Real-Time Defect Recognition and Optimized Decision Making for Structural Timber Jointing

Non-structural or out-of-grade timber framing material contains a large proportion of visual and natural defects. A common strategy to recover usable material from these timbers is the marking and removing of defects, with the generated intermediate lengths of clear wood then joined into a single piece of full-length structural timber. This paper presents a novel workflow that uses machine learning based image recognition and a computational decision-making algorithm to enhance the automation and efficiency of current defect identification and re-joining processes. The proposed workflow allows the knowledge of worker to be translated into a classifier that automatically recognizes and removes areas of defects based on image capture. In addition, a real-time optimization algorithm in decision making is developed to assign a joining sequence of fragmented timber from a dynamic inventory, creating a single piece of targeted length with a significant reduction in material waste. In addition to an industrial application, this workflow also allows for future inventory-constrained customizable fabrication, for example in production of non-standard architectural components or adaptive reuse or defect-avoidance in out-of-grade timber construction.

FE Simulation-Based Folding Defect Prediction and Avoidance in Forging of Axially Symmetrical Flanged Components

In the traditional metal forming product development paradigm, product design is generally based on heuristic know-how and experience, which are basically acquired through many years of practice. This kind of product design paradigm is of more trial-and-error than in-depth scientific calculation and analysis. Product defect prediction and quality assurance is, thus, a nontrivial issue in this product development paradigm. With the aid of finite element (FE) simulation, deformation-related defects can be predicted and analyzed. In this paper, flow-induced folding defect in forging of axially symmetrical flanged components is systematically investigated. A FE model to study the root-cause of the defect based on the material flow behavior is developed and a defect formation mechanism is revealed. The variation of material flow behavior with the changes of part geometry parameters is investigated extensively. Based on the simulation results, the parameter variation characteristics and the sensitivity of each parameter to folding defect avoidance are identified. Using industrial components as case studies, the efficiency of the proposed defect avoidance approach is verified. The approach is further proven to be able to provide practical guidelines for the design of defect-free axially symmetrical flanged components.