Automated machining feature recognition, a sub-discipline of solid modeling, has been an active research area for last three decades and is a critical component in digital manufacturing thread for ...detecting manufacturing information from computer aided design (CAD) models. In this paper, a novel framework using Deep 3D Convolutional Neural Networks (3D-CNNs) termed FeatureNet to learn machining features from CAD models of mechanical parts is presented. FeatureNet learns the distribution of complex manufacturing feature shapes across a large 3D model dataset and discovers distinguishing features that help in recognition process automatically. To train FeatureNet, a large-scale mechanical part datasets of 3D CAD models with labeled machining features is automatically constructed. The proposed framework can recognize manufacturing features from the low-level geometric data such as voxels with a very high accuracy. The developed framework can also recognize planar intersecting features in the 3D CAD models. Extensive numerical experiments show that FeatureNet enables significant improvements over the state-of-the-arts manufacturing feature detection techniques. The developed data-driven framework can easily be extended to identify a large variety of machining features leading to a sound foundation for real-time computer aided process planning (CAPP) systems.
•A novel deep 3D CNN framework to learn machining features from CAD models.•A large-scale labeled manufacturing features dataset with 3D CAD models.•Significant improvements over the state-of-the-arts manufacturing feature detection.
We review the literature about shop scheduling problems in manufacturing systems, revealing the concepts and methodologies that most impact the usage of scheduling theory in manufacturing ...environments. We focus our attention on the job shop and flow shop problems and their variants. We emphasize the interactions between the scheduling functions and manufacturing paradigms such as Industry 4.0, Computer Integrated Manufacturing, Computer‐Aided Process Planning, Advanced Planning and Scheduling, and Integrated Process Planning and Scheduling. We describe the main components and characteristics of the scheduling ecosystem, and we discuss how the scheduling interacts with the components that make it up and how it is affected by them. The metadata collected from the digital libraries on which the review was based (ScienceDirect, Scopus, and Elsevier) made it possible to characterize the historical evolution of the main concepts of the scheduling ecosystem in terms of scientific publications and research trends in the period 2000–2020.
•A feature-based part variety model is proposed.•A reconfigurable machining operation plan model is proposed.•A reconfigurable machining process plan model is proposed.•A global framework for ...reconfigurable process planning is proposed.
Conventional machining process planning approaches are inefficient to handle the process planning complexity induced by part variety. Reconfigurable process planning is a new process planning approach which has been well recognized as a key enabler for current manufacturing paradigms. However, in the literature, there is neither a comprehensive part variety representation model to support reconfigurable process planning nor a global solution framework to instruct the generation of the feasible process plans for a specific part variant. Therefore, this paper extends the concept of reconfigurable process planning to a concept of reconfigurable machining process planning which targets the process plan generation for a part family. A solution framework is developed for reconfigurable machining process planning. In this framework, a feature-based part variety model is proposed to represent a part family; A reconfigurable machining process plan is defined as a set of modular components which can be configured/reconfigured into the machining process plans for any part variant in the family; a novel configuration approach is proposed to generate the process plan components for a specific part variant while configuring this part variant from the family. The feasibility and effectiveness of the proposed framework and models are tested in a real case study.
Process planning and scheduling are two of the most important functions in the manufacturing system. Traditionally, process planning and scheduling were regarded as separate tasks performed ...sequentially, where scheduling was implemented after process plans had been generated. However, their functions are usually complementary. If the two systems can be integrated more tightly, greater performance and higher productivity of manufacturing system can be achieved. In this paper, a new hybrid algorithm (HA) based approach has been developed to facilitate the integration and optimization of these two systems. To improve the optimization performance of the approach, an efficient genetic representation, operator and local search strategy have been developed. Experimental studies have been used to test the performance of the proposed approach and to make comparisons between this approach and some previous works. The results show that the research on integrated process planning and scheduling (IPPS) is necessary and the proposed approach is a promising and very effective method on the research of IPPS.
Process planning and scheduling are modeled sequentially in the traditional manufacturing system. However, because of their complementarity, the increasing need to integrate them has emerged to ...enhance the manufacturing productivity significantly. Therefore, the integrated process planning and scheduling (IPPS) is becoming a hotspot in providing a blueprint for efficient manufacturing system. This paper proposes a novel algorithm hybridizing the genetic algorithm with strong global searching ability and variable neighborhood search with strong local searching ability for the IPPS problem. To improve the searching ability, a novel procedure, encoding method, and local search method have been designed. Effective operators have been adopted. Three experiments with totally 37 well-known benchmark problems are employed to evaluate the performance of the proposed method. Based on the results, the proposed algorithm outperforms the state-of-the-art methods and finds the new solutions (the best solutions found so far) for some problems. The proposed method has also been applied on a real-world case from a nonstandard equipment production workshop for the packaging machine of a machine tool company in China. The solution demonstrates that it can solve real-world cases very well.
Robotic machining centers offer diverse advantages: large operation reach with large reorientation capability, and a low cost, to name a few. Many challenges have slowed down the adoption or ...sometimes inhibited the use of robots for machining tasks. This paper deals with the current usage and status of robots in machining, as well as the necessary modelling and identification for enabling optimization, process planning and process control. Recent research addressing deburring, milling, incremental forming, polishing or thin wall machining is presented. We discuss various processes in which robots need to deal with significant process forces while fulfilling their machining task.
Ultra-short laser pulses are frequently used for material removal (ablation) in science, technology and medicine. However, the laser energy is often used inefficiently, thus, leading to low ablation ...rates. For the efficient ablation of a rectangular shaped cavity, the numerous process parameters such as scanning speed, distance between scanned lines, and spot size on the sample, have to be optimized. Therefore, finding the optimal set of process parameters is always a time-demanding and challenging task. Clear theoretical understanding of the influence of the process parameters on the material removal rate can improve the efficiency of laser energy utilization and enhance the ablation rate. In this work, a new model of rectangular cavity ablation is introduced. The model takes into account the decrease in ablation threshold, as well as saturation of the ablation depth with increasing number of pulses per spot. Scanning electron microscopy and the stylus profilometry were employed to characterize the ablated depth and evaluate the material removal rate. The numerical modelling showed a good agreement with the experimental results. High speed mimicking of bio-inspired functional surfaces by laser irradiation has been demonstrated.
As the core link of intelligent manufacturing, the process planning of aviation parts still faces the challenges such as relying on manual experiences for process decision-making and lack of linkage ...between process design and manufacturing for process optimisation. Process knowledge could support scientific decision-making on process issues, while twin data, namely high-fidelity simulation data and feedback information of manufacturing site, could further verify the process plans and optimise process parameters, so as to continuously improve the quality of process plans. Consequently, this paper proposes a general framework for twin data and knowledge-driven intelligent process planning (TDKIPP) of aviation parts, and analyses four standard procedures that support the above-mentioned reference framework, namely mechanism-data fusion process digital twin model, dynamic process knowledge base, process decision-making and evaluation, machining quality prediction and process feedback optimisation. A thus constructed test bed of TDKIPP and its four application examples about the process planning of a micro turbojet engine integral impeller demonstrate the feasibility and effectiveness of the proposed approach.
The transition to intelligent manufacturing provides a fulcrum for the revolution of product lifecycle like design, manufacturing and maintenance, so does it for process planning. Specifically, ...digital twin manufacturing cell (DTMC) is regarded as a new means of and also a basic unit for implementing intelligent manufacturing. Incorporating process planning in DTMC could improve the integrity of DTMC and enhance the feasibility of process planning. Consequently, this paper proposes a deep learning-enabled framework for intelligent process planning towards DTMC. Firstly, a process knowledge reuse network (PKR-Net) that takes deep residual networks as base architecture is embedding into the framework, which could understand design intents expressed in a drawing or a 3D computer-aided design (CAD) model via its views and automatically retrieve relevant knowledge for the quick generation of theorical processes. Then, an evaluation twin is constructed to transform the theorical processes into practical operations and produce an optimal process plan. Finally, a test bed of the framework is constructed and the experimental results demonstrate the feasibility and effectiveness of the approach.