A5100665315- Advanced Algorithms and Applications
- Geoscience and Mining Technology
- Robotics and Sensor-Based Localization
- Fault Detection and Control Systems
- Multi-Criteria Decision Making
- Evaluation Methods in Various Fields
- Manufacturing Process and Optimization
- Advanced Sensor and Control Systems
- Industrial Technology and Control Systems
- Iron and Steelmaking Processes
- Robotic Path Planning Algorithms
- Elevator Systems and Control
- Image Processing Techniques and Applications
- Simulation and Modeling Applications
- Infrared Target Detection Methodologies
- Advanced Image Processing Techniques
- Mineral Processing and Grinding
- Rough Sets and Fuzzy Logic
- Underwater Vehicles and Communication Systems
- Advanced Measurement and Detection Methods
- E-commerce and Technology Innovations
- Mobile and Web Applications
- Autonomous Vehicle Technology and Safety
- Wireless Sensor Networks and IoT
- Reliability and Maintenance Optimization
Hunan University of Technology
2019-2024
Kunming University of Science and Technology
2024
Yunnan Nationalities University
2024
Shandong Special Equipment Inspection Institute
2023
China Agricultural University
2022-2023
St Petersburg University
2023
Semiconductor Manufacturing International (China)
2019
Northeastern University
2010-2015
Shenyang Institute of Engineering
2015
Dalian Maritime University
2015
Most present studies on the acoustic emission signals of rotating machinery are experiment-oriented, while few them involve on-spot applications. In this study, a method redundant second generation wavelet transform based principle interpolated subdivision was developed. With method, not needed during decomposition. The lengths approximation and detail were same as those original ones, so data volume twice that signals; besides, redundancy characteristic also guaranteed excellent analysis...
The scientific and reasonable evaluation of the carrying capacity water resources is guiding significance for solving issues resource shortages pollution control. It also an important method realizing sustainable development resources. Aiming at resources, model based on cloud theory evidential reasoning approach studied. First, existing indicators, a index system pressure-state-response (PSR) constructed, classification grade designed. used to realize transformation between measured value...
As enterprises pay more and attention to environmental issues, the green supply chain management (GSCM) mode has been extensively utilized guarantee profit sustainable development. Green supplier selection (GSS), which is a key segment of GSCM, investigated put forward plenty GSS approaches. At present, prefer construct large-scale teams decision makers obtain reasonable ranking results during process. However, existing methods little procedure. To investigate issue with group makers, new...
Support vector machine (SVM) is an effective tool in deal with small sample, nonlinear and high dimension classification problems. In this paper, improved pre-treatment binary-tree SVM proposed to solve fault diagnosis. Furthermore ensemble method presented establish SVM. Here the isused as weak learning machine. The new can improve performance of single At end, algorithm applied diagnosis blast furnace faults Tennessee Eastman process (TEP). experiments results show that has excellent on...
For the map building of unknown indoor environment, compared with single robot, multi-robot collaborative mapping has higher efficiency. Map merging is one fundamental problems in mapping. However, process grid merging, image processing methods such as feature matching, a basic method, are challenged by low matching rate. Driven this challenge, novel method based on suppositional box that constructed right-angled points and vertical lines proposed. The paper firstly extracts selected from...
Abstract Aiming at the aggregation problem of online multi-attribute interactive ratings, a decision-making method based on Pythagorean Fuzzy Bonferroni mean with weighted interaction (PFWIBM) operator is developed by mining advantages ratings driven and quantitative fuzzy sets linguistic ratings. First, shortcomings existing operators in criterion representation are analyzed, improved its dual defined, which used to aggregate membership information non-membership under environment,...
Dynamic obstacle detection in unknown environments during mapping is a very essential problem for mobile robots. obstacles directly affect the precision of robot map building. An approach to detecting dynamic using 2D laser radar real-time proposed this paper. After filtering out noisy data, sensor readings are mapped into world coordinate system build grid and three consecutive maps maintained. By comparing state same cell considering eight-neighbor cell, static identified. then identified...
In view of the practical needs 96333 elevator emergency disposal, based on 59,789 answering and handling records disposal service platform from 2017 to now, fault cause analysis type classification were carried out by integrating expert experience form standardized marked data. On this basis, ERNIE(Enhanced Representation through Knowledge Integration) Tiny pre-training model is applied for migration learning realize automatic access hotline types causes auxiliary reminder. The application...
The traffic sign detection problem is investigated in this paper. A segmentation method for image HSV color space presented the of prohibition sign, warning and mandatory sign. First, pre-segmented by H S components with threshold value space. Second, regions that their area ratio width height are outside will be removed. Finally, final performed its location detected, which only background being matched given combination intensity requirements preserved. experimental results show three...
This paper studies the modeling and stability analysis of an extended car-following model based on delay response signal interruption probability. First, by linear analysis, we give condition model. The result shows that region traffic flow will expand with decrease in probability p transmission interruption. When effect driver weakens, become more stable. Second, mKdV equation is derived nonlinear reduction perturbation method. parameter p, amplitude density wave decreases, becomes stable,...
This study introduces a novel multi-criteria group evaluation approach grounded in the theory of basic uncertain information (BUI) to facilitate selection green recycling suppliers for shared electric bikes. Firstly, comprehensive index system is established, encompassing capacity, environmental sustainability, financial strength, maintenance capabilities, and policy support, provide solid foundation scientific process. Secondly, generalized power weighted average (BUIGPWA) operator proposed...
A novel approach to multi-robot cooperative map-building in complex environments is presented this paper. The lets all robots operate individually and then tries merge the different local grid maps into a single global one. Without using any pose information of robots, process map merging performed by measuring similarity between maps. distance transform an improved genetic algorithm are used effectively search maximum overlap at which can be joined together. Experimental results show...
In a radar system, clutter means any echoes which are not scattered by the wanted target. Usually, map stores an average level for each point or cell in range-azimuth coordinates as reference value. A target is then detected region if new echo value that exceeds background level. visual computing domain, model employed foreground segmentation, motion detection, salient feature etc. few kinds of models built on pixel sequential images, including recently popular non-parametric model. this...
Accurate load forecasting can keep the safety of power grid operation stability and guarantee normal production life society.Support vector regression machine is suitable to forecasting.Its nature learning method give a good ability according small amount data information.An algorithm combining weighted support with feature selection predict electricity load.It significance short-term load.The used have by correlation coefficient forecast on optimization sets.The simulation experimental...
This paper presents the research on problem of uncertain sensor information processing in map building mobile robots. In this paper, an improved method based probabilistic grid is proposed. has introduced range confidence factor ultrasonic model and applied to autonomous robot. So uncertainty caused by specular reflection responses can be successfully reduced. The experiment results indicate that improves performance sensors.
As technology advances, chip size becomes larger and larger, this brings challenges when engineers would like to do a quick investigation of the design in short time, hotspot detection layout fixing. An idea mitigate is decompose into patterns classify these unique ones. Engineers then prioritize their work on patterns. Patterns from different products can be accumulated recorded, new comes in, known will filtered out all seen design. When pattern database large enough contains safe weak...
The blast furnace faults will cause significant economic and human losses. Therefore, the study of intelligent fault diagnosis technology is necessary important. But some real data difficult to obtain .The training set can not be provided enough samples.So a new virtual samples generation method designed get tainning samples. uses group discovery technique Box-Muller generate candidate sample set. And then with help manifold contraction semi-supervised learning algorithm select better...
According to the characters of SVM, an improved binary-tree SVM is proposed for multi-class problems. Furthermore aiming at initial problems about choice kernel function and parameters ensemble method presented establish SVM. Here used as weak learning machine. The new can improve performance single At end, fault diagnosis TE process. experiments demonstrate that diagnose efficiently.