Transfer learning of machine learning models for multi-objective process optimization of a transferred mold to ensure efficient and robust injection molding of high surface quality parts

Gim, Jinsu; Hu, Yang; Turng, Lih‐Sheng

doi:10.1016/j.jmapro.2022.12.055

Cited by 30 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML is also utilized in smart refrigeration systems (Jiang et al, 2023), traceability and recall management (L. Zhang et al, 2024), quality prediction models, optimizing packaging (Gim et al, 2023), and dynamic pricing (Ben Slama & Mahmoud, 2023).…”

Section: Packaging and Chain Managementmentioning

confidence: 99%

Preservation of fruits through drying—A comprehensive review of experiments and modeling approaches

Kilic,

Sahin,

Hassan

et al. 2024

J Food Process Engineering

View full text Add to dashboard Cite

A significant part of the world's population still has problems in accessing food. The growing world population will exacerbate this issue in the future. Innovative studies conducted in this field play a crucial role in addressing the issue of drying and storage of foods. Atmospheric drying methods, such as rotary, tunnel, conveyor, cabinet, tower, and kiln dryers, offer advantages in relation to high production capacities, cost‐effective initial setup, and economical operating conditions. However, concurrently, the weaknesses of these methods arise from factors such as drying duration, uneven moisture content, and space requirements. The solar dryer method is especially effective in dehydrating agricultural products, offering an energy‐saving advantage compared to other methods. However, it is important to note that this approach, which involves exposing crops to direct sunlight, comes with several drawbacks affecting both food quality and health. In cases where the quality of highly valued foodstuffs is crucial, subatmospheric drying methods like vacuum, freeze, and microwave freeze are typically preferred. However, the primary drawback of this approach lies in its high operating costs, particularly in terms of energy consumption. Artificial neural networks (ANNs) can be used for predictive modeling, helping to forecast drying behavior and optimize process parameters in food drying applications especially nonlinear connections among variables. ANNs are adept at managing nonlinearities, offering a more precise depiction of the intricate interactions within food drying systems. This review examines articles from the last 5 years in the literature, synthesizing research conducted in food drying. The findings indicate a predominant interest among researchers in methodologies with lower environmental impact, prompting increased attention to studies addressing this aspect. There is a notable emphasis on the frequent exploration of energy‐efficient systems. The ongoing research focuses on the development of methods utilizing ultrasonic, infrared radiation, and electrohydrodynamic techniques to achieve more effective, shorter‐duration, energy‐efficient drying processes with enhanced control over the final product.

show abstract

Section: Packaging and Chain Managementmentioning

confidence: 99%

Preservation of fruits through drying—A comprehensive review of experiments and modeling approaches

Kilic,

Sahin,

Hassan

et al. 2024

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…The concerning hyperparameters and their ranges are listed in Table 1 (Partovi et al. , 2023; Gim et al. , 2023).…”

Section: Model and Algorithmmentioning

confidence: 99%

Multi-objective optimization of tribological properties of camshaft bearing pairs using DNN coupled with NSGA-II algorithm and TOPSIS

Zhao,

Li,

Xie

et al. 2024

ILT

View full text Add to dashboard Cite

Purpose This study aims to propose an optimization framework using deep neural networks (DNN) coupled with nondominated sorting genetic algorithm II and technique for order preference by similarity to an ideal solution method to improve the tribological properties of camshaft bearing pairs of internal combustion engine. Design/methodology/approach A lubrication model based on the theory of elastohydrodynamic lubrication and flexible multibody dynamics was developed for a V6 diesel engine. Setting DNN model as fitness function, the multi-objective optimization genetic algorithm and decision-making method were used to optimize the bearing pair structure with the goal of minimizing the total friction loss and the difference of the average values of minimum oil film thickness. Findings The results show that the lubrication state corresponding to the optimized bearing pair structure is elastohydrodynamic lubrication. Compared with the original structure, the optimized structure significantly reduces the total friction loss. Originality/value The optimized performance and corresponding structural parameters are obtained, and the optimization results were verified through multibody dynamics simulation. Peer review The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-12-2023-0417/

show abstract

“…However, during injection moulding, due to improper * Author to whom any correspondence should be addressed. parameters, substandard material pretreatment, accidental pollution, and other reasons, some surface defects that affect the function of moulded products inevitably occur [4][5][6][7][8]. Therefore, timely inspection for surface defects of injection moulded products is crucial for controlling product quality, optimising the manufacturing process, and enhancing the benefits of the enterprise.…”

Section: Introductionmentioning

confidence: 99%

A novel deep learning algorithm applied to machine vision inspection for surface defects of injection moulded products

Fan,

Qiu

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In modern industry, the surface defect inspection of injection moulded products is crucial for controlling product quality and optimizing the manufacturing process. With the development of optical measurement and computer technology, machine vision inspection methods have been widely adopted instead of manual inspection. However, current machine vision inspection methods are difficult to simultaneously ensure the accuracy and efficiency of surface defect inspection of injection moulded products. Considering this problem, a novel deep learning algorithm applied to machine vision inspection for surface defects of injection moulded products is proposed. To train and evaluate the proposed deep learning algorithm, an image acquisition platform is established and the dataset of surface defects in moulded products is obtained. In the proposed deep learning algorithm, reparameterization-based convolution modules are employed for feature extraction and feature fusion. A median iterative clustering algorithm based on hierarchical clustering initialization is proposed to obtain prior anchors that are highly matched with the actual distribution of defect sizes. A novel Focus-Entire Union over Covering (Focus-EUoC) loss function is utilized for bounding box regression. On these bases, the proposed deep learning algorithm applied to machine vision inspection is evaluated on the dataset of surface defects in moulded products. The experimental results indicate that compared to the traditional inspection algorithms and other deep learning algorithms currently used in machine vision inspection, the proposed deep learning algorithm exhibits superior inspection accuracy and inspection efficiency on the acquired dataset. The inspection precision reaches 0.964, the inspection recall reaches 0.955, and the inference time for each subgraph is only 6.1ms, confirming its effectiveness.

show abstract

Transfer learning of machine learning models for multi-objective process optimization of a transferred mold to ensure efficient and robust injection molding of high surface quality parts

Cited by 30 publications

References 9 publications

Preservation of fruits through drying—A comprehensive review of experiments and modeling approaches

Preservation of fruits through drying—A comprehensive review of experiments and modeling approaches

Multi-objective optimization of tribological properties of camshaft bearing pairs using DNN coupled with NSGA-II algorithm and TOPSIS

A novel deep learning algorithm applied to machine vision inspection for surface defects of injection moulded products

Contact Info

Product

Resources

About