Prediction Models for Co-Design in Industry 4.0

In the realm of Industry 4.0, significant changes have unfolded across various sectors, notably in construction, driven by the adoption of digitisation and automation. This transformation demands a reassessment of traditional practices within the Architectural, Engineering, and Construction (AEC) industry. In response, the concept of Co-Design has emerged, offering a promising avenue to integrate diverse expertise and stakeholders throughout the construction process. This study explores the fusion of Co-Design principles with ML techniques to elevate fabrication processes and project outcomes within the AEC industry. The research introduces a workflow that intertwines design, fabrication, and data analysis by implementing a fabrication prediction ML model. By harnessing real-world data from timber additive construction processes, the model is trained to predict task durations accurately. This not only tackles the inherent complexities of fabrication processes but also provides flexibility across different design scenarios and fabrication environments. Through systematic evaluation and testing, the study identifies the most effective ML algorithms for predicting fabrication times. Furthermore, it showcases the practical application of the prediction model in optimising fabrication setups, ultimately resulting in tangible enhancements in efficiency and productivity.