Pengfei He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Pengfei He has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Penghua Mu
Yantai University
5 shared publications - Gang Guo
FISEC Infomation Technology Company Limited, Weihai 264200, China
4 shared publications - Xintian Liu
FISEC Infomation Technology Company Limited, Weihai 264200, China
4 shared publications - Pengfei Fan
School of Physics and Electronic Information, Yantai University, Yantai, China
3 shared publications - Hongxin Zhang
School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications - Kun Wang
School of Physics and Electronic Information, Yantai University, Yantai 264005, China
2 shared publications
Latest Publications
- Open Access
- 8 September 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21  (9) , e0354121
DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images
Haze represents a key constraint on the application of optical remote sensing imagery. It not only impairs visual quality but also lowers the accuracy of remote sensing interpretation tasks such as classification and change detection. To tackle this issue, we present a Dehazing Enhanced Multi-branch Attention Network (DEMANet) for effective remote sensing image dehazing. The network adopts a U-Net-like structure with three hierarchical downsampling stages to implement progressive feature extraction from shallow to deep layers. Shallow and middle layers use a residual dual-path module to enhance local detailed features via a main-auxiliary dual-branch structure. Deep layers employ a dual-attention module with a two-layer attention mechanism to break the limitation of local receptive fields in traditional convolutions and accurately capture global semantics and haze features. A cross-stage feature interaction module embeds a haze-guided mechanism to locate haze regions based on edge and color differences, enabling cross-stage feature alignment and interaction between encoding and decoding. This reduces information loss during upsampling and improves detail preservation and dehazing performance. Experiments conducted on widely used public remote sensing datasets demonstrate that our innovative approach outperforms existing algorithms in haze removal, while simultaneously preserving intricate image details and color fidelity.
- 8 September 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21  (9) , e0354121
Open AccessDEMANet: A dehazing enhanced multi-branch attention network for remote sensing images
Haze represents a key constraint on the application of optical remote sensing imagery. It not only impairs visual quality but also lowers the accuracy of remote sensing interpretation tasks such as classification and change detection. To tackle this issue, we present a Dehazing Enhanced Multi-branch Attention Network (DEMANet) for effective remote sensing image dehazing. The network adopts a U-Net-like structure with three hierarchical downsampling stages to implement progressive feature extraction from shallow to deep layers. Shallow and middle layers use a residual dual-path module to enhance local detailed features via a main-auxiliary dual-branch structure. Deep layers employ a dual-attention module with a two-layer attention mechanism to break the limitation of local receptive fields in traditional convolutions and accurately capture global semantics and haze features. A cross-stage feature interaction module embeds a haze-guided mechanism to locate haze regions based on edge and color differences, enabling cross-stage feature alignment and interaction between encoding and decoding. This reduces information loss during upsampling and improves detail preservation and dehazing performance. Experiments conducted on widely used public remote sensing datasets demonstrate that our innovative approach outperforms existing algorithms in haze removal, while simultaneously preserving intricate image details and color fidelity.
- Open Access
WMC-DFINE: An Improved DFINE Model for Aluminum Profile Surface Defect Detection
The automated inspection of aluminum profile surface defects, which heavily relies on data acquired by machine vision sensors, is a critical task in industrial quality control. Addressing the current challenges of intense background texture interference and the difficulty in detecting defects with extreme aspect ratios on aluminum profiles, this research puts forward a complete end-to-end defect detection algorithm named WMC-DFINE (WIFA-MKSS-CSFF-DFINE) based on the DFINE framework. First, a Wavelet-Integrated Frequency Attention (WIFA) module is introduced, which utilizes a discrete wavelet transform to decouple features into the frequency domain, thereby dynamically suppressing high-frequency background noise and enhancing defect edge responses. Second, a Cross-Scale Feature Fusion (CSFF) module based on dual-channel pooling is designed to ensure the continuity of defect features, thereby resolving the semantic misalignment issue in traditional fusion. Third, a Multi-Kernel Strip Shuffle (MKSS) module is incorporated, utilizing decomposed convolution kernels to capture the geometric features of slender scratches. Finally, a knowledge distillation strategy is employed to transfer structured knowledge from a complex teacher model to a lightweight student model. Experiments on the Tianchi aluminum defect dataset demonstrate that WMC-DFINE achieves a mAP of 82.1%, which surpasses algorithms including YOLOv12, RT-DETR, and the baseline model DFINE. Furthermore, the distilled student model, WMC-DFINE-distill, improves the mAP by 3.2% compared to DFINE, reduces parameter count by 47%, and achieves an inference speed of 59.75 FPS on the experimental equipment. The proposed method effectively resolves the problem of balancing background suppression and defect detail feature preservation, offering a practical and efficient scheme for real-time industrial defect inspection.
Open AccessWMC-DFINE: An Improved DFINE Model for Aluminum Profile Surface Defect Detection
The automated inspection of aluminum profile surface defects, which heavily relies on data acquired by machine vision sensors, is a critical task in industrial quality control. Addressing the current challenges of intense background texture interference and the difficulty in detecting defects with extreme aspect ratios on aluminum profiles, this research puts forward a complete end-to-end defect detection algorithm named WMC-DFINE (WIFA-MKSS-CSFF-DFINE) based on the DFINE framework. First, a Wavelet-Integrated Frequency Attention (WIFA) module is introduced, which utilizes a discrete wavelet transform to decouple features into the frequency domain, thereby dynamically suppressing high-frequency background noise and enhancing defect edge responses. Second, a Cross-Scale Feature Fusion (CSFF) module based on dual-channel pooling is designed to ensure the continuity of defect features, thereby resolving the semantic misalignment issue in traditional fusion. Third, a Multi-Kernel Strip Shuffle (MKSS) module is incorporated, utilizing decomposed convolution kernels to capture the geometric features of slender scratches. Finally, a knowledge distillation strategy is employed to transfer structured knowledge from a complex teacher model to a lightweight student model. Experiments on the Tianchi aluminum defect dataset demonstrate that WMC-DFINE achieves a mAP of 82.1%, which surpasses algorithms including YOLOv12, RT-DETR, and the baseline model DFINE. Furthermore, the distilled student model, WMC-DFINE-distill, improves the mAP by 3.2% compared to DFINE, reduces parameter count by 47%, and achieves an inference speed of 59.75 FPS on the experimental equipment. The proposed method effectively resolves the problem of balancing background suppression and defect detail feature preservation, offering a practical and efficient scheme for real-time industrial defect inspection.
- Open Access
Rapid Aeolus L2B HLOS Wind Retrieval via BP Neural Network
Wind field information is a key variable in atmospheric science and weather prediction, and spaceborne Doppler wind lidar provides unique global observations of the horizontal line-of-sight (HLOS) wind. This study develops a data-driven model that maps Aeolus Rayleigh-channel Level-1B (L1B) observables to the operational Level-2B (L2B) HLOS wind product. Using the two Rayleigh discriminator responses as inputs, we train a backpropagation (BP) neural network to learn the nonlinear relationship between Rayleigh-channel measurements and the collocated L2B HLOS winds. The proposed approach is intended as a computationally efficient emulation/approximation of the L2B HLOS output from L1B observations, rather than as an independently validated accuracy-improving retrieval. Model performance is evaluated by agreement with the L2B reference across samples spanning July 2019 to May 2020 and an altitude range of 0–20 km. The results show that the proposed model reproduces the main statistical characteristics and along-track HLOS patterns of the L2B product, providing a fast option for generating L2B-like HLOS estimates from Rayleigh-channel inputs.
Open AccessRapid Aeolus L2B HLOS Wind Retrieval via BP Neural Network
Wind field information is a key variable in atmospheric science and weather prediction, and spaceborne Doppler wind lidar provides unique global observations of the horizontal line-of-sight (HLOS) wind. This study develops a data-driven model that maps Aeolus Rayleigh-channel Level-1B (L1B) observables to the operational Level-2B (L2B) HLOS wind product. Using the two Rayleigh discriminator responses as inputs, we train a backpropagation (BP) neural network to learn the nonlinear relationship between Rayleigh-channel measurements and the collocated L2B HLOS winds. The proposed approach is intended as a computationally efficient emulation/approximation of the L2B HLOS output from L1B observations, rather than as an independently validated accuracy-improving retrieval. Model performance is evaluated by agreement with the L2B reference across samples spanning July 2019 to May 2020 and an altitude range of 0–20 km. The results show that the proposed model reproduces the main statistical characteristics and along-track HLOS patterns of the L2B product, providing a fast option for generating L2B-like HLOS estimates from Rayleigh-channel inputs.
- Open Access
Maritime Small Target Image Detection Algorithm Based on Improved YOLOv11n
Aiming at the problems of small-sized ships (such as small patrol boats) in complex open-sea backgrounds, including small sizes, insufficient feature information, and high missed detection rates, this paper proposes a maritime small target image detection algorithm based on the improved YOLOv11n. Firstly, the BIE module is introduced into the neck feature fusion stage of YOLOv11n. Utilizing its dual-branch information interaction design, independent branches for key features of maritime small targets in infrared and visible light images are constructed, enabling the progressive fusion of infrared and visible light target features. Secondly, RepViTBlock is incorporated into the backbone network and combined with the C3k2 module of YOLOv11n to form C3k2-RepViTBlock. Through the lightweight attention mechanism and multi-branch convolution structure, this addresses the insufficient capture of tiny target features by the C3k2 module and enhances the model’s ability to extract local features of maritime small targets. Finally, the ConvAttn module is embedded at the end of the backbone network. With its dynamic small-kernel convolution, it adaptively extracts the contour features of small targets, maintaining the overall model’s light weight while reducing the missed detection rate for maritime small targets. Experiments on a collected infrared and visible light ship image dataset (IVships) and a public dataset (SeaShips) show that, on the basis of increasing only a small number of parameters, the improved algorithm increases the mAP@0.5 by 1.9% and 1.7%, respectively, and the average precision by 2.2% and 2.4%, respectively, compared with the original model, which significantly improves the model’s small target detection capabilities.
Open AccessMaritime Small Target Image Detection Algorithm Based on Improved YOLOv11n
Aiming at the problems of small-sized ships (such as small patrol boats) in complex open-sea backgrounds, including small sizes, insufficient feature information, and high missed detection rates, this paper proposes a maritime small target image detection algorithm based on the improved YOLOv11n. Firstly, the BIE module is introduced into the neck feature fusion stage of YOLOv11n. Utilizing its dual-branch information interaction design, independent branches for key features of maritime small targets in infrared and visible light images are constructed, enabling the progressive fusion of infrared and visible light target features. Secondly, RepViTBlock is incorporated into the backbone network and combined with the C3k2 module of YOLOv11n to form C3k2-RepViTBlock. Through the lightweight attention mechanism and multi-branch convolution structure, this addresses the insufficient capture of tiny target features by the C3k2 module and enhances the model’s ability to extract local features of maritime small targets. Finally, the ConvAttn module is embedded at the end of the backbone network. With its dynamic small-kernel convolution, it adaptively extracts the contour features of small targets, maintaining the overall model’s light weight while reducing the missed detection rate for maritime small targets. Experiments on a collected infrared and visible light ship image dataset (IVships) and a public dataset (SeaShips) show that, on the basis of increasing only a small number of parameters, the improved algorithm increases the mAP@0.5 by 1.9% and 1.7%, respectively, and the average precision by 2.2% and 2.4%, respectively, compared with the original model, which significantly improves the model’s small target detection capabilities.
- Open Access
- 9 October 2025
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 13  (10) , 1936
YOLO-PFA: Advanced Multi-Scale Feature Fusion and Dynamic Alignment for SAR Ship Detection
Maritime ship detection faces challenges due to complex object poses, variable target scales, and background interference. This paper introduces YOLO-PFA, a novel SAR ship detection model that integrates multi-scale feature fusion and dynamic alignment. By leveraging the Bidirectional Feature Pyramid Network (BiFPN), YOLO-PFA enhances cross-scale weighted feature fusion, improving detection of objects of varying sizes. The C2f-Partial Feature Aggregation (C2f-PFA) module aggregates raw and processed features, enhancing feature extraction efficiency. Furthermore, the Dynamic Alignment Detection Head (DADH) optimizes classification and regression feature interaction, enabling dynamic collaboration. Experimental results on the iVision-MRSSD dataset demonstrate YOLO-PFA’s superiority, achieving an mAP@0.5 of 95%, outperforming YOLOv11 by 1.2% and YOLOv12 by 2.8%. This paper contributes significantly to automated maritime target detection.
- 9 October 2025
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 13  (10) , 1936
Open AccessYOLO-PFA: Advanced Multi-Scale Feature Fusion and Dynamic Alignment for SAR Ship Detection
Maritime ship detection faces challenges due to complex object poses, variable target scales, and background interference. This paper introduces YOLO-PFA, a novel SAR ship detection model that integrates multi-scale feature fusion and dynamic alignment. By leveraging the Bidirectional Feature Pyramid Network (BiFPN), YOLO-PFA enhances cross-scale weighted feature fusion, improving detection of objects of varying sizes. The C2f-Partial Feature Aggregation (C2f-PFA) module aggregates raw and processed features, enhancing feature extraction efficiency. Furthermore, the Dynamic Alignment Detection Head (DADH) optimizes classification and regression feature interaction, enabling dynamic collaboration. Experimental results on the iVision-MRSSD dataset demonstrate YOLO-PFA’s superiority, achieving an mAP@0.5 of 95%, outperforming YOLOv11 by 1.2% and YOLOv12 by 2.8%. This paper contributes significantly to automated maritime target detection.
- Open Access
Receiver Location Optimization for Heterogeneous S-Band Marine Transmitters in Passive Multistatic Radar Networks via NSGA-II
Comprehensive maritime domain awareness is crucial for navigation safety, traffic management, and security surveillance. In the context of an increasingly complex modern electromagnetic environment, the disadvantages of traditional active single-station radars, such as their high cost and susceptibility to interference, have started to surface. Due to their unique advantages, such as low cost, environmental sustainability (by reusing existing signals), and resilience in congested spectral environments, non-cooperative passive multistatic radar (PMR) systems have gained significant interest in maritime monitoring. This paper presents the research background of non-cooperative passive multistatic radar systems, performs a fundamental analysis of the detection performance of multistatic radar systems, and suggests an optimization method for the transceiver configuration of non-cooperative passive multistatic radar systems based on geometric coverage theory and a signal-to-noise ratio model. A multi-objective optimization model is developed, considering both detection coverage and positioning error, and is solved using the Non-dominated Sorting Genetic Algorithm II (NSGA-II). The optimization aims to find the optimal receiver location relative to a fixed configuration of four transmitters, representing common maritime traffic patterns. According to the simulation results, the multi-target genetic algorithm can be utilized to optimize the receiver position under the S-band radar settings used in this work. Compared to a random placement baseline, this can reduce the positioning error by about 8.9% and extend the detection range by about 15.8%. Furthermore, for the specific four-transmitter configuration and S-band radar parameters considered in this study, it is found that the best detection performance is more likely to be obtained when the receiver is placed within 15 km of the transmitters’ geometric center.
Open AccessReceiver Location Optimization for Heterogeneous S-Band Marine Transmitters in Passive Multistatic Radar Networks via NSGA-II
Comprehensive maritime domain awareness is crucial for navigation safety, traffic management, and security surveillance. In the context of an increasingly complex modern electromagnetic environment, the disadvantages of traditional active single-station radars, such as their high cost and susceptibility to interference, have started to surface. Due to their unique advantages, such as low cost, environmental sustainability (by reusing existing signals), and resilience in congested spectral environments, non-cooperative passive multistatic radar (PMR) systems have gained significant interest in maritime monitoring. This paper presents the research background of non-cooperative passive multistatic radar systems, performs a fundamental analysis of the detection performance of multistatic radar systems, and suggests an optimization method for the transceiver configuration of non-cooperative passive multistatic radar systems based on geometric coverage theory and a signal-to-noise ratio model. A multi-objective optimization model is developed, considering both detection coverage and positioning error, and is solved using the Non-dominated Sorting Genetic Algorithm II (NSGA-II). The optimization aims to find the optimal receiver location relative to a fixed configuration of four transmitters, representing common maritime traffic patterns. According to the simulation results, the multi-target genetic algorithm can be utilized to optimize the receiver position under the S-band radar settings used in this work. Compared to a random placement baseline, this can reduce the positioning error by about 8.9% and extend the detection range by about 15.8%. Furthermore, for the specific four-transmitter configuration and S-band radar parameters considered in this study, it is found that the best detection performance is more likely to be obtained when the receiver is placed within 15 km of the transmitters’ geometric center.
- 13 September 2025
- Published by World Scientific Pub Co Pte Ltd in Nano
- Vol. 21  (09)
Dual Chaotic Optical Injection of Mutually Coupled Nanolaser Based on Phase Conjugate Feedback
Nanolasers have been widely used in optical fiber communications, and their nonlinear dynamical properties have been extensively investigated, but there is a lack of in–depth research on the high–quality chaotic output generated by NLs and their application to chaotic secure communications. In this paper, we make the time–delay signature of the mutually coupled NL completely hidden by using the phase conjugate feedback structure, and further achieve low–delay, high–quality synchronous communication through dual chaotic optical injection. We also investigate the influence of system parameters, Purcell factor [ ], and spontaneous emission coupling factor [ ] on the TDS and deeply explore the impact of parameter mismatch and injection parameters on chaotic synchronization and message recovery. The results show that the phase–conjugate feedback–based mutually coupled NL through dual chaotic optical injection is able to achieve complete hiding of the TDS under suitable parameters and work stably in a chaotic state over a wide parameter range, which provides a reliable operational basis for practical applications. In addition, under appropriate injection conditions, the system can achieve high–quality chaotic synchronization, which significantly enhances the security of chaotic communication.
- 13 September 2025
- Published by World Scientific Pub Co Pte Ltd in Nano
- Vol. 21  (09)
Dual Chaotic Optical Injection of Mutually Coupled Nanolaser Based on Phase Conjugate Feedback
Nanolasers have been widely used in optical fiber communications, and their nonlinear dynamical properties have been extensively investigated, but there is a lack of in–depth research on the high–quality chaotic output generated by NLs and their application to chaotic secure communications. In this paper, we make the time–delay signature of the mutually coupled NL completely hidden by using the phase conjugate feedback structure, and further achieve low–delay, high–quality synchronous communication through dual chaotic optical injection. We also investigate the influence of system parameters, Purcell factor [ ], and spontaneous emission coupling factor [ ] on the TDS and deeply explore the impact of parameter mismatch and injection parameters on chaotic synchronization and message recovery. The results show that the phase–conjugate feedback–based mutually coupled NL through dual chaotic optical injection is able to achieve complete hiding of the TDS under suitable parameters and work stably in a chaotic state over a wide parameter range, which provides a reliable operational basis for practical applications. In addition, under appropriate injection conditions, the system can achieve high–quality chaotic synchronization, which significantly enhances the security of chaotic communication.
- Open Access
Task Similarity-Aware Cooperative Computation Offloading and Resource Allocation for Reusable Tasks in Dense MEC Systems
As an emerging paradigm for supporting computation-intensive and latency-sensitive services, mobile edge computing (MEC) faces significant challenges in terms of efficient resource utilization and intelligent task coordination among heterogeneous user equipment (UE), especially in dense MEC scenarios with severe interference. Generally, task similarity and cooperation opportunities among UE are usually ignored in existing studies when dealing with reusable tasks. In this paper, we investigate the problem of cooperative computation offloading and resource allocation for reusable tasks, with a focus on minimizing the energy consumption of UE while ensuring delay limits. The problem is formulated as an intractable mixed-integer nonlinear programming (MINLP) problem, and we design a similarity-based cooperative offloading and resource allocation (SCORA) algorithm to obtain a solution. Specifically, the proposed SCORA algorithm decomposes the original problem into three subproblems, i.e., task offloading, resource allocation, and power allocation, which are solved using a similarity-based matching offloading algorithm, a cooperative-based resources allocation algorithm, and a concave–convex procedure (CCCP)-based power allocation algorithm, respectively. Simulation results show that compared to the benchmark schemes, the SCORA scheme can reduce energy consumption by up to 51.52% while maintaining low latency. Moreover, the energy of UE with low remaining energy levels is largely saved.
Open AccessTask Similarity-Aware Cooperative Computation Offloading and Resource Allocation for Reusable Tasks in Dense MEC Systems
As an emerging paradigm for supporting computation-intensive and latency-sensitive services, mobile edge computing (MEC) faces significant challenges in terms of efficient resource utilization and intelligent task coordination among heterogeneous user equipment (UE), especially in dense MEC scenarios with severe interference. Generally, task similarity and cooperation opportunities among UE are usually ignored in existing studies when dealing with reusable tasks. In this paper, we investigate the problem of cooperative computation offloading and resource allocation for reusable tasks, with a focus on minimizing the energy consumption of UE while ensuring delay limits. The problem is formulated as an intractable mixed-integer nonlinear programming (MINLP) problem, and we design a similarity-based cooperative offloading and resource allocation (SCORA) algorithm to obtain a solution. Specifically, the proposed SCORA algorithm decomposes the original problem into three subproblems, i.e., task offloading, resource allocation, and power allocation, which are solved using a similarity-based matching offloading algorithm, a cooperative-based resources allocation algorithm, and a concave–convex procedure (CCCP)-based power allocation algorithm, respectively. Simulation results show that compared to the benchmark schemes, the SCORA scheme can reduce energy consumption by up to 51.52% while maintaining low latency. Moreover, the energy of UE with low remaining energy levels is largely saved.
- Open Access
- 23 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 117608-117616
Mpox Virus Image Segmentation Based on Multiscale Expansion Convolution
A novel strategy for segmenting mpox virus images is proposed to address the challenge of distinguishing lesion areas from muscle tissue and other regions of infection. This strategy leverages a multiscale inflated convolutional feature fusion and attentional Swin-Unet approach. In this method, a multi-scale extended convolution module is employed in the coding stage of the Swin-Unet network to enhance complementary features while preserving different features at different scales. Additionally, a triple attention module is integrated into the downsampling process to address the issue of inter-channel independence. Finally, the Swin Transformer Block is utilized to modulate the network segmentation performance by adjusting the iteration count in the encoding and decoding stages. Experimental results on a self-constructed mpox dataset demonstrate that the proposed network achieves a pixel segmentation accuracy of 90.4% and an average intersection-over-union ratio of 80.3%. These values represent improvements of 8.6% and 14.6%, respectively, compared to the original Swin-Unet. This enhancement provides valuable support for the ancillary diagnosis of mpox.
- 23 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 117608-117616
Open AccessMpox Virus Image Segmentation Based on Multiscale Expansion Convolution
A novel strategy for segmenting mpox virus images is proposed to address the challenge of distinguishing lesion areas from muscle tissue and other regions of infection. This strategy leverages a multiscale inflated convolutional feature fusion and attentional Swin-Unet approach. In this method, a multi-scale extended convolution module is employed in the coding stage of the Swin-Unet network to enhance complementary features while preserving different features at different scales. Additionally, a triple attention module is integrated into the downsampling process to address the issue of inter-channel independence. Finally, the Swin Transformer Block is utilized to modulate the network segmentation performance by adjusting the iteration count in the encoding and decoding stages. Experimental results on a self-constructed mpox dataset demonstrate that the proposed network achieves a pixel segmentation accuracy of 90.4% and an average intersection-over-union ratio of 80.3%. These values represent improvements of 8.6% and 14.6%, respectively, compared to the original Swin-Unet. This enhancement provides valuable support for the ancillary diagnosis of mpox.
- Open Access
- 1 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 105703-105715
Optimization of Storage and Retrieval Strategies in Warehousing Based on Enhanced Genetic Algorithm
The Shuttle-Based Storage and Retrieval System (SBS/RS) faces challenges of low efficiency due to the constraints of single outbound or inbound operations. To overcome this limitation, a scheme enabling simultaneous outbound and inbound operations has been proposed. This involved developing a physical model that incorporates costs related to outbound cargo urgency, shelf stability, time, and warehouse busyness. The model was solved using a Genetic Algorithm with priority selection, adaptive operators, and a decay factor (GA-DF). Experimental results, validated across various environments, demonstrate that the proposed GA-DF algorithm achieves 50% higher efficiency compared to the IOSA algorithm when the shelf occupancy rate is 50% and multiple cost environments are considered. Additionally, GA-DF outperforms the Simulated Annealing algorithm, traditional Genetic Algorithm, and IOSA algorithm in optimizing storage and retrieval locations, significantly enhancing system optimization. This provides a crucial reference for optimizing such systems, particularly in dynamic and complex warehousing environments. The GA-DF algorithm’s applicability and advantages have been widely recognized through further validation, highlighting its potential to drive improvements in warehousing system efficiency and optimization strategies.
- 1 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 105703-105715
Open AccessOptimization of Storage and Retrieval Strategies in Warehousing Based on Enhanced Genetic Algorithm
The Shuttle-Based Storage and Retrieval System (SBS/RS) faces challenges of low efficiency due to the constraints of single outbound or inbound operations. To overcome this limitation, a scheme enabling simultaneous outbound and inbound operations has been proposed. This involved developing a physical model that incorporates costs related to outbound cargo urgency, shelf stability, time, and warehouse busyness. The model was solved using a Genetic Algorithm with priority selection, adaptive operators, and a decay factor (GA-DF). Experimental results, validated across various environments, demonstrate that the proposed GA-DF algorithm achieves 50% higher efficiency compared to the IOSA algorithm when the shelf occupancy rate is 50% and multiple cost environments are considered. Additionally, GA-DF outperforms the Simulated Annealing algorithm, traditional Genetic Algorithm, and IOSA algorithm in optimizing storage and retrieval locations, significantly enhancing system optimization. This provides a crucial reference for optimizing such systems, particularly in dynamic and complex warehousing environments. The GA-DF algorithm’s applicability and advantages have been widely recognized through further validation, highlighting its potential to drive improvements in warehousing system efficiency and optimization strategies.