Search

In recent years, the great trends of industry 4.0, internet of things (IoT), big data analytics, and cloud computing, the design and development of plastic injection molding (PIM) products has been more requested to achieve the requirements of light, thin, short, small, multi-function, high-precision, energy-saving, and obliged to fulfill a large number of customized production. To tackle this arduous challenge, effectively developing a novel PIM intelligent manufacturing system will play a crucial role. The aim of the proposed study is to carry on building an intelligent manufacturing system (IMS) for PIM industry, which is composed of three subsystems: a multiple response optimization systems of PIM, a database management system of process parameters, and a PIM real-time monitoring and control system. Firstly, the multiple response optimization systems present an intelligent optimization system to find optimal process parameters of multiple quality characteristics in the PIM process. Secondly, the database management system allows for saving the experimental data, PIM process parameter settings and quality goals. The third is a PIM real-time monitoring and control system, which establishes a graphic monitoring and control interface to real-time monitor the parameters of PIM machine and the optimal process parameter settings. The proposed PIM intelligent manufacturing systems enable the functions of real-time monitoring, process parameter optimization and database management, which can assure better PIM product quality and yield rate, effectively reduce the manufacturing cost, and promote the competition of the PIM industry in the future.

Globally, industries and economies have undergone rapid development and expansion over the last several decades. As a result, global warming and environmental contaminations have resulted in climate change and jeopardized food security. In many developing countries, already decreasing crop yields are threatened by extreme weather and soil damaged by genetically modified food, making environmental problems worse and increasing food and organic product prices. For these reasons, this study proposes a hybrid multicriteria decision-making (MCDM) model for new product development (NPD) in the light-emitting diode- (LED-) based lighting plant factory. First, literature reviews and expert interviews are employed in constructing a list of decision-making objectives and criteria for new product development. Then, a fuzzy Delphi method (FDM) is used to screen the elements of the objectives and criteria, while a fuzzy decision-making trial and evaluation laboratory (FDEMATEL) is used to determine the relationships among the objectives and criteria. Finally, a fuzzy analytic network process (FANP) and a composite priority vector (CPV) are manipulated to determine the relative importance weights of the critical objectives and criteria. Results show that the proposed method can create a useful and assessable MCDM model for decision-making applications in new product development, and a case study is herein performed to validate the feasibility of the proposed model in a Taiwanese LED-based lighting plant factory, which not only provides the decision-makers with a feasible hierarchical data structure for decision-making guidance but also increases the competitive advantages of trade-offs on developing novel products.

This paper proposes a systematic optimization model of process parameters in plastic injection molding (PIM). Firstly, the Taguchi method is employed for experimentation and data analysis, in which the quality characteristics for the plastic injection product are length and warpage. The control factors for the process are melt temperature, injection velocity, packing pressure, packing time, and cooling time. Moreover, the signal-to-noise (S/N) ratio and analysis of variance (ANOVA) are used to obtain a combination of parameter settings. Experimental data are set for the response surface methodology (RSM) in order to analyze and create two quality predictors and two S/N ratio predictors. The two quality predictors are associated with genetic algorithms (GA) to search for an optimal combination of process parameters that meets multiple-objective quality characteristics. Finally, four predictors are combined with the hybrid GA-PSO to find the final optimal combination of process parameters. The confirmation results show that the proposed model not only enhances the stability in the injection molding process, including the quality in length and warpage, but also reduces the costs of and time spent in the PIM process.

Research in assembly planning can be categorised into three types of approach: graph-based, knowledge-based and artificial intelligence approaches. The main drawbacks of the above approaches are as follows: the first is time-consuming; in the second approach it is difficult to find the optimal solution; and the third approach requires a high computing efficiency. To tackle these problems, this study develops a novel approach integrated with some graph-based heuristic working rules, robust back-propagation neural network (BPNN) engines via Taguchi method and design of experiment (DOE), and a knowledge-based engineering (KBE) system to assist the assembly engineers in promptly predicting a near-optimal assembly sequence. Three real-world examples are dedicated to evaluating the feasibility of the proposed model in terms of the differences in assembly sequences. The results show that the proposed model can efficiently generate BPNN engines, facilitate assembly sequence optimisation and allow the designers to recognise the contact relationships, assembly difficulties and assembly constraints of three-dimensional (3D) components in a virtual environment type.

Determining optimal process parameter settings critically influences productivity, quality, and cost of production in the plastic injection molding (PIM) industry. Previously, production engineers used either trial-and-error method or Taguchi's parameter design method to determine optimal process parameter settings for PIM. However, these methods are unsuitable in present PIM because the increasing complexity of product design and the requirement of multi-response quality characteristics. This research presents an approach in a soft computing paradigm for the process parameter optimization of multiple-input multiple-output (MIMO) plastic injection molding process. The proposed approach integrates Taguchi's parameter design method, back-propagation neural networks, genetic algorithms and engineering optimization concepts to optimize the process parameters. The research results indicate that the proposed approach can effectively help engineers determine optimal process parameter settings and achieve competitive advantages of product quality and costs.

This study develops a three-stage integrated approach with some heuristic working rules to assist the planner in generating a best and most effective assembly sequence. In the first stage, Above Graph and transforming rule are used to create a correct explosion graph of the assembly models. In the second stage, a three-level relational model, with geometric constraints and assembly precedence diagrams (APDs), is generated to create a complete relational model graph and an incidence matrix. In the third stage, the back-propagation neural network is employed to optimize the available assembly sequence. Two real-world examples are utilized to evaluate the feasibility of the proposed model in terms of the difference of assembly sequences. The results show that the proposed model can facilitate assembly sequence optimization and allows the designer to recognize the contact relationship and assembly constraints of three-dimensional (3D) components in a virtual environment type.

This study proposes a three-stage integrated approach with heuristic working rules to assist the planner to develop a better assembly plan. In the first stage, Above Graph and transforming rules were used to create a correct Explosion Graph of the assembly models. In the second stage, a three-level relational model was developed to create a complete relational model graph and an incidence matrix. In the third stage, a mathematical model, based on a penalty index was formulated, and a revised minimum spanning table method was used to generate and evaluate a feasible assembly sequence. The example of a military system is presented to demonstrate the feasibility of the proposed method. The contribution of this study is based on a design for assembly potential applications of three-dimensional (3D) component models to assist manual or automatic assembly in a virtual environment, and allows the designer to recognize the relative position, constraints and relationships of 3D components using graph-oriented methods: Above Graph, assembly precedent diagram, and relational model graph.

Stock price variation predictions are at the core of many research issues, and neural networks (NNs) are widely applied and were proven to be more efficient than time series forecasting for stock price forecasting. However, this type of research always determines the parameter settings of the NNs rationally through a trial-and-error methodology. This paper integrates design of experiment (DOE), Taguchi method, and back-propagation NN (BPNN) to construct a robust engine to further optimize the prediction accuracy under a robust DOE-based predictor. Adopting data from Taiwan Stock Exchange (TWSE), the technical analytical indexes and β value of the listed stocks of TWSE were computed. The research results indicated that the proposed approach can effectively improve the forecasting rate of stock price variations.

In this study, we developed a knowledge-based engineering (KBE) system to assist engineers in promptly predicting a near-optimal assembly sequence. A three-stage assembly optimization approach with some heuristic working rules was employed to establish the proposed system. In the first stage, Above Graph and a transforming rule were used to create a correct explosion graph of the assembly models. In the second stage, a three-level relational model graph, with geometric constraints and assembly precedence diagrams, was generated to create a completely relational model graph, an incidence matrix, and a feasible assembly sequence. In the third stage, a robust back-propagation neural network engine was developed and embedded in the Siemens NX system. System users can easily access the volume, weight, and feature number through the Siemens NX system interface, input the related parameters such as contact relationship number and total penalty value, and predict a feasible assembly sequence via a robust engine. Three real-world examples were used to evaluate the feasibility of the KBE system. The results show that the proposed system can facilitate feasible assembly sequences and allow designers to recognize contact relationships, assembly difficulties, and assembly constraints of three-dimensional components in a virtual environment type.

Determining optimal initial process parameter settings critically influences productivity, quality, and costs of production in the plastic injection molding (PIM) industry. Up to now, most production engineers have either used trial-and-error or Taguchi's parameter design method to determine initial settings for a number of parameters, including melt temperature, injection pressure, injection velocity, injection time, packing pressure, packing time, cooling temperature, and cooling time. But due to the increasing complexity of product design and multi-response quality characteristics, these multiple input-multiple output (MIMO) methods have some definite shortcomings. This research integrates Taguchi's parameter design methods with back-propagation neural networks, genetic algorithms, and engineering optimization concepts, to optimize the initial process settings of plastic injection molding equipment. The research results indicate that the proposed approach can effectively help engineers determine optimal initial process settings, reduce set-test iterations, and achieve competitive advantages on product quality and costs.

Research in assembly planning can be categorised into graph-based, knowledge-based and artificial intelligence approaches. The main drawbacks of the above approaches are as follows: the first is time-consuming; in the second approach it is difficult to find the optimal solution; and the third approach requires high computing efficiency. To tackle these problems, this study develops a novel integrated approach with some graph-based heuristic working rules and neural networks-based practices to assist the assembly engineers in generating and predicting a best and most effective assembly sequence. In the first stage, the Above Graph and transforming rules are used to create a correct explosion graph of the assembly models. In the second stage, a three-level relational model, with geometric constraints and assembly precedence diagrams (APDs), is generated to create a complete relational model graph, an incidence matrix and a globally optimal assembly sequence. In the third stage, Knowledge Fusion (KF) programming language and back-propagation neural network (BPNN) engine are employed to validate the available assembly sequences. Two real-world examples are utilised to evaluate the feasibility of the proposed model in terms of differences in assembly sequences. The results show that the proposed model can promptly generate feasible assembly sequences, facilitates assembly sequence optimisation and allows the designers to recognise contact relationships and assembly constraints of three-dimensional components in a virtual environment.

Assembly planning is commonly a tedious design procedure requiring a significant amount of manpower to obtain a feasible work plan. Poor assembly planning not only results in higher product cost and lower productivity but may also negatively impact the reliability, maintainability, and availability of a product during its life cycle. This study proposes a three-stage integrated approach with some heuristic working rules to assist the planner to develop a feasible assembly plan. In the first stage, Above Graph and transforming rules are used to create a correct Explosion Graph of the assembly models. In the second stage, a three-level relational model is developed to create a complete relational model graph and an incidence matrix. In the third stage, a genetic algorithm approach is used to generate and evaluate a near-optimal assembly sequence. An example of a military system is presented to demonstrate the feasibility of the proposed method.