Automated Defect Analysis System for Industrial Computerized Tomography Images of Solid Rocket Motor Grains Based on YOLO-V4 Model

Dai, Junjie; Li, Tianpeng; Xuan, Zhaolong; Zhang, Feng

doi:10.3390/electronics11193215

Cited by 9 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It predicts the final target box by generating a set of candidate boxes, and then classifying and regressing these boxes. The second type is the one-stage detection algorithm using regression, with YOLO as its typical representative [8][9][10][11]. It directly convolves and pools the image to generate candidate boxes, and performs classification and regression at the same time to detect the vehicle object.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Real-Time Small Target Vehicle Detection Algorithm with an Improved YOLOv5m Network Model

Du,

Jiang

2024

CMC

View full text Add to dashboard Cite

To address the challenges of high complexity, poor real-time performance, and low detection rates for small target vehicles in existing vehicle object detection algorithms, this paper proposes a real-time lightweight architecture based on You Only Look Once (YOLO) v5m. Firstly, a lightweight upsampling operator called Content-Aware Reassembly of Features (CARAFE) is introduced in the feature fusion layer of the network to maximize the extraction of deep-level features for small target vehicles, reducing the missed detection rate and false detection rate. Secondly, a new prediction layer for tiny targets is added, and the feature fusion network is redesigned to enhance the detection capability for small targets. Finally, this paper applies L1 regularization to train the improved network, followed by pruning and fine-tuning operations to remove redundant channels, reducing computational and parameter complexity and enhancing the detection efficiency of the network. Training is conducted on the VisDrone2019-DET dataset. The experimental results show that the proposed algorithm reduces parameters and computation by 63.8% and 65.8%, respectively. The average detection accuracy improves by 5.15%, and the detection speed reaches 47 images per second, satisfying real-time requirements. Compared with existing approaches, including YOLOv5m and classical vehicle detection algorithms, our method achieves higher accuracy and faster speed for real-time detection of small target vehicles in edge computing.

show abstract

Section: Related Workmentioning

confidence: 99%

“…[5,6,8,14,15,11] 80 × 80 × 128 8 × 8 [10,13,16,30,33,23] 40 × 40 × 256 16 × 16 [30,61,62,45,59,119] 20 × 20 × 512 32 × 32 [116,90,156,198,373,326]…”

mentioning

confidence: 99%

A Real-Time Small Target Vehicle Detection Algorithm with an Improved YOLOv5m Network Model

Du,

Jiang

2024

CMC

View full text Add to dashboard Cite

show abstract

“…The training data set has an output variable that needs to be predicted or classified. All algorithms learn some kind of pattern from the training data set and apply it to the test data set for prediction or classification [15].…”

Section: Supervised Learningmentioning

confidence: 99%

YOLOv7-Based Anomaly Detection Using Intensity and NG Types in Labeling in Cosmetic Manufacturing Processes

Beak,

Han,

Moon

et al. 2023

Processes

View full text Add to dashboard Cite

The advent of the Fourth Industrial Revolution has revolutionized the manufacturing sector by integrating artificial intelligence into vision inspection systems to improve the efficiency and quality of products. Supervised-learning-based vision inspection systems have emerged as a powerful tool for automated quality control in various industries. During visual inspection or final inspection, a human operator physically inspects a product to determine its condition and categorize it based on their know-how. However, the know-how-based visual inspection process is limited in time and space and is affected by many factors. High accuracy in vision inspection is highly dependent on the quality and precision of the labeling process. Therefore, supervised learning methods of 1-STAGE DETECTION, such as You Only Look Once (YOLO), are utilized in automated inspection to improve accuracy. In this paper, we proposed a labeling method that achieves the highest inspection accuracy among labeling methods such as NG intensity and NG intensity when performing anomaly detection using YOLOv7 in the cosmetics manufacturing process.

show abstract

“…Park et al [15] combined convolutional neural networks and extended short-term memory networks (LSTM) as fault detection for liquid-propellant rocket motors and compared them with traditional methods, confirming the effectiveness of this method. Dai and colleagues [16] proposed an automatic defect analysis system based on the YOLO-V4 model for SRM grain tomography, while Li et al [17] applied YOLO-V4 to detect internal defects in SRM housing. Gamdha et al [18] used convolutional neural networks to detect anomalies in solid propellants in rocket motors.…”

Section: Introductionmentioning

confidence: 99%

Lightweight RepVGG-Based Cross-Modality Data Prediction Method for Solid Rocket Motors

Yang,

Zheng,

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

Solid rocket motors (SRMs) have been popularly used in the current aerospace industry. Performance indicators, such as pressure and thrust, are of great importance for rocket monitoring and design. However, the measurement of such signals requires high economic and time costs. In many practical situations, the thrust measurement error is large and requires manual correction. In order to address this challenging problem, a lightweight RepVGG-based cross-modality data prediction method is proposed for SRMs. An end-to-end data prediction framework is established by transforming data across different modalities. A novel RepVGG deep neural network architecture is built, which is able to automatically learn features from raw data and predict new time-series data of different modalities. The effectiveness of the proposed method is extensively validated with the field SRM data. The accurate prediction of the thrust data can be achieved by exploring the pressure data. After calculation, the percentage error between the predicted data and the actual data is less than 5%. The proposed method offers a promising tool for cross-modality data prediction in real aerospace industries for SRMs.

show abstract

Automated Defect Analysis System for Industrial Computerized Tomography Images of Solid Rocket Motor Grains Based on YOLO-V4 Model

Cited by 9 publications

References 19 publications

A Real-Time Small Target Vehicle Detection Algorithm with an Improved YOLOv5m Network Model

A Real-Time Small Target Vehicle Detection Algorithm with an Improved YOLOv5m Network Model

YOLOv7-Based Anomaly Detection Using Intensity and NG Types in Labeling in Cosmetic Manufacturing Processes

Lightweight RepVGG-Based Cross-Modality Data Prediction Method for Solid Rocket Motors

Contact Info

Product

Resources

About