Surface Defect Detection for Small Samples of Particleboard Based on Improved Proximal Policy Optimization

Particleboard is an important forest product that can be reprocessed using wood processing by-products. This approach has the potential to achieve significant conservation of forest resources and contribute to the protection of forest ecology. Most current detection models require a significant numb...

Full description

Saved in:
Bibliographic Details
Main Authors: Haifei Xia, Haiyan Zhou, Mingao Zhang, Qingyi Zhang, Chenlong Fan, Yutu Yang, Shuang Xi, Ying Liu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/8/2541
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155047426457600
author Haifei Xia
Haiyan Zhou
Mingao Zhang
Qingyi Zhang
Chenlong Fan
Yutu Yang
Shuang Xi
Ying Liu
author_facet Haifei Xia
Haiyan Zhou
Mingao Zhang
Qingyi Zhang
Chenlong Fan
Yutu Yang
Shuang Xi
Ying Liu
author_sort Haifei Xia
collection DOAJ
description Particleboard is an important forest product that can be reprocessed using wood processing by-products. This approach has the potential to achieve significant conservation of forest resources and contribute to the protection of forest ecology. Most current detection models require a significant number of tagged samples for training. However, with the advancement of industrial technology, the prevalence of surface defects in particleboard is decreasing, making the acquisition of sample data difficult and significantly limiting the effectiveness of model training. Deep reinforcement learning-based detection methods have been shown to exhibit strong generalization ability and sample utilization efficiency when the number of samples is limited. This paper focuses on the potential application of deep reinforcement learning in particleboard defect detection and proposes a novel detection method, PPOBoardNet, for the identification of five typical defects: dust spot, glue spot, scratch, sand leak and indentation. The proposed method is based on the proximal policy optimization (PPO) algorithm of the Actor-Critic framework, and defect detection is achieved by performing a series of scaling and translation operations on the mask. The method integrates the variable action space and the composite reward function and achieves the balanced optimization of different types of defect detection performance by adjusting the scaling and translation amplitude of the detection region. In addition, this paper proposes a state characterization strategy of multi-scale feature fusion, which integrates global features, local features and historical action sequences of the defect image and provides reliable guidance for action selection. On the particleboard defect dataset with limited images, PPOBoardNet achieves a mean average precision (mAP) of 79.0%, representing a 5.3% performance improvement over the YOLO series of optimal detection models. This result provides a novel technical approach to the challenge of defect detection with limited samples in the particleboard domain, with significant practical application value.
format Article
id doaj-art-e6be703710fa4baa89cf2af0e83fb7ce
institution OA Journals
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e6be703710fa4baa89cf2af0e83fb7ce2025-08-20T02:25:04ZengMDPI AGSensors1424-82202025-04-01258254110.3390/s25082541Surface Defect Detection for Small Samples of Particleboard Based on Improved Proximal Policy OptimizationHaifei Xia0Haiyan Zhou1Mingao Zhang2Qingyi Zhang3Chenlong Fan4Yutu Yang5Shuang Xi6Ying Liu7Jiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaJiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaJiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaSchool of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, ChinaJiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaJiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaJiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaJiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, ChinaParticleboard is an important forest product that can be reprocessed using wood processing by-products. This approach has the potential to achieve significant conservation of forest resources and contribute to the protection of forest ecology. Most current detection models require a significant number of tagged samples for training. However, with the advancement of industrial technology, the prevalence of surface defects in particleboard is decreasing, making the acquisition of sample data difficult and significantly limiting the effectiveness of model training. Deep reinforcement learning-based detection methods have been shown to exhibit strong generalization ability and sample utilization efficiency when the number of samples is limited. This paper focuses on the potential application of deep reinforcement learning in particleboard defect detection and proposes a novel detection method, PPOBoardNet, for the identification of five typical defects: dust spot, glue spot, scratch, sand leak and indentation. The proposed method is based on the proximal policy optimization (PPO) algorithm of the Actor-Critic framework, and defect detection is achieved by performing a series of scaling and translation operations on the mask. The method integrates the variable action space and the composite reward function and achieves the balanced optimization of different types of defect detection performance by adjusting the scaling and translation amplitude of the detection region. In addition, this paper proposes a state characterization strategy of multi-scale feature fusion, which integrates global features, local features and historical action sequences of the defect image and provides reliable guidance for action selection. On the particleboard defect dataset with limited images, PPOBoardNet achieves a mean average precision (mAP) of 79.0%, representing a 5.3% performance improvement over the YOLO series of optimal detection models. This result provides a novel technical approach to the challenge of defect detection with limited samples in the particleboard domain, with significant practical application value.https://www.mdpi.com/1424-8220/25/8/2541reinforcement learningparticleboarddeep learningdefect detection
spellingShingle Haifei Xia
Haiyan Zhou
Mingao Zhang
Qingyi Zhang
Chenlong Fan
Yutu Yang
Shuang Xi
Ying Liu
Surface Defect Detection for Small Samples of Particleboard Based on Improved Proximal Policy Optimization
Sensors
reinforcement learning
particleboard
deep learning
defect detection
title Surface Defect Detection for Small Samples of Particleboard Based on Improved Proximal Policy Optimization
title_full Surface Defect Detection for Small Samples of Particleboard Based on Improved Proximal Policy Optimization
title_fullStr Surface Defect Detection for Small Samples of Particleboard Based on Improved Proximal Policy Optimization
title_full_unstemmed Surface Defect Detection for Small Samples of Particleboard Based on Improved Proximal Policy Optimization
title_short Surface Defect Detection for Small Samples of Particleboard Based on Improved Proximal Policy Optimization
title_sort surface defect detection for small samples of particleboard based on improved proximal policy optimization
topic reinforcement learning
particleboard
deep learning
defect detection
url https://www.mdpi.com/1424-8220/25/8/2541
work_keys_str_mv AT haifeixia surfacedefectdetectionforsmallsamplesofparticleboardbasedonimprovedproximalpolicyoptimization
AT haiyanzhou surfacedefectdetectionforsmallsamplesofparticleboardbasedonimprovedproximalpolicyoptimization
AT mingaozhang surfacedefectdetectionforsmallsamplesofparticleboardbasedonimprovedproximalpolicyoptimization
AT qingyizhang surfacedefectdetectionforsmallsamplesofparticleboardbasedonimprovedproximalpolicyoptimization
AT chenlongfan surfacedefectdetectionforsmallsamplesofparticleboardbasedonimprovedproximalpolicyoptimization
AT yutuyang surfacedefectdetectionforsmallsamplesofparticleboardbasedonimprovedproximalpolicyoptimization
AT shuangxi surfacedefectdetectionforsmallsamplesofparticleboardbasedonimprovedproximalpolicyoptimization
AT yingliu surfacedefectdetectionforsmallsamplesofparticleboardbasedonimprovedproximalpolicyoptimization