Ebook: Artificial Intelligence Technologies and Applications

It is our great pleasure to have you at the 5th International Conference on Artificial Intelligence Technologies and Applications (ICAITA 2023), which took place in Changchun, China from June 30th to July 2nd, 2023 (hybrid conference). The Conference was hosted by Changchun University of Science and Technology and successfully held, receiving unanimous praise from various experts and scholars all over the world.

ICAITA 2023 existed as an international forum for academic communications between experts and scholars in the field of artificial intelligence. It promoted the research and developmental activities in related fields and scientific information interchange among all the participants, establishing research connections for them to find global partners for potential collaboration.

We had about 300 participations both as speakers and participants, including senior experts, research talents, and young scholars from enterprises, research institutes, and universities worldwide. During the keynote speech part, each keynote speaker was given 30–40 minutes for keynote speech. Among them, Professor Philippe Fournier-Viger from Shenzhen University, China performed a keynote speech on Advances and Challenges for the Automatic Discovery of Interesting Patterns in Data. First, he briefly reviewed early studies on designing algorithms for identifying frequent patterns. Then, he presented an overview of recent challenges and advances to identify other types of interesting patterns in more complex data. Topics that were discussed include high utility patterns, locally interesting patterns, and periodic patterns. Lastly, the SPMF open-source software was mentioned and opportunities related to the combination of pattern mining algorithms with traditional artificial intelligence techniques for intelligent systems were discussed. These experts shared remarkable academic achievements in edge computing, computer communication, machine learning applications, and AI applications, and discussed critical challenges and research directions within these domains, triggering heated discussion during the Conference and even in the break.

After months of careful preparation and hard work, the Proceedings of ICAITA 2023, having been checked through rigorous review and processes to meet the requirements of publication, are published. These papers feature but are not limited to the following topics: Artificial Neural Networks, Computational Theories of Learning, Intelligent System Architectures, Pervasive Computing and Ambient Intelligence, Fuzzy Logic and Methods.

We would like to express our gratitude to the organizers, keynote speakers and all the participants of ICAITA 2023, for their fruitful work and contribution to the success of the Conference. We are thankful to all the reviewers for providing constructive criticisms, stimulated comments and suggestions to the authors. Particularly, our special thanks go to IOS Press, for the endeavor of all its colleagues in publishing this volume. May this event be a spark that ignites many more new inventions in the fields related to artificial intelligence technologies and applications!

The Conference Chairs of ICAITA 2023

The interior of CNC machine tools is relatively precise and the overall structure is very complex. It is a relatively advanced mechanical equipment and is widely used in some relatively large factories. In today’s society, various industries are using intelligent diagnostic technology, which is developed on the basis of computers and artificial intelligence. Because the process of fault diagnosis and processing of CNC machine tools is very cumbersome, the development of diagnosis technology is also becoming more and more intelligent with the development of the CNC industry, which provides a strong guarantee for ensuring the safety of machine tools. In CNC machining, intelligent detection technology also plays an increasingly important role. The intelligent diagnosis system of CNC machine tools is to apply artificial intelligence technology to the CNC system. This paper summarizes the types of CNC machine tool faults and explains in detail the characteristics of CNC machine tool fault diagnosis. Diagnose and repair, thereby reducing economic losses. Finally, this paper looks forward to the main research directions of the future intelligent fault diagnosis technology of CNC machine tools.

The LNG cylinder frame is one of the most important components of the LNG fuel device on heavy trucks. Under emergency braking, sharp turning, and actual road impact loads, the cylinder frame is vulnerable to static strength damage and fatigue damage caused by insufficient fatigue strength, which affects the safe operation of heavy trucks. Hypermesh is used to process the grid, Nastran is used to conduct static strength analysis, and Ncode is used to conduct fatigue analysis. The maximum stress value, maximum displacement value, fatigue damage value, and other data of the cylinder frame under different working conditions are obtained. The safety and structural weaknesses of the cylinder frame are analyzed, and an improvement scheme is proposed and verified through finite element analysis. The results show that the static strength safety factor of the improved cylinder frame is increased by 113%, and the maximum fatigue damage values at 8000 km and 16000 km are decreased by 53.5% and 27.9%, respectively.

The design for typical structural parts of aircraft directly affects the aircraft’s quality and maintenance cost. This paper analyzes the necessity of intelligent optimal design for typical aircraft structural parts and studies its current situation and development trend at home and abroad. In this paper, a new intelligent optimization design technology for typical aircraft structural parts is proposed. Based on its design framework, the technical system, the design method integrating knowledge, and the verification ideas based on the Internet architecture are described in detail. Finally, the next step is envisaged. Engineering implementation shows that the proposed intelligent optimization design technology greatly improves the quality of aircraft and reduces the cost of design and maintenance.

In order to reduce the impact of transmission line icing accidents on the safe production of the power grid, the power grid operation and maintenance department guides the deicing and melting work of the power grid by estimating the thickness of the line icing. This paper proposes to predict the ice thickness based on the entropy weight method and BP neural network learning method. First, the entropy weight method is used to select the main influencing factors of line icing. Then a BP neural network prediction model of ice coating is constructed with weather and terrain as input and ice thickness as output. Finally, performance evaluation is performed using artificial ice observation data. The goodness of fit between the test data and the artificial ice observation data is 0.76805. The error is 5.33mm, which is far lower than 6.51 mm compared with the stepwise regression model. This verifies the validity of the model and has certain significance for the research on transmission line icing prediction.

This paper mainly simulates the spinning process of tantalum tungsten alloy liner parts, simulates the spinning process with finite element analysis software, and obtains the stress and strain program in the spinning process. With the wall thickness difference of the spun parts as the analysis target, the influence law of the feed ratio, radius, and working angle of the spinning wheel on the wall thickness difference is obtained. The spinning experiment is conducted with the process parameters obtained from the simulation, and the experimental results are in good agreement with the simulation results, which shows that the method and means of simulation can guide the actual spinning process.

Landslides are one of the most frequent geological disasters in the Three Gorges Reservoir Area, and regional landslide risk assessment is of great significance for landslide risk prevention and control. This paper takes Yunyang County, Chongqing City, in the Three Gorges Reservoir Area as an example, selects seven evaluation factors including slope, aspect, shape, lithology, geological structure, river erosion, and human engineering activities, and uses the information value model and logistic regression model for landslide spatial probability prediction. Based on Bayesian statistics, a spatio-temporal model of landslide susceptibility index and disaster occurrence probability was established, combined with landslide disaster intensity index, to achieve the zoning evaluation of landslide hazard in Yunyang County. The results show that: (1) the predictive accuracy of the landslide susceptibility evaluation model is 0.730. (2) Based on the landslide events in Yunyang County in the past 20 years and the landslide spatial prediction results, the evaluation results show that the very high and high hazard areas cover an area of 1041.459 square kilometers, accounting for 58.69% of the total area. (3) Combined with the field investigation results, the very high and high hazard areas in Yunyang County are mainly distributed in areas where human activities are strong such as the main and tributary rivers of the Yangtze River and urban periphery, and it is recommended to implement key preventive and monitoring measures for landslide disasters.

A new bushing assembly robot assembly method is proposed to solve the print quality problems caused by the low accuracy of printing machine bushing assembly. The method is based on the laser positional measurement system, and the inverse kinematic analysis is conducted for 6-DOF to obtain the positional transformation volume, which is validated by simulation in Unity. The simulation results show that this method calculates the positional transformation quantity and achieves zero error in the attitude. In terms of position, it can be controlled within a circle with a radius of 0.03 mm in the radial plane of the ideal position, and the distance from the ideal position is less than 0.027 mm, and the result is consistent with the conception. The accuracy and reliability of the method are verified, which helps the platform to make accurate attitude adjustments.

Based on the research status of flapping-wing aircraft at home and abroad, the overall scheme of bionic flapping-wing aircraft is established in this paper. In the aspect of trajectory planning, the three-dimensional modeling and simulation analysis of bionic flapping-wing aircraft are carried out, and a new flapping-wing mechanism is adopted. Finally, the trajectory of flapping-wing aircraft is analyzed from the point of view of the operation, and verification experiments are carried out to obtain the best flapping-wing effect.

To analyze the effect of demand response (DR) in the regional power grid, a day-ahead optimal dispatching model of the regional power system considering the DR is established by using the elasticity matrix of electricity price, and a real-time rolling dispatching optimization model considering the renewable energy power prediction errors in different time scales is established. For the privacy of information in different regions, the alternate direction multiplier method (ADMM) is used for a distributed solution to obtain an optimal scheduling scheme. Taking a regional power grid in China as a case, we testify that the DR plays a crucial part in peak-load shifting in the regional power grid. Under the reasonable proportion of curtailable load (CL) and shiftable load (SL), the dispatching optimization model proposed can promote the total operation cost reduction and renewable energy consumption.

It is a common method to build a scaled-down test bench to simulate a large mechanical equipment movement to research its fatigue damage characteristics. However, few studies have confirmed that the damage features of the test bench correspond to the equipment itself. In this paper, in order to study the fatigue damage mechanism of the hydraulic miter gate and predict the life of its key components, we designed a test bench in accordance with a certain reduction in proportion based on the No.2 miter gate of Gezhouba dam. The finite element models of the actual gate and the test gate are established respectively, and their deformation and stress distribution are analyzed depending on the strength of the door in different working conditions. The results show that the variation law of the stress and strain distributions of the test gate and the actual gate are basically the same. Therefore, the damage position of the miter gate test bench should be consistent with the corresponding position of the actual gate, and it is reliable to use the designed test bench to find the damage of the actual gate.

In recent years, extreme weather occurs frequently, and the energy crisis is becoming more and more serious. The unified scheduling of new energy sources such as scenery can alleviate the problems of primary energy shortage. However, the randomness and fluctuation of new energy lead to its low internet access. Building an energy storage station for new energy generation side can not only solve the fluctuation problem of new energy grid connection, but also increase the grid connection of new energy sources. This article decomposes the output data of wind farm into high, medium and low frequency components through empirical mode decomposition. The low frequency component can be directly connected to the grid, battery could stabilize intermediate frequency component and and flywheel stabilize high frequency component.Combined with the objective function of minimum cost of the energy storage station, minimized capacity is carried out, and the economic optimal scheme is obtained.

This paper presents a method for mobile robots to recognize and dock shelves based on 2D LiDAR, which can autonomously identify shelves and perform high-precision docking. A geometric feature-based shelf leg recognition and multi-shelf model screening method is designed, which can quickly and accurately autonomously identify shelves. A fitting method for the center of shelf legs and shelf centers based on nonlinear least squares was proposed, and a real-time autonomous docking system was designed, which can autonomously distinguish shelf size types and perform precise docking. The experiment shows that the proposed method can achieve a docking accuracy of ± 1 cm.

The optimization of scheduling in spacecraft manufacturing workshops is an important measure taken to reduce production costs and improve processing efficiency. In solving scheduling problems, genetic algorithms have been widely applied as efficient optimization algorithms. This study establishes a mathematical model for workshop job processing with the objective of minimizing processing time. Addressing the issues of premature convergence and low solution accuracy in standard genetic algorithms (SGA), an improved genetic algorithm is proposed. To obtain better populations, the crossover and mutation probabilities are automatically adjusted by referencing individual fitness values. Additionally, to avoid generating invalid solutions, genes are divided into different segments based on processing operations to improve crossover operations. The results of the case study demonstrate that the improved genetic algorithm exhibits better convergence and global search capabilities compared to the standard genetic algorithm, achieving significant improvements in scheduling structure optimization.

In order to achieve optimal control of the Hydro-Turbine Speed Control System (HTSCS), this paper presents a speed control system parameter optimization method based on the Convergence Factor Particle Swarm Optimization and Gravitational Search Algorithm (CPG). Firstly, the basic model of the HTSCS is established, and then the parameters of the PID controller are optimized using the CPG algorithm. Simulation results demonstrate that the CPG algorithm can rapidly obtain the optimal initial parameters for the PID controller. Furthermore, compared to the traditional PID control system, the PID control system based on the CPG algorithm exhibits smaller speed fluctuations, shorter stabilization time, and faster dynamic response speed under frequency and load power disturbances. The application of the CPG-based PID control strategy to the HTSCS provides enhanced dynamic stability.

Artificial intelligence (AI) technology promotes human civilization, while it also raises concerns, mainly related to security. AI plays a double-edged sword role in the network space closely related to human life. On the one hand, AI assists in network protection by intelligently detecting network intrusion, reducing missed alarm rates and false alarm rates, forecasting network threats, automatically searching for malicious code, and supporting network defense. On the other hand, AI can also assist in network attacks, such as attacking voice recognition systems and malicious software detection. AI algorithms and computational data pose many security threats, affecting the security of face recognition, speech detection, malware detection, automated driving, and other security applications based on AI technology.

The vehicle-mounted equipment installation frame and its key components may produce plastic deformation and fracture due to the gravity and vibration of the equipment in the process of road transportation. In this paper, the strength of the vehicle equipment installation frame and vehicle frame was chosen and the structured to be optimized based on the static analysis, modal analysis and random vibration analysis. The results show that the maximum stress value of the whole structure is 403.41 Mpa under full load condition and the frame frequency does not coincide with the motor frequency and the maximum equivalent stress is 491.36 Mpa in the random vibration analysis. The structure design of the frame and equipment installation frame is reasonable and reliable.

This article introduces the simulation analysis of the motion characteristics of the die-cutting moving platform system. By establishing a three-dimensional model of the die-cutting moving platform, simulate and analyze the operating characteristics of the die-cutting machine, and grasp the basic characteristics of the moving platform movement. This article simulates the relationship curves between the displacement of the moving platform system and the crankshaft angle, the speed of the moving platform and the crankshaft angle, and the acceleration of the moving platform and the crankshaft angle, and analyzes the characteristics of each motion stage. Combining simulation calculations and mathematical models of a moving platform system can intuitively and accurately analyze and judge the motion characteristics and laws of the moving platform. By analyzing the motion characteristics and laws of the die-cutting moving platform, reference can be provided for the design, manufacturing, and optimization improvement of die-cutting machines.

The purpose of this study is to explore the application of intelligent temporary construction management technology in extra-high voltage projects and analyze its effect through practical cases. Firstly, we will introduce the basic concept and development history of wisdom-based pro-construction management technology, and then elaborate its features and advantages in extra-high voltage projects. Finally, this paper will take a special high voltage project as an example for empirical analysis to explore the application of intelligent temporary construction management technology and its impact on construction progress. The wisdom of temporary construction management technology is a kind of intelligent construction management method based on big data, cloud computing and Internet of things. It can realize real-time collection, storage, processing and analysis of engineering data, so as to improve construction efficiency, reduce cost and guarantee quality. In extra-high voltage projects, intelligent temporary construction management technology has the following advantages: first, it can effectively avoid problems during construction; second, it can optimize the construction process and shorten the construction period; third, it can provide more comprehensive data to support decision-making. Therefore, intelligent construction management technology is one of the indispensable technical means in the field of extra-high voltage engineering.

Wordle is a popular puzzle currently offered daily by the New York Times. Players try to solve the puzzle by guessing a five-letter word in six tries or less, receiving feedback with every guess. Wordle continues to grow in popularity and versions of the game are now available in over 60 languages.

In this paper, the scientific computing method is used to establish a wordle decision model by combining the statistical data of authoritative English corpus and a wordle solution model based on heuristic algorithm. Based on this, we propose the HSW model to fit and analyze the real game situation of wordle players, so as to make suggestions for designers of wordle.

Based on the previous social research reports and the principle of normal distribution, we summarize and propose a VP model that can describe the vocabulary size of the population. Based on the wordle game rules, we pioneered an heuristic solution strategy with multiple controllable variables. Combined with the previous VP model, we optimized the algorithm used and built a large-scale simulation wordle game model. Through continuous parameter adjustment,we obtained a HSW model that fits the real wordle game situation. Based on the HSW model, we discuss its structural characteristics to explain the different reasons for the results of wordle games in reality. In order to describe the difficulty of a given solution word in wordle, we establish a difficulty evaluation model based on the average number of guess rounds. Finally, we compare the attributes of possible words with fixed irrelevant variables to determine the influence of specific attributes on word difficulty.

The new type of gear with circular arc tooth line is a new type of gear with good meshing ability, high degree of overlap, good smoothness of transmission, almost no noise, theoretical basis for high-speed operation, and can adapt to long working hours. According to its tooth equations, the three-dimensional model of the gear was established in SolidWorks, and after the assembly of the major and minor gears was completed, the Motion analysis module was used to simulate the kinematics of the new circular arc cylindrical gear, and the corresponding angular velocity curves of the master and driven wheels were obtained. In order to better understand the effect of the fluctuation of the kinematic speed of the circular arc cylindrical gear at different modulus, different tooth widths and different tooth numbers, kinematic analysis was carried out by ANSYS analysis software. A modal finite element analysis of the new circular cylindrical gear was also carried out to calculate the first 15 orders of inherent frequency and principal vibration pattern of the circular cylindrical gear, as well as the corresponding maximum deformation. The results show that: (1) the actual ratio of the gear in the transmission process and the theoretical value of 1.463 and 1.458 respectively and the two ratio curves basically match, indicating that the smoothness of the transmission is good. (2) The larger the modulus of the gear, the more teeth and the width of the teeth between 0.33d and 0.43d, the smaller the speed fluctuation coefficient of the gear pair in the transmission process, the better the transmission smoothness. (3) Through the solution results, it is determined that the arc tooth line cylindrical gear basically does not deform at the low order inherent frequency, while at the middle order inherent frequency, it shows the convex vibration, the highest deformation, and the main vibration pattern tends to elliptical at the high order inherent frequency.

The article is dedicated to the design of a sampled-data controller (SDC) with exponential time-varying gain (ETVG) for a kind of complex dynamical networks. It establishes a set of sufficient conditions, expressed as linear matrix inequalities, for the design of SDC with ETVG using coordinate conversion and Lyapunov function. Finally, the validity of the presented results is demonstrated through a practical example.

All along, human exploration of the ocean has never stopped, and bionic fish robots have been produced. Currently, bionic fish have been used in a range of fields, including underwater archaeology, water quality monitoring, and other fields, because of their camouflage and flexibility. The bionic fish also can perform observation, reconnaissance, and other jobs, reduce battle risks, and play a crucial role in contemporary military tasks. It is increasingly being implemented in the military sphere. The efficacy of the bionic fish’s tail mechanism in terms of swimming and reconnaissance is crucial to the design of the fish. However, multiple servo joints are frequently used in the current bionic fishtail system, which increases the likelihood of failure. This research suggests a fishtail design strategy based on the transmission mechanism to operate more steadily. After analyzing the existing bionic fish mechanical structures, research proposes the schemes of living in three mechanical structures. By combining the actual fish body size, the comprehensive modeling design was carried out using Solid Work software, and the motion performance analysis of the mechanism was analyzed by Adams software. The experimental results provide a theoretical and reference for the actual design of bionic robotic fish.

This paper studied the error averaging effect of the linear guide pair based on finite element simulation method and proposed an assembly process to improve the accuracy of the kinematic subassembly. Firstly, a finite element modeling of a linear rolling guide pair is developed. The error transfer relationship between guide and kinematic subassembly is researched by simulating different combinations of guide errors. Secondly, the linear rolling guide pair experimental bench is built to experimentally verify, and the experimental results coincided with simulation analysis. Finally, in order to improve the accuracy of the kinematic parts, an assembly process is proposed.