Genetic algorithms for the scheduling in additive manufacturing

The advent of Additive Manufacturing (AM) process has greatly broadened the machining methods. Compared to conventional manufacturing methods, the process planning for AM is totally different. It should avoid process-induced defects such as warpage of overhang features. Process planning for AM should also generate necessary support structure not only to support the overhang structure but also to minimize thermal warpage and residual stress. In order to do so, a general process planning for AM is put forward in this paper. Given a specific part, the first step is the determination of build orientation. The choice of build orientation is one of the critical factors in AM since the build time, the material consumption, the removal of support structure, the deformation within final parts, the mechanical performance, and the surface roughness are all related to the build orientation. This paper utilizes the genetic algorithm to optimize the build orientation by considering the minimum volume of the support structure and the minimum strain energy of a part under specific working conditions. First, a general and feasible process planning for AM is proposed. Then detailed process planning for the optimization of build orientation is developed. The volume of support structure and strain energy are considered independently and corresponding optimal build orientations are obtained through genetic algorithm. A single weighted aggregate optimization function is then constructed to optimize the volume of support structure and strain energy simultaneously. Finally, a bracket is used to verify the feasibility of the proposed method.

Additive manufacturing (AM), also known as 3D printing is being widely used in the manufacturing industry. Moreover, from the past few years, there has been an increase in research toward the applicability of artificial intelligence (AI) technologies in the field of AM. The primary reason for the same includes the need to automate and deal with the complex problems in the domain of AM. This paper presents a first-of-its-kind scientometric analysis of the research being conducted toward the use of AI-in-AM. This study helps in uniquely presenting the visualization of data as well as understanding the trends, prominent journals, institutes, countries and topics of research interest and how they are linked with the studies available nowadays on AI-in-AM. Data corresponding to various research papers in this domain were collected from Scopus. Results obtained from the visual analysis indicate that machine learning, deep learning (neural networks), genetic algorithms, industry 4.0 are the most widely adopted AI techniques in the AM. Further deploying these AI techniques, computer-aided design, fabrication, industrial research, optimization, robotics, modeling, image processing are some of the key areas of research. As per the observed scenarios, future research directions such as the applicability of robotics and neural network techniques to AM domains have been emphasized. Also, 4D printing is the new trend with future holding to 5D printing as well. Overall, this study aims to provide a complete reference to researchers as well as industry practitioners regarding the trends and competences when employing AI-in-AM.

Effectiveness analysis of resources consumption, environmental impact and production efficiency in traditional manufacturing using new technologies: Case from sand casting

In this paper, on the basis of the analysis of common market model and some economic theories in the cloud computing resource management process, we propose a cloud resource management model based on combinatorial double auction. In order to solve the winner determination problem (WDP) in the combinatorial double auction, a cloud resource combinatorial double auction algorithm based on genetic algorithm and simulated annealing algorithm is proposed. Simulation results reveal that the algorithm combines genetic algorithm with simulated annealing algorithm (SAGA) outperforms genetic algorithm on fitness value and stability, and as the number of bidders increase, the solution have higher fitness value can be obtained.

Over the years, rapid prototyping (RP) has been implemented in several companies in the manufacture of three-dimensional (3D) models. This process produces parts in a short time, in small quantities, and with complex geometry and is cheaper. RP can be divided into additive manufacturing and subtractive manufacturing, the former being the most used in 3D object printing. Additive manufacturing is a widely used process consisting of the adding of material layer by layer for building 3D objects from a model projected on a computer. This technology allows the printing of objects with complex shapes and is being increasingly adopted by the aircraft industry, jewelry, footwear, automotive, fashion products and medical implants, among others. When printing 3D objects, the build orientation optimization of 3D models influences the costs and surface quality. In this work, three build orientation optimization problems are studied: the single-objective problem, bi-objective problem and many-objective problem. To this end, three quality measures are applied: the support area, the build time and the surface roughness, for the car hoodvent model. First, a single-objective optimization problem is presented and solved by the genetic algorithm, obtaining optimal solutions for each objective function. Then, a study of the bi-objective optimization problem is carried out for each pair of objectives, and some representative trade-off solutions are identified. Finally, the study of the many-objective optimization problem, considering the three measures optimized simultaneously, is presented with some more optimal solutions found. The bi-objective and many-objective problems are solved by a multi-objective genetic algorithm. For a better analysis and comparison of the solutions found, Pareto fronts are used, enabling a better visualization of the solutions between the objectives. This chapter aims to assist the decision-maker in choosing the best part print orientation angles according to his/her preferences. The proposed approach found optimal solutions confirming its effectiveness.

Metal additive manufacturing (AM) allows for the creation of complex, high-performance components; however, defects such as porosity, residual stresses, and microstructural inconsistencies continue to pose significant challenges. This study develops a physics-based analytical modeling framework to predict defects and porosity caused by a lack of fusion in metal AM processes and establishes the approach of optimizing process parameters to minimize defects and searching for optimized parameters. By integrating the thermal model, heat transfer boundary conditions, molten pool geometry, and image analysis, the analytical model establishes relationships between critical process features (e.g., laser power, scanning speed) and defect characteristics. Further, an optimization approach using a genetic algorithm (GA) is utilized to identify the best parameter sets that reduce porosity while largely reducing computational cost. Experimental validation confirms that the model accurately predicts defect trends and optimizes process conditions. This proposed framework provides a computationally efficient tool for mitigating defects, thereby enhancing reliability and promoting wider adoption of metal AM in industrial applications.

Additive manufacturing (AM) has impacted the manufacturing of complex three-dimensional objects in multiple materials for a wide array of applications. However, additive manufacturing, as an upcoming field, lacks automated and specific design rules for different AM processes. Moreover, the selection of specific AM processes for different geometries requires expert knowledge, which is difficult to replicate. An automated and data-driven system is needed that can capture the AM expert knowledge base and apply it to 3D-printed parts to avoid manufacturability issues. This research aims to develop a data-driven system for AM process selection within the design for additive manufacturing (DFAM) framework for Industry 4.0. A Genetic and Evolutionary Feature Weighting technique was optimized using 3D CAD data as an input to identify the optimal AM technique based on several requirements and constraints. A two-stage model was developed wherein the stage 1 model displayed average accuracies of 70% and the stage 2 model showed higher average accuracies of up to 97.33% based on quantitative feature labeling and augmentation of the datasets. The steady-state genetic algorithm (SSGA) was determined to be the most effective algorithm after benchmarking against estimation of distribution algorithm (EDA) and particle swarm optimization (PSO) algorithms, respectively. The output of this system leads to the identification of optimal AM processes for manufacturing 3D objects. This paper presents an automated design for an additive manufacturing system that is accurate and can be extended to other 3D-printing processes.

The choice of model orientation is a very important issue in Additive Manufacturing (AM). In this paper, the model orientation problem is formulated as a multi-objective optimization problem, aiming at minimizing the building time, the surface quality, and the supporting area. Then we convert the problem into a single-objective optimization in the linear-weighted way. After that, the Genetic Algorithm (GA) is used to solve the optimization problem and the process of GA is parallelized and implemented on GPU. Experimental results show that when dealing with complex models in AM, compared with CPU only implementation, the GPU based GA can speed up the process by about 50 times, which helps to significantly reduce the optimization time and ensure the quality of solutions. The GPU based parallel methods we proposed can help to reduce the execution time and improve the efficiency greatly, making the processes more efficient.

In this paper, we use the genetic algorithms (GA) technique to handle two problems in the manufacturing systems: the formation of manufacturing cell in cellular manufacturing and batch scheduling. In the formation of machine cells, we use multi-objective functions as criteria to form cell. These criteria are to minimise the inter-cell movement, to minimise variation of workload within cells and to maximise the similarity within cells. Results showed that by varying the weights of each criterion, the algorithm produced is flexible to adapt to changes in the manufacturing environment. Unlike traditional methods which merely rearrange the part-incidence matrix, this algorithm incorporates other parameters such as processing times of each part and number of parts required. The batch scheduling problem described in this paper is the problem of scheduling a single-machine with jobs of different due-dates and arrival times. We have developed an algorithm which is not only able to find the optimum or near-optimal sequence of jobs, but also able to determine the number of jobs to be processed in each batch. The objective function used is to minimise total tardiness.

An integrated machine vision based system for solving the nonconvex cutting stock problem using genetic algorithms

Deregulation of telecommunications has meant an increase in third-party service provision, personalized service delivery and integrated networks and media. The efficient allocation of services, without human intervention, to satisfy advanced service requirements spanning several networks is a crucial task. This can be modeled as a winner determination problem in combinatorial auctions where there are multiple services, service providers and winner determination criteria (like cost, bandwidth, delay, etc) but we have shown the problem is NP-complete. This paper describes a new two-stage algorithm for optimal anytime winner determination. In the first stage, a hierarchical task network planner is used to decompose a task into subtasks that can be solved by the available services. In the second stage, a genetic algorithm with heuristics is used to find the optimal combination of service providers to provide the services identified. We show through various experiments that the genetic algorithm finds optimal solutions quicker than a modified depth-first search algorithm.

Biomechanical investigation into the structural design of porous additive manufactured cages using numerical and experimental approaches

Adapted techniques of explainable artificial intelligence for explaining genetic algorithms on the example of job scheduling

This paper presents a methodology for designing key features of a flexible wind turbine blade with an actively variable twist distribution. Simulation results suggest this capability can increase the aerodynamic efficiency during Region 2 operation. The concept for the flexible blade consists of a rigid spar with flexible modular segments that form the surrounding shells. The segments are additively manufactured. The associated compliances of the each individual segment and actuator placement determine the Twist Angle Distribution (TAD). It is assumed that the degree of flexibility for each segment will be established through the design and additive manufacturing (AM) processes. Moreover, the variations in compliance make it possible for the blade to conform to the desired set of TAD geometries. The design process first determines the TAD that maximizes the aerodynamic efficiency for discrete points of wind speed in Region 2. The results are obtained using the National Renewable Energy Laboratory (NREL) Aerodyn software and a genetic algorithm. The TAD geometry is then passed to a mechanical design algorithm that locates a series of actuators and defines the stiffness ratio between the blade segments. The process employs a computer cluster to create the TAD for a set of design scenarios. The design selections are found through an objective function. It minimizes the amount of deviation between the actual TAD and that found in the aerodynamic analysis. The free-shape TAD is determined in the final step. The geometry is chosen to minimize the amount of deflection needed to shape the TAD, which changes with Region 2 wind speed. A case study suggests that a blade with only five actuators can achieve the full range of TAD geometry. Moreover, the design solution can increase the efficiency at cut-in and rated speeds up to 3.8% and 3.3%, respectively.

This work reports the development of robust and efficient algorithms for optimum process planning of Additive Manufacturing (AM) processes needing support structures during fabrication. In particular, it addresses issues like part hollowing, support structure generation and optimum part orientation. Input to the system is a CAD model in STL format which is voxelized and hollowed using the 2D Hollowing strategy. A novel approach to design external as well as internal support structures for the hollowed model is developed considering the wall thickness and material properties. Optimum orientation of the hollowed part model is computed using Genetic Algorithm (GA). The Fitness Function for optimization is the weighted average of process performance parameters like build time, part quality and material utilization. A new performance measure has been proposed to choose the weightages for performance parameters to obtain overall optimum performance. The paper presents, in detail, the design and development of algorithms with results for typical case studies. The proposed methodology will significantly contribute to improving part quality, productivity and material utilization for AM processes.