Improve Detection Efficiency Research Articles

Detecting delamination defects in CFRP plates using nonlinear defect index of air-coupled Lamb waves and adaptively weighted imaging algorithm

The air-coupled ultrasonic technique is capable of detecting defects in in-service CFRP plates and ensuring their application safety. Traditional air-coupled ultrasonic methods often rely on the linear defect index, which is not effective in characterizing small-size defects. Additionally, the scanning step length completely limits their imaging spatial resolution, resulting in the contradiction between imaging spatial resolution and detection efficiency. To address the above problems, the nonlinear defect index and the adaptively weighted imaging algorithm are proposed. The nonlinear defect index uses the relatively nonlinear coefficient of the Lamb wave to enhance the ability to detect small-size defects. Considering the beam width, the adaptively weighted imaging algorithm constructs the relationship between any imaging point and all scanning paths. At this time, the imaging spatial resolution can be set arbitrarily, eliminating the dependence on the scanning step length. The experimental results demonstrate that the proposed nonlinear defect index can characterize the small-size defect more accurately than the linear defect index. When the scanning step length is increased to improve detection efficiency, the adaptively weighted imaging algorithm can achieve better imaging spatial resolution compared to the traditional defect probability imaging algorithm. For the small-size defect with a diameter of 10 mm, the proposed method has an area detection error of only 7.8 %, whereas the traditional method has an error of 22.4 %. The proposed method is promising to detect small-size defects of in-service CFRP plates in the aircraft skin.

LSC screening of coloured water samples for simultaneous 137Cs and 90Sr/90Y measurements during nuclear emergencies

Simultaneous screening of 137Cs and 90Sr/90Y levels in coloured water samples by Liquid Scintillation Counter Quantulus 1220 via Cherenkov counting has been investigated. Ionic liquid 1-butyl-3-methylimidazolium salicylate with wavelength-shifting properties has been added to the counting vials, which significantly improved detection efficiency. The results of 137Cs activities obtained via LSC method have been compared with conventional gamma-spectrometric measurements. The performance and limitations of the method have been demonstrated on coloured samples spiked with known 137Cs and 90Sr/90Y activities. In the case of a nuclear accident, this method can be used without sample pre-treatment so that results are obtained within 2 h. The method provides results with up to 80% relative deviation from true 137Cs and 90Sr/90Y activities in the case of highly quenched samples. Its application is limited to the prompt screening of a larger number of samples when it is necessary to efficiently detect radioactive contamination of water.

Application of AI intelligent vision detection technology using deep learning algorithm

This study aims to design efficient and reliable artificial intelligence vision detection models to improve detection efficiency and accuracy. The study filters defect-free images by image preprocessing and region of interest detection techniques. AlexNet network is enhanced by introducing attention mechanism modules, deep separable convolutions, and more to effectively boost the network's feature extraction capacity. An area convolutional neural network is developed to rapidly identify and locate defects on steel plate surfaces, utilizing an enhanced AlexNet network for feature extraction. Results demonstrated that the algorithm attained an average detection rate of 98 % and can identify defects in a minimal time of only 0.0011 seconds. For the detection of six types of steel plate defects, the average accuracy of the optimized fast regional convolutional neural network reached more than 0.9, especially for the detection of small-size defects with excellent performance. This improved AlexNet network has a great advantage in F1 value. The conclusion of the study shows that the designed artificial intelligence vision detection model has high detection accuracy, speed, and performance stability in steel plate surface defect detection and has a wide range of application prospects.

Stolon-YOLO: A detecting method for stolon of strawberry seedling in glass greenhouse

Stolons are an essential nutritional organ of strawberry seedlings, whose quantity and vigorous growth directly impact the quality of the seedling cultivation. Accurately detecting stolon is essential for increasing productivity in seedling factories. To alleviate these issues of low recognition accuracy of stolon caused by complex backgrounds, diverse growth types and low proportion of effective information in the bounding box, we propose a Stolon-YOLO for visual recognition of stolon for the first time. In our method, improvements are focused on two aspects: HorBlock-decoupled head and Stem Block feature enhancement module. Firstly, a new decoupled head is designed by introducing the HorBlock, which enables the interaction of high-order spatial information and enhances the precision for locating stolons. Sequential gnConv of the HorBlock realizes better global modeling for incomplete and curved stolon to improve detection efficiency. Then, the Stem Block is used to reinforce feature expression and reduce dimensionality. We fuse the processing results of the Stem Block with the output of HorBlock in a residual form. Experimental results demonstrate that the Stolon-YOLO achieves 92.5% in precision, 89.7% in recall rate, 91.1% in F1 score and 88.5% in average precision for stolon detection, which outperforms the standard YOLOv7 by 3% in recall rate and 3.4% in average precision. Compared with YOLOX, SSD, CenterNet and Faster R-CNN, the Stolon-YOLO increases recall rate by 8.3%, 27.4%, 17%, and 3.5%, and increases AP by 12.2%, 28.9%, 2.4%, and 7.5%, respectively. Meanwhile, the Stolon-YOLO achieves a frame rate of 50.25 FPS, meeting real-time detection demands. The above results highlight that this study provides a fast and effective method for identifying the stolon of strawberry seedlings in glass greenhouses.

Improvement of Road Instance Segmentation Algorithm Based on the Modified Mask R-CNN

Although the Mask region-based convolutional neural network (R-CNN) model possessed a dominant position for complex and variable road scene segmentation, some problems still existed, including insufficient feature expressive ability and low segmentation accuracy. To address these problems, a novel road scene segmentation algorithm based on the modified Mask R-CNN was proposed. The multi-scale backbone network, Res2Net, was utilized to replace the ResNet network, and aimed to improve the feature extraction capability. The soft non-maximum suppression algorithm with attenuation function (soft-NMS) was adopted to improve detection efficiency in the case of a higher overlap rate. The comparison analyses of partition accuracy for various models were performed on the adopted Cityscapes dataset. The results demonstrated that the modified Mask R-CNN effectively increased the segmentation accuracy, especially for small and highly overlapping objects. The adopted Res2Net and soft-NMS can effectively enhance the feature extraction and improve segmentation performance. The average accuracy of the modified Mask R-CNN model reached up to 0.321, and was 0.054 higher than Mask R-CNN. This work provides important guidance to design a more efficient road scene instance segmentation algorithm for further promoting the actual application in automatic driving systems.

Real-Time Monitoring of Air Discharge in a Switchgear by an Intelligent NO2 Sensor Module.

An air-insulated power equipment adopts air as the insulating medium and is widely implemented in power systems. When discharge faults occur, the air produces decomposition products represented by NO2. The efficient NO2 sensor enables the identification of electrical equipment faults. However, single-sensor-dependent NO2 detection is vulnerable to interfering gases. Implementing the sensor array could reduce the interference and improve detection efficiency. In the field of NO2 detection, In2O3 sensors have exhibited tremendous advantages. In our work, four composites based on In2O3 are integrated into sensor arrays, which could detect 250 ppb of NO2 and exhibit excellent selectivity when simultaneously exposed to CO. To further reduce the impact of humidity on gas-sensing performance, a convolutional neural network and a long short-term memory model equipped with an attention mechanism are proposed to evaluate NO2 concentration within 1 ppm, and the detection error is 63.69 ppb. In addition, the NO2 concentration estimation platform based on a microgas sensor is established to detect air discharge faults. The average concentration of NO2 generated by 10 consecutive discharge faults at 15 kV is 726.58 ppb, which indicates severe discharge in the switchgear. Our NO2 estimation method has great potential for large-scale deployment in low- and medium-voltage switchgears.

Advancing Multiple Detection in RT-LAMP with a Specific Probe Assembled from Plural Three-Way-Junction Structures.

The timely detection of diseases and the accurate identification of pathogens require the development of efficient and reliable diagnostic methods. In this study, we have developed a novel specific multivariate probe termed MRTFP (multivariate real-time fluorescent probe) by assembling strand exchange three-way-junction (3WJ) structures. The 3WJ structures were incorporated into a four-angle probe (FP) and a hexagonal probe (HP), to target the multivariate genes of Salmonella. The FP and HP enable single-step and multiplexed detection in RT-LAMP (real-time loop-mediated isothermal amplification) with exceptional sensitivity and specificity. Encouragingly, real food samples contaminated with Salmonella (Salmonella enteritidis and Salmonella typhimurium) can be readily identified and distinguished with a minimum detectable concentration (MDC) of 103 CFU/mL without the need for further culture. The introduction of MRTFP allows for simultaneous detection of dual or three targets in a single tube for LAMP, thereby improving detection efficiency. The MRTFP simplifies the design of robust multivariate probes, exhibits excellent stability, and avoids interference from multiple probe units, offering significant potential for the development of specific probes for efficient and accurate disease detection and pathogen identification.

GBSG-YOLOv8n: A Model for Enhanced Personal Protective Equipment Detection in Industrial Environments

The timely and accurate detection of whether or not workers in an industrial environment are correctly wearing personal protective equipment (PPE) is paramount for worker safety. However, current PPE detection faces multiple inherent challenges, including complex backgrounds, varying target size ranges, and relatively low accuracy. In response to these challenges, this study presents a novel PPE safety detection model based on YOLOv8n, called GBSG-YOLOv8n. First, the global attention mechanism (GAM) is introduced to enhance the feature extraction capability of the backbone network. Second, the path aggregation network (PANet) structure is optimized in the Neck network, strengthening the model’s feature learning ability and achieving multi-scale feature fusion, further improving detection accuracy. Additionally, a new SimC2f structure has been designed to handle image features and more effectively improve detection efficiency. Finally, GhostConv is adopted to optimize the convolution operations, effectively reducing the model’s computational complexity. Experimental results demonstrate that, compared to the original YOLOv8n model, the proposed GBSG-YOLOv8n model in this study achieved a 3% improvement in the mean Average Precision (mAP), with a significant reduction in model complexity. This validates the model’s practicality in complex industrial environments, enabling a more effective detection of workers’ PPE usage and providing reliable protection for achieving worker safety. This study emphasizes the significant potential of computer vision technology in enhancing worker safety and provides a robust reference for future research regarding industrial safety.

Deep learning approaches for object recognition in plant diseases: a review

Plant diseases pose a significant threat to the economic viability of agriculture and the normal functioning of trees in forests. Accurate detection and identification of plant diseases are crucial for smart agricultural and forestry management. In recent years, the intersection of agriculture and artificial intelligence has become a popular research topic. Researchers have been experimenting with object recognition algorithms, specifically convolutional neural networks, to identify diseases in plant images. The goal is to reduce labor and improve detection efficiency. This article reviews the application of object detection methods for detecting common plant diseases, such as tomato, citrus, maize, and pine trees. It introduces various object detection models, ranging from basic to modern and sophisticated networks, and compares the innovative aspects and drawbacks of commonly used neural network models. Furthermore, the article discusses current challenges in plant disease detection and object detection methods and suggests promising directions for future work in learning-based plant disease detection systems.

DResInceptionNasNet method for offline grounding detection of distribution networks

Almost all existing distribution network grounding tests are online. The existing offline distribution network grounding detection methods are all manual handling methods, which are time-consuming, labor-intensive and cause damage to the environment. To save labor cost, reduce environmental damage, and improve detection efficiency and accuracy, this study designs an offline grounding detection device for distribution networks and proposes a DResInceptionNasNet method for grounding detection. The DResInceptionNasNet network, which is trained offline, can predict the location of distribution network grounding wire presence offline and accurately. In this study, the DResInceptionNasNet network is experimented in IEEE 9 and IEEE 39 systems. The obtained experimental results verify that the DResInceptionNasNet network has an average accuracy of at least 2.93 % higher than other 17 network models such as ResNet, NasNet, and Inception V3. In addition, the developed distribution network offline detection device and the proposed DResInceptionNasNet network can effectively and accurately detect the grounding location of distribution networks.

Well-oriented immobilized immunoaffinity magnetic beads for detection of fumonisins in grains and feeds via pre-column automatic derivatization of high-performance liquid chromatography.

In this study, based on the high-throughput automatic sample pretreatment with immunoaffinity magnetic beads with oriented immobilized antibodies, grain and feed fumonisin (FB) content was detected using pre-column automatic derivatization of high-performance liquid chromatography (HPLC). The FB capacity of well-oriented antibody immunoaffinity magnetic beads was 1.5-1.8 times that of magnetic beads with randomly fixed antibody. This pre-column automatic derivatization method using an autosampler can reduce error from manual injection and improve detection efficiency. The spiked recoveries for three different concentrations in maize, husked rice, and pig feed under optimized conditions were 84.6-104.0% (RSD<9.3%). Our novel method was also applied to the analysis of FBs in 63 maize samples collected from the main maize-production regions in China. The results showed that as latitude increased, the contamination level of FBs tended to decrease. High temperature and high humidity are also more favorable for FB growth.

PKAMNet: A Transmission Line Insulator Parallel- Gap Fault Detection Network Based on Prior Knowledge Transfer and Attention Mechanism

Insulator parallel gaps in a transmission line protect the insulator from arc burn and provide protection from lightning. Detection of insulator parallel-gap faults based on aerial inspection images of transmission lines may be hindered by various factors, such as complex background, scale distortion, and occlusion. In this study, we propose a prior knowledge transfer and attention mechanism network (PKAMNet) to detect faulty insulator parallel gaps. First, the capability of PKAMNet to learn the features of different types of parallel-gap faults is improved by constructing a prior knowledge transfer model based on visual saliency. Owing to the difficulty of effectively expressing the features of the fault target due to the deviation of the shooting angle and complex background of the inspection image, we enhance the feature expression ability of the fault area by embedding the coordinate attention block. Additionally, the parameters of the detection network are simplified, and the modules are optimized to improve detection efficiency. Comparison results on 3-year aerial inspection videos of 500 kV high-voltage transmission lines show that PKAMNet has a high detection accuracy and can ameliorate the phenomenon of missed and erroneous detection caused by insufficient expression of parallel-gap faults.

YOLOv8-Peas: a lightweight drought tolerance method for peas based on seed germination vigor.

Drought stress has become an important factor affecting global food production. Screening and breeding new varieties of peas (Pisum sativum L.) for drought-tolerant is of critical importance to ensure sustainable agricultural production and global food security. Germination rate and germination index are important indicators of seed germination vigor, and the level of germination vigor of pea seeds directly affects their yield and quality. The traditional manual germination detection can hardly meet the demand of full-time sequence nondestructive detection. We propose YOLOv8-Peas, an improved YOLOv8-n based method for the detection of pea germination vigor. We constructed a pea germination dataset and used multiple data augmentation methods to improve the robustness of the model in real-world scenarios. By introducing the C2f-Ghost structure and depth-separable convolution, the model computational complexity is reduced and the model size is compressed. In addition, the original detector head is replaced by the self-designed PDetect detector head, which significantly improves the computational efficiency of the model. The Coordinate Attention (CA) mechanism is added to the backbone network to enhance the model's ability to localize and extract features from critical regions. The neck used a lightweight Content-Aware ReAssembly of FEatures (CARAFE) upsampling operator to capture and retain detailed features at low levels. The Adam optimizer is used to improve the model's learning ability in complex parameter spaces, thus improving the model's detection performance. The experimental results showed that the Params, FLOPs, and Weight Size of YOLOv8-Peas were 1.17M, 3.2G, and 2.7MB, respectively, which decreased by 61.2%, 61%, and 56.5% compared with the original YOLOv8-n. The mAP of YOLOv8-Peas was on par with that of YOLOv8-n, reaching 98.7%, and achieved a detection speed of 116.2FPS. We used PEG6000 to simulate different drought environments and YOLOv8-Peas to analyze and quantify the germination vigor of different genotypes of peas, and screened for the best drought-resistant pea varieties. Our model effectively reduces deployment costs, improves detection efficiency, and provides a scientific theoretical basis for drought-resistant genotype screening in pea.

Path Planning for Conformal Antenna Surface Detection Based on Improved Genetic Algorithm

The conformal antenna is a precision device installed on the wing of an aircraft, and its components are distributed on a curved surface. Quality detection is required after assembly. In solving the path planning problem for conformal antenna surface detection, the traditional genetic algorithm faces problems such as slow convergence and easily falling into a local optimal solution. To solve this problem, an improved genetic algorithm combining the historical optimal population (CHOP-IGA) is proposed. First, the algorithm uses the probability-based four-nearest-neighbor method to construct an initial population. Subsequently, the probabilities of the crossover and mutation operators are dynamically adjusted. Next, the algorithm applies the crossover and mutation operators to the population and performs mutation operations on each individual of the historical optimal population. Then, the fitness value is calculated and the next generation of individuals is selected from the parent, offspring, and historical optimal populations according to the elite selection strategy. Finally, the current best fitness is checked to determine whether updating the historical optimal population is necessary. When the termination condition is satisfied, the algorithm outputs the optimal result. Experiments showed that the algorithm satisfactorily solved the path planning problem for conformal antenna surface detection, with a 48.44% improvement in detection efficiency.

An improved dual-porosity dual-permeability modeling workflow for representing nonplanar hydraulic fractures

The Dual-Porosity Dual-Permeability (DPDK) model is commonly used for upscaling and simulating fractured reservoirs. However, many common upscaling approaches lead to disconnected fracture, particularly when simulating Discrete Fracture Networks (DFN) and nonplanar hydraulic fractures that are not aligned with the axes of corner-point grids supported by most reservoir simulation packages using the Two-Point Flux Approximation (TPFA) technique for flow and mass transfer calculations. This misalignment could result in inaccurate computed fluxes when fractures are disconnected in the upscaling process. Our previous works attempted to address this problem in DFNs by detecting misalignments and adjusting DPDK fracture parameters locally. However, such methods required explicit knowledge of the fracture coordinates. This paper introduces a novel approach based on area interpolation, which identifies disconnected fractures from fracture images without extracting fracture coordinates, significantly improving detection efficiency. This study primarily focuses on nonplanar fractures, aiming to simulate them using the DPDK model accurately. The simulations are compared with those obtained using the Embedded Discrete Fracture Model (EDFM). This work illustrates how nonplanar hydraulic fractures can be effectively simulated in a DPDK model. Our results demonstrate that the adjusted/corrected DPDK model can offer superior or comparable performance to an EDFM for simulating nonplanar fractures. The proposed method is flexible and readily applied in commercial simulation software.

A Spatial–Temporal Block-Matching Patch-Tensor Model for Infrared Small Moving Target Detection in Complex Scenes

Detecting infrared (IR) small moving targets in complex scenes quickly, accurately, and robustly remains a challenging problem in the current research field. To address this issue, this paper proposes a novel spatial–temporal block-matching patch-tensor (STBMPT) model based on a low-rank sparse decomposition (LRSD) framework. This model enhances the traditional infrared patch-tensor (IPT) model by incorporating joint spatial–temporal sampling to exploit inter-frame information and constructing a low-rank patch tensor using image block matching. Furthermore, a novel prior-weight calculation is introduced, utilizing the eigenvalues of the local structure tensor to suppress interference such as strong edges, corners, and point-like noise from the background. To improve detection efficiency, the tensor is constructed using a matching group instead of using a traditional sliding window. Finally, the background and target components are separated using the alternating direction method of multipliers (ADMM). Qualitative and quantitative experimental analysis in various scenes demonstrates the superior detection performance and efficiency of the proposed algorithm for detecting infrared small moving targets in complex scenes.

Anomaly Detection in Social-Aware IoT Networks

Anomaly event coverage is usually related to several attributes, among which the primary attribute dominates at the time of improving detection efficiency. In the case of Internet of Things (IoT) devices with complex social-aware relationships, IoT nodes with primary attributes should cooperate with each other through their social-aware interactions, to detect potential event anomalies and further determine the coverage of such anomalies. Existing research has put a lot of effort into designing IoT detection frameworks to discover anomalous sensor data, rarely caring about the social-aware interactions. This paper targets this important efficiency problem, and develops a novel anomaly detection mechanism in collaborative social-edge-cloud architecture. The focus of it is to first construct a vector space based Aggregation Behavior Comparison Detection Model, and quantify the change of monitoring behavior by defining the clustering threshold of vector space. This can quickly judge whether a local social network is abnormal and speed up the abnormal detection rate. If it is, a Social Behavior Correlation Detection Model is further designed based on the correlation of primary attributes derived from the dominating social-aware interaction behavior captured by (primary) edge nodes. This strategy can help detect specific “abnormal" areas managed by one or more edge devices with higher accuracy. In the process of anomaly detection, we also propose a spatial index tree to store the information of IoT nodes, so as to effectively collect and route the perceived data of IoT nodes for anomaly analysis. Experimental results demonstrate that our anomaly detection method promotes the detection efficiency and accuracy in comparison with the state of art’s techniques.

A Machine Learning Approach for Automated Detection of Critical PCB Flaws in Optical Sensing Systems

The circuit boards in the fields of optical sensors and optical devices require extremely high levels of precision and performance. For instance, applications such as fiber optic communication, optical computing, biomedical devices, and high-performance computing devices all necessitate meticulous optical components. Any minute defect on the circuit boards of these components has the potential to adversely impact the performance of the entire device. Traditional circuit defect detection methods require manual inspection, which is very labor-intensive and time-consuming. The defect detection method based on deep learning can automatically learn features and more accurately find defects in printed circuit boards, improve detection efficiency, and reduce the workload, bringing better economic and social benefits. Based on the popular YOLOv8 model, this paper uses the open-source circuit defect dataset, introduces Wise IoU, proposes the W–YOLOv8 model, and uses the gradient gain allocation strategy of a dynamic non-monotonic focusing mechanism to make the model focus on ordinary-quality anchor boxes, which improves the performance of the original model. Experimental data show that the mAP50 of W–YOLOv8 is 97.3%, which is 1.35% higher than that of YOLOv8, and the mAP50-95 is 55.4%, which is 3.94% higher than that of YOLOv8.

The influence of EEG channels and features significance on automatic detection of epileptic waves in MECT

Modified Electric Convulsive Therapy (MECT) is an efficacious physical therapy in treating mental disorders. The occurrence of epilepsy is a crucial benchmark for evaluating therapeutic effectiveness. However, the medical field still lacks relevant research on automatically detecting epileptic waves in MECT. Therefore, this article proposes a novel automatic detection method of epileptic waves in MECT. In this article, EEG local features (time, frequency, and time-frequency domains) and global features (Pearson correlation coefficient) are combined for epileptic wave detection with SVM (Support Vector Machine). We researched the system with 15 EEG detection channels. The dataset under investigation contains EEG data from 22 patients who received MECT and presented with epileptic seizures. The results revealed that LA (Logarithm of Activity) feature exhibits the best classification significance. When epileptic waves appear, there is a decrease in the power ratio of delta waves and an increase in the power ratio of theta waves. Additionally, the complexity of EEG decreases while the correlation between EEG channels increases. The Cz, F4, and P3 channels exhibit the highest classification significance among all EEG channels. Furthermore, based on the channel classification significance, the EEG detection channels number can be reduced to 8. Similarly, based on the feature classification significance, the local feature number can be reduced from 9 to 3. These conclusions can improve detection efficiency and reduce the cost for MECT. Moreover, the method we proposed can effectively detect epileptic waves in MECT. This work can provide physicians with a reference for evaluating the effectiveness of MECT.

Defect Recognition in Ballastless Track Structures Based on Distributed Acoustic Sensors

Defect recognition in ballastless track structures, based on distributed acoustic sensors (DASs), was researched in order to improve detection efficiency and ensure the safe operation of trains on high-speed railways. A line in southern China was selected, and equipment was installed and debugged to collect the signals of trains and events along it. Track vibration signals were extracted by identifying a train track, denoising, framing and labeling to build a defect dataset. Time–frequency-domain statistical features, wavelet packet energy spectra and the MFCCs of vibration signals were extracted to form a multi-dimensional vector. An XGBoost model was trained and its accuracy reached 89.34%. A time-domain residual network (ResNet) that would expand the receptive field and test the accuracies obtained from convolution kernels of different sizes was proposed, and its accuracy reached 94.82%. In conclusion, both methods showed a good performance with the built dataset. Additionally, the ResNet delivered more effective detection of DAS signals compared to conventional feature engineering methods.