Journal of South China University of Technology(Natural Science Edition)

Research on Redundant Strapdown Inertial Navigation Information Fusion for eVTOL Aircraft

HU Qingchun, HUANG Si, CHEN Xingbin, ZHANG Ning, SU Qingpeng

2024, 52(10): 1-8. doi:10.12141/j.issn.1000-565X.230696

Asbtract ( 158 )

HTML ( 13)

PDF (2663KB) ( 121 )

Figures and Tables | References | Related Articles | Metrics

As a potential solution for future urban transportation, the using of electric vertical takeoff and landing (eVTOL) aircraft, has great potential to alleviate urban traffic congestion and improve air traffic efficiency. In its commonly used navigation systems, integrated navigation and sensor redundancy technology are usually used to improve system reliability and safety. However, in the current sensor redundancy technology of navigation systems, redundant sensors only serve as data backup, resulting in insufficient information utilization of measurement data. To address this issue, this paper took the integrated navigation system of a triple redundant strapdown inertial navigation system (SINS) and a global navigation satellite system (GNSS) as the research object and proposed a real-time estimation method for gyroscope noise based on second-order differencing and redundant information of the inertial measurement unit (IMU). It derived recursive expressions for gyroscope noise estimation in the case of two and three redundancies. After obtaining the estimated noise value of the gyroscope, the navigation information of SINS and GNSS was fused to improve the accuracy and robustness of the integrated navigation system. Through simulation and real sports car tests on the SINS/GNSS integrated navigation system, the results show that the method proposed in this paper can accurately estimate gyroscope noise. Compared with traditional fusion methods, the navigation accuracy and anti-interference ability of the combined navigation system are improved after introducing the real-time estimation of gyroscope noise, which has practical engineering significance.

Feature-Space Optimization-Inspired and Multi-Hypothesis Cross-Attention Reconstruction Neural Network for Video Compressive Sensing

YANG Chunling, CHEN Wenjun, LIU Jiahui

2024, 52(10): 9-21. doi:10.12141/j.issn.1000-565X.230578

Asbtract ( 100 )

HTML ( 12)

PDF (4456KB) ( 193 )

Figures and Tables | References | Related Articles | Metrics

The existing video compressive sensing reconstruction network usually uses the optical flow network to achieve pixel domain motion estimation and motion compensation. However, during the reconstruction process, the input of the optical flow network is the estimated frame with poor quality, resulting in inaccurate optical flow. The optical flow-based pixel domain alignment and fusion operation will cause noise accumulation, lead to obvious artificial effects in video reconstruction frames and affect the reconstruction quality. Based on the fact that multi-channel information in the feature space has strong robustness to interference noise, this paper applied the idea of feature space optimization to the design of the video compressive sensing reconstruction neural network, and proposed a feature-space optimization-inspired and flow-guided multi-hypothesis cross-attention network (FOFMCNet). To avoid the image structure destruction caused by the noise in the optical flow when warping the image, the study designed multi-hypothesis motion estimation module guided by optical flow and the motion compensation module based on cross-attention to realize the motion estimation and motion compensation of inter-frame in feature space, so as to make full use of inter-frame correlation to assist non-key frame reconstruction. In order to strengthen the reuse of effective information in the process of feature optimization, improve the learning ability of the network and alleviate the problem of gradient explosion, this paper designed a feature-space optimization-inspired u-shape network (FOUNet) as a sub-network of FOFMCNet. Through the cascade of multiple FOUNets, the FOFMCNet realizes the optimization and reconstruction of non-key frames in the feature space. Experimental results show that the reconstruction results of the proposed algorithm are obviously better than those of the existing video compression sensing algorithms on the classical low-resolution dataset (UCF-101 and QCIF) and new high-resolution dataset (REDS4).

Blood Flow Velocity Estimation Method Based on Multi-Frequency Pulse Sampling

MA Biyun, FAN Yihua, LIU Jiaojiao

2024, 52(10): 22-30. doi:10.12141/j.issn.1000-565X.230628

Asbtract ( 111 )

HTML ( 10)

PDF (2735KB) ( 199 )

Figures and Tables | References | Related Articles | Metrics

The traditional dual-mode ultrasound technology has greater potential for wearable implementation compared to the other emerging technologies. During pulse Doppler blood flow velocity estimation, dual-mode ultrasound needs to emit B-mode pulses simultaneously for imaging localization, which requires that B-mode pulses and Doppler pulses share sampling time. This issue can be addressed by using a sparse interval emission method based on single-frequency Doppler pulses. However, common sparse emission arrangements (such as nested emission, coprime emission, etc.) have the disadvantage of a long sampling time window. Especially, there is the problem of insufficient temporal resolution with significant changes in blood flow velocity. In addition, a longer time window contains more blood flow velocity components, which is prone to artifacts caused by sparse sampling, thereby affecting the accuracy of blood flow velocity estimation. Therefore, this paper proposed a novel blood flow velocity estimation method based on multi-frequency pulse sampling. Firstly, a multi-frequency pulse sampling echo model was constructed and derived. It is proved that under the assumption of stationary frequency band attenuation, this mathematical model is equivalent to the spare interval emission method of single-frequency Doppler pulses. That is, the multi-frequency pulse sampling can achieve performance similar to that of the long time window of the single-frequency pulse sampling mode through a shorter time window, thereby improving the temporal resolution and estimation accuracy of the blood flow velocity spectrum. Subsequently, this paper proposed two methods for constructing the blood flow velocity spectrum for multi-frequency pulse sampling mode, namely the BMUSIC algorithm with lower complexity and the VMUSIC algorithm with better artifact suppression effect. The experimental results based on Field Ⅱ simulation data and in vivo data show that, compared with the sparse emission method of single-frequency Doppler pulses, the proposed method in this paper can not only use a shorter time window to improve the temporal resolution of the blood flow velocity spectrum, but also obtain continuous, clear, high-precision, and better artifact suppression effect of blood flow velocity estimation results. In the experiments with in vivo data, due to the limitation of experimental constraints, the proposed method cannot achieve non-integer multiples of frequency, and the performance advantage of the VMUSIC algorithm is not fully demonstrated.

Multi-Task Assisted Driving Policy Learning Method for Autonomous Driving

LUO Yutao, XUE Zhicheng

2024, 52(10): 31-40. doi:10.12141/j.issn.1000-565X.230503

Asbtract ( 1862 )

HTML ( 14)

PDF (3027KB) ( 211 )

Figures and Tables | References | Related Articles | Metrics

With the development of autonomous driving technology, deep reinforcement learning has become an important means to realize the efficient driving policy learning. However, the implementation of autonomous driving is faced with the challenges brought by the complex and changeable traffic scenes, and the existing deep reinforcement learning methods have the problems of single scene adaptation ability and slow convergence speed. To address these issues and to improve the scene adaptability and policy learning efficiency of autonomous vehicles, this paper proposed a multi-task assisted driving policy learning method. Firstly, this method constructed the encoder-multi-task decoder module based on the deep residual network, squeezing high-dimensional driving scenes into low-dimensional representations, and adopted multi-task-assisted learning of semantic segmentation, depth estimation and speed prediction to improve the scene information richness of low-dimensional representations. Then, the low-dimensional representation was used as the state input to build a decision network based on reinforcement learning, and the multi-constraint reward function was designed to guide the learning of driving strategies. Finally, simulation experiments were conducted in CARLA. The experimental results show that, compared to classic methods such as DDPG and TD3, the proposed method improves the training process through multi-task assistance and learns better driving policies. It achieves higher task success rates and driving scores in several typical urban driving scenarios such as roundabouts and intersections, demonstrating excellent decision-making capabilities and scene adaptability.

Semantic-Visual Consistency Constraint Network for Zero-Shot Image Semantic Segmentation

CHEN Qiong, FENG Yuan, LI Zhiqun, et al

2024, 52(10): 41-50. doi:10.12141/j.issn.1000-565X.230673

Asbtract ( 124 )

HTML ( 11)

PDF (2148KB) ( 119 )

Figures and Tables | References | Related Articles | Metrics

Zero-shot image semantic segmentation is one of the important tasks in the visual field of zero-shot learning, aiming to segment novel categories unseen during training. The current distribution of visual features based on pixel-level visual feature generation is inconsistent with real visual feature distribution. The synthesized visual features inadequately reflect class semantic information, leading to low discriminability in these features. Some existing generative methods consume significant computational resources to obtain the discriminative information conveyed by semantic features. In view of the above problems, this paper proposed a zero-shot image semantic segmentation network called SVCCNet, which is based on semantic-visual consistency constraints. SVCCNet uses a semantic-visual consistency constraint module to facilitate the mutual transformation between semantic features and visual features, enhancing their correlation and diminishing the disparity between the spatial structures of real and synthesized visual features, which mitigates the inconsistency problem between the distributions of synthesized and real visual features. The semantic-visual consistency constraint module achieves the correspondence between visual features and class semantics through two mutually constrained reconstruction mappings, while maintaining low model complexity. Experimental results on the PASCAL-VOC and PASCAL-Context datasets demonstrate that SVCCNet outperforms mainstream methods in terms of pixel accuracy, mean accuracy, mean intersection over union (IoU), and harmonic IoU.

A Batch Scheduling Method of Flexible Job-Shop with Partially Out-of-Ordered Execute Operation

LIU Ning, HUA Tianbiao, WANG Gao, et al

2024, 52(10): 51-63. doi:10.12141/j.issn.1000-565X.230722

Asbtract ( 137 )

HTML ( 13)

PDF (5299KB) ( 116 )

Figures and Tables | References | Related Articles | Metrics

Actual job-shop scheduling problems often exhibit high complexity, and the scheduling algorithm needs to consider more constraints, so it increases the difficulty of solving the problem. To address the challenge of out-of-order processing for different batches and processes in the flexible job shop’s batch scheduling scenario, it is necessary to overcome the issues related to low utilization rates of existing job shop machines and unbalanced workload distribution among machines of the same type. Therefore, this paper constructed a flexible job shop equal batch scheduling model that incorporates partially out-of-order execution of processes. Firstly, based on the widely adopted fast non-dominated sorting genetic algorithm (NSGA-Ⅱ), this paper introduced a novel two-stage coding structure that integrates batch information and process sorting information. The priority rule method was used to obtain the initial population, and with minimizing the completion time, machine load equilibrium rate and total machine load as the optimization goal, the greedy algorithm was used to obtain the optimal value of the model, and then the processing path of different batches was dynamically constructed.Then, the optimized objective functions were sorted, and the non-dominant sorting process was added step by step to solve the problem that multiple optimized objective functions are difficult to optimize at the same time and improve the solving efficiency. Finally, taking the wood products processing workshop of a printing and packaging enterprise as an example, the scheduling process was realized according to the field operation information. The results show that, compared with the priority scheduling rules, the completion time of the proposed method is shortened by 6.6%, the average machine load balancing variance is reduced by 10.7%, and the average of the proposed method is reduced by 53.3% compared with the genetic algorithm, thus verifying the feasibility of the method. This method can meet the high performance scheduling requirements of the flexible workshop of printing and packaging enterprises.

A Small Sample Rolling Bearing Fault Diagnosis Method Based on Gramian Angular Difference Field and Generative Adversarial Network

QIANG Ruiru, ZHAO Xiaoqiang

2024, 52(10): 64-75. doi:10.12141/j.issn.1000-565X.240021

Asbtract ( 2009 )

HTML ( 13)

PDF (4151KB) ( 135 )

Figures and Tables | References | Related Articles | Metrics

Aiming at the problem that deep learning-based rolling bearing fault diagnosis algorithms need to learn from a large amount of labeled data and face poor diagnosis effect when the number of samples is limited, this paper proposed a small-sample rolling bearing fault diagnosis method based on the Gramian angular difference field (GADF) and generative adversarial networks (GAN). Firstly, a data enhancement method based on GADF transform was proposed, and it converts a few 1D vibration signals into 2D GADF images by GADF transform. GADF subgraphs are obtained by cropping to obtain a large number of image samples. Then, a conditional generative adversarial network (CGAN) was combined with Wasserstein GAN with gradient penalty (WGAN-GP) to construct a novel generative adversarial network, which enhances the model training stability by conditional auxiliary information with gradient penalty and designs dynamic coordinate attention mechanism to enhance the spatial perception of the model, so as to generate high-quality samples. Finally, the generative samples were used to train the classifier, and the diagnosis results were obtained on the validation set. Two sets of bearing fault diagnosis experiments in a small sample environment were conducted using the Southeast University dataset and the Case Western Reserve University dataset, respectively. The results show that, compared with traditional generative adversarial networks as well as advanced small-sample fault diagnosis methods, the proposed method can obtain the best results in five fault diagnosis metrics, including accuracy and precision, and can accurately diagnose the type of bearing faults under small-sample conditions.

Iron Occurrence State of Steel Slag Under Different Treatment Processes and Its Influence on the Yield of Magnetic Separation Powder and the Cementitious Activity of Tailings

YIN Suhong, ZENG Lisha, LIANG Kang, et al

2024, 52(10): 76-86. doi:10.12141/j.issn.1000-565X.240151

Asbtract ( 87 )

HTML ( 8)

PDF (6748KB) ( 17 )

Figures and Tables | References | Related Articles | Metrics

Steel slag contains metallic iron and its oxide, which are high value‐added renewable resources, and it can be utilized as a mineral admixture in the building materials industry. After different cooling treatment processes, the phase of steel slag evolves, thus affecting the recovery of iron in steel slag and the cementitious activity of tailings. In order to improve the recycling of iron resources in steel slag and the effective utilization of tailings, this paper studied the steel slag of three different treatment processes, namely, hot splash, roller crushing‐pressurized hot stewing and roller crushing‐hot splash. It used petrography analysis, XRD, SEM‐EDS, and chemical phase‐selective dissolution, and other methods to analyze the distribution of the iron phases and the state of enrichment of steel slags, and to determine the rate of magnetic separation powder and iron grade, and the cementitious activity of tailings. The results show that: the metal iron is easier to be enriched and deposited under the hot splash process, and the iron phase is mainly in the form of FeO uniformly distributed in the RO phase and the ferrite phase, with less Fe in the phase, and the yield of magnetic separation powder is higher, but the grade is poorer, which is 32.22% and 33.43%, respectively. After roll crushing‐pressurized hot stewing, no obvious metal iron particles can be seen in the slag; Fe in the phase accounts for more, and the yield of the magnetic separation powder is low but the grade is higher, which is 28.37% and 37.12%, respectively; after roll crushing‐hot splashing, the iron phase mainly exists in calcium ferrite phase and silicate phase in the form of Fe₂O₃, Fe in the phase accounts for more and contains Fe₃O₄, and the magnetic separation powder has high yield and high iron grade, which is 37.60% and 39.69%, respectively. Under roll crushing‐pressurized hot stewing, the C₂S content in steel slag is relatively more and better developed, and has high cementitious activity, 7 d and 28 d activity index of tailings is 78% and 92%, respectively; the 7 d activity index of the roll crushed‐hot splash slag is low at 66%, but the 28 d activity index grows to 92%; the cementitious activity of the hot splash slag is in the middle.

Physical and Chemical Characteristics of Incineration Bottom Ash (IBA) from Different Sources and Strength Variability of IBA Recycled Mortar

CHEN Chunhong, ZHANG Haiyan, ZHANG Yonggang, et al

2024, 52(10): 87-100. doi:10.12141/j.issn.1000-565X.240106

Asbtract ( 92 )

HTML ( 12)

PDF (4583KB) ( 107 )

Figures and Tables | References | Related Articles | Metrics

Municipal solid waste incineration bottom ash (IBA) shows large heterogeneity because of different garbage composition, incineration process and storage conditions. The effective cooperation for one batch of recycled concrete (mortar) may be ineffective for another batch, resulting in large dispersion of recycled concrete (mortar) performance, which limits its application. In order to explore the heterogeneity of IBA from different sources and the strength variability of recycled mortar, this study collected a total of 14 batches of IBA samples from different incinerators and different monthly sources and tested for their physical and chemical properties. And it investigated the workability, compressive strength, and splitting tensile strength of IBA recycled mortar. Statistical analysis was conducted to assess the level of strength variability in IBA recycled mortar. The test results showed that the crushing index, porosity, sulfide, and chloride content of IBA did not meet the specifications for recycled fine aggregates, and there is significant heterogeneity in IBA from different origins. When the recycled cement mortar below M20 strength grade is prepared with a substitution rate of 50% IBA which is from a single incineration plant of different months, the strength is not significantly reduced compared with that of natural aggregate mortar, and the strength variability is similar to that of ordinary recycled aggregate concrete and the standard deviation is also lower than the recommended value of the specification. However, when used to prepare the recycled cement mortar above M20, the reduction in compressive strength was significant (reduced by 23%~32%). Due to higher compressive strength variability of IBA recycled mortars from two different incineration plants, it was not recommended to use IBA recycled mortars from different incineration plants together.

Study on Internal Stress of Asphalt Mixture Under Three-Point Bending Mode

WANG Wei, TAN Yiqiu, XU Yongjiang

2024, 52(10): 101-111. doi:10.12141/j.issn.1000-565X.240102

Asbtract ( 1712 )

HTML ( 11)

PDF (5042KB) ( 113 )

Figures and Tables | References | Related Articles | Metrics

The bending and tensile properties of asphalt mixture affect the service quality and life of asphalt pavement, and its internal stress determines the bending and tensile performance. In order to investigate the internal stress characteristics of asphalt mixtures, this paper adopted the discrete element method to quantitatively evaluate the force chains of each component in asphalt mixtures under the three-point bending mode. Firstly, it constructed a template library of coarse aggregates based on image recognition and realized efficient three-dimensional modeling of asphalt mixture specimen and proposed a three-point bending simulation method. Then the internal force chain distribution of asphalt mixture was visually represented, and data of force chains of each component were extracted. The force chain characteristics were analyzed from the three aspects of composition, strength, and angle. The results show that under the three-point bending mode, the internal force chain field of asphalt mixture exhibits tension and compression zones, and the extrusion of aggregates only takes effect in the compressed zone. 70.8% of the internal contact force of SMA 13 asphalt mixture is provided by the asphalt mortar, and that of AC13 asphalt mixture is 83.2%, indicating that coarse aggregates have little effect under bending and tensile stress and asphalt mortar plays a major role in resisting external loads. The proportion of force chains decrease as the strength increased, and the proportion of strong force chains in the interior of the mortar and the mortar-aggregate interface position is basically the same. The stress between coarse aggregates is uneven, and the mortar plays a significant role in ensuring uniform stress within the asphalt mixture. The strength of horizontal force chains at the aggregate-mortar interface is slightly higher than that in the vertical direction, and the strength of aggregate force chains fluctuates greatly with the change of angle. Asphalt mortar bears the main load during bending and tensile force of asphalt mixture and the research findings can serve as a reference for the structural design and performance evaluation of asphalt mixtures.

Surface Defect Detection Method for Industrial Products Based on Photometric Stereo and Dual Stream Feature Fusion Network

HU Guanghua, TU Qianxi

2024, 52(10): 112-123. doi:10.12141/j.issn.1000-565X.230638

Asbtract ( 130 )

HTML ( 13)

PDF (5761KB) ( 197 )

Figures and Tables | References | Related Articles | Metrics

Surface defect detection is an important part of the modern industrial production process. The existing visual defect detection methods generally achieve detection by analyzing a single RGB or grayscale image of the target object and using differential features between the defect and the background. They are suitable for objects with a large difference between the target and the background, such as the detection of metal surface oxidation and spot defects. However, the simple RGB image cannot effectively characterize the 3D defect features such as dents and bulges, which are mainly formed by depth changes, ultimately resulting in missed detection. To this end, this paper extracted the 3D geometric appearance information of the object surface to be tested according to multi-directional light imaging and photometric stereo principle. Next, the original multi-directional light images were effectively fused using the contrast pyramid fusion algorithm to obtain the enhanced 2D RGB fusion image features of the defects. Then, on the basis of the multi-target detection framework YOLOv5, with the above geometric appearance and RGB fusion images as inputs, a defect detection network model based on dual stream feature fusion detection network model was constructed. The model introduces the spatial channel attention residual module and the gated recurrent unit (GRU) feature fusion module and is able to organically fuse the different modal features at multiple levels to realize the effective extraction of the 2D RGB and 3D appearance information of the surface defects, so as to achieve the purpose of dealing with the detection of 2D and 3D defects at the same time. Finally, the detection experiments were conducted on the surface defects of several typical industrial products. The results show that mAP of the method in the paper is above 90% on several datasets, and it can simultaneously cope with the detection of 2D and 3D defects, so the detection performance is better than that of the current mainstream methods, and it can meet the detection requirements of different industrial products.

A New Integer U Transform Algorithm for Image Compression

YUAN Xixi, CAI Zhanchuan, SHI Wuzhen, et al

2024, 52(10): 124-134. doi:10.12141/j.issn.1000-565X.230784

Asbtract ( 110 )

Table of Content