts, accidents may occur, and the risk of injury or loss of life of staff may be increased.
At present, in the existing method, when fault detection and positioning are carried out, vibration sensors are respectively installed at different mechanical component positions, so that the fault position is obtained according to the change of vibration data at different positions, and then overhaul is carried out. In practice, however, the faults in the process often originate from an engine fault or a track fault, and the vibration influence is caused on the whole mechanical structure no matter whether the engine fault or the track fault exists, that is, the vibration of other parts can influence the judgment of the fault part, and then an error exists in judging the fault position.
Disclosure of Invention
In order to solve the technical problems that according to the change of vibration data of different positions, a fault position is obtained, the vibration of other parts can influence the judgment of the fault position, and then errors exist when the fault position is judged, the invention aims to provide a mining flameproof crawler-type carrier vehicle, and the adopted technical scheme is as follows:
the invention provides a mining flameproof crawler-type transport vehicle, which comprises a crawler-type transport vehicle body, wherein the crawler-type transport vehicle body comprises an anomaly monitor, the anomaly monitor further comprises an anomaly monitoring and analyzing module, and the anomaly monitoring and analyzing module comprises: a vibration sensor module and an abnormal data processor;
the signal output end of the vibration sensor module is connected with the signal input end of the abnormal data processor, the vibration sensor module is used for collecting vibration data from the engine to different positions on the crawler and outputting the vibration data to the abnormal data processor, and the abnormal data processor combines the vibration sensors at different positions into different position combinations; obtaining independent components of vibration data corresponding to each position combination;
dividing the independent components according to the periodicity of the independent components to obtain independent component dividing sections; constructing a matrix corresponding to each independent component based on the independent component segmentation segment of each independent component; determining the feature enhancement between different position combinations according to the matching degree between the feature vectors of the matrixes corresponding to the independent components; screening out independent components according to the characteristic enhancement property to be used as independent components of the engine;
decomposing the independent components of the engine to obtain a plurality of IMF components; matching IMF components of the independent components of the engine corresponding to all the position combinations to obtain a matching string; determining the degree of abnormality of the matching string based on the characteristic enhancement condition of the matching string;
and determining the abnormal condition and the corresponding abnormal position of the crawler-type transport vehicle according to the abnormal degree.
Preferably, the acquiring an independent component of vibration data corresponding to each position combination includes:
and obtaining two independent components corresponding to each position combination by utilizing an independent component analysis algorithm and vibration data corresponding to vibration sensors at different positions in each position combination.
Preferably, the dividing the independent component according to the periodicity of the independent component to obtain independent component divided segments includes:
matching the independent components of the two position combinations to obtain independent matching pairs;
taking any independent matching pair as a target matching pair, respectively carrying out Fourier transformation on independent components in the target matching pair, taking the reciprocal of the frequency corresponding to the maximum amplitude of the independent components as a period value, obtaining the period value of the independent components, and respectively dividing the independent components based on the period value to obtain an independent component initial section;
calculating the average value of cosine similarity of each independent component initial segment and the independent component initial segments adjacent to two sides as periodicity; taking the average value of the periodicity of the initial segment of the independent component in each independent component as the initial segment length of each independent component;
taking the largest initial segment length of the two initial segment lengths in the target matching pair as a target segment length;
and dividing the independent component based on the target segment length to obtain an independent component dividing segment.
Preferably, the constructing a matrix corresponding to each independent component based on the independent component segmentation segment of each independent component includes:
for the independent components, taking a first independent component segment of the independent components as a first row of the matrix, taking a second independent component segment of the independent components as a second row of the matrix, taking a third independent component segment of the independent components as a third row of the matrix, and so on, so as to obtain the matrix corresponding to each independent component.
Preferably, the determining the feature enhancement between different combinations of positions according to the matching degree between the feature vectors of the matrix corresponding to the independent components includes:
decomposing the matrix of each independent component in the target matching pair to obtain the characteristic value and the corresponding characteristic vector of each matrix; matching the feature vectors of the matrix corresponding to the independent components in the target matching pair to obtain a matching feature vector pair;
and obtaining the characteristic enhancement of the independent component in the target matching pair according to the matching degree of the matching characteristic vector pair of the characteristic vector of the independent component in the target matching pair.
Preferably, the obtaining the feature enhancement of the independent component in the target matching pair according to the matching degree of the matching feature vector pair of the feature vector of the independent component in the target matching pair includes:
calculating the difference of the characteristic values of the characteristic vectors in the same matching characteristic vector pair, and marking the difference as the characteristic difference; and taking the average value of the feature differences corresponding to the feature vectors corresponding to the independent components in the target matching pair as the feature enhancement of the independent components in the target matching pair.
Preferably, the screening of the independent component according to the characteristic enhancement property as the independent component of the engine comprises:
for matched position combinations, the independent component in the independent matching pair with the greatest characteristic enhancement is taken as the independent component of the engine.
Preferably, the matching the IMF components of the independent engine components corresponding to all the position combinations to obtain a matching string includes:
sequencing the independent components of the engine combined at different positions according to the position sequence to obtain an independent component sequence of the engine;
matching IMF components of adjacent engine independent components in the engine independent component sequence to obtain component matching pairs of the adjacent engine independent components; and connecting the component matching pairs according to the positions of the engine independent components in the engine independent component sequence to obtain a matching string.
Preferably, the determining the degree of abnormality of the matching string based on the feature enhancement condition of the matching string includes:
calculating feature enhancement between adjacent IMF components in the matching string;
and carrying out inverse proportion normalization on the average value of the characteristic enhancement between adjacent IMF components in the matching string, and taking the result value as the abnormality degree of the matching string.
Preferably, the determining the abnormal condition and the corresponding abnormal position of the crawler-type carrier vehicle according to the abnormal degree includes:
when the abnormality degree is greater than a preset abnormality threshold value, judging that the engine of the crawler-type transport vehicle is abnormal; when the degree of abnormality is smaller than or equal to a preset abnormality threshold, calculating the similarity degree of vibration data and speed data in a preset time range, and when the similarity degree is smaller than a preset correlation threshold, judging that the abnormal position of the crawler carrier vehicle is a crawler.
The embodiment of the invention has at least the following beneficial effects:
according to the invention, the abnormal monitoring analysis module is arranged on the crawler type transport vehicle body, and as the vibration sensors at different positions are influenced by engine vibration, crawler vibration and the like when the crawler type transport vehicle is subjected to fault monitoring, a single vibration sensor can judge that a large error exists at the abnormal position, so that vibration data from the engine to different positions on the crawler is acquired through the vibration sensor module in the abnormal monitoring analysis module and is output to the abnormal data processor, the abnormal data processor firstly analyzes independent components of the vibration data to obtain independent components through the specific arrangement of the distribution positions of the vibration sensors and the change of abnormal vibration source signals caused by the change of the vibration sensor, and further, the characteristic enhancement between the different position combinations is realized through changing the different position combinations of the vibration sensor, and further, the independent components of the engine are screened, namely the vibration data caused by the engine. The vibrations caused by the independent components of the engine typically have a fixed or relatively stable frequency that is related to the rotational speed of the engine. Therefore, when the engine is in fault, the vibration frequency of the engine is often changed obviously or a new frequency component appears, so that frequency data which is not corresponding or has lower matching rate appears in the process of increasing the information quantity of the engine, and finally matching is carried out based on IMF components of independent components of the engine, the abnormality degree of the matched matching strings is determined, and the abnormality condition and the corresponding abnormality position of the crawler-type carrier vehicle are determined based on the abnormality degree. According to the invention, independent component analysis is carried out on vibration data, so that the problem that vibration of other parts can affect judgment of fault parts is avoided, and the accuracy in judging fault positions is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for processing abnormal data in a mining flameproof crawler-type carrier vehicle according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the mining flameproof crawler-type carrier vehicle according to the invention with reference to the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The mining flameproof crawler-type carrier vehicle provided by the embodiment of the invention comprises a crawler-type carrier vehicle body, wherein the crawler-type carrier vehicle body comprises an anomaly monitoring and analyzing module, and the anomaly monitoring and analyzing module is used for detecting vibration data and analyzing the anomaly condition and the anomaly position in the crawler-type carrier vehicle body based on the vibration data. The abnormal monitoring and analyzing module comprises a vibration sensor module and an abnormal data processor, wherein the vibration sensor module is connected with the abnormal data processor, the abnormal data processor is used for data processing, and the chip type is an FPGA and receives vibration data of the vibration sensor module.
The signal output end of the vibration sensor module is connected with the signal input end of the abnormal data processor, and the vibration sensor module is used for collecting vibration data from the engine to different positions on the crawler belt and outputting the vibration data to the abnormal data processor.
In the embodiment of the invention, the sensor in the vibration sensor module is a vibration sensor, and in other embodiments, the vibration sensor module can also comprise a slidable device, so that the vibration sensor can be moved to different positions to acquire vibration data of different positions. Wherein, there is the position that some vibration sensor among the vibration sensor module is close to the engine, and the position that some vibration sensor is close to the track, and some vibration sensor is located between engine and the track. The vibration sensor module in the abnormality monitoring and analyzing module is used for monitoring abnormal vibration, and five vibration sensors in the vibration sensor module are arranged in the embodiment of the invention, wherein two vibration sensors are arranged at a position close to an engine, two vibration sensors are arranged at a position close to a crawler, and one vibration sensor is arranged at a position between the engine and the crawler.
Referring to fig. 1, a flowchart of steps for analyzing and determining an abnormal situation and a corresponding abnormal position of a crawler-type carrier vehicle by an abnormal data processor in a mining flameproof crawler-type carrier vehicle according to an embodiment of the present invention is shown, and the method includes the following steps:
step S100, combining vibration sensors at different positions into different position combinations; an independent component of vibration data corresponding to each position combination is acquired.
Since the vibration data monitored by the vibration sensor may be caused by abnormal vibration of the engine or may be caused by uneven ground, different countermeasures are required for different sources of the abnormality.
Because vibration sensors at different positions are simultaneously affected by engine vibration and crawler vibration, the vibration signals monitored by each vibration sensor are mixed signals. The independent component analysis is a method for separating the original signals from the mixed signals, and because the number of the mixed signals is required to be larger than the number of the signal sources by the independent component analysis, the vibration data at three positions are analyzed each time in the embodiment of the invention, so that the number of the mixed signals is ensured to be larger than the number of the signal sources.
Further, engine-induced vibrations typically have a fixed or relatively stable frequency that is related to the rotational speed of the engine. Therefore, when the engine fails, the vibration frequency thereof tends to be significantly changed or new frequency components appear. In contrast, since the condition of the ground varies irregularly, such as potholes, stones, etc., appear randomly on the ground, the randomness of the vibration frequency caused by the unevenness of the ground is strong.
When the engine signal in the mixed signal is increased, the engine signal in the independent component obtained through decomposition is closer to the signal of the real engine, and at this time, if the engine signal is abnormal, the matching rate of a certain frequency component is always lower in the frequency components in the obtained independent component along with the increase of the engine signal in the mixed signal.
The vibration sensors at different positions are combined into different position combinations, and in the embodiment of the invention, since 5 vibration sensors are set in the vibration sensor module, the vibration sensors are respectively numbered as q1, q2, q3, q4 and q5. Wherein q1, q2, q3, q4 and q5 are arranged in order, but are not limited to being from the engine position to the track position or from the track position to the engine position.
The vibration sensors of different positions are combined into different position combinations, wherein each position combination comprises vibration sensor data of three different positions. In the embodiment of the invention, the vibration sensor q1, the vibration sensor q2 and the vibration sensor q5 form a position combination, the vibration sensor q1, the vibration sensor q2 and the vibration sensor q4 form a position combination, and the vibration sensor q1, the vibration sensor q2 and the vibration sensor q3 form a position combination.
And for any position combination, acquiring vibration data of the vibration sensors in each position combination in a preset time period, and taking different vibration sensors in the position combination as inputs of an independent component analysis algorithm to obtain two independent degrees corresponding to the position combination. Namely, by utilizing an independent component analysis algorithm, two independent components corresponding to each position combination are obtained from vibration data corresponding to vibration sensors at different positions in each position combination in a preset time period. In the embodiment of the invention, the preset time period is 5 minutes.
And respectively acquiring independent components of vibration data corresponding to each position combination, wherein each position combination has two independent components corresponding to each position combination.
Step S200, dividing the independent components according to the periodicity of the independent components to obtain independent component dividing sections; constructing a matrix corresponding to each independent component based on the independent component segmentation segment of each independent component; determining the feature enhancement between different position combinations according to the matching degree between the feature vectors of the matrixes corresponding to the independent components; and screening out independent components according to the characteristic enhancement property to be used as independent components of the engine.
Two independent components corresponding to each position combination respectively correspond to the vibration data of the engine and the vibration data of the crawler belt, but currently, the vibration data of the engine is not known, and the vibration data of the crawler belt is not known.
The engine data or the crawler data corresponding to the independent components can be obtained by changing the positions of the vibration sensors participating in the independent component analysis and further analyzing which independent component is enhanced in the process of changing the positions of the vibration sensors participating in the independent component analysis.
In the analysis from the position combinations q1, q2, q5 to the position combinations q1, q2, q4 to the combinations q1, q2, q3, if the engine information contained in the position combinations increases, the component with gradually enhanced characteristics is the independent component corresponding to the engine.
Firstly, according to the periodicity of the independent components, the independent components are segmented to obtain independent component segmented sections, and the method is specific:
step S210, matching the independent components of the two position combinations to obtain independent matching pairs.
For example, for the position combinations q1, q2, q5 and the position combinations q1, q2, q4, the corresponding matching relationship of the position combinations q1, q2, q5 and the independent components in the position combinations q1, q2, q4 is obtained, which is realized by KM matching in the embodiment of the present invention. The existing KM matching is realized by calculating the matching of the left node and the right node through bipartite graph matching calculation. In the embodiment of the invention, two independent components obtained by the position combinations q1, q2 and q5 are taken as left nodes, two independent components obtained by the position combinations q1, q2 and q4 are taken as right nodes, the edge value is the cosine similarity between the nodes, and the one-to-one matching relationship between the left nodes and the right nodes is obtained according to the maximum matching principle. Namely, matching the independent components corresponding to the two position combinations through KM matching to obtain two independent distribution pairs. Wherein each independent distribution pair comprises independent components in two position combinations, namely one independent degree in the position combinations q1, q2 and q5 and one independent degree in the position combinations q1, q2 and q4 respectively.
And S220, taking any independent matching pair as a target matching pair, respectively carrying out Fourier transform on independent components in the target matching pair, taking the reciprocal of the frequency corresponding to the maximum amplitude of the independent components as a period value, obtaining the period value of the independent components, and respectively dividing the independent components based on the period value to obtain an independent component initial segment.
Further, two matching relations are obtained, that is, two target matching pairs can be obtained by combining every two positions.
Taking any one of the target matching pairs as an example, two independent components in the target matching pair are denoted by a1 and a2, for example, a1 is an independent component in the position combinations q1, q2, q5, and a2 is an independent component in the position combinations q1, q2, q 4.
And carrying out Fourier transformation on the independent components in the target matching pair, and taking the reciprocal of the frequency corresponding to the maximum amplitude of the independent components as a period value to obtain the period value of the independent components. For example, the independent component a1 is fourier-transformed to obtain a period value of the independent component a1, and the independent component a2 is fourier-transformed to obtain a period value of the independent component a 2.
And dividing the independent components based on the period value to obtain initial sections of the independent components. For example, the individual component a1 and the individual component a2 are divided by the cycle values of the individual component a1 and the individual component a2, respectively, to obtain a plurality of individual component initial segments.
Step S230, calculating the average value of cosine similarity of each independent component initial segment and the independent component initial segments adjacent to two sides as periodicity; the average value of the periodicity of the initial segment of the independent component in each independent component is taken as the initial segment length of each independent component.
Step S240, taking the largest initial segment length of the two initial segment lengths in the target matching pair as the target segment length.
And step S250, dividing the independent component based on the target segment length to obtain an independent component divided segment.
After the independent components are segmented to obtain independent component segments, a matrix corresponding to each independent component is constructed based on the independent component segments of each independent component, specifically:
for the independent components, taking a first independent component segmentation section of the independent components as a first row of the matrix, taking a second independent component segmentation section of the independent components as a second row of the matrix, taking a third independent component segmentation section of the independent components as a third row of the matrix, and so on to obtain the matrix corresponding to each independent component.
Further, according to the matching degree between the feature vectors of the matrix corresponding to the independent components, determining the feature enhancement between different position combinations, and specifically:
first, for each matrix of independent components in the target match pair, the matrix is decomposed, more specifically: and decomposing the matrix corresponding to the independent component through a singular value decomposition algorithm to obtain a plurality of eigenvalues and eigenvectors of the matrix.
And matching the feature vectors of the matrix corresponding to the independent components in the target matching pair to obtain a matching feature vector pair. In the embodiment of the invention, the characteristic vectors corresponding to the matrixes of the independent components can be matched by utilizing a KM matching algorithm, the characteristic values of the characteristic vectors are used as edge weights, the minimum matching principle is followed, and in other embodiments, the matching between the characteristic vectors of the matrixes corresponding to the independent components in the target matching pair can be realized by other matching algorithms.
And obtaining the characteristic enhancement of the independent component in the target matching pair according to the matching degree of the matching characteristic vector pair of the characteristic vector of the independent component in the target matching pair.
In the process of calculating from the position combinations p1, p2 and p5 to the combinations p1, p2 and p4 and then to the combinations p1, p2 and p3, the characteristic enhancement acquisition method comprises the following steps: calculating the difference of the characteristic values of the characteristic vectors in the same matching characteristic vector pair, and marking the difference as the characteristic difference; and taking the average value of the feature differences corresponding to the feature vectors corresponding to the independent components in the target matching pair as the feature enhancement of the independent components in the target matching pair.
The calculation formula of the characteristic enhancement is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Is characteristic enhancement; />Combining the feature vector corresponding to the position in front of the i-th matched feature vector pair; />Combining the corresponding feature vector for a position in the ith matching feature vector pair which is positioned at the back of the position; n is the number of matching feature vector pairs.
That is, in the matching feature vector pair, the larger the feature value corresponding to the feature vector belonging to the position combinations p1, p2, and p4 is, the larger the feature enhancement is, and the larger the probability that the corresponding independent component represents the vibration curve of the engine is.
And then screening out independent components according to characteristic enhancement property, wherein the independent components are used as independent components of the engine, and specifically: for matched position combinations, the independent component in the independent matching pair with the greatest characteristic enhancement is taken as the engine independent degree. That is, for example, in the correspondence relationship between the position combinations p1, p2, and p4 and the independent components of the position combinations p1, p2, and p5, the independent component in the independent matching pair having the greatest characteristic enhancement is set as the engine independent component.
Step S300, decomposing independent components of the engine to obtain a plurality of IMF components; matching IMF components of the independent components of the engine corresponding to all the position combinations to obtain a matching string; and determining the degree of abnormality of the matching string based on the characteristic enhancement condition of the matching string.
It should be noted that vibrations caused by the independent components of the engine typically have a fixed or relatively stable frequency that is related to the rotational speed of the engine. Therefore, when the engine fails, the vibration frequency of the engine tends to be changed significantly or new frequency components appear, so that frequency data which is not corresponding or has a low matching rate appears in the process of increasing the information amount of the engine.
The engine independent components belonging to the engine vibration curves in the process from the position combinations p1, p2, p5 to the combinations p1, p2, p4 to the position combinations p1, p2, p3 are obtained through the previous calculation, a sequence is formed and is recorded as an engine independent component sequence, and each element in the sequence is an engine independent component. I.e. the independent components of the engine combined at different positions are ordered according to the position order, and the independent component sequences of the engine are obtained.
Decomposing engine independent components to obtain a plurality of IMF components, specifically: and decomposing each engine independent component in the engine independent component sequence by an EMD decomposition method to obtain a plurality of IMF components.
Matching IMF components of the independent engine components corresponding to all the position combinations to obtain a matching string, and specifically: and matching IMF components of adjacent engine independent components in the engine independent component sequence to obtain component matching pairs of the adjacent engine independent components.
More specifically: performing KM matching on IMF components of independent components of adjacent engines in the independent component sequences of the engines, wherein nodes on two sides are IMF components, and the boundary values are as follows: and corresponding to cosine similarity of the two nodes, obtaining a one-to-one matching relationship of IMF components of the adjacent engine curves through calculation, namely obtaining component matching pairs of independent components of the adjacent engines. After obtaining the matching relationship of IMF components of engine independent components from the position combinations p1, p2, p5 to the position combinations p1, p2, p4, the matching relationship of IMF components of engine independent components from the position combinations p1, p2, p4 to the position combinations p1, p2, p3 can also be obtained. And then connecting the component matching pairs according to the positions of the engine independent components in the engine independent component sequence to obtain a matching string. For example: the IMF component a in the position combinations p1, p2, p5 corresponds to the IMF component C in the position combinations p1, p2, p3 to the IMF component B in the position combinations p1, p2, p4, and a matching string a-B-C is formed.
Based on the characteristic enhancement condition of the matching string, determining the abnormality degree of the matching string, and specifically:
firstly, calculating feature enhancement between adjacent IMF components in a matching string, wherein the feature enhancement acquisition method between the IMF components is the same as that of the feature enhancement acquisition method of the independent component, and specifically:
dividing the IMF component according to the periodicity of the IMF component to obtain an IMF component dividing section; based on the IMF component segmentation segments of each IMF component, constructing a matrix corresponding to each IMF component; and determining the feature enhancement between different IMF components according to the matching degree between the feature vectors of the matrixes corresponding to the IMF components.
According to the periodicity of the IMF component, the IMF component is segmented to obtain an IMF component segmentation section, and the IMF component segmentation section is specific: matching the two IMF components to obtain an IMF component matching pair; taking any IMF component matching pair as a first matching pair, respectively carrying out Fourier transform on the IMF components in the first matching pair, taking the reciprocal of the frequency corresponding to the maximum amplitude of the IMF component as a period value, obtaining the period value of the IMF component, and respectively dividing the IMF component based on the period value of the IMF component to obtain an IMF component initial section; calculating the average value of cosine similarity of each IMF component initial segment and the IMF component initial segments adjacent to two sides, and taking the average value as the periodicity of the IMF components; taking the periodic average value of the initial section of the IMF component in each IMF component as the initial section length of each IMF component; taking the largest initial segment length in the initial segment lengths of the two IMF components in the first matching pair as the target segment length of the IMF component; and dividing the IMF component based on the target segment length of the IMF component to obtain an IMF component divided segment.
Based on the IMF component segments of each IMF component, a matrix corresponding to each IMF component is constructed, specifically: for the IMF components, taking a first IMF component segment of the IMF components as a first row of the matrix, taking a second IMF component segment of the IMF components as a second row of the matrix, taking a third IMF component segment of the IMF components as a third row of the matrix, and so on, so as to obtain the matrix corresponding to each IMF component.
The feature enhancement between the IMF components is determined according to the matching degree between the feature vectors of the matrix corresponding to the IMF components, and the feature enhancement between the IMF components is specifically:
decomposing the matrix of each IMF component in the first matching pair to obtain a characteristic value and a corresponding characteristic vector of each matrix; matching the feature vectors of the matrix corresponding to the IMF components in the first matching pair to obtain a first feature vector pair; and obtaining the characteristic enhancement of the IMF component in the first matching pair according to the matching degree of the first characteristic vector pair of the characteristic vector of the IMF component in the first matching pair.
And after obtaining the characteristic enhancement between the adjacent IMF components in the matching string, carrying out inverse proportion normalization on the average value of the characteristic enhancement between the adjacent IMF components in the matching string, and taking the result value as the abnormality degree of the matching string.
When the engine is in fault, the vibration frequency of the engine tends to be obviously changed or new frequency components appear, so that frequency data which is not corresponding or has lower matching rate can appear in the process of increasing the information quantity of the engine.
And step S400, determining the abnormal condition and the corresponding abnormal position of the crawler-type transport vehicle according to the abnormal degree.
When an abnormality of the engine is detected, the engine needs to be braked in time to overhaul the engine; when the non-engine abnormality is detected, the correlation between the speed and the vibration change is observed by adjusting the speed, and then whether the track is abnormal or abnormal vibration caused by the uneven road surface is determined.
So the abnormal condition and the corresponding abnormal position of the crawler-type transport vehicle are determined according to the obtained abnormal degree, and the method is specific: and when the abnormality degree is greater than a preset abnormality threshold value, judging that the engine of the crawler-type transport vehicle is abnormal. In the embodiment of the invention, the preset abnormal threshold value is 0.7, and in other embodiments, the preset abnormal threshold value can be adjusted according to the specific requirements of an implementer, for example, when the safety requirements of the implementer are higher, the preset abnormal threshold value can be properly adjusted, so that the acquisition of the abnormal condition is more sensitive.
When the degree of abnormality is less than or equal to a preset abnormality threshold, further judgment is made, and the degree of similarity of vibration data and speed data within a preset time range is calculated. In the embodiment of the invention, the similarity is set to be the cosine similarity of the vibration data sequence and the speed data sequence, and the value of the preset time range is 2 minutes, and in other embodiments, the preset time range can be adjusted by an implementer according to actual conditions. However, when the similarity is greater than or equal to the preset correlation threshold, it may be an abnormal vibration due to uneven ground, and it is determined that the crawler carrier vehicle is not abnormal. And when the similarity is smaller than a preset related threshold value, judging that the abnormal position of the crawler-type transport vehicle is the crawler, gradually reducing the speed until stopping, and then manually overhauling.
In summary, the embodiment of the invention provides a mining flameproof crawler-type carrier vehicle, which comprises a crawler-type carrier vehicle body, wherein the crawler-type carrier vehicle body further comprises an abnormality monitoring and analyzing module. The abnormality monitoring and analyzing module comprises: the system comprises a vibration sensor module and an abnormal data processor, wherein the abnormal data processor is used for determining and monitoring abnormal conditions and corresponding abnormal positions of the crawler-type transport vehicle by performing independent component analysis on vibration data obtained by the vibration sensor module. According to the invention, independent component analysis is carried out on vibration data, so that the problem that vibration of other parts can affect judgment of fault parts is avoided, and the accuracy in judging fault positions is improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. The utility model provides a mining flame proof crawler-type transport vechicle, includes crawler-type transport vechicle body, crawler-type transport vechicle body includes anomaly monitor, its characterized in that, anomaly monitor still includes anomaly monitoring analysis module, anomaly monitoring analysis module includes: a vibration sensor module and an abnormal data processor;
the signal output end of the vibration sensor module is connected with the signal input end of the abnormal data processor, the vibration sensor module is used for collecting vibration data from the engine to different positions on the crawler and outputting the vibration data to the abnormal data processor, and the abnormal data processor combines the vibration sensors at different positions into different position combinations; obtaining independent components of vibration data corresponding to each position combination;
dividing the independent components according to the periodicity of the independent components to obtain independent component dividing sections; constructing a matrix corresponding to each independent component based on the independent component segmentation segment of each independent component; determining the feature enhancement between different position combinations according to the matching degree between the feature vectors of the matrixes corresponding to the independent components; screening out independent components according to the characteristic enhancement property to be used as independent components of the engine;
decomposing the independent components of the engine to obtain a plurality of IMF components; matching IMF components of the independent components of the engine corresponding to all the position combinations to obtain a matching string; determining the degree of abnormality of the matching string based on the characteristic enhancement condition of the matching string;
and determining the abnormal condition and the corresponding abnormal position of the crawler-type transport vehicle according to the abnormal degree.
2. The mining flameproof crawler carrier vehicle according to claim 1, wherein the acquiring the independent component of the vibration data corresponding to each position combination comprises:
and obtaining two independent components corresponding to each position combination by utilizing an independent component analysis algorithm and vibration data corresponding to vibration sensors at different positions in each position combination.
3. The mining flameproof crawler-type carrier vehicle according to claim 1, wherein the dividing the independent component according to the periodicity of the independent component to obtain independent component divided sections comprises:
matching the independent components of the two position combinations to obtain independent matching pairs;
taking any independent matching pair as a target matching pair, respectively carrying out Fourier transformation on independent components in the target matching pair, taking the reciprocal of the frequency corresponding to the maximum amplitude of the independent components as a period value, obtaining the period value of the independent components, and respectively dividing the independent components based on the period value to obtain an independent component initial section;
calculating the average value of cosine similarity of each independent component initial segment and the independent component initial segments adjacent to two sides as periodicity; taking the average value of the periodicity of the initial segment of the independent component in each independent component as the initial segment length of each independent component;
taking the largest initial segment length of the two initial segment lengths in the target matching pair as a target segment length;
and dividing the independent component based on the target segment length to obtain an independent component dividing segment.
4. A mining flameproof crawler-type carrier vehicle according to claim 3, wherein the constructing a matrix corresponding to each independent component based on the independent component segments of each independent component comprises:
for the independent components, taking a first independent component segment of the independent components as a first row of the matrix, taking a second independent component segment of the independent components as a second row of the matrix, taking a third independent component segment of the independent components as a third row of the matrix, and so on, so as to obtain the matrix corresponding to each independent component.
5. A mining flameproof crawler carrier vehicle according to claim 3, wherein the determining the feature enhancement between the combinations of different positions according to the degree of matching between the feature vectors of the matrix corresponding to the independent components comprises:
decomposing the matrix of each independent component in the target matching pair to obtain the characteristic value and the corresponding characteristic vector of each matrix; matching the feature vectors of the matrix corresponding to the independent components in the target matching pair to obtain a matching feature vector pair;
and obtaining the characteristic enhancement of the independent component in the target matching pair according to the matching degree of the matching characteristic vector pair of the characteristic vector of the independent component in the target matching pair.
6. The mining flameproof crawler carrier vehicle according to claim 5, wherein the obtaining the characteristic enhancement of the independent component in the target matching pair according to the matching degree of the matching characteristic vector pair of the characteristic vector of the independent component in the target matching pair comprises:
calculating the difference of the characteristic values of the characteristic vectors in the same matching characteristic vector pair, and marking the difference as the characteristic difference; and taking the average value of the feature differences corresponding to the feature vectors corresponding to the independent components in the target matching pair as the feature enhancement of the independent components in the target matching pair.
7. A mining flameproof crawler carrier vehicle according to claim 3, wherein said screening of individual components according to said characteristic enhancement as engine individual components comprises:
for matched position combinations, the independent component in the independent matching pair with the greatest characteristic enhancement is taken as the independent component of the engine.
8. The mining flameproof crawler carrier vehicle according to claim 1, wherein the matching of IMF components of independent components of the engine corresponding to all combinations of positions to obtain a matching string comprises:
sequencing the independent components of the engine combined at different positions according to the position sequence to obtain an independent component sequence of the engine;
matching IMF components of adjacent engine independent components in the engine independent component sequence to obtain component matching pairs of the adjacent engine independent components; and connecting the component matching pairs according to the positions of the engine independent components in the engine independent component sequence to obtain a matching string.
9. The mining flameproof crawler carrier vehicle according to claim 1, wherein the determining of the degree of abnormality of the matching string based on the characteristic enhancement condition of the matching string comprises:
calculating feature enhancement between adjacent IMF components in the matching string;
and carrying out inverse proportion normalization on the average value of the characteristic enhancement between adjacent IMF components in the matching string, and taking the result value as the abnormality degree of the matching string.
10. The mining flameproof crawler carrier vehicle according to claim 1, wherein the determining the abnormal condition and the corresponding abnormal position of the crawler carrier vehicle according to the degree of abnormality comprises:
when the abnormality degree is greater than a preset abnormality threshold value, judging that the engine of the crawler-type transport vehicle is abnormal; when the degree of abnormality is smaller than or equal to a preset abnormality threshold, calculating the similarity degree of vibration data and speed data in a preset time range, and when the similarity degree is smaller than a preset correlation threshold, judging that the abnormal position of the crawler carrier vehicle is a crawler.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410063896.1A CN117565807B (en) | 2024-01-17 | 2024-01-17 | Mining flameproof crawler-type transport vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410063896.1A CN117565807B (en) | 2024-01-17 | 2024-01-17 | Mining flameproof crawler-type transport vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117565807A CN117565807A (en) | 2024-02-20 |
| CN117565807B true CN117565807B (en) | 2024-03-19 |
Family
ID=89886681
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410063896.1A Active CN117565807B (en) | 2024-01-17 | 2024-01-17 | Mining flameproof crawler-type transport vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117565807B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105628419A (en) * | 2015-12-18 | 2016-06-01 | 国网安徽省电力公司 | System and method of diagnosing GIS (Gas Insulated Switchgear) mechanical defects based on independent component analysis denoising |
| CN112098088A (en) * | 2020-08-19 | 2020-12-18 | 昆明理工大学 | Rolling bearing fault diagnosis method based on KICA-fractal theory |
| CN113435314A (en) * | 2021-06-25 | 2021-09-24 | 陈珅 | Rolling bearing acoustic signal early fault sensitivity characteristic screening method and system |
| DE102020214459A1 (en) * | 2020-11-18 | 2022-05-19 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method for determining damage to a component, computer program, digital storage medium and control unit |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080059086A1 (en) * | 2002-02-21 | 2008-03-06 | Ziyad Duron | System and method for determining and detecting stability loss in structures |
| US7693643B2 (en) * | 2005-02-14 | 2010-04-06 | Honeywell International Inc. | Fault detection system and method for turbine engine fuel systems |
-
2024
- 2024-01-17 CN CN202410063896.1A patent/CN117565807B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105628419A (en) * | 2015-12-18 | 2016-06-01 | 国网安徽省电力公司 | System and method of diagnosing GIS (Gas Insulated Switchgear) mechanical defects based on independent component analysis denoising |
| CN112098088A (en) * | 2020-08-19 | 2020-12-18 | 昆明理工大学 | Rolling bearing fault diagnosis method based on KICA-fractal theory |
| DE102020214459A1 (en) * | 2020-11-18 | 2022-05-19 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method for determining damage to a component, computer program, digital storage medium and control unit |
| CN113435314A (en) * | 2021-06-25 | 2021-09-24 | 陈珅 | Rolling bearing acoustic signal early fault sensitivity characteristic screening method and system |
Non-Patent Citations (4)
| Title |
|---|
| 基于自适应变分模态分解的齿轮箱故障诊断;谢锋云等;推进技术;20231219;全文 * |
| 滚动轴承的多点复合故障诊断研究;张迪;中国优秀硕士学位论文全文数据库工程科技Ⅱ辑;20200215(第02期);全文 * |
| 联合收割机工作部件装配质量振动检测关键技术研究;赵思夏;中国优秀硕士学位论文全文数据库工程科技Ⅱ辑;20230715(第07期);全文 * |
| 采煤机截割传动系统故障诊断及可靠性分析;钱沛云;中国博士学位论文全文数据库工程科技Ⅰ辑;20160615(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117565807A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Delvecchio et al. | Vibro-acoustic condition monitoring of Internal Combustion Engines: A critical review of existing techniques | |
| Hashim et al. | Combustion fault detection technique of spark ignition engine based on wavelet packet transform and artificial neural network | |
| CN110826054A (en) | Vehicle-mounted CAN bus intrusion detection method based on message data field characteristics | |
| CN109993222B (en) | Data anomaly detection system and method | |
| CN117565807B (en) | Mining flameproof crawler-type transport vehicle | |
| Hansen et al. | A new approach to the challenge of machinery prognostics | |
| US11630135B2 (en) | Method and apparatus for non-intrusive program tracing with bandwidth reduction for embedded computing systems | |
| US6907341B2 (en) | Misfire detector | |
| CN115758289B (en) | Rail wave mill identification method based on multitask learning neural network | |
| Chen et al. | Machine learning for misfire detection in a dynamic skip fire engine | |
| CN114486259A (en) | Signal processing method of distributed optical fiber acoustic sensing system for optimizing variational modal decomposition | |
| CA3197079A1 (en) | Undercarriage wear prediction based on machine vibration data | |
| US20080091715A1 (en) | Method and system of creating health operating envelope for dynamic systems by unsupervised learning of a sequence of discrete event codes | |
| CN116842410A (en) | Intelligent helmet antitheft management method and system based on dynamic perception | |
| CN112665713B (en) | Reciprocating mechanical equipment fault detection method based on real-time vibration data | |
| Lee et al. | A comparative study of deep learning-based diagnostics for automotive safety components using a raspberry pi | |
| Agogino et al. | Entropy based anomaly detection applied to space shuttle main engines | |
| Wang et al. | Design of pump fault diagnosis system based on T-FMEA | |
| Xing et al. | Ground target detection, classification, and sensor fusion in distributed fiber seismic sensor network | |
| Deuschle et al. | Robust sensor spike detection method based on dynamic time warping | |
| Dogan et al. | Performance analysis of SVM, ANN and KNN methods for acoustic road-type classification | |
| CN106017955A (en) | Method and system for identifying mechanical equipment state types | |
| Salnyk et al. | Stochastic model of the reaction the unattended ground sensor system based on {3+ 3} scheme | |
| Al-Nafjan et al. | Intrusion detection using PCA based modular neural network | |
| US11973769B1 (en) | Auto-encoders for anomaly detection in a controller area network (CAN) |
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 |