Genetic Algorithm
Assembly Line
An ensemble neural network for optimising a CNC milling process
Computer numerical control (CNC) milling is a common method for the efficient mass production of products. Process efficiency and product quality have a strong dependency on the cutting process conditions. Furthermore, optimising a process for material removal rate (MRR) and surface roughness (SR), which are measures of process efficiency and product quality, respectively, is a complex optimisation task due to their contrasting relationships with process parameters. In this work, CNC end milling is performed on aluminium 6061 to investigate the influence of key process input variables (feed per tooth, cutting speed, and depth of cut) on the machined part’s SR. Firstly, a full factorial parametric study is conducted and analysed using Analysis of Variance (ANOVA) before an Ensemble Neural Network (ENN) is trained on the experimental data. To capture the complex nonlinear relationships accurately, each base model of the ENN is a combined genetic algorithm-artificial neural network, whose hyperparameters are optimised using a Bayesian optimisation framework.
Multi-granularity service composition in industrial cloud robotics
Industrial cloud robotics employs cloud computing technology to provide various operational services, such as robotic control modules that enable customized screwing and welding. Service composition technology enables the flexible implementation of complex industrial robotic applications based on the collaboration of multiple industrial cloud robotic services. Most studies considered cloud robotic services with a single robotic manipulator with a fixed function. To utilize the advantages of coarse-grained services encapsulated by multi-functional robots, manipulators, and control applications, a multi-granularity service composition method is introduced considering the multi-functional resources and capabilities of the cloud robotic services. Then a quality-of-service-aware multi-granularity robotic service composition model is built to evaluate the composition solution. Furthermore, a multi-granularity robotic service matching strategy is proposed according to the matching constraints of coarse-grained services. Six representative multi-objective evolutionary algorithms are adopted to optimize five quality-of-service attributes of the composite service simultaneously. Experiments demonstrate that the proposed multi-granularity robotic service composition method can remarkably improve the quality of robotic composite services for complex manufacturing tasks by utilizing coarse-grained services in addition to fine-grained services. The performances of six multi-objective evolutionary algorithms are compared to determine the most suitable algorithm for the multi-granularity robotic service composition problem.
The Multi Crane Scheduling Problem: A Comparison Between Genetic Algorithms and Neural Network approaches based on Simulation Modeling
The internal logistics for warehouses of many industrial applications, based on the movement of heavy goods, is commonly solved by the installment of a multi-crane system. The job scheduling of a multi-crane is an interesting problem of optimization, solved in many ways in the past: this paper describes a comparison between the optimization by the use of Genetic Algorithms and the machine learning piloting driven by Neural Networks. A case-study for steel coil production is proposed as a test frame for two different simulation software tools, one based on heuristic solution and one on machine learning; performances and data achieved from reviews and simulations are compared.
Manufacturing line design configuration with optimized resource groups
Skilled line engineers spend several months designing a manufacturing line based on their experience. Optimization of the four design specifications from the viewpoint of productivity and equipment continuity is required for the line design process. However, these four design specifications are highly dependent on each other and the number of feasible combinations of the specifications is enormous and difficult to automate.
To solve these issues, our research introduces the concept of a resource group that enables a methodology to solve the four design items hierarchically and develops methods to quickly build new manufacturing lines in response to changes in product varieties and manufacturing fluctuations in a factory.
Quality prediction of ultrasonically welded joints using a hybrid machine learning model
Ultrasonic metal welding has advantages over other joining technologies due to its low energy consumption, rapid cycle time and the ease of process automation. The ultrasonic welding (USW) process is very sensitive to process parameters, and thus can be difficult to consistently produce strong joints. There is significant interest from the manufacturing community to understand these variable interactions. Machine learning is one such method which can be exploited to better understand the complex interactions of USW input parameters. In this paper, the lap shear strength (LSS) of USW Al 5754 joints is investigated using an off-the-shelf Branson Ultraweld L20. Firstly, a 33 full factorial parametric study using ANOVA is carried out to examine the effects of three USW input parameters (weld energy, vibration amplitude & clamping pressure) on LSS. Following this, a high-fidelity predictive hybrid GA-ANN model is then trained using the input parameters and the addition of process data recorded during welding (peak power).
Scientists Set to Use Social Media AI Technology to Optimize Parts for 3D Printing
“My idea was that a material’s structure is no different than a 3D image,” he explains. “It makes sense that the 3D version of this neural network will do a good job of recognizing the structure’s properties — just like a neural network learns that an image is a cat or something else.”
To see if his idea would work, Messner designed a defined 3D geometry and used conventional physics-based simulations to create a set of two million data points. Each of the data points linked his geometry to ‘desired’ values of density and stiffness. Then, he fed the data points into a neural network and trained it to look for the desired properties.
Finally, Messner used a genetic algorithm – an iterative, optimization-based class of AI – together with the trained neural network to determine the structure that would result in the properties he sought. Impressively, his AI approach found the correct structure 2,760x faster than the conventional physics simulation.