Defect Detection of Industry Wood Veneer Based on NAS and Multi-Channel Mask R-CNN

Wood veneer defect detection plays a vital role in the wood veneer production industry. Studies on wood veneer defect detection usually focused on detection accuracy for industrial applications but ignored algorithm execution speed; thus, their methods do not meet the required speed of online detection. In this paper, a new detection method is proposed that achieves high accuracy and a suitable speed for online production. Firstly, 2838 wood veneer images were collected using data collection equipment developed in the laboratory and labeled by experienced workers from a wood company. Then, an integrated model, glance multiple channel mask region convolution neural network (R-CNN), was constructed to detect wood veneer defects, which included a glance network and a multiple channel mask R-CNN. Neural network architect search technology was used to automatically construct the glance network with the lowest number of floating-point operations to pick out potential defect images out of numerous original wood veneer images. A genetic algorithm was used to merge the intermediate features extracted by the glance network. Multi-Channel Mask R-CNN was then used to classify and locate the defects. The experimental results show that the proposed method achieves a 98.70% overall classification accuracy and a 95.31% mean average precision, and only 2.5 s was needed to detect a batch of 50 standard images and 50 defective images. Compared with other wood veneer defect detection methods, the proposed method is more accurate and faster.

Spectrophotometric Online Detection of Drinking Water Disinfectant: A Machine Learning Approach

The spectra fingerprint of drinking water from a water treatment plant (WTP) is characterised by a number of light-absorbing substances, including organic, nitrate, disinfectant, and particle or turbidity. Detection of disinfectant (monochloramine) can be better achieved by separating its spectra from the combined spectra. In this paper, two major focuses are (i) the separation of monochloramine spectra from the combined spectra and (ii) assessment of the application of the machine learning algorithm in real-time detection of monochloramine. The support vector regression (SVR) model was developed using multi-wavelength ultraviolet-visible (UV-Vis) absorbance spectra and online amperometric monochloramine residual measurement data. The performance of the SVR model was evaluated by using four different kernel functions. Results show that (i) particles or turbidity in water have a significant effect on UV-Vis spectral measurement and improved modelling accuracy is achieved by using particle compensated spectra; (ii) modelling performance is further improved by compensating the spectra for natural organic matter (NOM) and nitrate (NO₃) and (iii) the choice of kernel functions greatly affected the SVR performance, especially the radial basis function (RBF) appears to be the highest performing kernel function. The outcomes of this research suggest that disinfectant residual (monochloramine) can be measured in real time using the SVR algorithm with a precision level of ± 0.1 mg L⁻¹.

Cocaine Detection by a Laser-Induced Immunofluorometric Biosensor

The trafficking of illegal drugs by criminal networks at borders, harbors, or airports is an increasing issue for public health as these routes ensure the main supply of illegal drugs. The prevention of drug smuggling, including the installation of scanners and other analytical devices to detect small traces of drugs within a reasonable time frame, remains a challenge. The presented immunosensor is based on a monolithic affinity column with a large excess of immobilized hapten, which traps fluorescently labeled antibodies as long as the analyte cocaine is absent. In the presence of the drug, some binding sites of the antibody will be blocked, which leads to an immediate breakthrough of the labeled protein, detectable by highly sensitive laser-induced fluorescence with the help of a Peltier-cooled complementary metal-oxide-semiconductor (CMOS) camera. Liquid handling is performed with high-precision syringe pumps and microfluidic chip-based mixing devices and flow cells. The biosensor achieved limits of detection of 7 ppt (23 pM) of cocaine with a response time of 90 s and a total assay time below 3 min. With surface wipe sampling, the biosensor was able to detect 300 pg of cocaine. This immunosensor belongs to the most sensitive and fastest detectors for cocaine and offers near-continuous analyte measurement.

Online Detection of Watercore Apples by Vis/NIR Full-Transmittance Spectroscopy Coupled with ANOVA Method

Watercore is an internal physiological disorder affecting the quality and price of apples. Rapid and non-destructive detection of watercore is of great significance to improve the commercial value of apples. In this study, the visible and near infrared (Vis/NIR) full-transmittance spectroscopy combined with analysis of variance (ANOVA) method was used for online detection of watercore apples. At the speed of 0.5 m/s, the effects of three different orientations (O1, O2, and O3) on the discrimination results of watercore apples were evaluated, respectively. It was found that O3 orientation was the most suitable for detecting watercore apples. One-way ANOVA was used to select the characteristic wavelengths. The least squares-support vector machine (LS-SVM) model with two characteristic wavelengths obtained good performance with the success rates of 96.87% and 100% for watercore and healthy apples, respectively. In addition, full-spectrum data was also utilized to determine the optimal two-band ratio for the discrimination of watercore apples by ANOVA method. Study showed that the threshold discrimination model established based on O3 orientation had the same detection accuracy as the optimal LS-SVM model for samples in the prediction set. Overall, full-transmittance spectroscopy combined with the ANOVA method was feasible to online detect watercore apples, and the threshold discrimination model based on two-band ratio showed great potential for detection of watercore apples.

Research on Online Nondestructive Detection Technology of Duck Egg Origin Based on Visible/Near-Infrared Spectroscopy

As living standards rise, people have higher requirements for the quality of duck eggs. The quality of duck eggs is related to their origin. Thus, the origin traceability and identification of duck eggs are crucial for protecting the rights and interests of consumers and preserving food safety. As the world's largest producer and consumer of duck eggs, China's duck egg market suffers from a severe lack of duck egg traceability and rapid origin identification technology. As a result, a large number of duck eggs from other regions are sold as products from well-known brands, which seriously undermines the rights and interests of consumers and is not conducive to the sound development of the duck egg industry. To address the above issues, this study collected visible/near-infrared spectral data online from duck eggs of three distinct origins. To reduce noise in the spectral data, various pre-processing algorithms, including MSC, SNV, and SG, were employed to process the spectral data of duck eggs in the range of 400-1100 nm. Meanwhile, CARS and SPA were used to select feature variables that reflect the origin of duck eggs. Finally, classification models of duck egg origin were developed based on RF, SVM, and CNN, achieving the highest accuracy of 97.47%, 98.73%, and 100.00%, respectively. To promote the technology's implementation in the duck egg industry, an online sorting device was built for duck eggs, which mainly consists of a mechanical drive device, spectral software, and a control system. The online detection performance of the machine was validated using 90 duck eggs, and the final detection accuracy of the RF, SVM, and CNN models was 90%, 91.11%, and 94.44%, with a detection speed of 0.1 s, 0.3 s, and 0.5 s, respectively. These results indicate that visible/near-infrared spectroscopy can be exploited to realize rapid online detection of the origin of duck eggs, and the methodologies used in this study can be immediately implemented in production practice.

Online Detection of Fabric Defects Based on Improved CenterNet with Deformable Convolution

The traditional manual defect detection method has low efficiency and is time-consuming and laborious. To address this issue, this paper proposed an automatic detection framework for fabric defect detection, which consists of a hardware system and detection algorithm. For the efficient and high-quality acquisition of fabric images, an image acquisition assembly equipped with three sets of lights sources, eight cameras, and a mirror was developed. The image acquisition speed of the developed device is up to 65 m per minute of fabric. This study treats the problem of fabric defect detection as an object detection task in machine vision. Considering the real-time and precision requirements of detection, we improved some components of CenterNet to achieve efficient fabric defect detection, including the introduction of deformable convolution to adapt to different defect shapes and the introduction of i-FPN to adapt to defects of different sizes. Ablation studies demonstrate the effectiveness of our proposed improvements. The comparative experimental results show that our method achieves a satisfactory balance of accuracy and speed, which demonstrate the superiority of the proposed method. The maximum detection speed of the developed system can reach 37.3 m per minute, which can meet the real-time requirements.

Online and Offline Diagnosis of Motor Power Cables Based on 1D CNN and Periodic Burst Signal Injection

We introduce a new approach for online and offline soft fault diagnosis in motor power cables, utilizing periodic burst injection and nonintrusive capacitive coupling. We focus on diagnosing soft faults because local cable modifications or soft faults that occur without any indication while the cable is still operational can eventually develop into hard faults; furthermore, advance diagnosis of soft faults is more beneficial than the later diagnosis of hard faults, with respect to preventing catastrophic production stoppages. Both online and offline diagnoses with on-site diagnostic ability are needed because the equipment in the automated lines operates for 24 h per day, except during scheduled maintenance. A 1D CNN model was utilized to learn high-level features. The advantages of the proposed method are that (1) it is suitable for wiring harness cables in automated factories, where the installed cables are extremely short; (2) it can be simply and identically applied for both online and offline diagnoses and to a variety of cable types; and (3) the diagnosis model can be directly established from the raw signal, without manual feature extraction and prior domain knowledge. Experiments conducted with various fault scenarios demonstrate that this method can be applied to practical cable faults.

Online detection of class-imbalanced error-related potentials evoked by motor imagery

Objective.Error-related potentials (ErrPs) are spontaneous electroencephalogram signals related to the awareness of erroneous responses within brain domain. ErrPs-based correction mechanisms can be applied to motor imagery-brain-computer interface (MI-BCI) to prevent incorrect actions and ultimately improve the performance of the hybrid BCI. Many studies on ErrPs detection are mostly conducted under offline conditions with poor classification accuracy and the error rates of ErrPs are preset in advance, which is too ideal to apply in realistic applications. In order to solve these problems, a novel method based on adaptive autoregressive (AAR) model and common spatial pattern (CSP) is proposed for ErrPs feature extraction. In addition, an adaptive threshold classification method based spectral regression discriminant analysis (SRDA) is suggested for class-unbalanced ErrPs data to reduce the false positives and false negatives.Approach.As for ErrPs feature extraction, the AAR coefficients in the temporal domain and CSP in the spatial domain are fused. Given that the performance of different subjects' MI tasks is different but stable, and the samples of ErrPs are class-imbalanced, an adaptive threshold based SRDA is suggested for classification. Two datasets are used in this paper. The open public clinical neuroprosthetics and brain interaction (CNBI) dataset is used to validate the performance of the proposed feature extraction algorithm and the real-time data recorded in our self-designed system is used to validate the performance of the proposed classification algorithm under class-imbalanced situations. Different from the pseudo-random paradigm, the ErrPs signals collected in our experiments are all elicited by four-class of online MI-BCI tasks, and the sample distribution is more natural and suitable for practical tests.Main results.The experimental results on the CNBI dataset show that the average accuracy and false positive rate for ErrPs detection are 94.1% and 8.1%, which outperforms methods using features extracted from a single domain. What's more, although the ErrPs induction rate is affected by the performance of subjects' MI-BCI tasks, experimental results on data recorded in the self-designed system prove that the ErrPs classification algorithm based on an adaptive threshold is robust under different ErrPs data distributions. Compared with two other methods, the proposed algorithm has advantages in all three measures which are accuracy, F1-score and false positive rate. Finally, ErrPs detection results were used to prevent wrong actions in a MI-BCI experiment, and it leads to a reduction of the hybrid BCI error rate from 48.9% to 24.3% in online tests.Significance.Both the AAR-CSP fused feature extraction and the adaptive threshold based SRDA classification methods suggested in our work are efficient in improving the ErrPs detection accuracy and reducing the false positives. In addition, by introducing ErrPs to multi-class MI-BCIs, the MI decoding results can be corrected after ErrPs are detected to avoid executing wrong instructions, thereby improving the BCI accuracy and lays the foundation for using MI-BCIs in practical applications.

[Application progress on data-driven technologies in intelligent manufacturing of traditional Chinese medicine extraction]

The application of new-generation information technologies such as big data, the internet of things(IoT), and cloud computing in the traditional Chinese medicine(TCM)manufacturing industry is gradually deepening, driving the intelligent transformation and upgrading of the TCM industry. At the current stage, there are challenges in understanding the extraction process and its mechanisms in TCM. Online detection technology faces difficulties in making breakthroughs, and data throughout the entire production process is scattered, lacking valuable mining and utilization, which significantly hinders the intelligent upgrading of the TCM industry. Applying data-driven technologies in the process of TCM extraction can enhance the understanding of the extraction process, achieve precise control, and effectively improve the quality of TCM products. This article analyzed the technological bottlenecks in the production process of TCM extraction, summarized commonly used data-driven algorithms in the research and production control of extraction processes, and reviewed the progress in the application of data-driven technologies in the following five aspects: mechanism analysis of the extraction process, process development and optimization, online detection, process control, and production management. This article is expected to provide references for optimizing the extraction process and intelligent production of TCM.

The Number of Microbubbles Generated During Cardiopulmonary Bypass Can Be Estimated Using Machine Learning From Suction Flow Rate, Venous Reservoir Level, Perfusion Flow Rate, Hematocrit Level, and Blood Temperature

GOAL

Microbubbles (MBs) are known to occur within the circuits of cardiopulmonary bypass (CPB) systems, and higher-order dysfunction after cardiac surgery may be caused by MBs as well as atheroma dispersal associated with cannula insertion. As complete MB elimination is not possible, monitoring MB count rates is critical. We propose an online detection system with a neural network-based model to estimate MB count rate using five parameters: suction flow rate, venous reservoir level, perfusion flow rate, hematocrit level, and blood temperature.

METHODS

Perfusion experiments were performed using an actual CPB circuit, and MB count rates were measured using the five varying parameters.

RESULTS

Bland-Altman analysis indicated a high estimation accuracy (R2 > 0.95, p < 0.001) with no significant systematic error. In clinical practice, although the inclusion of clinical procedures slightly decreased the estimation accuracy, a high coefficient of determination for 30 clinical cases (R2 = 0.8576) was achieved between measured and estimated MB count rates.

CONCLUSIONS

Our results highlight the potential of this system to improve patient outcomes and reduce MB-associated complication risk.

Full-surface defect detection of navel orange based on hyperspectral online sorting technology

The whole-surface hyperspectral image acquisition of navel orange is particularly important for surface defect detection and quality classification. Because the light intensity at the edge of the navel orange is lower than that in the middle, the defects on the surface of the navel orange cannot be effectively identified. In this paper, a hyperspectral online sorting device for the whole-surface defects of navel orange is proposed. First of all, the image data of navel orange is collected by online detection sorting equipment and the spectral image of the characteristic wave peak of 1655.72 nm was extracted. Then, the light intensity at the edge of the navel orange is enhanced by nonuniformity correction based on quadratic curve fitting, and the light intensity correction of the navel orange is realized. Finally, the corrected image is segmented by the threshold to obtain surface defects, and the number of surface defect pixels is improved effectively compared with that before light intensity correction. Ultimately, the online sorting test is carried out, and the detection accuracy is 100%. This indicates that this method effectively improves the sensitivity of defect detection. At the same time, the dimensionality reduction of hyperspectral data is also carried out, which is conducive to improving the efficiency of online detection.

Moisture content online detection system based on multi-sensor fusion and convolutional neural network

To monitor the moisture content of agricultural products in the drying process in real time, this study applied a model combining multi-sensor fusion and convolutional neural network (CNN) to moisture content online detection. This study built a multi-sensor data acquisition platform and established a CNN prediction model with the raw monitoring data of load sensor, air velocity sensor, temperature sensor, and the tray position as input and the weight of the material as output. The model's predictive performance was compared with that of the linear partial least squares regression (PLSR) and nonlinear support vector machine (SVM) models. A moisture content online detection system was established based on this model. Results of the model performance comparison showed that the CNN prediction model had the optimal prediction effect, with the determination coefficient (R2) and root mean square error (RMSE) of 0.9989 and 6.9, respectively, which were significantly better than those of the other two models. Results of validation experiments showed that the detection system met the requirements of moisture content online detection in the drying process of agricultural products. The R2 and RMSE were 0.9901 and 1.47, respectively, indicating the good performance of the model combining multi-sensor fusion and CNN in moisture content online detection for agricultural products in the drying process. The moisture content online detection system established in this study is of great significance for researching new drying processes and realizing the intelligent development of drying equipment. It also provides a reference for online detection of other indexes in the drying process of agricultural products.

The Design and Experimentation of a Corn Moisture Detection Device Based on Double Capacitors

Detecting the moisture content of grain accurately and rapidly has important significance for harvesting, transport, storage, processing, and precision agriculture. There are some problems with the slow detection speeds, unstable detection, and low detection accuracy of moisture contents in corn harvesters. In that case, an online moisture detection device was designed, which is based on double capacitors. A new method of capacitance complementation and integration was proposed to eliminate the limitation of single data. The device is composed of a sampling mechanism and a double-capacitor sensor consisting of a flatbed capacitor and a cylindrical capacitor. The optimum structure size of the capacitor plates was determined by simulation optimization. In addition to this, the detection system with software and hardware was developed to estimate the moisture content. Indoor dynamic measurement tests were carried out to analyze the influence of temperature and porosity. Based on the influencing factors and capacitance, a model was established to estimate the moisture content. Finally, the support vector machine (SVM) regressions between the capacitance and moisture content were built up so that the R2 values were more than 0.91. In the stability test, the standard deviation of the stability test was 1.09%, and the maximum relative error of the measurement accuracy test was 1.22%. In the dynamic verification test, the maximum error of the measurement was 4.62%, less than 5%. It provides a measurement method for the accurate, rapid, and stable detection of the moisture content of corn and other grains.

Determination of soluble solids content of multiple varieties of tomatoes by full transmission visible-near infrared spectroscopy

Introduction

Soluble solids content (SSC) is a pivotal parameter for assessing tomato quality. Traditional measurement methods are both destructive and time-consuming.

Methods

To enhance accuracy and efficiency in SSC assessment, this study employs full transmission visible and near-infrared (Vis-NIR) spectroscopy and multi-point spectral data collection techniques to quantitatively analyze SSC in two tomato varieties ('Provence' and 'Jingcai No.8' tomatoes). Preprocessing of the multi-point spectra is carried out using a weighted averaging approach, aimed at noise reduction, signal-to-noise ratio improvement, and overall data quality enhancement. Taking into account the potential influence of various detection orientations and preprocessing methods on model outcomes, we investigate the combination of partial least squares regression (PLSR) with two orientations (O1 and O2) and two preprocessing techniques (Savitzky-Golay smoothing (SG) and Standard Normal Variate transformation (SNV)) in the development of SSC prediction models.

Results

The model achieved the best results in the O2 orientation and SNV pretreatment as follows: 'Provence' tomato (Rp = 0.81, RMSEP = 0.69°Brix) and 'Jingcai No.8' tomatoes (Rp = 0.84, RMSEP = 0.64°Brix). To further optimize the model, characteristic wavelength selection is introduced through Least Angle Regression (LARS) with L1 and L2 regularization. Notably, when λ=0.004, LARS-L1 produces superior results ('Provence' tomato: Rp = 0.95, RMSEP = 0.35°Brix; 'Jingcai No.8' tomato: Rp = 0.96, RMSEP = 0.33°Brix).

Discussion

This study underscores the effectiveness of full transmission Vis-NIR spectroscopy in predicting SSC in different tomato varieties, offering a viable method for accurate and swift SSC assessment in tomatoes.

Detection of soluble solids content in tomatoes using full transmission Vis-NIR spectroscopy and combinatorial algorithms

Introduction

Soluble solids content (SSC) is an important indicator for evaluating tomato flavor, and general physical and chemical methods are time-consuming and destructive.

Methods

This study utilized full transmittance visible and near infrared (Vis-NIR) spectroscopy for multi-posed data acquisition of tomatoes in different orientations. The role of two directions (Z1 and Z2) and four preprocessing techniques, as well as three wavelength selection methods in the exploitation of SSC regression models was investigated.

Results

After using the Outlier elimination method, the spectra acquired in the Z2 direction and the raw spectral data processed by preprocessing methods gave the best result by the PLSR model (Rp = 0.877, RMSEP = 0.417 %). Compared to the model built using the full 2048 spectral wavelengths, the prediction accuracy using 20 wavelengths obtained by a combination wavelength selection: backward variable selection - partial least squares and simulated annealing (BVS-PLS and SA) was further improved (Rp = 0.912, RMSEP = 0.354 %).

Discussion

The findings of this research demonstrate the efficacy of full-transmission visible-near infrared (Vis-NIR) spectroscopy in forecasting SSC of tomatoes, and most importantly, the combination of the packing method in wavelength selection with an intelligent optimization algorithm provides a viable idea for accurately and rapidly assessing the SSC of tomatoes.

Advances in Online Detection Technology for Laser Additive Manufacturing: A Review

In additive manufacturing (AM), the mechanical properties of manufactured parts are often insufficient due to complex defects and residual stresses, limiting their use in high-value or mission-critical applications. Therefore, the research and application of nondestructive testing (NDT) technologies to identify defects in AM are becoming increasingly urgent. This article reviews the recent progress in online detection technologies in AM, a special introduction to the high-speed synchrotron X-ray technology for real-time in situ observation, and analysis of defect formation processes in the past 5 years, and also discusses the latest research efforts involving process monitoring and feedback control algorithms. The formation mechanism of different defects and the influence of process parameters on defect formation, important parameters such as defect spatial resolution, detection speed, and scope of application of common NDT methods, and the defect types, advantages, and disadvantages associated with current online detection methods for monitoring three-dimensional printing processes are summarized. In response to the development requirements of AM technology, the most promising trends in online detection are also prospected. This review aims to serve as a reference and guidance for the work to identify/select the most suitable measurement methods and corresponding control strategy for online detection.

Optimization of Online Soluble Solids Content Detection Models for Apple Whole Fruit with Different Mode Spectra Combined with Spectral Correction and Model Fusion

Soluble solids content (SSC) is one of the main quality indicators of apples, and it is important to improve the precision of online SSC detection of whole apple fruit. Therefore, the spectral pre-processing method of spectral-to-spectral ratio (S/S), as well as multiple characteristic wavelength member model fusion (MCMF) and characteristic wavelength and non-characteristic wavelength member model fusion (CNCMF) methods, were proposed for improving the detection performance of apple whole fruit SSC by diffuse reflection (DR), diffuse transmission (DT) and full transmission (FT) spectra. The modeling analysis showed that the S/S- partial least squares regression models for all three mode spectra had high prediction performance. After competitive adaptive reweighted sampling characteristic wavelength screening, the prediction performance of all three model spectra was improved. The particle swarm optimization-extreme learning machine models of MCMF and CNCMF had the most significant enhancement effect and could make all three mode spectra have high prediction performance. DR, DT, and FT spectra all had some prediction ability for apple whole fruit SSC, with FT spectra having the strongest prediction ability, followed by DT spectra. This study is of great significance and value for improving the accuracy of the online detection model of apple whole fruit SSC.

Raman and Surface-Enhanced Raman Scattering Detection in Flowing Solutions for Complex Mixture Analysis

Raman scattering provides a chemical-specific and label-free method for identifying and quantifying molecules in flowing solutions. This review provides a comprehensive examination of the application of Raman spectroscopy and surface-enhanced Raman scattering (SERS) to flowing liquid samples. We summarize developments in online and at-line detection using Raman and SERS analysis, including the design of microfluidic devices, the development of unique SERS substrates, novel sampling interfaces, and coupling these approaches to fluid-based chemical separations (e.g., chromatography and electrophoresis). The article highlights the challenges and limitations associated with these techniques and provides examples of their applications in a variety of fields, including chemistry, biology, and environmental science. Overall, this review demonstrates the utility of Raman and SERS for analysis of complex mixtures and highlights the potential for further development and optimization of these techniques.

Rapid online plant leaf area change detection with high-throughput plant image data

High-throughput plant phenotyping (HTPP) has become an emerging technique to study plant traits due to its fast, labor-saving, accurate and non-destructive nature. It has wide applications in plant breeding and crop management. However, the resulting massive image data has raised a challenge associated with efficient plant traits prediction and anomaly detection. In this paper, we propose a two-step image-based online detection framework for monitoring and quick change detection of the individual plant leaf area via real-time imaging data. Our proposed method is able to achieve a smaller detection delay compared with some baseline methods under some predefined false alarm rate constraint. Moreover, it does not need to store all past image information and can be implemented in real time. The efficiency of the proposed framework is validated by a real data analysis.

Efficient online detection device and method for cottonseed breakage based on Light-YOLO

High-quality cottonseed is essential for successful cotton production. The integrity of cottonseed hulls plays a pivotal role in fostering the germination and growth of cotton plants. Consequently, it is crucial to eliminate broken cottonseeds before the cotton planting process. Regrettably, there is a lack of rapid and cost-effective methods for detecting broken cottonseed at this critical stage. To address this issue, this study developed a dual-camera system for acquiring front and back images of multiple cottonseeds. Based on this system, we designed the hardware, software, and control systems required for the online detection of cottonseed breakage. Moreover, to enhance the performance of cottonseed breakage detection, we improved the backbone and YOLO head of YOLOV8m by incorporating MobileOne-block and GhostConv, resulting in Light-YOLO. Light-YOLO achieved detection metrics of 93.8% precision, 97.2% recall, 98.9% mAP50, and 96.1% accuracy for detecting cottonseed breakage, with a compact model size of 41.3 MB. In comparison, YOLOV8m reported metrics of 93.7% precision, 95.0% recall, 99.0% mAP50, and 95.2% accuracy, with a larger model size of 49.6 MB. To further validate the performance of the online detection device and Light-YOLO, this study conducted an online validation experiment, which resulted in a detection accuracy of 86.7% for cottonseed breakage information. The results demonstrate that Light-YOLO exhibits superior detection performance and faster speed compared to YOLOV8m, confirming the feasibility of the online detection technology proposed in this study. This technology provides an effective method for sorting broken cottonseeds.