Solve Complex Engineering Problems Research Articles

Pathways for the Construction of Labor Education Courses for Students Major in Measurement and Control

In March 2020, the Central Committee of the Communist Party of China and the State Council issued the Opinions on Comprehensively Strengthening Labor Education in Primary and Secondary Schools in the New Era, emphasizing that "fully understand the new requirements for strengthening labor education in the new era to train socialist builders and successors; Comprehensively build a labor education system that reflects the characteristics of The Times; Carry out labor education practice extensively; Efforts to improve labor education support and security ability; Effectively strengthen the organization and implementation of labor education." Therefore, college students' labor education has become a compulsory course for the major of measurement and control technology and instrument. The course is divided into two parts: theoretical study and practical study. In view of the increasing emphasis of the society on college students' labor quality education and the key role of mapping in solving complex engineering problems, the traditional "passing through" theoretical teaching methods and "visiting" practical teaching methods are no longer suitable for the new teaching needs in the contemporary background. Therefore, in order to improve the teaching quality and students' learning effect on this malleable and open knowledge, Changzhou Institute of Technology invited technical directors of representative enterprises in the industry to conduct classroom case analysis and field visits of relevant knowledge, so as to realize the teaching reform of production-education integration in school-enterprise joint teaching. The latest industry status and development trend of measurement and control technology and instrument technology will be brought into the classroom teaching, effectively improve the teaching quality, and deeply cultivate students' labor consciousness.

Groupers and moray eels (GME) optimization: a nature-inspired metaheuristic algorithm for solving complex engineering problems

AbstractAs engineering technology advances and the number of complex engineering problems increases, there is a growing need to expand the abundance of swarm intelligence algorithms and enhance their performance. It is crucial to develop, assess, and hybridize new powerful algorithms that can be used to deal with optimization issues in different fields. This paper proposes a novel nature-inspired algorithm, namely the Groupers and Moray Eels (GME) optimization algorithm, for solving various optimization problems. GME mimics the associative hunting between groupers and moray eels. Many species, including chimpanzees and lions, have shown cooperation during hunting. Cooperative hunting among animals of different species, which is called associative hunting, is extremely rare. Groupers and moray eels have complementary hunting approaches. Cooperation is thus mutually beneficial because it increases the likelihood of both species successfully capturing prey. The two predators have complementary hunting methods when they work together, and an associated hunt creates a multi-predator attack that is difficult to evade. This example of hunting differs from that of groups of animals of the same species due to the high level of coordination among the two species. GME consists of four phases: primary search, pair association, encircling or extended search, and attacking and catching. The behavior characteristics are mathematically represented to allow for an adequate balance between GME exploitation and exploration. Experimental results indicate that the GME outperforms competing algorithms in terms of accuracy, execution time, convergence rate, and the ability to locate all or the majority of local or global optima.

A Practical Exploration on the Teaching Reform of Integration of Production and Teaching in College Students' Labor Education Curriculum

In March 2020, the Central Committee of the Communist Party of China and the State Council issued the "Opinions on Strengthening Labor Education in Colleges and Universities in the New Era," emphasizing the "need to fully recognize the new requirements for cultivating socialist builders and successors in the new era for strengthening labor education; to build a comprehensive labor education system that reflects the times; to conduct extensive labor education practical activities; to enhance the support and guarantee capacity for labor education; and to strengthen the organization and implementation of labor education." As a result, labor education has become a required course for students majoring in Test and Control Technology and Instrumentation. The course is divided into two parts: theoretical learning and practical learning. Due to the increasing social emphasis on labor quality education and its reflection in the key role it plays in solving complex engineering problems, the traditional "walking-horse-view" theoretical teaching method and "visiting-style" practical teaching method are no longer suitable for the new teaching needs in the contemporary context. Therefore, in order to improve the teaching quality and students' learning effect of the flexible and open knowledge, Changzhou Institute of Technology's Test and Control Technology and Instrumentation major has invited the technical directors of representative enterprises in the industry to conduct case analysis in class and on-site visits, achieving the goal of joint teaching reform between schools and enterprises. Bringing the latest industrial status and development trends of Test and Control Technology and Instrumentation technology into classroom teaching, it effectively improves the teaching quality and deeply cultivates students' labor awareness.

Optimizing the production of solketal from glycerol: a case study integrating Aspen Plus and a MATLAB subroutine

The use of process simulators has increased dramatically due to their ability to solve complex engineering problems. However, most simulators use a black-box modeling approach, which hinders the application of derivative-based optimization models. This work aims to present a case study of the glycerol ketalization reaction by integrating the Aspen Plus® simulator with MEIGO, an optimization tool available for MATLAB®. The kinetic parameters of the reaction were estimated using a Python algorithm. The simulation was validated, and the optimization of the reactive section was performed using an Enhanced Scatter Search method. After optimization for 80% glycerol conversion, the temperature, acetone:glycerol molar ratio in the reactor feed, and reactor volume were 80 °C, 8.83, and 24.17 m³, respectively, for processing 5.149 m³/h of glycerol. The integration of Aspen Plus® with MATLAB® using the MEIGO add-on is shown as a valid strategy for optimizing complex problems involving black-box models.

Exploration and Practice on the Construction of Engineering Training Centers in Applied Undergraduate Universities

Based on the exploration of the reform and development practice of the Engineering Training Center, with the reform of talent cultivation concept as the core, the upgrading of teaching system and the drive of entrepreneurship education as the path, and the innovation and entrepreneurship education platform and entrepreneurship competition as the starting point, the focus is on cultivating students' self-learning ability, practical hands-on ability, innovative development ability, and ability to solve complex engineering problems, achieving the transformation of knowledge into ability. The practical results have shown that the Engineering Training Center has achieved significant results in cultivating students' innovation, practical skills, abilities, and engineering qualities.

Improving the Kepler optimization algorithm with chaotic maps: comprehensive performance evaluation and engineering applications

The Kepler Optimisation Algorithm (KOA) is a recently proposed algorithm that is inspired by Kepler’s laws to predict the positions and velocities of planets at a given time. However, although promising, KOA can encounter challenges such as convergence to sub-optimal solutions or slow convergence speed. This paper proposes an improvement to KOA by integrating chaotic maps to solve complex engineering problems. The improved algorithm, named Chaotic Kepler Optimization Algorithm (CKOA), is characterized by a better ability to avoid local minima and to reach globally optimal solutions thanks to a dynamic diversification strategy based on chaotic maps. To confirm the effectiveness of the suggested approach, in-depth statistical analyses were carried out using the CEC2020 and CEC2022 benchmarks. These analyses included mean and standard deviation of fitness, convergence curves, Wilcoxon tests, as well as population diversity assessments. The experimental results, which compare CKOA not only to the original KOA but also to eight other recent optimizers, show that the proposed algorithm performs better in terms of convergence speed and solution quality. In addition, CKOA has been successfully tested on three complex engineering problems, confirming its robustness and practical effectiveness. These results make CKOA a powerful optimisation tool in a variety of complex real-world contexts. After final acceptance, the source code will be uploaded to the Github account: nawal.elghouate@usmba.ac.ma.

Assessment of RANS turbulence models based on the cell-based smoothed finite element model for prediction of turbulent flow

There is a growing body of literature that recognizes the importance of Smoothed Finite Element Method (S-FEM) in computational fluid dynamics (CFD) fields and, to a lesser extent, in complex turbulent flow problems. This study evaluates the performance of Reynolds-averaged Navier-Stokes (RANS) turbulence models within the S-FEM framework for predicting incompressible turbulent flows. Our assessment of three turbulence models based on the cell-based S-FEM (CS-FEM) is convincingly supported by testing on three flow problems. It is found that the CS-FEM exhibits superior mesh robustness compared to the Finite Volume Method (FVM) and achieves higher computational accuracy than the Finite Element Method (FEM). Notably, the CS-FEM combined with the standard k-epsilon model (CS-FEM-SKE) and the realizable k-epsilon model (CS-FEM-RKE) demonstrate robust performance in handling severely distorted meshes, with CS-FEM-RKE outperforming in regions of strong flow separation and convection. The Spalart-Allmaras model with CS-FEM (CS-FEM-SA) offers faster computational speed but shows poor mesh robustness. The hexcore mesh based on CS-FEM-RKE is employed to evaluate the aerodynamic performance of High-speed train (HST), resulting in enhanced computational efficiency. The outcomes show good agreement with other numerical studies and experimental data. Overall, it also highlights the latent capability of CS-FEM in solving complex engineering problems.

A unified optimization design method for multi-stage non-circular gear transmission based on periodic B-spline interpolation

This research introduces a novel and unified optimization design method for multi-stage non-circular gear transmission (MNCGT) to address the challenges in designing MNCGT for complex motion requirements. The method optimizes non-circular gears comprehensively, reducing design and manufacturing difficulties while ensuring the realization of specified transmission requirements. A unified parameterization method, grounded on periodic B-spline interpolation, is introduced to establish the transmission function of non-circular gears and map it to a finite unified variable space. This innovative approach effectively reduces the difficulty and constraints of MNCGT optimization design. The proposed method takes into account crucial factors such as non-circularity, smoothness, processing conditions, and contact ratio, which significantly impact the transmission performance and manufacturing feasibility of non-circular gears. The effectiveness and superiority of this method are demonstrated through two practical examples and a real-world application in a planetary gear transplant mechanism, highlighting its potential for solving complex engineering problems.

Advanced UAV Design Optimization Through Deep Learning-Based Surrogate Models

The conceptual design of unmanned aerial vehicles (UAVs) presents significant multidisciplinary challenges requiring the optimization of aerodynamic and structural performance, stealth, and propulsion efficiency. This work addresses these challenges by integrating deep neural networks with a multiobjective genetic algorithm to optimize UAV configurations. The proposed framework enables a comprehensive evaluation of design alternatives by estimating key performance metrics required for different operational requirements. The design process resulted in a significant improvement in computational time over traditional methods by more than three orders of magnitude. The findings illustrate the framework’s capability to optimize UAV designs for a variety of mission scenarios, including specialized tasks such as intelligence, surveillance, and reconnaissance (ISR), combat air patrol (CAP), and Suppression of Enemy Air Defenses (SEAD). This flexibility and adaptability was demonstrated through a case study, showcasing the method’s effectiveness in tailoring UAV configurations to meet specific operational requirements while balancing trade-offs between aerodynamic efficiency, stealth, and structural weight. Additionally, these results underscore the transformative impact of integrating AI into the early stages of the design process, facilitating rapid prototyping and innovation in aerospace engineering. Consequently, the current work demonstrates the potential of AI-driven optimization to revolutionize UAV design by providing a robust and effective tool for solving complex engineering problems.

DMT-OMPA: Innovative applications of an efficient adversarial Marine Predators Algorithm based on dynamic matrix transformation in engineering design optimization

This paper introduces an innovative variant of the Marine Predators Algorithm (MPA), termed the Dynamic Matrix Transformation-based Oppositional Marine Predators Algorithm (DMT-OMPA), aimed at enhancing the efficiency of engineering optimization strategies. Traditional MPAs have several shortcomings, including insufficient solution diversity and coverage in the initialization phase, a tendency to become trapped in local optima, and inadequate search capabilities in the later stages of iteration, all of which negatively impact the algorithm’s efficiency and effectiveness. To address these issues, the DMT-OMPA incorporates oppositional learning mechanisms and dynamic matrix transformation strategies, significantly enhancing global search capabilities and accelerating convergence speed, particularly in handling complex multidimensional optimization problems.Experimental results on the CEC2013 and CEC2017 test suites demonstrate that DMT-OMPA outperforms other recent MPA variants, various classical algorithm variants, and newly proposed algorithms, verifying its advantages in precision and reliability. Furthermore, the application of this algorithm to various real-world engineering problems substantiates its broad applicability and high efficiency. The study’s findings not only deepen our understanding of swarm intelligence optimization algorithms but also provide a new efficient tool for solving complex engineering problems. The results indicate a promising potential for wider application in diverse fields, suggesting that the DMT-OMPA algorithm could become an effective tool for tackling complex optimization problems in the future.

Research on Flipped Classroom Based on the Course of Polymer Modification

How to improve students' self-learning ability and cultivate their ability to solve complex engineering problems during the teaching process is a challenge to undergraduate course teaching. This study focuses on the teaching of "Polymer Modification" for third year students majoring in Polymer Materials and Engineering at the School of Materials Science and Engineering, North China University of Technology. The shortcomings of the original teaching methods were systematically analyzed, and a teaching model of "BOPPPS+flipped classroom" was constructed. The teaching content was reconstructed, and the specific process and operational effects of the new teaching model were systematically discussed. This study provides ideas and references for the teaching reform of courses related to polymer materials and engineering.

New bandgap analysis method for metamaterial structures using variational principle

This paper presents an efficient bandgap analysis method for metamaterial structures based on variational principle and linear expression technique. This is in view of the challenges in constructing a displacement function that satisfies the Bloch boundary when applying the traditional energy method to analyze the dispersion relations of metamaterial structures. Also, the inclusion of the wave numbers in the displacement function leads to inefficient computation. While there have been methods, such as virtual springs, proposed to deal with such problems, issues remain to be resolved. The main idea of the current paper is the solution of linear uncorrelated coefficients by processing the constraints. In this way, the unknown coefficients in the equations of motion can be linearly expressed, thereby allowing the equations to become variational. Both Gaussian elimination and null-space techniques are used to implement the method. The solution procedures of the two techniques are detailed and demonstrated by using one-dimensional and two-dimensional metamaterial structures. The accuracy of the method is verified by comparing the results with those from using finite element method. The calculation efficiency is compared with that of the traditional energy method in terms of both the matrix dimension and the number of the points of wave numbers. The results show that the method has a much higher calculation efficiency than that of the traditional energy method. The method proposed in this paper is free of convergence problems in dealing with boundary problems. Furthermore, in the discussion of combined periodic structures, it is shown that the method still has good geometrical applicability to structures containing multiple boundary conditions, showing great potential in solving complex engineering problems.

Physics-informed neural networks in groundwater flow modeling: Advantages and future directions

In recent years, there has been enormous development in soft computing, especially artificial intelligence (AI), which has developed robust methods for solving complex engineering problems. Researchers in the field of water resources engineering have applied these AI methods to solve a variety of hydrological problems. Despite their widespread use in the surface and atmospheric hydrology fields, groundwater hydrologists have not widely used AI methods in their routine field-scale modeling efforts. This is because AI models have been primarily considered black box models that lack physical meaning. Furthermore, using AI models to generate the space-time distribution of transient groundwater level variations is challenging and requires further flux balance and mass transport analyses. More recently, a new type of physics-informed neural network (PINN) model has been developed to address several limitations by integrating governing physics (groundwater flow equations) into the AI tools. This study presents the systematic advantages of the PINN algorithm for solving groundwater problems using a set of classic test problems. As discussed in detail in the article, these advantages and potentials are associated with the meshless nature of PINN, its continuous time and space dimensions, its independence from time-stepping and incremental marching in space, and its efficiency in running time. However, despite PINN's promising attributes, it is important to acknowledge its nascent stage of development and the inherent limitations of all neural network models, such as training challenges and hyperparameter selection. Thus, collaborative efforts between groundwater modelers and computer scientists are imperative to explore and exploit the full potential of PINN in tackling increasingly complex groundwater problems and nurturing PINN into a dependable modeling tool in industry and academia.

Platform Design of Passive Target Perception and Localization Based on Sensor Networks

With the rapid development, extensive knowledge, and diverse application scenarios of target perception and positioning technology in sensor networks, a passive target perception and localization platform based on Wireless Sensor Networks (WSN) has been designed. The platform is mainly applied for the teaching of electronic information, communication, and Internet of Things (IoT) engineering. The platform follows the teaching concept of “developing students’ ability to solve complex engineering problems” in the emerging engineering discipline and combines experimental simulation with real-world testing, as well as integrating scientific research and teaching. It encompasses technical elements such as perception and localization theory, sparse representation classification modeling, solving underdetermined equations, data analysis, and sparse coding, as well as nontechnical aspects such as team collaboration and cost budgeting. The platform boasts high fidelity and scalability, providing students with the opportunity to develop comprehensive practical and innovative skills in solving complex engineering problems.

An inspired chaos-based estimation-theory optimization for low-density parity-check (LDPC) code decoding

Optimization techniques have emerged as powerful tools for solving complex engineering problems in real-time applications, surpassing traditional heuristic methods. This paper introduces a novel chaos optimization algorithm that integrates the bisection search method to enhance the convergence ability, solution accuracy, and search speed of conventional optimization problems. The proposed algorithm is applied to the design and analysis of a reduced complexity decoding scheme using Low-Density Parity-Check (LDPC) codes. By leveraging the Linear Minimum Mean Square Error (LMMSE) estimation criterion, the proposed method approximates the estimated parameters acquired during the message computation process. This combined approach effectively mitigates error propagation and premature convergence issues. The presented research offers a low-complexity decoding algorithm for LDPC codes, leveraging an optimized chaos bisection search method. The adoption of the LMMSE criterion overcomes data dependency and error propagation concerns during the estimation process. The modified chaos optimization technique, integrated with the bisection search, efficiently determines optimal values from perturbed observations, leading to improved convergence rates and data processing precision by reducing the observation dimension (search space). Simulation results validate the proposed approach, showcasing its ability to mitigate error propagation and premature convergence while maintaining coding gain accuracy. Experimental validation on an FPGA RF-SoC device (model XCZU27DR) demonstrates that the proposed method achieves a maximum throughput of 8.7 Gbps at a clock frequency of 386.72 MHz, with reduced hardware complexity. The experimental verification on an FPGA RF-SoC device highlights the algorithm's minimal hardware complexity, superior decoding throughput, and Bit Error Rate (BER) performance.

The Assessment Method Reform of “Machine Design” Course Based on OBE Education Concept

In order to strengthen students' grasp of the knowledge of "Machine Design" and to improve students' ability to solve complex engineering problems and innovate, based on the OBE education concept, this paper analyzes the problems existing in the course of "Machine Design" and reforms the assessment method of "Machine Design" course. The reform highlights the character of the course and the main position of the students, and gives play to the incentive role of the assessment method. Starting from the concrete practice, under the premise of ensuring students' good adaptability, a number of measures focusing on cultivating students' engineering ability and innovation ability are introduced in the assessment. Students' attention to practical projects, academic performance and competition results have been significantly improved, which reflects the effectiveness of this reform to a certain extent.

Reform of the Comprehensive Practical Course System for Mechanical and Electronic Engineering Majors Under the Background of New Engineering

Under the background of new engineering, the reform of the comprehensive practical course system formechanical and electronic engineering majors actively responds to the challenges posed by the new round of technological revolution and industrial transformation to higher education, cultivating top-notch innovative intellectuals with comprehensive engineering qualities, meeting the requirements of being able to solve complex engineering problems rather than just cognitive capabilities, forming two core courses through reconstructing and reshaping the core courses of the major. The core courses include Drive, Measurement, and Control I and Drive, Measurement, and Control II, which highlight the comprehensive framework of mechanical and electronic engineering professional knowledge, continuing the comprehensive practical course system based on the unity of knowledge and practice, following the trend of new engineering, highlighting the practicality of professional innovation, assisting engineering education reform, and promoting high-quality development of new engineering professionals cultivation.

An LSTM-stacked autoencoder multisource response prediction and constraint optimization for scaled expansion tubes

Deep learning is attracting increasing attention due to its excellent predictive power and its ability to be applied in traditional research areas. In this paper, we propose a multisource response prediction network architecture based on a long short-term memory (LSTM)-stacked autoencoder to predict key crashworthiness indicators and complete curve reconstruction. Taking an expansion tube as an example using an equivalent scaling research method, a scaled expandable tubular (SET) finite element model was established and verified using a quasistatic compression test and a full-size coupler and buffer system experiment. A design of experiments (DOE) approach was used to obtain a dataset for training the prediction network. Neural network hyperparameters are critical to network prediction accuracy, and after comparison, the multisource response prediction network architecture showed good computational efficiency and satisfactory prediction accuracy when appropriate hyperparameters were selected. Subsequently, multiobjective constraint optimization was performed using the nondominated sorting genetic algorithm-II (NSGA-II) based on a prediction network architecture, which greatly improved the energy-absorption structure optimization accuracy. The results are expected to provide a research methodology for solving complex engineering problems by establishing a new framework for deep learning algorithms combined with optimization methods.

Introduction to the Special Issue on Computational Intelligent Systems for Solving Complex Engineering Problems: Principles and Applications

Introduction to the Special Issue on Computational Intelligent Systems for Solving Complex Engineering Problems: Principles and Applications

Model Based Systems Engineering applied to Digital Twin engineering: why and how to?

In addition to inheriting concepts and methodological principles from System Engineering, Model-Based Systems Engineering (MBSE) emphasizes the role of modelling and models in engineering processes. Different types of models are then constructed and used, each being a digital representation of a system that is undeniably partial, but also necessary. It highlights and enables the analysis of certain characteristics of this system, e.g. its behaviour, its functions or its composition to make relevant design choices. Digital Twins are the ultimate representation of a system, expected to be faithful and realistic for the purpose they serve, as well as to be connected and synchronized to the modelled physical asset. Hence, they support stakeholders to manage, train or optimize the target system when implemented and put into operation. However, defining and engineering Digital Twins remains a difficult process, with little methodology available to build and ensure it remains faithful to a continuously evolving reality. MBSE provides concepts and a methodological framework that are well adapted to solve complex engineering problems with many constraints. This position paper introduces a MBSE based Digital Twin engineering framework foundation, applied to an manufacturing system.