A wind resistance identification method, system, device and storage medium

Abstract

The present invention discloses a method, system, device, and storage medium for identifying wind brakes, and relates to the field of railway brake detection technology. The method comprises: using an improved YOLOv8m network to detect whether an image contains a bellows rod and a brake cylinder head; if the bellows rod and the brake cylinder head are contained, the bellows rod length is calculated; when the bellows rod length exceeds a preset length threshold, a brake risk warning is issued; wherein, a spatial pyramid pooling module and a partial self-attention module are introduced in the fourth stage of the original YOLOv8m backbone network; and a coordinate attention mechanism is introduced in the third stage of the neck network. The present invention adaptively adjusts feature weights so that the detection model can focus on the target boundary more accurately, thereby achieving efficient detection and positioning of the bellows rod. Experiments show that the accuracy of target detection of the present invention can reach the millimeter level, and the recognition rate of the bellows rod is as high as 99.9%.

Description

Technical Field

[0001] The present invention relates to the technical field of railway brake detection technology, and in particular to a wind brake identification method, system, equipment and storage medium. Background Art

[0002] During the railway hump shunting operation, if the brake shoes hold the wheels and brake, the vehicle will operate with the brakes on. The shunting process of the vehicle with brakes on may cause it to stop, or even collide or derail, which will seriously affect the railway operation efficiency and may even cause safety accidents.

[0003] Intelligent identification of railway brake engagement is a critical technology for railway transportation safety. Braking refers to situations where all brake shoes remain pressed against the wheel treads during hump dismantling and shunting operations due to issues such as failure to properly ventilate the vehicle being shunted or failure to release the manual brake mechanism as required. This can cause the vehicle to stop mid-flight, leading to frequent collisions, derailments, and other accidents. Railway freight cars use two types of brakes to stop and control speed during operation: air brakes and manual brakes. Air brakes involve injecting air into an air cylinder, pushing a piston and extending a bellows rod, which drives the brake shoes to engage the wheels, creating friction between the wheels and braking the train. Manual brakes involve manually rotating the manual brake mechanism, which pulls the brake chain and engages the wheels, creating friction between the wheels and braking the train. Wind lock occurs when the brake shoes engage the wheels during shunting operations due to failure to properly ventilate the vehicle during hump operations, causing the brakes to engage the wheels, resulting in the train operating with the brakes engaged.

[0004] In recent years, with the continuous emergence of new models in the field of deep learning, vehicle intelligent detection technology based on computer vision has also made great progress. In the field of target detection, mainstream algorithms are mainly divided into two categories: (1) Single-stage model: This type of model simplifies the target detection task into a regression and classification problem, directly predicting the target category and bounding box by inputting the image. Due to its simple structure, the single-stage model has a high detection speed and is suitable for real-time detection scenarios and devices with limited computing power. (2) Two-stage model: Unlike the single-stage model, the two-stage model divides the detection task into two stages. The first stage generates candidate regions, and the second stage further classifies and regresses these candidate regions. By gradually refining the target features, the model performs better in small target detection and complex scenes. However, the multi-stage computational characteristics make the model structure more complex, which correspondingly increases the computational overhead.

[0005] Therefore, it is worth studying how to use deep learning to dynamically detect and warn of railway brake risks in real time. Summary of the Invention

[0006] In view of the above problems, the present invention proposes a wind resistance identification method, system, device and storage medium to attempt to solve or alleviate one or more of the above problems.

[0007] According to one aspect of the present invention, a wind resistance identification method is proposed, the method comprising:

[0008] Get a training image dataset;

[0009] Preprocess the training image data;

[0010] The preprocessed training image dataset is input into the target detection model based on the improved YOLOv8m network for training to obtain the trained target detection model;

[0011] Input the image to be detected into the trained target detection model for detection to obtain a detection result; the detection result is whether the image to be detected contains the bellows rod and the brake cylinder head;

[0012] If the image to be detected contains a bellows rod and a brake cylinder head, determining whether the bellows rod is a valid bellows rod based on the positional relationship between the bellows rod and the brake cylinder head; the criterion for determining whether the bellows rod is a valid bellows rod is that the brake cylinder head is within a certain pixel range around the bellows rod in the image;

[0013] When a valid bellows rod exists in the image to be detected, the bellows rod length is calculated; the bellows rod length is compared with a preset length threshold, and when the bellows rod length exceeds the preset length threshold, a brake risk warning is issued.

[0014] Furthermore, the improvements of the improved YOLOv8m network include: adding a spatial pyramid pooling module and a partial self-attention module to the original YOLOv8m backbone network; and adding a coordinate attention mechanism after the neck network and before the head network.

[0015] Furthermore, the step of inputting the image to be detected into the trained target detection model for detection and obtaining the detection result includes:

[0016] The image to be detected is input into the backbone network for feature extraction, including: using multiple C2f feature extraction modules in the backbone network to extract local features of the image and perform feature fusion; then, aggregating features of different scales through the spatial pyramid pooling module; then, using the partial self-attention module, evenly splitting the aggregated feature map into two parts. One part of the feature map enters the self-attention module for global information modeling, extracting key features through matrix operations between the query vector, key vector and value vector, and the other part of the feature map is fused with the output of the self-attention module through skip connections;

[0017] The neck network is used to fuse, enhance and process the features extracted by the backbone network;

[0018] The coordinate attention mechanism is used to generate feature maps with enhanced position information. The method includes the following steps: first, global average pooling is performed on the features output by the neck network in the horizontal and vertical directions to extract compressed features in different directions; then, these features are fused through a set of convolutions with shared weights; the fused features are re-divided into horizontal and vertical parts, and the attention matrix is generated by 1×1 convolution and sigmoid activation function respectively; finally, the features output by the neck network are weighted by the attention matrix through element-wise multiplication to obtain a feature map with enhanced position information;

[0019] The head network is used to transform the feature map enhanced with position information into the final object detection result.

[0020] Furthermore, the aggregating features of different scales through the spatial pyramid pooling module includes: processing features of different scales through convolution layers, batch normalization and SiLU activation functions to obtain feature maps with half the number of channels; passing through multiple maximum pooling layers in sequence to gradually reduce the size of the feature maps; and splicing the feature maps after pooling at different scales in the channel dimension.

[0021] Furthermore, the dimension of the query vector and the key vector in the partial self-attention module is half of the value vector; batch normalization is used instead of layer normalization for normalization.

[0022] Furthermore, the preprocessing includes data enhancement, and the data enhancement includes rotation, flipping, scaling, and brightness adjustment.

[0023] Furthermore, the target detection model based on the improved YOLOv8m network introduces regularization technology during the training process, and the regularization technology includes weight decay and Dropout.

[0024] According to another aspect of the present invention, a wind resistance identification system is provided, the system comprising:

[0025] The detection model training module includes a training data acquisition submodule, a preprocessing submodule, and a model training submodule; the training data acquisition submodule is configured to acquire a training image data set; the preprocessing submodule is configured to preprocess the training image data; and the model training submodule is configured to input the preprocessed training image data set into a target detection model based on an improved YOLOv8m network for training to obtain a trained target detection model;

[0026] An object detection module is configured to input an image to be detected into a trained object detection model for detection and obtain a detection result; the detection result is whether the image to be detected contains a bellows rod and a brake cylinder head;

[0027] A brake holding recognition module is configured to determine whether the bellows rod is a valid bellows rod based on the positional relationship between the bellows rod and the brake cylinder head if the image to be detected contains the bellows rod and the brake cylinder head; the judgment standard for the valid bellows rod is that the brake cylinder head in the image is located within a certain pixel range around the bellows rod; when a valid bellows rod exists in the image to be detected, the bellows rod length is calculated; the bellows rod length is compared with a preset length threshold, and when the bellows rod length exceeds the preset length threshold, a brake holding risk warning is issued.

[0028] According to another aspect of the present invention, an electronic device is also proposed, comprising a memory, a processor, and a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the above-mentioned wind embrace identification method.

[0029] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program; the computer program is executed by a processor to implement the above-mentioned wind resistance identification method.

[0030] The beneficial technical effects of the present invention are:

[0031] This invention proposes a brake lock detection method, system, device, and storage medium. The method utilizes an improved YOLOv8m network to detect whether an image contains a bellows rod and a brake cylinder head. If so, the bellows rod length is calculated. When the bellows rod length exceeds a preset threshold, a brake lock risk warning is issued. A spatial pyramid pooling module and a partial self-attention module are introduced into the fourth stage of the original YOLOv8m backbone network, while a coordinate attention mechanism is introduced into the third stage of the neck network. By adaptively adjusting feature weights, the method enables the detection model to more accurately focus on target boundaries, thereby achieving efficient bellows detection and positioning. Experiments have demonstrated that the method can achieve millimeter-level target detection accuracy and a bellows rod recognition rate of up to 99.9%. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily apparent by reading the following detailed description with reference to the accompanying drawings, in which several embodiments of the present invention are shown by way of example and not limitation, in which:

[0033] Figure 1 This is a flow chart of a wind resistance identification method according to an embodiment of the present invention.

[0034] Figure 2 1 is another flow chart of a wind resistance identification method according to an embodiment of the present invention.

[0035] Figure 3Schematic diagram of the structure of the improved YOLOv8m network in an embodiment of the present invention.

[0036] Figure 4 1 is a schematic structural diagram of a wind embrace identification system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0038] Those skilled in the art will appreciate that embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software. It should be understood that any number of elements in the figures is for illustrative purposes only and not limiting, and any nomenclature is for distinction only and does not have any limiting meaning.

[0039] The brake lock recognition system utilizes automated control technology to automatically capture panoramic color images of the vehicle's underbody and builds an efficient recognition model based on deep learning. It can automatically identify and locate the brake cylinder and its piston travel components on the underbody for different vehicle models, and issue risk warnings based on changes in the target shape of the brake cylinder piston travel. The acquisition equipment is pre-installed on the train track. When the magnetic steel detects an oncoming vehicle signal, the system acquires continuous video frames as input. This input data is then processed by both the main program and the intelligent detection module. During this process, the main program receives image detection notifications from the intelligent detection module and issues a warning if it deems a brake lock risk.

[0040] Therefore, the embodiment of the present invention proposes a wind resistance identification method, such as Figures 1 and 2 As shown, the method includes:

[0041] S1. Obtain training image dataset;

[0042] S2, preprocessing the training image data;

[0043] S3. Input the preprocessed training image dataset into the target detection model based on the improved YOLOv8m network for training to obtain a trained target detection model;

[0044] S4. Input the image to be detected into the trained target detection model for detection to obtain a detection result; the detection result is whether the image to be detected contains the bellows rod and the brake cylinder head;

[0045] S5. If the image to be detected contains a bellows rod and a brake cylinder head, determining whether the bellows rod is a valid bellows rod based on the positional relationship between the bellows rod and the brake cylinder head; the criterion for determining whether the bellows rod is a valid bellows rod is that the brake cylinder head is located within a certain pixel range around the bellows rod in the image;

[0046] S6. Calculating the length of the bellows when a valid bellows exists in the image to be detected;

[0047] S7. Compare the bellows rod length with a preset length threshold, and issue a brake risk warning when the bellows rod length exceeds the preset length threshold.

[0048] The method begins with S1. In S1, a training image dataset is obtained.

[0049] According to an embodiment of the present invention, the object detection model is trained and tested using a custom dataset compiled from field data collected from multiple stations and divided into training and test sets in an 8:2 ratio. The dataset includes images of two key components: the brake cylinder and the bellows rod. A professional team meticulously annotated the images according to strict annotation standards, ensuring high data quality and accurate annotations.

[0050] During data collection, the actual environmental differences between stations were fully considered to enhance the model's adaptability to diverse scenarios. For example, the data collection tasks encompassed a variety of lighting conditions, including strong daylight, low nightlight, and shadowed areas; a variety of equipment, including brake cylinders and bellows from various vehicle models; and complex backgrounds, including raindrops, leaves, and debris obstructing the view.

[0051] Then S2 is executed, in which the training image data is preprocessed.

[0052] According to an embodiment of the present invention, in order to further improve the generalization ability of the model for diverse scenarios, data augmentation operations are performed on the training data. These enhancements include rotation, flipping, scaling, brightness adjustment, etc., so that the model can adapt to complex real-world environments.

[0053] Then execute S3. In S3, the preprocessed training image dataset is input into the target detection model based on the improved YOLOv8m network for training to obtain the trained target detection model.

[0054] According to an embodiment of the present invention, in order to balance the accuracy and inference speed of the model, YOLOv8m, which is a more mature technology in the single-stage model, is selected as the basic framework of the model. As a member of the YOLO series, YOLOv8m is also composed of three networks: backbone, neck and head. Specifically, the backbone network effectively captures the local and global information of the image by stacking the C2f feature extraction module designed with multiple gradient flows; the neck network adopts the idea of path aggregation network, and extracts effective information from feature maps at multiple levels by contracting and expanding paths, thereby enhancing the detection ability of small objects and multi-scale targets; the head network is responsible for completing the final target detection task, including category prediction, bounding box regression, and target confidence estimation.

[0055] In complex scenes, since the background and the target share similar texture or color features, the feature extraction process of the model is easily disturbed, resulting in false detection and missed detection. In order to better meet the detection requirements of the task target, this paper has made targeted improvements and optimizations based on YOLOv8m. The specific architecture of the improved model is as follows: Figure 3 The improved model structure still consists of the backbone, neck, and head. Improvements include the introduction of a spatial pyramid pooling module and a partial self-attention module in the fourth stage of the backbone network, and a coordinate attention mechanism in the third stage of the neck network. This aims to further enhance the model's ability to accurately locate object boundaries, enabling it to better meet the system's actual detection accuracy requirements while maintaining efficient inference speed.

[0056] The backbone network is responsible for extracting multi-level, multi-scale universal features from the input image, forming a feature map with high-level semantic information to support subsequent detection tasks. First, the C2f feature extraction module, as the basic unit of the network, is responsible for extracting local features at each stage and enhancing the expression of multi-scale information through feature fusion. This module adopts the CSP structure design and divides the input feature map into two branches through 1×1 convolution: one branch is through multiple residual modules. The first branch performs processing, while the other branch directly performs convolution operations. The outputs of the two branches are then concatenated using the Concat operation. After batch normalization (BN) and SiLU activation functions, the features are finally organized through convolution operations to obtain the final output. By stacking multiple C2f modules, the network can learn rich feature expressions at different levels, while optimizing the fusion of high-level semantic information and low-level detail information at different stages. The formula for the C2f feature extraction module can be expressed as follows:

[0057]

[0058] in, is the input feature, is the output feature, represents 1×1 convolution, Indicates channel splitting operation, is the residual module, Represents a feature concatenation operation. It is the intermediate feature of the module processing process and is the output obtained by N times of residual module processing.

[0059] Subsequently, the Spatial Pyramid Pooling-Fast (SPPF) module aggregates features of different scales, allowing the network to better retain semantic information when processing complex scenes and generate richer feature representations. The SPPF module first processes the input feature map through a convolutional layer, batch normalization (BN), and SiLU activation function to obtain a feature map with half the number of channels. Next, the feature map passes through three 5×5 maximum pooling layers in sequence, and the size of the feature map is gradually reduced after each pooling. The output of each pooling layer serves as the input for the next pooling. This serial pooling process can effectively capture information at different scales and improve the model's ability to capture details and global information in the image. Finally, by splicing the feature maps after pooling at different scales in the channel dimension, the SPPF module can integrate feature information from different scales to form a multi-scale feature representation. The formula of the spatial pyramid pooling module can be expressed as follows:

[0060]

[0061] in, is the input feature, is the output feature of the module, represents the maximum pooling operation of 5×5, Represents the output obtained after k times of maximum pooling.

[0062] When separating target and background features, the model inevitably introduces unnecessary background information that interferes with the target features, leading to false detections and missed detections. To address this issue, a common approach is to introduce an attention mechanism deep within the model to highlight the target features. However, existing mainstream attention mechanisms are mostly implemented through convolution operators. The inherent limitations of convolution operators make it difficult to establish long-range dependencies between features, which are crucial for accurately locating targets. In contrast, the Transformer structure, thanks to its self-attention mechanism, can efficiently capture global long-range dependencies. However, the Transformer has high computational complexity and memory usage, which often results in significant time overhead in real-time inference tasks.

[0063] Therefore, a partial self-attention (PSA) module is introduced into the backbone network. The PSA module is designed to effectively enhance the network's ability to model long-range dependencies while avoiding the computational overhead associated with the global self-attention mechanism. Specifically, the input feature map is evenly split into two parts, keeping the complexity of the self-attention computation low. One portion of the features is fed into the self-attention module for global information modeling, capturing long-range dependencies and enhancing contextual understanding of the target. Matrix operations between the query vector (Query), key vector (Key), and value vector (Value) are used to perform global information modeling, capturing long-range correlations between features. The other portion of the features is fused with the output of the self-attention module via skip connections. Furthermore, to further improve inference efficiency, the PSA module optimizes the dimensions of the query and key vectors in the self-attention mechanism, setting them to half that of the value vector, thereby reducing computational overhead. Furthermore, the module uses batch normalization (BN) instead of layer normalization (LN) for normalization, improving model speed and stability. This module is placed after the fourth stage, which has the lowest resolution in the model, and focuses on extracting and sorting out key information from high-level abstract features. Due to the lower feature resolution of the fourth stage, the quadratic complexity of self-attention calculations is significantly reduced, so the overall inference speed can still meet real-time requirements. The formula for some self-attention modules can be expressed as follows:

[0064]

[0065] in, is the input feature, is the output feature, Represents the Transformer module. Through the above operations, without significantly increasing the computational overhead, we can effectively capture the long-range dependencies between features, thereby better processing the semantic information deep in the network.

[0066] The neck network is used to integrate the features extracted from the backbone network for fusion, enhancement and processing to help the model better detect objects of different scales. Specifically, the neck network receives the features of the P3, P4 and P5 levels in the backbone network as input, first enhances the low-level features through a bottom-up information transmission path, and then fuses them with high-level features to ensure that the network can obtain rich multi-level feature representations. Subsequently, the network diffuses the detail information to deeper levels of the network through a top-down information transmission path, enhances the interaction between high-level semantic features and low-level detail features, and further improves the model's sensitivity to details. The combination of bottom-up and top-down information flow ensures that the network maintains efficient detection performance in complex scenarios, especially showing significant advantages in multi-scale object detection tasks.

[0067] To further improve the model's ability to extract target location information, a coordinate attention mechanism (CA) is introduced before the head network in the third-stage output of the neck network to enhance the ability to accurately locate the target boundary. The formula for the coordinate attention mechanism can be expressed as follows:

[0068]

[0069] in, is the input feature, is the output feature, and Represents the average pooling operation in the horizontal and vertical directions of the feature, is the Sigmoid activation function.

[0070] The head network is responsible for converting feature maps processed from the trunk and neck into final object detection results. Specifically, the network consists of three detection heads, each of which can be divided into two parts: two 3×3 convolutions and one 1×1 convolution, which are used to predict coordinate regression information and category confidence information, respectively.

[0071] In order to prevent the model from overfitting, regularization techniques such as weight decay and Dropout are introduced during the model training process to improve the robustness of the model.

[0072] Then, S4 is executed. In S4, the image to be detected is input into the trained target detection model for detection to obtain a detection result; the detection result is whether the image to be detected contains the bellows rod and the brake cylinder head.

[0073] According to an embodiment of the present invention, whether a detection target (bellows rod and brake cylinder head) exists in a certain frame image is determined based on the output of the model, thereby deciding whether to perform subsequent calculations or end the detection of the frame.

[0074] Then execute S5~S7. In S5, if the image to be detected contains a bellows rod and a brake cylinder head, determine whether the bellows rod is a valid bellows rod based on the positional relationship between the bellows rod and the brake cylinder head; the judgment standard of the valid bellows rod is: the brake cylinder head in the image is located within a certain pixel range around the bellows rod; in S6, calculate the bellows rod length when there is a valid bellows rod in the image to be detected; in S7, compare the bellows rod length with a preset length threshold, and when the bellows rod length exceeds the preset length threshold, issue a brake risk warning.

[0075] According to an embodiment of the present invention, if the bellows rod and the brake cylinder head are detected, it is further determined whether the brake cylinder head is within 50 pixels around the bellows rod. If this condition is met, the subsequent calculations will continue; otherwise, the detection of this frame will end. When the positional relationship between the bellows rod and the brake cylinder meets the requirements, it is determined whether a complete brake cylinder head exists in the image based on the aspect ratio of the brake cylinder. If a complete brake cylinder head is detected, the brake cylinder size corresponding to the bottom component of the vehicle model is matched according to the model output, and the length of the bellows rod is automatically calibrated and calculated. Since the diameter of the brake cylinder head is a known fixed value, the actual physical length corresponding to a single pixel can be calculated based on the model output result. By further analyzing the number of detected bellows rod pixels, its length can be accurately calculated; the specific formula is:

[0076]

[0077] in, and are the actual lengths of the bellows rod and the diameter of the brake cylinder head, and The number of pixels representing the bellows rod length and the brake cylinder head diameter, respectively.

[0078] Subsequently, it is determined whether the length exceeds the set threshold and a notification is sent to the main program based on the judgment result. If it exceeds, an early warning notification is issued. If the complete brake cylinder head is not detected, the detection of the current frame will end.

[0079] Specifically, the bellows rod is generally more than 50 mm, which is greater than 50 pixels when converted into pixels. The maximum range of the image recognition area is reduced by 50 pixels; for example, the image pixels , the valid range is 50 to 1230 in width and 50 to 670 in height. If the bellows rod appears in the valid range, it is identified as a valid bellows rod, otherwise it is invalid data, which can prevent the problem of other edge devices identifying it as a bellows rod. Furthermore, the width of the bellows rod is generally less than 1 / 2 of the air cylinder. If the width of the bellows rod is less than 1 / 2 of the air cylinder, it is a valid bellows rod, otherwise it is invalid data, which can prevent the problem of the bellows rod being disproportionate to the air cylinder. Furthermore, the air cylinder and the bellows rod are connected together and will not overlap. The overlap ratio is set not to exceed 50% of the bellows rod area, which can effectively prevent the problem of fuzzy identification of the brake cylinder bellows rod. Furthermore, in a carriage, the number of bellows rods exceeding the threshold / the total number of recognized brake cylinder data accounts for more than 50% and is valid data, which can prevent problems caused by angle recognition of the bellows rod being too long.

[0080] The technical effects of the present invention are further verified through experiments.

[0081] The experiments used a dataset collected from multiple field trials for training and testing. This dataset contains 17,251 images of gate cylinders and bellows rods. To ensure the model's effectiveness in real-world applications, the dataset was rigorously labeled and filtered to cover targets in various scenarios and lighting conditions. The model was built using the PyTorch deep learning framework, with a batch size of 16. The SGD optimizer was trained for 300 epochs using an initial learning rate of 0.01 and a momentum of 0.937. To ensure training stability and convergence, a learning rate scheduling strategy was implemented, reducing the learning rate by a factor of 10 every 100 epochs to achieve a balance between model exploration and convergence.

[0082] To achieve optimal detection accuracy, detailed adjustments and optimizations were made to data enhancement. The final data enhancement parameters are shown in Table 1 below.

[0083] Table 1 Data augmentation parameters

[0084]

[0085] In order to verify the advanced nature of the detection model, the method proposed in the present invention is compared with advanced methods in the field, including Faster R-CNN, SSD, YOLOv5m, YOLOv8m, etc. Faster R-CNN is a two-stage target detection model, and the other methods are single-stage target detection models. In order to ensure a fair comparison, the public codes of these methods were used to reproduce their network structures, and the models were trained and evaluated under the same training environment. The experiments used the same hyperparameter settings, data sets, and evaluation indicators to ensure the comparability of the results. As shown in Table 2, the model proposed in the present invention achieved the highest evaluation index in the comparison with other target detection methods, proving its advantage in target detection accuracy.

[0086] Table 2 Comparison results of the present invention with other target detection methods

[0087]

[0088] To verify the effectiveness of the introduced modules, ablation experiments were conducted. Using YOLOv8m as the baseline model, the experiment sequentially added a partial self-attention module to the backbone network and a coordinate attention mechanism to the head network to verify the contribution and effectiveness of each module. The experimental results are shown in Table 3. The partial self-attention module effectively enhanced the model's understanding of global context and improved detection accuracy; the coordinate attention mechanism further improved the ability to localize the object, especially in complex backgrounds. These results demonstrate the practical value of the design of each module, and their combination significantly improves overall model performance, validating the effectiveness and rationality of the approach.

[0089] Table 3 Experimental results

[0090]

[0091] To improve inference speed, the detection model underwent a conversion from PyTorch to TensorRT to fully leverage hardware acceleration. The inference GPU deployed on-site was an NVIDIA GeForce RTX 4070, supporting both FP16 and FP32 computations, each delivering 29.15 TFLOPS of computing performance. Through TensorRT optimization, the model's inference speed was significantly improved, with inference time for a single image (including pre- and post-processing) reaching approximately 12ms. To further enhance processing efficiency, multi-threaded inference was implemented during deployment, enhancing concurrent processing capabilities. Ultimately, the optimized and deployed wind-hold recognition system was able to process image data captured by multiple cameras in real time at a speed of 125 frames per second during field operation, meeting the requirements of real-time monitoring and detection.

[0092] After testing, the system can accurately identify and locate targets, quickly determine the status changes of key components, and meet the needs of industrial-grade high-precision detection; the detection accuracy of the Fengbao intelligent recognition system reaches ±5mm, demonstrating its good performance and reliability.

[0093] This paper proposes a wind-hold detection method based on the YOLOv8m core algorithm, customized for the task. This method incorporates a spatial pyramid pooling module, a partial self-attention module, and a coordinate attention mechanism to address the demanding positioning requirements of the task. By adaptively adjusting feature weights, the model can more precisely focus on target boundaries, enabling efficient detection and location of bellows. These optimizations and improvements achieve millimeter-level target detection accuracy, and a bellows recognition rate of 99.9%.

[0094] Another embodiment of the present invention provides a wind resistance identification system, such as Figure 4 As shown, the system includes:

[0095] The detection model training module 410 includes a training data acquisition submodule 4110, a preprocessing submodule 4120, and a model training submodule 4130; the training data acquisition submodule 4110 is configured to acquire a training image dataset; the preprocessing submodule 4120 is configured to preprocess the training image data; and the model training submodule 4130 is configured to input the preprocessed training image dataset into an object detection model based on the improved YOLOv8m network for training, thereby acquiring a trained object detection model.

[0096] The target detection module 420 is configured to input the image to be detected into the trained target detection model for detection and obtain a detection result; the detection result is whether the image to be detected contains the bellows rod and the brake cylinder head;

[0097] The brake engagement recognition module 430 is configured to determine whether the bellows rod is a valid bellows rod based on the positional relationship between the bellows rod and the brake cylinder head if the image to be detected contains the bellows rod and the brake cylinder head; the judgment standard for the valid bellows rod is: the brake cylinder head in the image is located within a certain pixel range around the bellows rod; when a valid bellows rod exists in the image to be detected, the bellows rod length is calculated; the bellows rod length is compared with a preset length threshold, and when the bellows rod length exceeds the preset length threshold, a brake risk warning is issued.

[0098] For the undetailed parts of a wind resistance identification system according to an embodiment of the present invention, please refer to the above detailed description of the method embodiment.

[0099] The method of the present invention can be executed in an electronic device. The electronic device can be any device with storage and computing capabilities, such as a server, workstation, or personal computer such as a desktop computer or laptop computer, or a terminal device such as a mobile phone, tablet computer, smart wearable device, or Internet of Things device, but is not limited thereto.

[0100] An electronic device may include: a processor, a memory, an input / output interface, a communication interface, and a bus. The processor, memory, input / output interface, and communication interface are interconnected within the electronic device via the bus. The processor may be implemented as a general-purpose CPU, a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification. The memory may be implemented as a ROM, RAM, static storage device, dynamic storage device, etc. The memory may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification via software or firmware, the relevant program code is stored in the memory and called and executed by the processor. The input / output interface is used to connect to an input / output module to enable information input and output. The input / output module can be configured as a component within the electronic device or can be externally connected to the electronic device to provide corresponding functions. Input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and output devices may include a display, a speaker, a vibrator, an indicator light, etc. The communication interface is used to connect to a communication module to enable communication between the electronic device and other devices. The communication module may communicate via wired or wireless communication. A bus comprises a pathway that transmits information between components of an electronic device.

[0101] An embodiment of the present invention also provides a non-transitory readable storage medium, which stores instructions, and the instructions are used to enable the electronic device to execute the method according to the embodiment of the present invention. The readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. The information can be a computer-readable instruction, a data structure, a program module or other data. Examples of readable storage media include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape and disk storage, etc.

[0102] It should be noted that the terms used in the present invention are only for describing specific embodiments and are not intended to limit the scope of this application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular and may also include the plural. The terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method or device comprising a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the presence of other identical elements in the process, method or device comprising the elements.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying wind resistance, characterized in that: include: Get a training image dataset; Preprocess the training image data; The preprocessed training image dataset is input into the target detection model based on the improved YOLOv8m network for training to obtain the trained target detection model; The improvements of the improved YOLOv8m network include: adding a spatial pyramid pooling module and a partial self-attention module to the original YOLOv8m backbone network; adding a coordinate attention mechanism after the neck network and before the head network; The image to be detected is input into the trained target detection model for detection to obtain the detection result; the detection result is whether the bellows rod and the brake cylinder head are contained in the image to be detected; including: inputting the image to be detected into the backbone network for feature extraction, including: using multiple C2f feature extraction modules in the backbone network to extract local features of the image and perform feature fusion; then, aggregating features of different scales through the spatial pyramid pooling module; then, the aggregated feature map is evenly divided into two parts through the partial self-attention module, and one part of the feature map enters the self-attention module to perform global information modeling through matrix operations between the query vector, key vector and value vector, and the dimension of the query vector and key vector in the partial self-attention module is half of the value vector; batch normalization is used instead of layer normalization for normalization; the other part of the feature map is uniformly divided into two parts through the partial self-attention module, and the matrix operation between the query vector, key vector and value vector is used for global information modeling .... The graph is fused with the output of the self-attention module through jump connections; the neck network is used to fuse, enhance and process the features extracted by the backbone network; the coordinate attention mechanism is used to generate a feature map with enhanced position information, including: first, performing global average pooling on the features output by the neck network in the horizontal and vertical directions respectively to extract compressed features in different directions; then, these features are fused through a set of convolutions with shared weights; the fused features are re-divided into two parts in the horizontal and vertical directions, and the attention matrix is generated by 1×1 convolution and Sigmoid activation function respectively; finally, the features output by the neck network are weighted by the attention matrix through element-wise multiplication to obtain a feature map with enhanced position information; the feature map with enhanced position information is converted into the final target detection result using the head network; If the image to be detected contains a bellows rod and a brake cylinder head, determining whether the bellows rod is a valid bellows rod based on the positional relationship between the bellows rod and the brake cylinder head; the criterion for determining whether the bellows rod is a valid bellows rod is that the brake cylinder head is within a certain pixel range around the bellows rod in the image; When a valid bellows rod exists in the image to be detected, the bellows rod length is calculated; the bellows rod length is compared with a preset length threshold, and when the bellows rod length exceeds the preset length threshold, a brake risk warning is issued.

2. A wind resistance identification method according to claim 1, characterized in that: The aggregating features of different scales through the spatial pyramid pooling module includes: processing features of different scales through convolution layers, batch normalization and SiLU activation functions to obtain feature maps with half the number of channels; passing through multiple maximum pooling layers in sequence to gradually reduce the size of the feature maps; and splicing the feature maps after pooling at different scales in the channel dimension.

3. A wind resistance identification method according to claim 1, characterized in that: The preprocessing includes data enhancement, and the data enhancement includes rotation, flipping, scaling, and brightness adjustment.

4. A wind resistance identification method according to claim 1, characterized in that: The target detection model based on the improved YOLOv8m network introduces regularization technology during the training process, and the regularization technology includes weight decay and Dropout.

5. A wind resistance identification system, characterized in that: include: Detection model training module, including training data acquisition submodule, preprocessing submodule, and model training submodule; The training data acquisition submodule is configured to acquire a training image dataset; The preprocessing submodule is configured to preprocess the training image data; The model training submodule is configured to input the preprocessed training image data set into the target detection model based on the improved YOLOv8m network for training, thereby obtaining a trained target detection model; The improvements of the improved YOLOv8m network include: adding a spatial pyramid pooling module and a partial self-attention module to the original YOLOv8m backbone network; adding a coordinate attention mechanism after the neck network and before the head network; The target detection module is configured to input the image to be detected into a trained target detection model for detection and obtain a detection result; the detection result is whether the bellows rod and the brake cylinder head are contained in the image to be detected; the module comprises: inputting the image to be detected into the backbone network for feature extraction, including: utilizing multiple C2f feature extraction modules in the backbone network to extract local features of the image and perform feature fusion; subsequently, aggregating features of different scales through a spatial pyramid pooling module; subsequently, evenly dividing the aggregated feature map into two parts through a partial self-attention module, one part of the feature map enters the self-attention module, and performs global information modeling through matrix operations between a query vector, a key vector, and a value vector, wherein the dimension of the query vector and the key vector in the partial self-attention module is half of the value vector; and using batch normalization instead of layer normalization for normalization; Another part of the feature map is fused with the output of the self-attention module through a skip connection; the neck network is used to fuse, enhance, and process the features extracted by the backbone network; the coordinate attention mechanism is used to generate a feature map with enhanced position information, including: first, performing global average pooling on the features output by the neck network in the horizontal and vertical directions to extract compressed features in different directions; then, these features are fused through a set of convolutions with shared weights; the fused features are re-divided into two parts in the horizontal and vertical directions, and the attention matrix is generated through 1×1 convolution and sigmoid activation function respectively; finally, the features output by the neck network are weighted by the attention matrix through element-wise multiplication to obtain a feature map with enhanced position information; the head network is used to convert the feature map with enhanced position information into the final target detection result; A brake holding recognition module is configured to determine whether the bellows rod is a valid bellows rod based on the positional relationship between the bellows rod and the brake cylinder head if the image to be detected contains the bellows rod and the brake cylinder head; the judgment standard for the valid bellows rod is that the brake cylinder head in the image is located within a certain pixel range around the bellows rod; when a valid bellows rod exists in the image to be detected, the bellows rod length is calculated; the bellows rod length is compared with a preset length threshold, and when the bellows rod length exceeds the preset length threshold, a brake holding risk warning is issued.

6. An electronic device, characterized in that: include: A memory, a processor, and a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the wind embrace identification method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The storage medium stores a computer program; the computer program is executed by a processor to implement the wind resistance identification method according to any one of claims 1 to 4.

Images