Concurrent Engineering

This study presents an advanced Siamese-based Squeeze Googlenet and LeNet-5 (SSGL) model for the early detection of root diseases in plants, which is crucial for agricultural productivity and crop management. The methodology integrates state-of-the-art image processing techniques and Deep Learning (DL) algorithms across several key stages. In the pre-processing phase, techniques like median filtering, histogram equalization, i-CLAHE, and Z-score normalization are applied to enhance image quality and prepare the data for segmentation. The segmentation process utilizes a modified DeepLab V3 model, renowned for its precision in isolating root structures from complex backgrounds, ensuring accurate subsequent analysis. Feature extraction focuses on deriving comprehensive characteristics from segmented root images, including texture features using GLCM, color histograms, geometric metrics like area and perimeter, and shape descriptors such as circularity and rectangularity. A hybrid optimization approach employs the Hybrid Pufferfish-based Coati Optimization (HPCO) algorithm for feature selection, effectively identifying the most relevant features crucial for disease detection. For detection, the SSGL model integrates optimized architectures from SqueezeNet, GoogleNet, and LeNet-5 within a Siamese network framework. This setup enables efficient classification of root images into healthy and diseased categories based on cosine similarity. The proposed SSGL model outperforms other models with the highest accuracy (0.9856), precision (0.9760), sensitivity (0.9764), and F-measure (0.9771), while also achieving the lowest FPR (0.0149) and FNR (0.0109).

Drilling holes on a Printed Circuit Board is a complicated task and it is usually ensured via a Computer Numerical Control (CNC) machine using a drilling robot arm. Commonly, to increase the performance of the CNC, the movement of its robot arm is minimized via the optimization of the holes drilling route. Hence, different metaheuristics are used to plan the shortest drilling route. In this purpose, we designed a novel metaheuristic namely Dhouib-Matrix-4 (DM4) and in this paper DM4 is enhanced with a Tabu list (T) and adapted to plan the shortest route for the drilling robot arm: the proposed method is entitled Dhouib-Matrix-4-Tabu (DM4-T). In fact, DM4-T combines two techniques in a multi-start structure: (i) An initial basic solution is generated using the novel Dhouib-Matrix-TSP1 heuristic (ii) this initial solution is intensified via the innovative Far-to-Near local search technique with the Tabu list. Experimental results indicate the performance and robustness of DM4-T to solve several instances up to 2152 holes. Indeed, DM4- T outperforms several existing metaheuristics in the literature such as Genetic Algorithm, Ants Colony Optimization, Integrated Genetic Simulated Annealing and Modified Shuffled Frog Leaping Algorithm.

Graphical Abstract

Buffer management is an effective way for projects to cope with schedule risk and variability. However, current research on buffer management methods mainly focuses on optimizing time buffer sizing, overlooking the impact of resource buffer as an early warning mechanism for improving the efficiency and accuracy of project buffer management. In this study, we propose a method for determining the timing of resource buffer early warnings based on a BP neural network. First, BP neural network theory is introduced into the field of critical chain buffer management, analyzing its application in the early warning processes of project resource buffer and its predictive capabilities. Subsequently, the BP neural network is used to dynamically forecast actual execution deviations of activity resources by utilizing project risk variations and buffer deviation data related to resource execution. Based on these dynamic deviation predictions, a model for determining the timing of resource buffer early warnings is developed. The experimental results demonstrate that, compared to the traditional buffer setting method, the proposed approach reduces the project duration by 19.81% and lowers the project cost by 17.59%, achieving optimization of both project duration and cost without compromising the project completion probability.

This paper proposes the implementation of a Smart Solar PV Monitoring System that utilizes the Internet of Things (IoT) technology integrated with the Nodemcu microcontroller and the Blynk application for real-time data visualization. The system aims to evaluate the impact of dust and fly ash on solar photovoltaic (PV) systems performance. By integrating the monitoring system with the Blynk app, real-time monitoring, and analysis of the effects of dust on system efficiency becomes possible. Data for 18 days of operation on an experimental 5.5 W solar panel is collected and analyzed to establish a correlation between dust accumulation and the performance of solar PV systems. Experimental investigations were performed using artificial dust viz., fly ash and normal dust in the study duration in quantities of 2, 4 and 6 g. It was found that fly ash’s average efficiency loss is 49.16%, and for normal dust is 17.46%. The findings of this research point to integrating IoT-based smart solar monitoring systems using the Blynk application for real-time data monitoring dust effect on solar PV systems efficiency.

Optimization of cutting parameters is crucial for increasing energy efficiency in CNC milling operations. This research aims to compare the efficiency of the Genetic Algorithm (GA) optimization technique with two different selection strategies and Hybrid Simulated Annealing Genetic Algorithm (HSAGA). Each of these optimization methods is applied to three different power prediction models to evaluate how well they perform in various scenarios and to assess their robustness. The evaluation is conducted across different materials, including steel, aluminum, and ductile iron. Experimental trials were conducted using L16 and L27 Taguchi’s orthogonal arrays for GA and HSAGA, respectively. The results indicate that HSAGA, when combined with the approach based on Specific Energy Consumption (SEC) and Material Removal Rate (MRR), effectively minimizes cutting power consumption across the studied materials. This study underscores the importance of method selection and parameter optimization for enhancing CNC machining efficiency and provides insights into the most effective strategies for predicting material removal power consumption.

Crude oil fractions are essential products which are major sources of income that influence the economic growth. However, the complex nature of crude oil is calling for manufacturing innovation that will ease its process monitoring. Thus, there is need to design the crude distillation unit (CDU) operation to meet customers’ demand for the crude oil fractions. In this study, artificial neural network was applied for the process design and monitoring of a CDU in a petroleum refinery. A total of 230 data sets was used as experimental data (comprising controllable and uncontrollable variables) from which 88%, 6% and 6% were used for training, validation and testing of neural network respectively. The architectures for the CDU unit design and its neural network controller were 14 inputs, one hidden layer and seven outputs (14-1-7) and; 13 inputs, one hidden layer and six outputs (13-1-6) respectively. Logistic sigmoid transfer function was used as the activation function for the neural network training in the algorithms. The mean absolute error (MAE) and the mean square error (MSE) were used to test the accuracy of the model. After iteration numbers of 396 and 786 for CDU design and its neural network controller respectively, convergence was attained with training error of less than 10⁻⁶. For CDU design, the minimum values of MSE and MAE were 0.0055 and 0.0568 while their maximum values were 0.3517 and 0.4139 between the testing data and experimental data respectively. For the CDU neural network controller, the minimum values of MSE and MAE were 0.0000 and 0.000 while their maximum values were 0.1412 and 0.2922 between the testing data and experimental data respectively. In conclusion, artificial neural network could effectively be used as a machine learning tool for process monitoring of CDU in a petroleum refinery.

Hand Gesture Recognition (HGR) has become a vital approach in monitoring patients by their medical professionals to mitigate health risks. To recognize hand gesture signs, advanced deep learning architectures have been widely applied recently. Despite these advancements, balancing accuracy and efficiency remains a major constraint for the current models. Hence, advanced object detection methods, such as the You Only Look Once (YOLO), have been increasingly adopted to bridge this gap. Thus, this work designs a lightweight hand gesture recognition by developing a feature extraction strategy and hybrid metaheuristic optimization for the YOLOv5s network. Initially, it considers key features from RGB, depth, and skeleton hand gesture images, involving the extraction of inter-frame, intra-frame, and finger features. Secondly, the backbone of the YOLOv5s network is updated by the ResNet50 to precisely maintain the tradeoff between accuracy and efficiency through the concise learning of the gesture patterns. It potentially captures various dimensions of finger features, such as direction, shape, and quantity extraction, to improve gesture sign detection. Finally, the proposed model utilizes a novel hybrid metaheuristic algorithm design with a Genetic algorithm and Crow Search Algorithm (GCSA), significantly increasing the speed and improving the quality by selecting the optimal set of hyperparameters. The experimental results on the Praxis hand gesture dataset show the superiority of YOLOv5s.

Tyre pressure plays a vital role in dynamic control over the vehicle and enhancing overall fuel efficiency by lowering rolling resistance and, as a result, tractive effort. Excessive speeding causes traction loss, which is a primary cause of accidents. Wet roads make driving more perilous, hence the majority of accidents occur during the rainy season. As the world’s crude oil sources deplete and the electric car industry expands, it is critical to extend the range of currently existing automobiles by improving its fuel efficiency. In order to find a solution to the above problems, authors investigated the impact of tyre pressure on the coefficient of rolling resistance and friction and designed and developed a tyre pressure regulating system that uses an infrared rpm sensor to track the rate at which a tire’s rotational speed decreases as a function of time, and it then uses that information to calculate the ideal tyre pressure based on the current environmental conditions and data from various accelerometers. This unique system automatically changes tyre pressure to provide the best combination of fuel efficiency and driver safety based on data from sensors detecting tyre slip and lateral acceleration, regardless of road surface conditions.

Aluminum alloy 2219 is commonly used in the aerospace and automobile industries due to its favorable properties of low density, high strength, and good performance at cryogenic temperatures. To improve the mechanical and thermal properties of Al 2219, three reinforcements were added in preparation for the hybrid metal matrix composite (HMMC) such as silicon carbide (SiC), molybdenum disulfide (MoS₂), and graphite (Gr). Drilling is a significant manufacturing process, and the investigation of drilling parameters indicates the quality of the drilling process in terms of tool life, hole quality, and energy consumption. In this research work, drilling parameters such as thrust force, torque, and burr were evaluated. Taguchi method is implemented to design an experiment with an L9 orthogonal array. The experiment was conducted with coated carbide and uncoated carbide drill tools. Coated carbide was used because it improves oxidation resistance and reduces friction. The specimen prepared with Al 2219 + 15%SiC + 5%Gr produced the maximum thrust force, torque, and burr when drilled with a coated carbide drill tool compared to other specimens. Feed rate was the main parameter that influenced thrust force and torque. The maximum burr height was produced by the coated carbide drill tool compared to the uncoated carbide drill tool. The metal matrix composite specimen is prepared with a novel combination of reinforcement and matrix materials such as aluminum alloy 2219, Silicon carbide (SiC), and Molybdenum disulfide (MoS₂).

This study examines the productivity of excavation and haulage equipment in overburden removal operations at the Borneo Indobara site, with a primary focus on optimizing front-loading geometry, improving material flow, and enhancing equipment performance through advanced modeling and real-time monitoring. Particular emphasis was placed on the optimization of front-loading geometry, material flow dynamics, and equipment configurations to enhance overall operational efficiency and reduce inefficiencies across excavation cycles. A novel framework integrating machine learning, metaheuristic algorithms, and IoT-enabled real-time monitoring was implemented to predict productivity, improve bucket fill factors, and reduce cycle times. Results demonstrated that optimal front dimensions and innovative loading patterns significantly increased productivity. Gradient Boosting and Particle Swarm Optimization were employed for precise modeling and resource allocation, while dynamic simulations validated the proposed solutions. The findings highlight the potential for advanced data-driven methods to mitigate inefficiencies and enhance performance in open-pit mining operations.

The viability of modern production systems hinges on maintaining high product quality and minimizing rejection rates. This has driven a shift towards digitalization in the industrial sector as a means of controlling and predicting product quality. For data-driven manufacturing methods to be effective, model performance must be high. The automated detection and classification of casting product defects is a difficult job. Recently, Convolutional Neural Networks (CNNs) have demonstrated improved efficacy in defect detection and classification. This research proposes a framework using deep learning techniques applied to a dataset of 8678 images of pump impellers. The quality of the cast is predicted using a custom CNN model and four pre-trained models (VGG16, ResNet50V2, InceptionV3, and MobileNetV2) with the help of a transfer learning method. Promising outcomes in predicting defective casting products have been achieved, with the VGG16 model demonstrating the highest accuracy at 94.31%. The proposed framework offers a significant practical impact by enabling manufacturing companies to identify defective products early in the production cycle. This early detection can substantially reduce inspection costs, lower resource loss from scrapping, and ultimately enhance the economic viability of the production system.

Energy consumption in additive manufacturing processes is critical in improving environmental quality and attaining a sustainable equilibrium between energy use and environmental degradation. The study employs two widely accepted non-parametric machine learning (ML) methods, i.e., Artificial Neural Network (ANN) and Gaussian Process Regression (GPR), to predict the energy consumption in the Fused Deposition Modeling manufacturing process (AM-FDM). The ANN and GPR models are compared based on a numerical general factorial design accounting for six graded-level parameters, i.e., A: learning rate, B: momentum. C: number of hidden nodes, D: proportions of the training data, E: proportion of test data, and F: the activation function. The sensitivity of the ANN and GPR models for the training subsets is further examined using different percentages of the original dataset—25%, 50%, and 75%—that are sampled using a modified hypercube sampling technique. Under all circumstances, the GPR model has performed better than the ANN.

The existence of notch or crack leads to impact the material behavior of any material, owed to the formation of discontinuity on the surface. In this study, the creep performance of AlSiMgCuFe alloy has been examined using molecular dynamics package under various creep conditions along with the existence of notch (crack) and un-notch (without crack) conditions and found that the notch existence has invoked larger impact on the creep performance of aluminum-silicon alloys tailed by the temperature and pressure (applied), due to the incidence of severe diffusion performance amidst the atoms. Further, it is quantified that the surge in the displacement and shear strain performance as a outcome of creep distortion time under various creep circumstances shows a vigorous part on the creep behavior and the pair correlation function and mean square displacement behavior has confirmed the similar performance which leads to modify its creep life.

Monitoring tool health is essential for maintaining efficiency, productivity, and quality in lathe turning operations. Traditional methods rely on manual assessments and subjective judgments, which can be time-consuming, inconsistent, and inadequate for detecting subtle tool wear. Therefore, this review discusses the literature review on predicting tool wear in the turning process, comprehensively examining the methods documenting for sensing and testing parameter design, image processing, and classification methods. The review outlines the use of vibration signals and images as datasets and advanced artificial intelligence techniques like machine learning, computer vision, deep learning, and expert systems to predict the accurate wear percentage in the tool. It also discusses the benefits and limitations of methods used in reviewed papers. To conclude, the performance of AI techniques from the reviewed papers, RNN from deep learning, gives more accuracy, with 97.04% predicting the tool wear. Within the Industry 4.0 framework, after a detailed review of the AI techniques, the combination of deep learning techniques that ensemble vibration signals and image information develops as a vital technology for evolving intelligent manufacturing.

To meet evolving customer expectations, companies need to take into consideration most challenging requirements. To help designers meet these increased needs, various methodologies, known as “Design for X (DfX)”, have been created. Nowadays, companies rely on a conventional view of Lean application during the use phase to integrate new requirements: let the system produce, detect wastes, then apply Lean tools to remedy them. However, this solution confront several limitations and constraints such as the initial design of the existing system, time and cost of implementing new Lean tools and resistance to change, etc. This implies a change of mindset by proactively integrate Lean requirements from the design phase. This paper aims to support designers in improving the overall performance of production systems by designing Leanless (Minimal Lean application required) sustainable, adaptable systems with minimal waste and human-centered considerations. For this purpose, we have analyzed Lean principles and tools in an Industry 5.0 context in the aim to extract a set of Lean requirements and parameters in line with Industry 5.0 principles. In addition, we have conducted a literature review of 34 DfX methodologies and classified them into six categories: Production, maintenance, quality, sustainability, human-centricity and Resilience. For each category, we have identified the Lean requirements and parameters that meet its objectives. To assess Lean requirements and select the appropriate Lean tools to be integrated from the design phase, we recommend the use of Multi-Criteria Decision Making (MCDM) methods. In addition, this study proposes to take advantage of inventive design to resolve potential contradictions between Lean requirement parameters and technical parameters. This study can serve as a guide for designers, assisting them in considering various requirements that can enhance the performance of the system being designed.

Bioinspired microrobots, a rapidly advancing field at the intersection of biology, microengineering, and medicine, has gained momentum due to recent progress in microfabrication techniques, smart materials, and precision control systems. Microrobots, miniaturized machines typically less than a millimeter in size, are engineered to emulate natural organisms such as bacteria, spermatozoa, and insects, enabling them to navigate complex, viscous biological environments. These devices offer transformative potential for targeted drug delivery, in vivo diagnostics, microsurgery, and tissue manipulation, especially in regions inaccessible to conventional medical tools. Despite their promise, microrobots face significant challenges related to propulsion efficiency, biocompatibility, actuation, and real-time imaging within the human body. This review contributes a comprehensive synthesis of current research in the field, organizing into four key sections: (1) bioinspired locomotion strategies, (2) advanced fabrication techniques and material innovations, (3) external actuation and control methodologies, and (4) current and emerging clinical applications. In addition to reviewing recent breakthroughs, this work critically discusses the limitations of current designs and outlines practical considerations for clinical translation, and scalability. This article emphasizes cross-disciplinary integration and application-specific design, positioning it as a valuable resource for guiding future innovations in minimally invasive microrobotic systems for medicine.