CN116542916A - Method and device for detecting abnormality of chassis part of train, electronic equipment and medium - Google Patents
Method and device for detecting abnormality of chassis part of train, electronic equipment and medium Download PDFInfo
- Publication number
- CN116542916A CN116542916A CN202310446573.6A CN202310446573A CN116542916A CN 116542916 A CN116542916 A CN 116542916A CN 202310446573 A CN202310446573 A CN 202310446573A CN 116542916 A CN116542916 A CN 116542916A
- Authority
- CN
- China
- Prior art keywords
- train
- net
- chassis
- module
- anomaly detection
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000005856 abnormality Effects 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 130
- 230000002159 abnormal effect Effects 0.000 claims abstract description 58
- 239000013598 vector Substances 0.000 claims abstract description 32
- 238000013135 deep learning Methods 0.000 claims abstract description 20
- 230000009467 reduction Effects 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims description 11
- 238000012512 characterization method Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 239000006096 absorbing agent Substances 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000035939 shock Effects 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 16
- 230000001537 neural effect Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 10
- 238000013528 artificial neural network Methods 0.000 description 8
- 238000003709 image segmentation Methods 0.000 description 7
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a method and a device for detecting abnormality of a chassis part of a train, electronic equipment and a medium. The method comprises the following steps: shooting and acquiring images of different visual angles of a train chassis through a camera; constructing a U-Net anomaly detection model by adopting a deep learning algorithm; analyzing the image through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module; converting the image data into feature vectors; performing dimension reduction and reconstruction on the feature vector through an Autoencoder module, and calculating to obtain a reconstruction error; and under the condition that the reconstruction error exceeds a preset threshold value, judging that the target part has an abnormal event of the chassis part of the train. Therefore, abnormal events of chassis parts of different kinds of train vehicles can be effectively detected.
Description
Technical Field
The invention relates to the technical field of train operation safety management, in particular to a train chassis part abnormality detection method and device, electronic equipment and a medium.
Background
At present, abnormal detection of chassis parts of a train mainly depends on manual detection, and the manual detection efficiency is low. The existing detection system can only detect a single event, can not detect different types of abnormal events, and has the problem that the existing detection method can not effectively detect the abnormality of the part due to complex detection scene of the train chassis.
Disclosure of Invention
The embodiment of the invention mainly aims to provide a method and a device for detecting abnormal chassis parts of a train, electronic equipment and a medium, which can effectively detect abnormal events of chassis parts of different kinds of trains.
In order to achieve the above object, a first aspect of an embodiment of the present invention provides a method for detecting an anomaly of a chassis part of a train vehicle, the method including:
shooting and acquiring images of different visual angles of a train chassis through a camera;
constructing a U-Net anomaly detection model by adopting a deep learning algorithm;
analyzing the image through the U-Net anomaly detection model to obtain image data of a target part in the train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module;
converting the image data into feature vectors;
performing dimension reduction and reconstruction on the feature vector through the Autoencoder module, and calculating to obtain a reconstruction error;
and under the condition that the reconstruction error exceeds a preset threshold value, judging that the abnormal event of the chassis part of the train occurs to the target part.
In some embodiments, the training method of the U-Net anomaly detection model is as follows:
calculating the reconstruction error of each normal sample by using an Autoencoder module;
generating a greater number of abnormal samples than the normal number of samples from the reconstruction error using a GAN module;
and mixing the normal sample and the generated abnormal sample together to form a new data set, and training by using a two-classification model to obtain the trained U-Net abnormality detection model.
In some embodiments, before the analyzing the image by the U-Net anomaly detection model to obtain image data of the target part in the train chassis, the U-Net anomaly detection model includes an afflicientnets network model, an Autoencoder module, and a GAN module, the method further includes:
and processing the image by using a YOLOv7 target detection algorithm to identify a target part in the image.
In some embodiments, the EfficientNet serves as an encoder for the U-Net anomaly detection model for improving feature extraction and characterization capabilities of the U-Net anomaly detection model.
In some embodiments, the method further comprises:
and obtaining the world coordinates of the target part through a calibration algorithm.
In some embodiments, the obtaining the world coordinates of the target part by a calibration algorithm includes:
acquiring internal parameters of the camera;
calculating a translation vector of the camera model perpendicular to the target part;
calculating a rotation matrix of the world coordinate system around the image coordinate system;
combining the actual position of the camera to obtain a coordinate conversion relation between the image coordinate and the world coordinate;
and obtaining world coordinates of the target part based on the coordinate conversion relation.
In some embodiments, when the reconstruction error exceeds the preset threshold, after determining that the abnormal event of the chassis part of the train occurs to the target part, the method further includes:
and early warning and reporting the abnormal event of the train chassis part, wherein the abnormal event of the train chassis part comprises breakage of a train chassis transmission shaft, looseness of a train brake and damage or loss of a train shock absorber.
To achieve the above object, a second aspect of the embodiments of the present invention provides a train chassis part abnormality detection device, including:
the shooting module is used for shooting and acquiring images of different visual angles of the train chassis through a camera;
the construction module is used for constructing a U-Net anomaly detection model by adopting a deep learning algorithm;
the analysis module is used for analyzing the image through the U-Net anomaly detection model to obtain image data of a target part in the train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module;
a conversion module for converting the image data into feature vectors;
the reconstruction module is used for performing dimension reduction and reconstruction on the feature vector through the Autoencoder module, and calculating to obtain a reconstruction error;
and the judging module is used for judging that the abnormal event of the chassis part of the train occurs to the target part under the condition that the reconstruction error exceeds a preset threshold value.
To achieve the above object, a third aspect of the embodiments of the present invention proposes an electronic device, including a memory storing a computer program and a processor implementing the method according to the first aspect when the processor executes the computer program.
To achieve the above object, a fourth aspect of the embodiments of the present invention proposes a computer-readable storage medium storing a computer program which, when executed by a processor, implements the method of the first aspect.
According to the method and device for detecting the abnormality of the train chassis part, the electronic equipment and the medium, the images of different visual angles of the train chassis are obtained through camera shooting; constructing a U-Net anomaly detection model by adopting a deep learning algorithm; analyzing the image through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module; converting the image data into feature vectors; performing dimension reduction and reconstruction on the feature vector through an Autoencoder module, and calculating to obtain a reconstruction error; and under the condition that the reconstruction error exceeds a preset threshold value, judging that the target part has an abnormal event of the chassis part of the train. Based on the above, compared with the existing human detection method, the embodiment of the invention adopts a machine vision technology and a U-Net abnormality detection model to realize the abnormality detection of the chassis parts of the train, and constructs the U-Net abnormality detection model by adopting a deep learning algorithm; the image is analyzed through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module, and the EfficientNet uses a technology named neural architecture search (Neural Architecture Search, NAS) to automatically search out an efficient neural network structure so as to adapt to different image classification tasks. The U-Net is a network for image segmentation, which can segment images into different areas so as to analyze different parts in the images, and the Efficient Net is added into the U-Net, so that the Efficient Net is used as an encoder of the U-Net, and the feature extraction and characterization capability of the U-Net can be improved. In order to improve the robustness of the model, an Autoencoder module is added to a U-Net decoding part, meanwhile, the generation capacity and the accuracy of the model are further optimized by using GAN, and the problem that the abnormal parts cannot be effectively detected due to the fact that the detection scene of a train chassis is complex is solved by combining different algorithm modules. Therefore, the embodiment of the invention can effectively detect abnormal events of chassis parts of different kinds of train vehicles.
Drawings
FIG. 1 is a flow chart of a method for detecting anomalies in chassis parts of a train in accordance with an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a device for detecting abnormality of chassis parts of a train according to an embodiment of the present invention;
fig. 3 is a schematic hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention 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 invention.
It should be noted that although functional block division is performed in a device diagram and a logic sequence is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the block division in the device, or in the flowchart. The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Aiming at the problems that in the prior art, abnormal events of train chassis parts mainly depend on manual detection, the efficiency is low, and the existing detection method cannot effectively detect abnormal parts due to complex detection scenes of the train chassis, the embodiment of the invention provides a method and a device for detecting abnormal parts of the train chassis, electronic equipment and media, and images of different visual angles of the train chassis are obtained through camera shooting; constructing a U-Net anomaly detection model by adopting a deep learning algorithm; analyzing the image through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module; converting the image data into feature vectors; performing dimension reduction and reconstruction on the feature vector through an Autoencoder module, and calculating to obtain a reconstruction error; and under the condition that the reconstruction error exceeds a preset threshold value, judging that the target part has an abnormal event of the chassis part of the train. Based on the above, compared with the existing human detection method, the embodiment of the invention adopts a machine vision technology and a U-Net abnormality detection model to realize the abnormality detection of the chassis parts of the train, and constructs the U-Net abnormality detection model by adopting a deep learning algorithm; the image is analyzed through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module, and the EfficientNet uses a technology named neural architecture search (Neural Architecture Search, NAS) to automatically search out an efficient neural network structure so as to adapt to different image classification tasks. The U-Net is a network for image segmentation, which can segment images into different areas so as to analyze different parts in the images, and the Efficient Net is added into the U-Net, so that the Efficient Net is used as an encoder of the U-Net, and the feature extraction and characterization capability of the U-Net can be improved. In order to improve the robustness of the model, an Autoencoder module is added to a U-Net decoding part, meanwhile, the generation capacity and the accuracy of the model are further optimized by using GAN, and the problem that the abnormal parts cannot be effectively detected due to the fact that the detection scene of a train chassis is complex is solved by combining different algorithm modules. Therefore, the embodiment of the invention can effectively detect abnormal events of chassis parts of different kinds of train vehicles.
The embodiment of the invention provides a method and a device for detecting abnormality of a chassis part of a train, electronic equipment and a medium, and specifically describes the following embodiment.
Fig. 1 is an optional flowchart of a method for detecting an anomaly of a chassis part of a train according to an embodiment of the present invention, where the method in fig. 1 may include, but is not limited to, steps S101 to S106.
Step S101, capturing images of different view angles of a train chassis through a camera;
step S102, constructing a U-Net anomaly detection model by adopting a deep learning algorithm;
s103, analyzing the image through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module;
step S104, converting the image data into feature vectors;
step S105, performing dimension reduction and reconstruction on the feature vector through an Autoencoder module, and calculating to obtain a reconstruction error;
and step S106, judging that the target part has an abnormal event of the chassis part of the train vehicle under the condition that the reconstruction error exceeds the preset threshold value.
In some embodiments, the train chassis part anomaly event includes a train chassis drive shaft break, a train brake slackening, a train damper breakage or loss, etc.
In some embodiments, since the chassis of the train is composed of different components, in order to fully detect the chassis of the train, multiple views of different angles of the train need to be acquired, including, for example, side views of the left and right sides of the chassis of the train, top views of the train (if the chassis of the train is detached), and bottom shooting views of the chassis of the train, the shooting can be performed from different positions for the position to be detected.
In some embodiments, the present invention employs a YOLOv7 object detection algorithm in identifying an asset, which YOLOv7 object detection algorithm can identify a plurality of different part objects simultaneously.
In some embodiments, the method and the device take the problems that when an algorithm model is constructed, gradient explosion and the like of the algorithm model possibly occur due to the problems of excessive layers and the like of the deep neural network when the algorithm model is used for carrying out anomaly detection, so that the method and the device adopt a U-Net anomaly detection model, an EfficientNet network is added in the U-Net, the U-Net is mainly used for an image anomaly detection task, the EfficientNet is an efficient deep neural network model, the feature extraction and characterization capability of the U-Net can be improved, and an Autoencoder module and a GAN module are added, so that the whole model has better feature extraction and characterization capability, reconstruction capability, generalization capability, generation capability and accuracy, and a finer and efficient part image anomaly detection task can be realized.
In some embodiments, efficientNet and U-Net are both image analysis frameworks based on convolutional neural networks. EfficientNet uses a technique called neural architecture search (Neural Architecture Search, NAS) that automatically searches for an efficient neural network structure to accommodate different image classification tasks. While U-Net is a network for image segmentation that can segment images into different regions to facilitate analysis of different parts of the image. Both frames have better feature extraction and dimension reduction capabilities, and can convert high-dimensional image data into low-dimensional feature vectors. Secondly, autoencoder is a commonly used unsupervised learning algorithm that can map high-dimensional data into a low-dimensional space and restore the low-dimensional data back to the original dimension. In the anomaly detection, the image data may be reduced in size using an Autoencoder, and the anomaly detection may be performed by reconstructing an error. The eigenvectors extracted by EfficientNet or U-Net are used as the input of Autoencoder, which is then encoded and decoded, and then the reconstruction error is calculated. If the reconstruction error is above a certain threshold, the sample may be considered an outlier sample.
In some embodiments, the GAN module is a generation model that can generate new data samples from random noise. In anomaly detection, GAN can be used to generate more part anomaly samples and combine these samples with the original normal samples to form a richer data set. Specifically, the reconstruction error for each normal sample may be calculated using an Autoencoder, and then GAN may be used to generate more abnormal samples from the reconstruction error. This process is equivalent to expanding the data set to increase the richness of the data set. Finally, the normal sample and the generated abnormal sample are mixed together to form a new data set, and training is carried out by using a two-classification model. At the time of the test, a new sample is input into the model, and whether it is an abnormal sample is detected. Specifically, the eigenvectors extracted by EfficientNet or U-Net can be used as input, and the eigenvectors can be subjected to the reduction and reconstruction by an Autoencoder, and then the reconstruction error can be calculated. If the reconstruction error is above a certain threshold, the sample may be considered an outlier sample.
In some embodiments, the EfficientNet is added in the U-Net, the Autoencoder module is added in the U-Net decoding part, meanwhile, the GAN module is used for further optimizing the generation capacity and accuracy of the model, the problem that abnormal parts cannot be effectively detected due to the fact that a train chassis detection scene is complex is solved by combining different algorithm modules, and the problems that abnormal events of different types of vehicle chassis parts can be detected, deformation, loss, looseness and the like of the parts can be effectively detected by using the model.
In some embodiments, in order to locate the actual position of an abnormal event of a road facility and improve the detection precision of the abnormal event, the invention calibrates a camera, and determines the actual position of a detected target part through a calibration algorithm. Firstly, acquiring internal parameters of a camera, then calculating a translation vector of a camera model perpendicular to a detected target part, then calculating a rotation matrix of a world coordinate system around an image coordinate system, and combining the actual position of the camera to obtain a coordinate conversion relation between the image coordinate and the world coordinate, and obtaining the world coordinate of the target part based on the coordinate conversion relation. The position of the world coordinates is the position of the target in real space.
In some embodiments, in a training stage of the U-Net anomaly detection model, training data is input into a yolov7+resnet model to perform data training, so as to obtain detection accuracy of the detection model. When the ResNet network model is data trained, 80% of the data is used for training and 20% is used for testing, and if the required detection accuracy is not achieved, the ResNet network model is continuously trained through the data until the required accuracy is achieved.
In some embodiments, images of different perspectives of a train chassis are captured by a camera; constructing a U-Net anomaly detection model by adopting a deep learning algorithm; analyzing the image through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module; converting the image data into feature vectors; performing dimension reduction and reconstruction on the feature vector through an Autoencoder module, and calculating to obtain a reconstruction error; and under the condition that the reconstruction error exceeds a preset threshold value, judging that the target part has an abnormal event of the chassis part of the train. Based on the above, compared with the existing human detection method, the embodiment of the invention adopts a machine vision technology and a U-Net abnormality detection model to realize the abnormality detection of the chassis parts of the train, and constructs the U-Net abnormality detection model by adopting a deep learning algorithm; the image is analyzed through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module, and the EfficientNet uses a technology named neural architecture search (Neural Architecture Search, NAS) to automatically search out an efficient neural network structure so as to adapt to different image classification tasks. The U-Net is a network for image segmentation, which can segment images into different areas so as to analyze different parts in the images, and the Efficient Net is added into the U-Net, so that the Efficient Net is used as an encoder of the U-Net, and the feature extraction and characterization capability of the U-Net can be improved. In order to improve the robustness of the model, an Autoencoder module is added to a U-Net decoding part, meanwhile, the generation capacity and the accuracy of the model are further optimized by using GAN, and the problem that the abnormal parts cannot be effectively detected due to the fact that the detection scene of a train chassis is complex is solved by combining different algorithm modules. Therefore, the embodiment of the invention can effectively detect abnormal events of chassis parts of different kinds of train vehicles.
In some embodiments, step S106 may be followed by, but is not limited to including step S107:
and step S107, early warning and reporting abnormal events of the chassis parts of the train are carried out, wherein the abnormal events of the chassis parts of the train comprise breakage of a transmission shaft of the chassis of the train, looseness of a brake of the train and damage or loss of a shock absorber of the train.
In some embodiments, the embodiment of the invention adopts a machine vision technology and a U-Net abnormality detection model to detect the abnormality of the train chassis part, and can report the occurred event to related departments in real time, thereby playing the roles of real-time detection and real-time early warning.
Referring to fig. 2, the embodiment of the invention further provides a device for detecting an abnormality of a chassis part of a train, which can implement the method for detecting an abnormality of a chassis part of a train, and the device includes:
the shooting module 210 is used for shooting and acquiring images of different view angles of the train chassis through a camera;
the construction module 220 is configured to construct a U-Net anomaly detection model using a deep learning algorithm;
the analysis module 230 is configured to analyze the image through a U-Net anomaly detection model to obtain image data of a target part in a chassis of the train, where the U-Net anomaly detection model includes an afflicientnets network model, an Autoencoder module, and a GAN module;
a conversion module 240 for converting the image data into feature vectors;
the reconstruction module 250 is configured to perform dimension reduction and reconstruction on the feature vector through the Autoencoder module, and calculate a reconstruction error;
and the judging module 260 is used for judging that the abnormal event of the chassis part of the train occurs to the target part under the condition that the reconstruction error exceeds the preset threshold value.
Based on this, in the train chassis part abnormality detection device of the embodiment of the present invention, the photographing module 210 photographs images of different view angles of the train chassis through the camera; the construction module 220 adopts a deep learning algorithm to construct a U-Net anomaly detection model; the analysis module 230 analyzes the image through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module; the conversion module 240 converts the image data into feature vectors; the reconstruction module 250 performs dimension reduction and reconstruction on the feature vector through the Autoencoder module, and calculates a reconstruction error; the determining module 260 determines that the target part has an abnormal event of the chassis part of the train vehicle if it determines that the reconstruction error exceeds the preset threshold. According to the embodiment of the invention, images of different visual angles of the train chassis are obtained through camera shooting; constructing a U-Net anomaly detection model by adopting a deep learning algorithm; analyzing the image through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module; converting the image data into feature vectors; performing dimension reduction and reconstruction on the feature vector through an Autoencoder module, and calculating to obtain a reconstruction error; and under the condition that the reconstruction error exceeds a preset threshold value, judging that the target part has an abnormal event of the chassis part of the train. Based on the above, compared with the existing human detection method, the embodiment of the invention adopts a machine vision technology and a U-Net abnormality detection model to realize the abnormality detection of the chassis parts of the train, and constructs the U-Net abnormality detection model by adopting a deep learning algorithm; the image is analyzed through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module, and the EfficientNet uses a technology named neural architecture search (Neural Architecture Search, NAS) to automatically search out an efficient neural network structure so as to adapt to different image classification tasks. The U-Net is a network for image segmentation, which can segment images into different areas so as to analyze different parts in the images, and the Efficient Net is added into the U-Net, so that the Efficient Net is used as an encoder of the U-Net, and the feature extraction and characterization capability of the U-Net can be improved. In order to improve the robustness of the model, an Autoencoder module is added to a U-Net decoding part, meanwhile, the generation capacity and the accuracy of the model are further optimized by using GAN, and the problem that the abnormal parts cannot be effectively detected due to the fact that the detection scene of a train chassis is complex is solved by combining different algorithm modules. Therefore, the embodiment of the invention can effectively detect abnormal events of chassis parts of different kinds of train vehicles.
The specific implementation manner of the device for detecting abnormal chassis parts of the train is basically the same as the specific implementation manner of the method for detecting abnormal chassis parts of the train, and is not repeated here.
The embodiment of the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the method for detecting the abnormal parts of the chassis of the train when executing the computer program. The electronic equipment can be any intelligent terminal including a tablet personal computer, a vehicle-mounted computer and the like.
Referring to fig. 3, fig. 3 illustrates a hardware structure of an electronic device according to another embodiment, where the electronic device includes:
the processor 301 may be implemented by a general-purpose CPU (central processing unit), a microprocessor, an application-specific integrated circuit (ApplicationSpecificIntegratedCircuit, ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solutions provided by the embodiments of the present invention.
The memory 302 may be implemented in the form of read-only memory (ReadOnlyMemory, ROM), static storage, dynamic storage, or random access memory (RandomAccessMemory, RAM). The memory 302 may store an operating system and other application programs, and when the technical solution provided in the embodiments of the present disclosure is implemented by software or firmware, relevant program codes are stored in the memory 302, and the processor 301 invokes the method for detecting abnormal parts of the chassis of the train vehicle according to the embodiments of the present disclosure, that is, images of different perspectives of the chassis of the train vehicle are obtained by shooting with a camera; constructing a U-Net anomaly detection model by adopting a deep learning algorithm; analyzing the image through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module; converting the image data into feature vectors; performing dimension reduction and reconstruction on the feature vector through an Autoencoder module, and calculating to obtain a reconstruction error; and under the condition that the reconstruction error exceeds a preset threshold value, judging that the target part has an abnormal event of the chassis part of the train. Based on the above, compared with the existing human detection method, the embodiment of the invention adopts a machine vision technology and a U-Net abnormality detection model to realize the abnormality detection of the chassis parts of the train, and constructs the U-Net abnormality detection model by adopting a deep learning algorithm; the image is analyzed through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module, and the EfficientNet uses a technology named neural architecture search (Neural Architecture Search, NAS) to automatically search out an efficient neural network structure so as to adapt to different image classification tasks. The U-Net is a network for image segmentation, which can segment images into different areas so as to analyze different parts in the images, and the Efficient Net is added into the U-Net, so that the Efficient Net is used as an encoder of the U-Net, and the feature extraction and characterization capability of the U-Net can be improved. In order to improve the robustness of the model, an Autoencoder module is added to a U-Net decoding part, meanwhile, the generation capacity and the accuracy of the model are further optimized by using GAN, and the problem that the abnormal parts cannot be effectively detected due to the fact that the detection scene of a train chassis is complex is solved by combining different algorithm modules. Therefore, the embodiment of the invention can effectively detect abnormal events of chassis parts of different kinds of train vehicles.
An input/output interface 303 for implementing information input and output.
The communication interface 304 is configured to implement communication interaction between the device and other devices, and may implement communication in a wired manner (e.g., USB, network cable, etc.), or may implement communication in a wireless manner (e.g., mobile network, WIFI, bluetooth, etc.).
A bus that transfers information between the various components of the device, such as the processor 301, memory 302, input/output interfaces 303, and communication interfaces 304.
Wherein the processor 301, the memory 302, the input/output interface 303 and the communication interface 304 are communicatively connected to each other within the device via a bus.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program which is executed by a processor to realize the method for detecting the abnormal parts of the chassis of the train.
The memory, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
According to the train chassis part abnormality detection method, the train chassis part abnormality detection device, the electronic equipment and the storage medium provided by the embodiment of the invention, images of different visual angles of the train chassis are obtained through camera shooting; constructing a U-Net anomaly detection model by adopting a deep learning algorithm; analyzing the image through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module; converting the image data into feature vectors; performing dimension reduction and reconstruction on the feature vector through an Autoencoder module, and calculating to obtain a reconstruction error; and under the condition that the reconstruction error exceeds a preset threshold value, judging that the target part has an abnormal event of the chassis part of the train. Based on the above, compared with the existing human detection method, the embodiment of the invention adopts a machine vision technology and a U-Net abnormality detection model to realize the abnormality detection of the chassis parts of the train, and constructs the U-Net abnormality detection model by adopting a deep learning algorithm; the image is analyzed through a U-Net anomaly detection model to obtain image data of a target part in a train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module, and the EfficientNet uses a technology named neural architecture search (Neural Architecture Search, NAS) to automatically search out an efficient neural network structure so as to adapt to different image classification tasks. The U-Net is a network for image segmentation, which can segment images into different areas so as to analyze different parts in the images, and the Efficient Net is added into the U-Net, so that the Efficient Net is used as an encoder of the U-Net, and the feature extraction and characterization capability of the U-Net can be improved. In order to improve the robustness of the model, an Autoencoder module is added to a U-Net decoding part, meanwhile, the generation capacity and the accuracy of the model are further optimized by using GAN, and the problem that the abnormal parts cannot be effectively detected due to the fact that the detection scene of a train chassis is complex is solved by combining different algorithm modules. Therefore, the embodiment of the invention can effectively detect abnormal events of chassis parts of different kinds of train vehicles.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable programs, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable programs, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
The embodiments described in the embodiments of the present invention are for more clearly describing the technical solutions of the embodiments of the present invention, and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention, and those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present invention are equally applicable to similar technical problems.
It will be appreciated by persons skilled in the art that the embodiments of the invention are not limited by the illustrations, and that more or fewer steps than those shown may be included, or certain steps may be combined, or different steps may be included.
The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
The terms "first," "second," "third," "fourth," and the like in the description of the invention and in the above figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present invention, "at least one (item)" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the above-described division of units is merely a logical function division, and there may be another division manner in actual implementation, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including multiple instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing a program.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, and are not thereby limiting the scope of the claims of the embodiments of the present invention. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and spirit of the embodiments of the present invention shall fall within the scope of the claims of the embodiments of the present invention.
Claims (10)
1. A method for detecting anomalies in chassis parts of a train, the method comprising:
shooting and acquiring images of different visual angles of a train chassis through a camera;
constructing a U-Net anomaly detection model by adopting a deep learning algorithm;
analyzing the image through the U-Net anomaly detection model to obtain image data of a target part in the train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module;
converting the image data into feature vectors;
performing dimension reduction and reconstruction on the feature vector through the Autoencoder module, and calculating to obtain a reconstruction error;
and under the condition that the reconstruction error exceeds a preset threshold value, judging that the abnormal event of the chassis part of the train occurs to the target part.
2. The method according to claim 1, wherein the training method of the U-Net anomaly detection model is as follows:
calculating the reconstruction error of each normal sample by using an Autoencoder module;
generating a greater number of abnormal samples than the normal number of samples from the reconstruction error using a GAN module;
and mixing the normal sample and the generated abnormal sample together to form a new data set, and training by using a two-classification model to obtain the trained U-Net abnormality detection model.
3. The method of claim 1, wherein before the analyzing the image by the U-Net anomaly detection model to obtain image data of a target part in the train chassis, the U-Net anomaly detection model includes an EfficientNets network model, an Autoencoder module, and a GAN module, further includes:
and processing the image by using a YOLOv7 target detection algorithm to identify a target part in the image.
4. A method according to claim 3, wherein said EfficientNets act as encoders for said U-Net anomaly detection model for improving the feature extraction and characterization capabilities of said U-Net anomaly detection model.
5. The method according to claim 1, wherein the method further comprises:
and obtaining the world coordinates of the target part through a calibration algorithm.
6. The method of claim 5, wherein the obtaining world coordinates of the target part by a calibration algorithm comprises:
acquiring internal parameters of the camera;
calculating a translation vector of the camera model perpendicular to the target part;
calculating a rotation matrix of the world coordinate system around the image coordinate system;
combining the actual position of the camera to obtain a coordinate conversion relation between the image coordinate and the world coordinate;
and obtaining world coordinates of the target part based on the coordinate conversion relation.
7. The method according to any one of claims 1 to 6, wherein, in the case where it is determined that the reconstruction error exceeds a preset threshold, after determining that the abnormal event of the chassis part of the train has occurred in the target part, further comprising:
and early warning and reporting the abnormal event of the train chassis part, wherein the abnormal event of the train chassis part comprises breakage of a train chassis transmission shaft, looseness of a train brake and damage or loss of a train shock absorber.
8. An abnormality detection device for a chassis part of a train vehicle, the device comprising:
the shooting module is used for shooting and acquiring images of different visual angles of the train chassis through a camera;
the construction module is used for constructing a U-Net anomaly detection model by adopting a deep learning algorithm;
the analysis module is used for analyzing the image through the U-Net anomaly detection model to obtain image data of a target part in the train chassis, wherein the U-Net anomaly detection model comprises an EfficientNet network model, an Autoencoder module and a GAN module;
a conversion module for converting the image data into feature vectors;
the reconstruction module is used for performing dimension reduction and reconstruction on the feature vector through the Autoencoder module, and calculating to obtain a reconstruction error;
and the judging module is used for judging that the abnormal event of the chassis part of the train occurs to the target part under the condition that the reconstruction error exceeds a preset threshold value.
9. An electronic device comprising a memory and a processor, the memory storing a computer program, the processor implementing the method of detecting anomalies in a chassis part of a rail vehicle of any one of claims 1 to 7 when the computer program is executed.
10. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the train vehicle chassis part anomaly detection method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310446573.6A CN116542916A (en) | 2023-04-23 | 2023-04-23 | Method and device for detecting abnormality of chassis part of train, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310446573.6A CN116542916A (en) | 2023-04-23 | 2023-04-23 | Method and device for detecting abnormality of chassis part of train, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116542916A true CN116542916A (en) | 2023-08-04 |
Family
ID=87455286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310446573.6A Pending CN116542916A (en) | 2023-04-23 | 2023-04-23 | Method and device for detecting abnormality of chassis part of train, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116542916A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117150388A (en) * | 2023-11-01 | 2023-12-01 | 江西现代职业技术学院 | Abnormal state detection method and system for automobile chassis |
-
2023
- 2023-04-23 CN CN202310446573.6A patent/CN116542916A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117150388A (en) * | 2023-11-01 | 2023-12-01 | 江西现代职业技术学院 | Abnormal state detection method and system for automobile chassis |
| CN117150388B (en) * | 2023-11-01 | 2024-01-26 | 江西现代职业技术学院 | Abnormal state detection method and system for automobile chassis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11645744B2 (en) | Inspection device and inspection method | |
| US8811663B2 (en) | Object detection in crowded scenes | |
| CN111898581B (en) | Animal detection method, apparatus, electronic device, and readable storage medium | |
| CN113052029A (en) | Abnormal behavior supervision method and device based on action recognition and storage medium | |
| CN110458126B (en) | Pantograph state monitoring method and device | |
| CN116542916A (en) | Method and device for detecting abnormality of chassis part of train, electronic equipment and medium | |
| CN111832492A (en) | Method and device for distinguishing static traffic abnormality, computer equipment and storage medium | |
| CN104573680A (en) | Image detection method, image detection device and traffic violation detection system | |
| CN110928967A (en) | Ship behavior analysis method and system based on big data | |
| CN112802076A (en) | Reflection image generation model and training method of reflection removal model | |
| CN116258991A (en) | Abnormality detection apparatus, abnormality detection system, abnormality detection method, and computer program product | |
| CN114170585B (en) | Dangerous driving behavior recognition method and device, electronic equipment and storage medium | |
| US20090310855A1 (en) | Event detection method and video surveillance system using said method | |
| CN113014876B (en) | Video monitoring method and device, electronic equipment and readable storage medium | |
| CN112052823A (en) | Target detection method and device | |
| KR102546598B1 (en) | Apparatus And Method For Detecting Anomalous Event | |
| CN115147752A (en) | Video analysis method and device and computer equipment | |
| Aiordachioaie et al. | Change Detection by Feature Extraction and Processing from Time-Frequency Images | |
| US20110234912A1 (en) | Image activity detection method and apparatus | |
| CN107886542B (en) | A kind of the target restoration methods and system of vision-based detection | |
| US20230278550A1 (en) | Monitoring Agricultural Operations | |
| CN114387311B (en) | LKJ file and locomotive video automatic time setting method, device and computer equipment | |
| Habeb et al. | Video Anomaly Detection using Residual Autoencoder: A Lightweight Framework | |
| US20210390847A1 (en) | Driving assistance device and method, and storage medium in which program is stored | |
| CN118169674A (en) | Target detection method and device, electronic equipment and storage medium |
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 |