CN116958599A - Automatic detection method and system for vibration abnormality of vibrating trough connecting rod, readable medium and application - Google Patents
Automatic detection method and system for vibration abnormality of vibrating trough connecting rod, readable medium and application Download PDFInfo
- Publication number
- CN116958599A CN116958599A CN202310714035.0A CN202310714035A CN116958599A CN 116958599 A CN116958599 A CN 116958599A CN 202310714035 A CN202310714035 A CN 202310714035A CN 116958599 A CN116958599 A CN 116958599A
- Authority
- CN
- China
- Prior art keywords
- vibration
- connecting rod
- module
- image
- tobacco shred
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 78
- 230000005856 abnormality Effects 0.000 title claims abstract description 40
- 238000012216 screening Methods 0.000 claims abstract description 79
- 241000208125 Nicotiana Species 0.000 claims abstract description 77
- 235000002637 Nicotiana tabacum Nutrition 0.000 claims abstract description 77
- 230000004927 fusion Effects 0.000 claims abstract description 38
- 230000005236 sound signal Effects 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 239000008186 active pharmaceutical agent Substances 0.000 claims abstract 10
- 230000002159 abnormal effect Effects 0.000 claims description 40
- 238000000034 method Methods 0.000 claims description 29
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000003491 array Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 claims description 2
- 230000002547 anomalous effect Effects 0.000 claims 1
- 238000007689 inspection Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 7
- 230000009467 reduction Effects 0.000 abstract description 6
- 238000012360 testing method Methods 0.000 description 12
- 238000005057 refrigeration Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007667 floating Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 235000019505 tobacco product Nutrition 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- XYUINKARGUCCQJ-UHFFFAOYSA-N 3-imino-n-propylpropan-1-amine Chemical group CCCNCCC=N XYUINKARGUCCQJ-UHFFFAOYSA-N 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 101100136092 Drosophila melanogaster peng gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 239000003507 refrigerant Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application discloses a vibration trough connecting rod vibration abnormality automatic detection method and system, a readable medium and application, wherein the system is provided with an image acquisition module, a KLT algorithm module, a microphone array, a wavelet denoising module, a DS theory fusion module, a connecting rod vibration state conflict factor calculation module, a connecting rod vibration state judgment module and an abnormality detection output module; the application discloses a DS theory-based automatic detection technology for vibration abnormality of a tobacco shred screening vibration groove connecting rod, which utilizes gradient calculation to extract continuous frame characteristics of images, adopts square matching image matching of image gray level differences, utilizes a KLT algorithm to complete image characteristic point tracking, establishes a microphone array to acquire noise source signals, utilizes wavelet coefficient noise reduction sound signals, combines the image characteristic points and the noise reduction sound signals to fuse to acquire conflict factors, realizes automatic detection of vibration abnormality of the tobacco shred screening vibration groove connecting rod, and improves the accuracy of automatic detection of vibration abnormality.
Description
Technical Field
The application relates to a vibration trough connecting rod vibration abnormality automatic detection method and system based on DS theory fusion image and sound signals, a readable medium and application, which realize timely detection and treatment of the abnormal state of the connecting rod vibration by collecting internal image data and sound signals and utilizing DS theory to carry out fusion analysis, and belongs to the field of tobacco processing.
Background
A large number of mechanical equipment is required to perform various operations during tobacco production. The main structure of the tobacco shred screening vibration groove (figure 1) comprises a groove body 1, a frame 2, a spring plate assembly 3, a vibration exciter 4 and a belt elastic device 5, wherein the tobacco shred screening vibration groove is used as one of the most important equipment in the tobacco leaf processing process, and can be used for effectively and accurately grading tobacco shreds, so that the quality of tobacco products is guaranteed. However, along with the increase of the service time of the equipment, parts and mechanical structures in the tobacco shred screening vibration groove are gradually aged, so that the equipment is loosened, worn and the like, and abnormal vibration of the connecting rod is caused, so that uneven tobacco shred screening is caused, and the quality of tobacco products is affected.
Currently, related scholars have conducted a great deal of research on detection of vibration anomalies of mechanical equipment. Li Beibei and Peng Li propose a bearing vibration anomaly detection method based on an improved self-coding network, which uses mahalanobis distance to reduce the training data volume of the self-coding network, improve the training efficiency and complete the detection of low-dimensional bearing vibration anomalies. However, this method has a problem in that the detection takes a long time. Wang Yuantao et al propose a method for detecting abnormal vibration of a refrigeration compressor based on a self-encoder, and construct a self-encoder model to obtain a basis for judging abnormal vibration of the compressor, so as to improve the accuracy of judging abnormal vibration. However, this method is computationally intensive to be further validated. Xue Yingjie et al propose a mechanical abnormal sound detection method based on self-supervision feature extraction, which converts sound samples into spectrograms, and constructs a self-supervision feature extractor to complete the recognition of abnormal sounds of non-supervision mechanical equipment. However, the method is not combined with image processing, and the detection accuracy is required to be improved. Therefore, the conventional detection method cannot effectively meet the requirements of modern generation.
DS (Dempster-Shafer Theory) Theory is a mathematical Theory based on uncertainty reasoning that derives the confidence of the final conclusion by computing and combining the confidence of the individual hypotheses.
Disclosure of Invention
Aiming at the current situation of enterprises and the defects of the prior art, the application aims to design a technology capable of automatically detecting abnormal vibration of a tobacco shred screening vibration groove connecting rod. The technology collects image data in a tobacco shred screening vibration groove, performs continuous frame tracking of images by using a KLT algorithm, and extracts characteristic points of connecting rods. Meanwhile, a plurality of microphone array arrays are constructed, the emitting positions of noise source signals are obtained, and the noise source signals are subjected to denoising processing by utilizing wavelet coefficients. And then, carrying out fusion analysis on the image characteristics and the sound signals by utilizing DS theory, calculating a conflict factor of the vibration state of the connecting rod, judging the vibration state of the connecting rod according to the conflict factor, and realizing automatic detection of abnormal vibration of the connecting rod of the vibration groove of the tobacco shred screening.
In order to solve the above technical problems, the present application firstly provides an automated detection system for vibration abnormality of a vibrating trough connecting rod based on DS theory fused image and sound signals, the specific signal transmission route is shown in FIG. 1, including:
an image acquisition module for acquiring image data of the inside of the tobacco shred screening vibration groove;
the KLT algorithm module is in signal connection with the image acquisition module and is used for tracking continuous frames of images and extracting connecting rod characteristic points at adjacent moments of the tobacco shred screening vibration groove;
a plurality of microphone array arrays for obtaining the emission position of the noise source signal;
the wavelet denoising module is in signal connection with the microphone array arrays and is used for denoising noise source signals;
the DS theory fusion module is respectively connected with the KLT algorithm module and the wavelet denoising module in a signal way and is used for carrying out fusion analysis on the characteristic points of the connecting rod obtained by the KLT algorithm module and the emission positions of the noise source signals obtained by the wavelet denoising module;
the connecting rod vibration state conflict factor calculation module is in signal connection with the DS theory fusion module and is used for calculating the connecting rod vibration state conflict factor by utilizing the fusion analysis result obtained by the DS theory fusion module;
the connecting rod vibration state judging module is in signal connection with the connecting rod vibration state conflict factor calculating module and is used for judging the vibration state of the connecting rod according to the connecting rod vibration state conflict factor;
and the abnormality detection output module is in signal connection with the connecting rod vibration state judging module and is used for outputting detection results of abnormal vibration of the connecting rod of the tobacco shred screening vibration groove.
In the automatic detection system for abnormal vibration of the tobacco shred screening vibrating trough connecting rod, the image acquisition module further comprises an image sensor and a data acquisition unit.
The image sensor acquires images, and the data acquisition unit acquires the images from the image sensor and transmits the images to the KLT algorithm module.
In the automatic detection system for abnormal vibration of the tobacco shred screening vibration groove connecting rod, the KLT algorithm module further comprises a characteristic point extraction unit and a continuous frame tracking unit.
Consecutive frame tracking unit: tracking successive frames of the image; feature point extraction unit: connecting rod characteristic points at adjacent moments of the tobacco shred screening vibration groove are extracted from the image.
In the automatic detection system for abnormal vibration of the tobacco shred screening vibration groove connecting rod, the DS theory fusion module further comprises a feature fusion unit and a conflict factor calculation unit.
Feature fusion unit: fusing the image features and the sound signals; conflict factor calculation unit: and calculating a conflict factor by using the fusion result obtained by the feature fusion unit.
In the automatic detection system for abnormal vibration of the connecting rod of the tobacco shred screening vibration groove, the connecting rod vibration state judging module further comprises a state judging rule base and a state judging logic unit.
State determination logic: acquiring a judging rule from a state judging rule library, and judging a vibration abnormal level corresponding to the conflict factor; state determination rule base: vibration levels corresponding to different ranges of conflict factors are stored.
The application also provides a connecting rod vibration abnormality automatic detection method for the tobacco shred screening vibration groove, which comprises the following steps:
a) Collecting image data in a tobacco shred screening vibration groove;
b) Tracking continuous frames of the image by utilizing a KLT algorithm aiming at the image data acquired in the step a and extracting characteristic points of the connecting rod;
c) Constructing a plurality of microphone array arrays, and acquiring the emitting positions of noise source signals;
d) Denoising the noise source signal by utilizing wavelet denoising processing aiming at the noise signal acquired in the step c;
e) Aiming at the image and sound signals in b and d, fusing image characteristics and sound signals by utilizing DS theory, and performing fusion analysis;
f) Calculating a connecting rod vibration state conflict factor by utilizing fusion analysis in the step e;
g) Judging the vibration state of the connecting rod according to the conflict factor calculated by the f;
h) And outputting a detection result of abnormal vibration of the connecting rod of the tobacco shred screening vibrating slot according to the calculation result of the vibration state of the connecting rod in g.
In the automatic detection method for vibration abnormality of the tobacco shred screening vibrating slot connecting rod, the DS theory fusion analysis in the step e) further comprises the steps of converting image features and sound signals into a DS theory trust degree function respectively, and calculating by utilizing DS synthesis rules to obtain the fused trust degree function.
In the automatic detection method for abnormal vibration of the connecting rod of the tobacco shred screening vibrating trough, the judgment of the vibration state of the connecting rod in the step g) further comprises the steps of judging the state according to a preset state judgment rule and a threshold value of a conflict factor, and determining whether the vibration state of the connecting rod is normal or abnormal.
The application also provides a computer readable storage medium storing a computer program for executing the automatic detection method of vibration abnormality of the tobacco shred screening vibration groove connecting rod.
The application also provides an application of the automatic detection system for the vibration abnormality of the connecting rod of the tobacco shred screening vibration groove, which comprises the step of applying the automatic detection system for the vibration abnormality of the connecting rod of the tobacco shred screening vibration groove to the tobacco shred screening vibration groove of the tobacco industry, and is used for monitoring and detecting the vibration abnormality state of the connecting rod in real time so as to improve the quality and the production efficiency of tobacco products.
Compared with the prior art, the application has at least the following beneficial effects: the application discloses a DS theory-based automatic detection technology for vibration abnormality of a tobacco shred screening vibration groove connecting rod, which comprises the steps of extracting continuous frame characteristics of images by utilizing gradient calculation, adopting square matching image matching of image gray level differences, utilizing a KLT algorithm to complete image characteristic point tracking, establishing a microphone array, acquiring noise source signals, utilizing wavelet coefficient noise reduction sound signals, combining the DS theory to fuse the image characteristic points with the noise reduction sound signals, and acquiring conflict factors, thereby realizing automatic detection for vibration abnormality of the tobacco shred screening vibration groove connecting rod. The vibration abnormality automatic detection technology improves the accuracy of vibration abnormality automatic detection.
Drawings
Signal transmission route of automatic detection system for vibration abnormality of vibrating trough connecting rod in figure 1
Fig. 2 is a block diagram of a conventional tobacco shred screening apparatus.
Fig. 3 is a relationship between the actual rotation speed of the vibration motor and the vibration state of the connecting rod.
FIG. 4 is a vibration anomaly magnitude result based on a bearing vibration anomaly detection method that improves the self-encoding network.
Fig. 5 is a vibration anomaly amplitude result of a method for detecting abnormal vibration of a refrigerant compressor based on a self-encoder.
FIG. 6 is a vibration anomaly magnitude result of a method for automated detection of vibration anomalies of a vibrating trough link based on DS theory fused image and sound signals.
Detailed Description
The present application will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
1. Description of image continuous frame tracking, sound Signal denoising, image feature and Sound Signal fusion
(1) Image continuous frame tracking based on KLT algorithm
A plurality of sensors are arranged in the tobacco shred screening vibration groove, and a sensing technology is utilized to collect the images of the connecting rods of the tobacco shred screening vibration groove. When the characteristic points of the vibration groove connecting rod for screening the cut tobacco are matched and tracked, the characteristic points which can be identified only need to be provided in the image, and the known labels do not need to be provided in the image, so that the calculation power can be improved by utilizing the KLT algorithm.
Assuming that the floating point image frame of the tobacco shred screening vibrating trough connecting rod at the moment t is I (x, y and t), creating a first floating point image frame as I 1 (x 1 ,y 1 T). According to a two-dimensional Gaussian function pair I 1 (x 1 ,y 1 T) gaussian blur:
wherein (x, y, t) represents the pixel coordinates in the horizontal and vertical directions of the image at time t, and σ is x 1 Is a variance of (c). Will I' 1 (x 1 ,y 1 T) into a sequence of multi-scale pyramid images, which are convolved with a gaussian kernel (5*5):
calculate Q 1 Gradient, obtaining the characteristic points of the tobacco shred screening vibrating groove connecting rod:
ζ＝wQ 1max ,0＜w＜1 (3)
wherein w is an image threshold; q (Q) 1max Is Q 1 Maximum eigenvalue. And extracting characteristic points in the reference frame through gradient calculation.
Creating a second frame floating point image as I after zeta value is acquired 2 (x 2 ,y 2 T) using the sum of squares of the image gray differences as I 2 (x 2 ,y 2 Matching criteria of t):
will I 2 ′(x 2 ,y 2 T) is also decomposed into a sequence of pyramid images of multiple scales, completing the convolution:
calculate Q 2 Gradient, finishing image feature matching of the tobacco shred screening vibrating groove connecting rod:
ζ′＝wQ 2max ,0＜w＜1 (6)
after the zeta' value is obtained, calculate I 2 (x 2 ,y 2 T) pixel shift distance:
I i (x i ,y i ,t)＝I i (x i +dx i ,y i +dy i ,t+dt) (7)
taylor expansion, obtaining a displacement vector:
where ε is the minimum sum of squares of the gray differences of the image. Neglecting second order parameters, and transforming to obtain:
and dividing the characteristic points of the tobacco shred screening vibration slot connecting rod image into a set I, completing continuous tracking of the characteristic points of the tobacco shred screening vibration slot connecting rod image, and providing data support for subsequent image characteristic fusion.
(2) Sound signal denoising based on wavelet coefficients
The acoustic camera is a microphone array, a plurality of high-sensitivity microphones are arranged according to a certain rule, sound pressure level distribution of sound on a plane is generated through an array signal processing algorithm, and sound visualization is realized in a color contour diagram mode. Synchronously collecting vibration sound signals of a tobacco shred screening vibration groove connecting rod by using a plurality of microphones:
wherein M is the output of each array element in the array; p is p k (υ l ) Is the pair v on the kth microphone array element l Sensitivity of signal to directional incidence, s l (g) A signal transmitted for the first target source; u (u) k (g) Is the noise on the kth array element; lambda is the acoustic wavelength.
The array output is:
wherein b is k The weighting coefficient of the kth microphone array element; z c (n) input Sound Signal received for the c-th target Source, τ k The arrival time delay of the sound signal for the kth microphone array element.
According to the signal phase difference between the microphones, acquiring the emission position of the noise source signals:
in the method, in the process of the application,is the noise source signal phase. Setting soft and hard threshold suppression noise source signal wavelet coefficients, wherein the hard threshold is defined as formula (13), and the soft threshold is defined as formula (14):
wherein d j,k As a function of the vibration signal; sgn (d) j,k ) As a sign function.
Obtaining a vibration signal after noise suppression through the reconstruction signal:
wherein, c l And (t) reconstructing a signal by using the χ mark as a signal component after wavelet threshold noise reduction.
(3) DS theory-based image feature and sound signal fusion
In the automatic detection process of vibration abnormality of the tobacco shred screening vibrating slot connecting rod, DS theory is mainly used for fusing image characteristics and sound signals, judging the vibration state of the connecting rod and realizing automatic detection. It should be noted that all propositions are represented by means of the recognition framework, and in order to effectively distinguish the degree of propositions trust in the recognition framework, the analysis and calculation of the propositions is realized by using a BPA (Basic Probability Assignment ) function. Introducing an interval number theory, and constructing an interval number model to fuse image features and sound signals:
in the method, in the process of the application,characteristic point functions of the ith floating point image; />A set of locations is issued for the noise source signal.
And constructing a tobacco shred screening vibrating slot connecting rod vibration IBPA function by combining a similarity judging method:
where Θ is the recognition frame of the IBPA function,representing an empty set, i.e. when the intersection of the number of intervals between all categories is empty.
Introducing a aroma entropy parameter to quantitatively measure and calculate the vibration of the tobacco shred screening vibration groove connecting rod:
in the method, in the process of the application,the interval aroma concentration entropy parameters, namely the quantity, of the vibration data class n of the vibration groove connecting rod of the tobacco shred screening under the j attributeNumber of intervals after conversion. Introducing a similarity index function into the calculation result shown in the formula (18) to calculate a conflict factor:
wherein D (t) is a similarity function, and tau is the fusion dependence of the intra-dimensional image characteristics and the sound signals;and fusing dimensions for the image features and the sound signals.
The collision factor τ is an index for determining the vibration state of the connecting rod, and is usually between 0 and 1. The vibration abnormality of the tobacco shred screening vibration groove connecting rod is classified into five grades, and the five grades are shown in the table 1.
Table 1 vibration classification of tobacco screening vibrating trough links
And the larger the tau value result is, the more abnormal the vibration of the tobacco shred screening vibration groove connecting rod is. And according to the tau value, timely judging the working state of the tobacco shred screening vibration groove in operation, and finishing automatic detection of vibration abnormality.
2. Detailed description of the preferred embodiments
In order to verify the effectiveness of the DS theory-based tobacco shred screening vibrating trough connecting rod vibration abnormality automatic detection technology, a comparison test is carried out. ZS series linear vibration screening equipment produced by a certain company is selected as a test object (a group of equipment with faults eliminated and a group of equipment currently used), vibration motor excitation is used as a vibration source to enable tobacco shreds to be thrown up on a screen, meanwhile, the tobacco shreds do linear motion forwards, oversize products and undersize products with a plurality of specifications are produced through a plurality of layers of screens, and the oversize products and the undersize products are discharged from respective discharge ports, so that screening operation is completed. A concrete structure diagram of the screening vibration groove of the tobacco shred screening device is shown in figure 2.
The simulation of the actual running stage state of the tobacco shred screening vibration groove connecting rod is realized by using the tobacco shred screening equipment shown in fig. 2. When the specific vibration state is controlled and regulated, the vibration signal obtained by fusing the image characteristic and the sound signal is used as an input signal, and the corresponding conflict factor is used as an output signal.
The present embodiment obtains an output signal according to the following steps:
a) Collecting image data in a tobacco shred screening vibration groove;
b) Tracking continuous frames of the image by using a KLT algorithm and extracting characteristic points of the connecting rod;
c) Constructing a plurality of microphone array arrays, and acquiring the emitting positions of noise source signals;
d) Denoising the noise source signal by utilizing wavelet denoising processing;
e) Fusing image characteristics and sound signals by using DS theory to perform fusion analysis; the fusion analysis comprises the steps of respectively converting the image characteristics and the sound signals into trust functions of DS theory, and calculating by utilizing DS synthesis rules to obtain the fused trust functions;
f) Calculating a conflict factor of the vibration state of the connecting rod;
g) Judging the vibration state of the connecting rod according to the conflict factors; the link vibration state judgment includes performing state judgment and determining whether the link vibration state is normal or abnormal according to a preset state judgment rule and a threshold value of a collision factor.
h) Outputting a detection result of abnormal vibration of the tobacco shred screening vibrating slot connecting rod.
As can be seen from the equipment structure diagram 2, the fault location of the ZS-series linear vibration screening equipment is an elastic device. The elastic device is an important component part in the linear vibration screening equipment, if the elastic device fails, the damping effect of the linear vibration screening equipment can be reduced, vibration and impact cannot be effectively reduced, and the stability of the screening equipment is further reduced. Meanwhile, the elastic device can also play a role in noise reduction, and once the elastic device fails, the noise can be increased, so that the comfort level of the production environment is affected.
The method is adopted to calculate similarity index functions of a groove body, a frame, a spring plate assembly, a vibration exciter and a belt elastic device of the linear vibration screening equipment, obtain tau value and divide abnormal vibration grades of the connecting rod. The specific results are shown in Table 2.
Table 2 vibration classification of tobacco screening vibrating trough links
| Test point | Tau value | Abnormality rating |
| 1 | 0 | First level |
| 2 | 0 | First level |
| 3 | 0.02 | First level |
| 4 | 0.01 | First level |
| 5 | 0.9 | Five-stage |
According to the calculation results of table 2, τ values of test point 1, test point 2, test point 3 and test point 4 are all less than 0.05, no fault position exists, and no influence is caused on the linear vibration screening equipment. And tau > 0.7 of the test point 5, the detection result is that the elastic device has faults, and the abnormal level is five levels. The test result of the method is consistent with the actual fault position of the linear vibration screening equipment, so that the method can accurately position the fault position of the linear vibration screening equipment and ensure the safe operation of the equipment.
In order to further verify the vibration abnormality automatic detection performance of the tobacco shred screening vibrating trough connecting rod of the method, a bearing vibration abnormality detection method based on an improved self-coding network and a refrigeration compressor abnormal vibration detection method based on a self-coder are selected as comparison methods, and the vibration abnormality detection precision of the method is verified by analyzing the detection precision of different test groups on vibration signals. The experiment adopted a vibration motor with power of 2X 3.0kW and the maximum executable rotating speed of 960r/min. And acquiring the relation between the rotating speed of the vibration motor in the normal state and the vibration state of the connecting rod. As particularly shown in fig. 3.
As can be seen by combining the information shown in FIG. 3, when the rotating speed of the vibrating motor reaches 360r/min, the connecting rod of the tobacco shred screening vibrating groove generates abnormal vibration, and the vibration amplitude of the connecting rod is between-10.0 and 10.0.
And by combining the data, the vibration state of the connecting rod when the rotating speed of the vibration motor is 360r/min is obtained by adopting three different methods, and is compared with the actual vibration, and the consistency of the vibration abnormal amplitude result and the actual vibration result is higher, so that the method is more excellent. The specific test results are shown in fig. 4 to 6.
As can be seen from the test results shown in fig. 4 to 6, there is a certain difference between the vibration abnormality amplitude of the bearing vibration abnormality detection method based on the improved self-encoding network and the abnormal vibration detection method of the refrigeration compressor based on the self-encoder and the actual vibration result of the vibration motor. When the rotating speed of the vibration motor is 360r/min, the vibration amplitude of the connecting rod obtained based on the bearing vibration abnormality detection method of the improved self-coding network is between-4.0 and 4.0, and the vibration amplitude of the connecting rod obtained based on the detection of the abnormal vibration detection method of the refrigeration compressor of the self-coding network is between-8.0 and 4.0. The vibration amplitude of the connecting rod detected by the method is between-9.8 and 9.5, and the connecting rod has higher consistency with the actual result. The method is characterized in that DS theory is adopted to fuse the collected continuous frame characteristic points of the image and the noise-reduced sound signals, and the visualized graph is converted into data, so that the accuracy of automatic detection of vibration abnormality is improved. Therefore, the application has higher precision in the automatic detection of the vibration abnormality of the tobacco shred screening vibration groove connecting rod.
"bearing vibration anomaly detection method based on improved self-encoding network" see: li Beibei, peng Li bearing vibration anomaly detection based on improved self-encoding network [ J ]. Computer science and exploration 2022,16 (01): 163-175.
"method for detecting abnormal vibration of refrigeration compressor based on self-encoder" see: wang Yuantao, feng Tao, sun Qia, etc. method for detecting abnormal vibration of refrigeration compressor based on self-encoder [ J ]. Food and machine
Mechanical, 2021,37 (04): 120-123+128.
Automatic detection system for abnormal vibration of vibrating trough connecting rod
The automatic detection system for vibration abnormality of the vibrating trough connecting rod based on DS theory fusion image and sound signals can more simply realize automatic detection of vibration abnormality of the vibrating trough connecting rod, and the system comprises:
an image acquisition module for acquiring image data of the inside of the tobacco shred screening vibration groove;
a KLT algorithm module for tracking continuous frames of the image and extracting connecting rod characteristic points at adjacent moments of the tobacco shred screening vibration groove;
a plurality of microphone array arrays for obtaining the emission position of the noise source signal;
the wavelet denoising module is used for denoising the noise source signal;
the DS theory fusion module is used for carrying out fusion analysis on the image characteristics and the sound signals;
the connecting rod vibration state conflict factor calculation module is used for calculating the connecting rod vibration state conflict factor;
the connecting rod vibration state judging module is used for judging the vibration state of the connecting rod according to the conflict factors;
and the abnormality detection output module is used for outputting detection results of abnormal vibration of the tobacco shred screening vibration groove connecting rod.
The signaling relationship of each module or array is shown in fig. 1.
The image acquisition module further comprises an image sensor and a data acquisition unit.
The KLT algorithm module further includes a feature point extraction unit and a continuous frame tracking unit.
The DS theory fusion module further comprises a feature fusion unit and a conflict factor calculation unit.
The link vibration state judgment module further includes a state judgment rule base and a state judgment logic unit.
Computer readable storage medium
A computer readable storage medium stores a computer program for executing the automatic detection method for the vibration abnormality of the tobacco shred screening vibration groove connecting rod.
Application of
The automatic detection system for the abnormal vibration of the connecting rod of the tobacco shred screening vibration groove is applied to the tobacco shred screening vibration groove of the tobacco industry and is used for monitoring and detecting the abnormal vibration state of the connecting rod in real time so as to improve the quality and the production efficiency of tobacco products.
Although the application has been described herein with reference to illustrative embodiments thereof, it should be understood that numerous other modifications and embodiments can be devised by those skilled in the art that will fall within the scope and spirit of the principles of this disclosure. More specifically, various modifications and improvements may be made to the component parts and/or arrangements of the subject combination layout within the scope of the disclosure. In addition to variations and modifications in the component parts and/or arrangements, other uses will be apparent to those skilled in the art.
Claims (10)
1. The utility model provides a groove connecting rod vibration anomaly automatic detection system shakes which characterized in that includes:
an image acquisition module for acquiring image data of the inside of the tobacco shred screening vibration groove;
the KLT algorithm module is in signal connection with the image acquisition module and is used for tracking continuous frames of images and extracting connecting rod characteristic points at adjacent moments of the tobacco shred screening vibration groove;
a plurality of microphone array arrays for obtaining the emission position of the noise source signal;
the wavelet denoising module is in signal connection with the microphone array arrays and is used for denoising noise source signals;
the DS theory fusion module is respectively connected with the KLT algorithm module and the wavelet denoising module in a signal way and is used for carrying out fusion analysis on the characteristic points of the connecting rod obtained by the KLT algorithm module and the emission positions of the noise source signals obtained by the wavelet denoising module;
the connecting rod vibration state conflict factor calculation module is in signal connection with the DS theory fusion module and is used for calculating the connecting rod vibration state conflict factor by utilizing the fusion analysis result obtained by the DS theory fusion module;
the connecting rod vibration state judging module is in signal connection with the connecting rod vibration state conflict factor calculating module and is used for judging the vibration state of the connecting rod according to the connecting rod vibration state conflict factor;
and the abnormality detection output module is in signal connection with the connecting rod vibration state judging module and is used for outputting detection results of abnormal vibration of the connecting rod of the tobacco shred screening vibration groove.
2. The automated vibration detection system of claim 1, wherein the image acquisition module further comprises an image sensor and a data acquisition unit.
3. The automated vibration anomaly detection system of claim 1, wherein the KLT algorithm module further comprises a feature point extraction unit and a continuous frame tracking unit.
4. The automated vibration anomaly detection system of claim 1, wherein the DS theory fusion module further comprises a feature fusion unit and a collision factor calculation unit.
5. The automated vibration detection system of a vibrating trough link according to claim 1, wherein the link vibration state determination module further comprises a state determination rule base and a state determination logic unit.
6. The automatic detection method for the vibration abnormality of the vibrating trough connecting rod is characterized by comprising the following steps of:
a) Collecting image data in a tobacco shred screening vibration groove;
b) Tracking continuous frames of the image by utilizing a KLT algorithm aiming at the image data acquired in the step a and extracting characteristic points of the connecting rod;
c) Constructing a plurality of microphone array arrays, and acquiring the emitting positions of noise source signals;
d) Denoising the noise source signal by utilizing wavelet denoising processing aiming at the noise signal acquired in the step c;
e) Aiming at the image and sound signals in b and d, fusing image characteristics and sound signals by utilizing DS theory, and performing fusion analysis;
f) Calculating a connecting rod vibration state conflict factor by utilizing fusion analysis in the step e;
g) Judging the vibration state of the connecting rod according to the conflict factor calculated by the f;
h) And outputting a detection result of abnormal vibration of the connecting rod of the tobacco shred screening vibrating slot according to the calculation result of the vibration state of the connecting rod in g.
7. The automated vibration anomaly detection method of claim 6, wherein the DS theory fusion analysis in step e) further includes converting the image features and the sound signals into a trust function of the DS theory, respectively, and calculating the fused trust function using a DS synthesis rule.
8. The automated inspection method of vibration anomalies of a vibrating trough link according to claim 6, wherein the link vibration state judgment in step g) further comprises making a state judgment and determining whether the link vibration state is normal or anomalous, based on a preset state judgment rule and a threshold value of a collision factor.
9. The use of the automatic detection system for abnormal vibration of the vibrating trough connecting rod according to any one of claims 1 to 5, which is characterized by comprising the step of applying the automatic detection system for abnormal vibration of the connecting rod of the vibrating trough of the tobacco shred screening to the vibrating trough of the tobacco industry for monitoring and detecting abnormal vibration states of the connecting rod in real time.
10. A readable medium having stored therein a computer program for executing the method for automated detection of vibration anomalies of a vibrating trough link according to any one of claims 6 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310714035.0A CN116958599A (en) | 2023-06-15 | 2023-06-15 | Automatic detection method and system for vibration abnormality of vibrating trough connecting rod, readable medium and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310714035.0A CN116958599A (en) | 2023-06-15 | 2023-06-15 | Automatic detection method and system for vibration abnormality of vibrating trough connecting rod, readable medium and application |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116958599A true CN116958599A (en) | 2023-10-27 |
Family
ID=88455587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310714035.0A Pending CN116958599A (en) | 2023-06-15 | 2023-06-15 | Automatic detection method and system for vibration abnormality of vibrating trough connecting rod, readable medium and application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116958599A (en) |
-
2023
- 2023-06-15 CN CN202310714035.0A patent/CN116958599A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111339882B (en) | Power transmission line hidden danger detection method based on example segmentation | |
| CN110148130B (en) | Method and device for detecting part defects | |
| CN107330437B (en) | Feature extraction method based on convolutional neural network target real-time detection model | |
| CN102903122B (en) | Video object tracking method based on feature optical flow and online ensemble learning | |
| CN109784204B (en) | Method for identifying and extracting main fruit stalks of stacked cluster fruits for parallel robot | |
| CN104268505A (en) | Automatic cloth defect point detection and recognition device and method based on machine vision | |
| JP7380019B2 (en) | Data generation system, learning device, data generation device, data generation method, and data generation program | |
| CN109003275B (en) | Segmentation method of weld defect image | |
| US20090240641A1 (en) | Optimizing method of learning data set for signal discrimination apparatus and signal discrimination apparatus capable of optimizing learning data set | |
| CN115797354A (en) | Method for detecting appearance defects of laser welding seam | |
| CN116402825B (en) | Bearing fault infrared diagnosis method, system, electronic equipment and storage medium | |
| CN116229052B (en) | Method for detecting state change of substation equipment based on twin network | |
| CN111898419A (en) | Partition landslide detection system and method based on cascade deep convolutional neural network | |
| CN114972882B (en) | Wear surface damage depth estimation method and system based on multi-attention mechanism | |
| CN117237902B (en) | Robot character recognition system based on deep learning | |
| CN117876381A (en) | AI visual detection method and system for identifying and analyzing concrete structure cracks | |
| CN111256596B (en) | Size measuring method and device based on CV technology, computer equipment and medium | |
| CN115830302B (en) | Multi-scale feature extraction fusion power distribution network equipment positioning identification method | |
| CN116735610A (en) | Steel pipe surface defect detection method based on machine vision | |
| CN116958599A (en) | Automatic detection method and system for vibration abnormality of vibrating trough connecting rod, readable medium and application | |
| CN106175822A (en) | A kind of elctrocolonogram system based on sound transducer | |
| CN114119562B (en) | Brake disc outer surface defect detection method and system based on deep learning | |
| CN115797970A (en) | Dense pedestrian target detection method and system based on YOLOv5 model | |
| CN114563771A (en) | Double-threshold laser radar cloud layer detection algorithm based on cluster analysis | |
| CN113919396A (en) | Vibration signal and image characteristic machine tool cutter wear state monitoring method based on semi-supervised learning |
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 |