Technical Basis Research Articles

Transcriptome-Wide Identification and Integrated Analysis of a UGT Gene Involved in Ginsenoside Ro Biosynthesis in Panax ginseng.

Panax ginseng as a traditional medicinal plant with a long history of medicinal use. Ginsenoside Ro is the only oleanane-type ginsenoside in ginseng, and has various pharmacological activities, including anti-inflammatory, detoxification, and antithrombotic activities. UDP-dependent glycosyltransferase (UGT) plays a key role in the synthesis of ginsenoside, and the excavation of UGT genes involved in the biosynthesis of ginsenoside Ro has great significance in enriching ginsenoside genetic resources and further revealing the synthesis mechanism of ginsenoside. In this work, ginsenoside-Ro-synthesis-related genes were mined using the P. ginseng reference-free transcriptome database. Fourteen hub transcripts were identified by differential expression analysis and weighted gene co-expression network analysis. Phylogenetic and synteny block analyses of PgUGAT252645, a UGT transcript among the hub transcripts, showed that PgUGAT252645 belonged to the UGT73 subfamily and was relatively conserved in ginseng plants. Functional analysis showed that PgUGAT252645 encodes a glucuronosyltransferase that catalyzes the glucuronide modification of the C3 position of oleanolic acid using uridine diphosphate glucuronide as the substrate. Furthermore, the mutation at 622 bp of its open reading frame resulted in amino acid substitutions that may significantly affect the catalytic activity of the enzyme, and, as a consequence, affect the biosynthesis of ginsenoside Ro. Results of the in vitro enzyme activity assay of the heterologous expression product in E. coli of PgUGAT252645 verified the above analyses. The function of PgUGAT252645 was further verified by the result that its overexpression in ginseng adventitious roots significantly increased the content of ginsenoside Ro. The present work identified a new UGT gene involved in the biosynthesis of ginsenoside Ro, which not only enriches the functional genes in the ginsenoside synthesis pathway, but also provides the technical basis and theoretical basis for the in-depth excavation of ginsenoside-synthesis-related genes.

Study on Dynamic Coupling Behavior of End-Meshing Harmonic Reducers

To study the coupling mechanism and dynamic responses of an end-face-movable gear transmission system under complex excitation, a specific configuration of end-meshing, movable-gear reduction mechanism was used to achieve predetermined rigid-thrust-transmission and mismatched-gear-meshing functions, which solved the inherent defects of traditional harmonic gear mechanisms of thin-wall-flexible wheels that are easily damaged by fatigue. Considering the phenomenon of elastic deformation of live teeth that is accompanied by significant changes in meshing characteristics in the transmission process of an end-meshing harmonic reducer, the influences of dynamic meshing parameters, live tooth deformation, time-varying stiffness of tooth meshing, and time-varying backlash on nonlinear dynamic performance were explored, as well as the mechanisms of multi-parameter coupling effects on transmission performance. The nonlinear dynamics model of the end-meshing harmonic reducer was established to solve the chattering prediction problem. Finally, a comprehensive test bed for the transmission system of a harmonic reducer with a meshing type with an adjustable-characteristic end was built to verify the correctness of the theoretical model and provide the theoretical and technical basis for exploring the optimal parameter selection to address the passive vibration-suppression problem.

Evaluation on model-driven knowledge graph and platform for grid operation and maintenance

With the continuous expansion of the power grid, the forms of faults are becoming increasingly complex, with a wide range of impacts and long maintenance cycles, posing increasingly severe challenges for power grid operators. In the current power system (PS), due to system limitations, there is a large amount of data, and the current computing system is limited by hardware and computing power, making it difficult to satisfy the requirements of real-time computing, comprehensive analysis, and expansion. This paper analyzed the technical basis of the knowledge graph (KG) of power grid operation and maintenance (O&M), and clarified the key role of model driving in the current large-scale smart grid (SG), which can effectively improve the efficiency and reliability of data processing in the SG. This paper also analyzed the model-driven PG O&M KG platform, and analyzed the role of particle swarm optimization (PSO) algorithm in PG operation and fault maintenance. After applying the PSO algorithm in this article, in the experimental results section, the fault rate of Transformer 5 was 2.1% lower than that of Transformer 4. The knowledge mapping model of grid O&M and the particle swarm algorithm in this paper can significantly reduce the failure rate of the grid, which has wide extension value.

Study on the implementation effect evaluation of Specifications of Air Sampling for Hazardous Substances Monitoring in the Workplace (GBZ 159-2004)

Systematically evaluate the implementation of Specifications of Air Sampling for Hazardous Substances Monitoring (GBZ 159-2004) , so as to provide technical basis for the future standard revision. The semi-structured interview method was used to interview the industry experts from centers for disease control and prevention, occupational disease prevention and control hospitals/institutes, employers, third-party technical service institutions and universities, and the induction method was used to refine the topics and relevant suggestions. Some technical indicators of GBZ 159 are not suitable for the current actual work of occupational health, and need to be revised and improved urgently. The revised GBZ 159 should comply with the current situation of China's industrial development and the development of occupational health testing equipment in the new era, and improve the relevant technical requirements of sampling quality control.

Characterization and classification of EEG signals evoked by different CAD models

AbstractThe past two decades have witnessed dramatic advancement in computer‐aided design (CAD). However, development of human–computer interfaces (HCI) for CAD have not kept up with these advances. Windows, Icons, Menus, Pointer (WIMP) is still the mainly used interface for CAD applications which limits the naturalness and intuitiveness of the CAD modeling process. As a novel interface, Brain–computer interfaces (BCIs) have great potential in the application of CAD modeling. Utilizing BCIs, the user can create CAD models just by thinking about it in principle, because BCIs provide an end‐to‐end interaction channel between users and CAD models. However, current related studies are mainly limited to the existing BCIs paradigms, while ignoring the relationship between electroencephalogram (EEG) signals and CAD models, which largely increases the cognitive load on the users. In this study, we aimed to explore the potential of using BCI to create CAD models directly independent of the classical BCIs paradigms. For this purpose, EEG signals evoked by six basic CAD models (i.e., point, square, trapezoid, line, triangle, and circle) were collected from 28 participants. After preprocessing and sub‐trial principal components analysis (st‐PCA) of recorded data, the peak, mean and time‐frequency energy features were extracted from EEG signals. By applying the one‐way repeated measures analysis of variance, we demonstrated that there were significant differences among these EEG features evoked by different CAD models. These features from EEG electrode channels ranked by mutual information were then used to train a discriminant classifier of genetic algorithm‐based support vector machine. The empirical result showed that this classifier can discriminate the CAD models with an average accuracy of about 72%, which turns out that EEG based model generation is feasible, and provides the technical and theoretical basis for building a novel BCI for CAD modeling.

RETRACTED ARTICLE: Preliminary risk assessment of in-vessel leakage accident in ITER

The ITER project is one of the largest international cooperative scientific projects in the world, aiming to verify the feasibility of magnetic confinement controlled nuclear fusion technology and provide a technical basis for the subsequent construction of fusion energy power stations. The success or failure of ITER will greatly affect the commercialization process of fusion energy. The probabilistic safety assessment (PSA) was a powerful means to evaluate the risk and reliability of nuclear facility and achieved great success in safety assessment of fission power plants. Based on this, the PSA progress for ITER was proposed in this paper. And the in-vessel leakage accident was investigated to verify the effectiveness of proposed method. The result shows the maximum possible radiological consequences of ITER in-vessel leakage accident of ITER is 1.6E−3 mSv, and the frequencies of this consequence is 1.63E−8/year. The reason of this consequence was also discussed in this paper. Those result could provide some valuable reference for radiation risk assessment and safety supervision of fusion commercial reactor in the nuclear future.

Research on variable universe fuzzy PID control for semi-active suspension with CDC dampers based on dynamic adjustment functions

The vehicle suspension system is a complex system with multiple variables, nonlinearity and time-varying characteristics, and the traditional variable universe fuzzy PID control algorithm has the problems of over-reliance on expert experience and non-adaptive adjustment of the contracting-expanding factor parameters, which make it difficult to achieve a better control effect. In this paper, the system error e(t) and its change rate ec(t) are introduced into the contracting-expanding factor as dynamic parameters to realize the adaptive adjustment of the contracting-expanding factor parameters, and propose a variable universe fuzzy PID control based on dynamic adjustment functions (VUFP-DAF), which uses the real-time contracting-expanding factor to realize the adaptive adjustment of the fuzzy universe, so as to improve the ride comfort of vehicles. The research results show that the proposed VUFP-DAF has strong adaptability and can effectively improve the ride comfort and handling stability of vehicles under different speeds and road excitations, providing a certain technical basis for the development of the semi-active suspension system.

A Study on the Thermal Behavior of Series and Parallel Connection Methods in the Process of Hydrogenation of Ship-Borne Hydrogen Storage Cylinder

As a subdivision of the hydrogen energy application field, ship-borne hydrogen fuel cell systems have certain differences from vehicle or other application scenarios in terms of their structural type, safety, environmental adaptability, and test verification. The connection method of the ship-borne hydrogen storage cylinder (SHSC) is very important for the hydrogen fuel cell ship, and the structural parameters of the SHSC are particularly important in the hydrogen refueling process. To ensure the safe and reliable operation of the hydrogen-powered ship, research on the filling of the SHSC under different connection modes was carried out during refueling. In our study, a thermal flow physical model of the SHSC was established to research the hydrogen refueling process of the series and parallel SHSCs. The influence of series and parallel modes of the SHSCs on the hydrogen refueling process was explored, and the evolution law of the internal flow field, pressure, and temperature of series and parallel SHSCs under different filling parameters was analyzed by numerical simulation. Our results confirmed the superiority of the parallel modular approach in terms of thermal safety during refueling. The results can supply a technical basis for the future development of hydrogen refueling stations and ship-board hydrogenation control algorithms.

Molecular Characterization of Plant Volatile Compound Interactions with Cnaphalocrocis medinalis Odorant-Binding Proteins.

Odorant-binding proteins (OBPs) play important roles in the insect olfactory system since they bind external odor molecules to trigger insect olfactory responses. Previous studies have identified some plant-derived volatiles that attract the pervasive insect pest Cnaphalocrocis medinalis (Lepidoptera: Pyralidae), such as phenylacetaldehyde, benzyl acetate, 1-heptanol, and hexanal. To characterize the roles of CmedOBPs in the recognition of these four volatiles, we analyzed the binding abilities of selected CmedOBPs to each of the four compounds, as well as the expression patterns of CmedOBPs in different developmental stages of C. medinalis adult. Antennaes of C. medinalis adults were sensitive to the studied plant volatile combinations. Expression levels of multiple CmedOBPs were significantly increased in the antennae of 2-day-old adults after exposure to volatiles. CmedOBP1, CmedOBP6, CmedPBP1, CmedPBP2, and CmedGOBP2 were significantly up-regulated in the antennae of volatile-stimulated female and male adults when compared to untreated controls. Fluorescence competition assays confirmed that CmedOBP1 could strongly bind 1-heptanol, hexanal, and phenylacetaldehyde; CmedOBP15 strongly bound benzyl acetate and phenylacetaldehyde; and CmedOBP26 could weakly bind 1-heptanol. This study lays a theoretical foundation for further analysis of the mechanisms by which plant volatiles can attract C. medinalis. It also provides a technical basis for the future development of efficient plant volatile attractants of C. medinalis.

Algorithmic implementation and optimisation of path planning

Path planning algorithms are widely used in the fields of robotics and robotic arms, unmanned devices, automatic navigation, etc., and are an important technical basis for promoting the development of automation as well as the popularisation of artificial intelligence technology. This paper will briefly introduce various path planning algorithms implemented by mathematical models or inspired by biological features or genetics from the aspects of geometric search algorithms, intelligent search algorithms, artificial intelligence algorithms, and hybrid algorithms, including the characteristics, advantages and disadvantages, and important improvements of typical path planning algorithms as well as hybrid algorithms which are made by imitating and improving each other of several algorithms. Meanwhile, the development trend of path planning algorithms is also summarised, and the outlook of its development is made to provide reference for related fields.

Technical aspects and innovations in non-invasive and invasive ventilation

Non-invasive and invasive ventilation have become essential for therapy in acute and chronic respiratory failure. More than one-third of patients in intensive care units receive invasive ventilation, and the number of ventilated patients in out-of-hospital care is also steadily increasing. While normalization of blood gases was considered the most significant goal in past decades, and the idea that mechanical ventilation also poses dangers played little role, the dominant thought at present is the application of ventilation from the most protective point of view possible. Because fundamental change in equipment technology is likely to be difficult, improvement of protective ventilation and further development of understanding of pathophysiologic processes in acute and chronic respiratory failure will continue to be of great importance in the future. This article summarizes different aspects of the technical basis of noninvasive and invasive ventilation and their practical implementation.

Experimental investigation of seismic behavior of precast pier‐footing socket connection with different design parameters

AbstractAccelerated bridge construction, with innovative connection details and construction technologies, has been extensively investigated and put into practical application for years. Nowadays, there are three commonly used connection methods of accelerated bridge construction technology, namely, lap‐spliced connection, sleeve connection, and socket connection. Due to the convenience of construction and lower requirements of construction accuracy, the socket connection is more suitable for reconstruction and expansion projects of traffic infrastructure, which could minimize the impact on traffic and accelerate construction progress. According to the structural characteristics of the socket connection, there are some design parameters that may significantly affect the seismic resistance of the structure, such as socket embedment length, fabrication of the shear key, and grouting material strength. To fully study the influence of different design parameters on structural performance, an experiment was carried out to investigate the seismic behavior of the precast pier‐footing socket connections with different design parameters. Five 1:2 scale reinforced concrete precast pier‐footing socket connection specimens with different design parameters were designed and tested under cyclically reversed horizontal loads. The development of hysteresis features, failure mode, load‐bearing capacity, stiffness degradation, structural ductility, energy dissipation capacity, and residual drift are analyzed to reveal the influence of the different design parameters on the seismic behavior of the precast pier‐footing socket connection. The seismic behavior of the precast pier‐footing socket connection was significantly influenced by the embedment length especially when the embedment length was less than 1.0bc. When the embedment length was 0.5bc, the failure mode changed from bending damage at the bottom of the precast pier to the anchorage failure of the precast pier‐footing socket connection. When the embedment length was 1.5bc, the fabrication of the shear key had limited improvement on the seismic performance of the specimen, while reducing the ductility of the specimen. When the embedment length was 1.0bc, the grouting material with a strength grade of C60 could be used in the socket connection between the precast pier and footing. The research presented in this paper provides some design suggestions and a technical basis for evaluating the seismic behavior of precast pier‐footing structures with socket connection.

Extraction and Chemical Composition Analyses of Intracellular and Extracellular Polysaccharides from Trametes lactinea Liquid Fermentation

Trametes lactinea is a macrofungus commonly found on broadleaf tree felling piles with rich bioactivity, and its main active substances are polysaccharides, which have a certain medicinal value. Few studies have been conducted on the simultaneous study of intracellular and extracellular polysaccharides of fermented mycelia in liquid culture. In this study, T. lactinea collected from Eucalyptus stumps was subjected to liquid fermentation culturing and the extraction of intracellular and extracellular polysaccharides from the mycelium was optimized using unidirectional and orthogonal test methods. The intracellular and extracellular crude polysaccharides were isolated and purified, and polysaccharide fractions were obtained and assayed for their chemical composition. The main findings of this study are as follows: (1) The optimal conditions for the extraction of intracellular polysaccharides from T. lactinea mycelium were a material–liquid ratio of 1:40, an extraction temperature of 100 °C, a time of 5 h, and four repeats, wherein the polysaccharide extraction rate reached 5.1%. The optimal extraction conditions for the extracellular polysaccharides were a concentration ratio of 5:1, a concentration temperature of 70 °C, an ethanol concentration of 100.0%, and an alcohol settling time of 12 h. The polysaccharides could thus be extracted up to 0.63 mg/mL. (2) The intracellular and extracellular crude polysaccharides of T. lactinea mycelium were successfully isolated and purified, resulting in three homogeneous fractions of intracellular polysaccharides (IP-1, IP-2, and IP-3) and two homogeneous fractions of extracellular polysaccharides (EP-1 and EP-2). (3) The polysaccharide chemical composition resulted in the highest total sugar content of EP-1. IP-3 had the highest uronic acid content. The results of the monosaccharide composition analysis showed that the mycelial intracellular polysaccharides IP-1, IP-2, and IP-3 were all highest in glucose. Both IP-2 and IP-3 contained guluronic acid and glucuronic acid. Mannose was the most abundant extracellular polysaccharide in both EP-1 and EP-2. This study provides theoretical and technical bases for the comprehensive development and utilization of T. lactinea polysaccharides.

Prediction of Sucker Rod-tubing Wear Depth in Surface Drive Screw Pump Production Wells

With the wide application of ground drive screw pump in the process of oil production, the wear problem of screw pump sucker rod-tubing is becoming more and more prominent. In order to systematically study the wear of the rod and tube of the screw pump production well and quantify the wear of the rod and tube, this paper establishes a calculation model of the contact force of the screw pump sucker rod by analyzing the force of the rod and tube string in the three-dimensional wellbore trajectory. Based on the indoor rod and tube wear simulation experiment, combined with the wear efficiency theory, a prediction model of sucker rod-tubing wear under different working conditions was established, and an example well calculation was carried out. The results show that the force of sucker rod is mainly affected by sucker rod size, submergence degree and other factors, and the wear of sucker rod and tubing is mainly affected by working time, rotational speed and wear efficiency. The research results can not only accurately carry out accurate quantitative calculation of downhole rod and tube wear, but also provide theoretical and technical basis for prediction of rod and tube wear depth.

Large dynamic range stellar radiation simulation optical system

For the current stellar spectral simulation can not realize the stellar color temperature information with large dynamic range simulation, this paper proposes a broad spectrum high-resolution subdivision and spatial beam zoning modulation combined with a large dynamic range of stellar radiation information simulation method, designed a kind of imaging and non-imaging stellar radiation information simulation optical system, using an optical system to achieve multi-color temperature spectrum and large dynamic range stellar simulation. The experimental results show that the designed system can simultaneously achieve the spectral simulation accuracy (single point evaluation) better than ± 7% in the range of spectral 450–1000 nm and color temperature 3000–11,000 K; on the premise of ensuring the spectral simulation accuracy, the magnitude simulation range reaches 0 to + 12 Mv, and the magnitude simulation accuracy is better than ± 0.05 Mv; Accurate simulation of stellar spectral information and energy large dynamic range tuning is realized, and the system is extended. The system function has been extended to realize the switching of broadband and narrowband modes, The half-peak width of the narrowband output beam is better than 4.1 nm, which extends the application of the spectral simulation technology and provides the theoretical and technical basis for the ground calibration of the development of the high-precision stellar radiation information ground simulation system.

Integrated characterization of filler tobacco leaves: HS–SPME–GC–MS, E-nose, and microbiome analysis across different origins

This study delves into the aroma characteristics and microbial composition of filler tobacco leaves (FTLs) sourced from six distinct cigar-growing regions within Yunnan, China, following standardized fermentation. An integrated approach using gas chromatography-mass spectrometry (GC–MS), electronic nose (E-nose), and microbiome analysis was employed for comprehensive profiling. Results derived from Linear Discriminant Analysis (LDA) using E-nose data confirmed the presence of notable variability in flavor substance profiles among the FTLs from six regions. Additionally, GC–MS was used to discern disparities in volatile organic compound (VOC) distribution across FTLs from these regions, identifying 92, 81, 79, 58, 69, and 92 VOCs within each respective sample set. Significantly, 24 VOCs emerged as pivotal determinants contributing to the heterogeneity of flavor profiles among FTLs from diverse origins, as indicated by Variable Importance for the Projection (VIP) analysis. Furthermore, distinctions in free amino acid content and chemical constituents were observed across FTLs. Of noteworthy significance, solanone, isophorone, durene, (-)-alpha-terpineol, and 2,3'-bipyridine exhibited the strongest correlations with microbiome data, with fungal microorganisms exerting a more pronounced influence on metabolites, as elucidated through two-way orthogonal partial least-squares (O2PLS) modeling. These findings provide a theoretical and technical basis for accurately evaluating the synchronization of FTLs in aromas and fermentation processes, and they will enhance the quality of fermented FTLs and foster the growth of the domestic cigar tobacco industry ultimately.Graphical

Simultaneous determination of 14 analgesics in postoperative analgesic solution by HPLC–DAD and LC–MS/MS

A green, efficient, sensitive and accurate detection method by HPLC–DAD and LC–MS/MS was developed and validated for the quantification of morphine, hydromorphone, oxycodone, ketamine tramadol, dezocine, ropivacaine, remifentanil, butorphanol, bupivacaine, droperidol, fentanyl, lornoxicam and sufentanil. The 14 mixtures were chromatographed via HPLC–DAD method which employed 0.05 mol/L potassium dihydrogen phosphate solution-acetonitrile as the mobile phase, the analytes were gradient elution on a SinoChrom ODS-BP C18 column with a total separation time of 35 min, and 14 mixtures showed a good linear relationship in the linear range. The Limit of Quantitation (LOQ) ranged from 0.10 to 20.0 µg/mL, the inter-day and intra-day precision of each analyte is within 1.1–2.0% and 0.4–1.3%, and the average absolute recovery of all compounds was above 98%. The LC–MS/MS method was used to successfully separate the 14 mixtures within 10 min which employed 0.1% formic acid-acetonitrile as the mobile phase, the analytes were gradient elution on a ACQUITY UPLC-BEH C18 column with a total separation time of 13 min, and 14 mixtures showed a good linear relationship in the linear range. The LOQ ranged from 0.005 to 0.2 ng/mL, the inter-day and intra-day precision of each analyte is within 1.2–4.1% and 0.6–3.3%, and the average absolute recovery of all compounds was above 93%. The proposed method has been successfully applied in the clinic and provides a strong technical basis for the quantitative detection of these 14 mixtures for detecting drug abuse, and for studying the stability and compatibility of analgesic solutions. The proposed methods were validated against ICH guidelines.

Optical genome mapping: technical basis and applications in hematological malignancies

Optical genome mapping: technical basis and applications in hematological malignancies

Empowering 6G maritime communications with distributed intelligence and over-the-air model sharing

Introduction: Shipping and maritime transportation have gradually gained a key role in worldwide economical strategies and modern business models. The realization of Smart Shipping (SMS) powered by advanced 6G communication networks, as well as innovative Machine Learning (ML) solutions, has recently become the focal point in the maritime sector. However, conventional centralized learning schemes are unsuitable in the maritime domain, due to considerable data communication overhead, stringent energy constraints, increased transmission failures in the harsh propagation environment, as well as data privacy concerns.Methods: To overcome these challenges, we propose the joint adoption of Federated Learning (FL) principles and the utilization of the Over-the-Air computation (AirComp) wireless transmission framework. Thus, this paper initially describes the mathematical considerations of a 6G maritime communication system, focusing on the heterogeneity of the relevant nodes and the channel models, including an Unmanned Aerial Vehicle (UAV)-aided relaying model that is usually required in maritime communications. The communication network, enhanced with the AirComp technique for efficiency purposes, forms the technical basis for the collaborative learning across multiple Internet of Maritime Things (IoMT) nodes in FL tasks. The workflow of the FL/AirComp scheme is illustrated and proposed as a communication-efficient and privacy-aware SMS framework, considering spectrum and energy efficiency aspects under a sum transmitting power constraint.Results: Then, the performance of the proposed methodology is assessed in an important ML task, related to intelligent maritime transportation systems, namely, the prediction of the Cargo Ship Propulsion Power using real data originating from six cargo ships and utilizing long-short-term-memory (LSTM) neural networks. Upon extensive experimentation, FL showed higher prediction accuracy relative to the typical Ensemble Learning technique by a factor of 3.04. The AirComp system performance was evaluated under varying noise conditions and number of IoMT nodes, using simulation data for the channel state information by regulating the power of the transmitting IoMT entities and the scaling factor at the shore base station.Discussion: The results clearly indicate the efficiency of the proposed FL/AirComp scheme in achieving low computation error, collaborative learning, spectrum efficiency and privacy protection in wireless maritime communications, while providing adequate accuracy levels with respect to the optimization objective.

Detection of surface defects for maize seeds based on YOLOv5

The external appearance of maize seeds is one of important quality evaluation indicators for maize seeds. For traditional maize seed appearance quality detection, which mainly relies on naked eyes to inspect surface defects. Although computer vision as a relative mature way can be used for sample appearance quality inspection, manual feature extraction is still required. Meanwhile, machine learning technology, especially deep learning, has developed rapidly in the last decades. The maize seed surface defect detection coupled with deep learning can effectively replace traditional detection methods, reduce manual intervention, and decrease costs. In this paper, the collection and preprocessing of maize seed images, as well as the surface defects evaluation methods of maize seeds using a deep learning framework YOLOv5 were proposed. Firstly, in terms of image acquisition, maize seed batch surface defect detection system was established to obtain images. Then, the quality of maize seed images was improved by filtering, segmentation, and enhancement, which could significantly reduce noise in the images, separate the targets from the background and replace the background. Finally, ECA-Improved-YOLOv5S-Mobilenet model, which was established to improve the feature learning performance, could extracted the features from the maize seeds image and detect defects quickly at different levels. The experimental results showed that the precision was 92.8%, the recall rate was 98.9%, and the mPA0.5 was 95.5% with 8.8 MB of model size. In general, the proposed maize seeds surface defect detection method combined with deep learning could provide a theoretical support and technical basis for future development of seed grading and plantation.