The ready-mix concrete supply chain is highly disruptive due to its product perishability and Just-in-Time (JIT) production style. A lack of technology makes the ready-mix concrete (RMC) industry suffer from frequent production failures, ultimately causing high customer dissatisfaction and loss of revenues. In this paper, we propose the first-ever digital twin (DT) system in the RMC industry that can serve as a decision support tool to manage production risk efficiently and effectively via predictive maintenance. This study focuses on the feasibility of digital twins for the RMC industry in three main areas holistically: (1) the technical feasibility of the digital twin system for ready-mix concrete plant production risk management; (2) the business value of the proposed product to the construction industry; (3) the challenges of implementation in the real-world RMC industry. The proposed digital twin system consists of three main phases: (1) an IoT system to get the real-time production cycle times; (2) a digital twin operational working model with descriptive analytics; (3) an advanced analytical dashboard with predictive analytics to make predictive maintenance decisions. Our proposed digital twin solution can provide efficient and interpretable predictive maintenance insights in real time based on anomaly detection, production bottleneck identification, process disruption forecast and cycle time analysis. Finally, this study emphasizes that state-of-the-art solutions such as digital twins can effectively manage the production risks of ready-mix concrete plants by automatically detecting and predicting the bottlenecks without waiting until a production failure happens to react.
Intelligent Robotic Process Automation (IRPA) combines Artificial Intelligence (AI) and Robotic Process Automation (RPA) to automate complex unstructured tasks, improve decision-making, and cope with changing scenarios. A process analysis framework for IRPA adoption was developed by identifying key factors through a literature review and semi-structured expert opinion survey. The employed experts in the survey comprised RPA/IRPA consultants, RPA/IRPA initiative team leaders, and RPA/IRPA developers with three years or more experience. For the initial factor collection phase, there were a total of eighteen (18) responses, and for the factor evaluation phase, a total of twenty-six (26) experts were used to collect responses. Identified factors were shortlisted and evaluated using a Relative Importance Index (RII) analysis. The study’s findings are presented through a Causal-Loop Diagram (CLD) to illustrate the relationships between factors. The framework provides practical guidance for organizations planning to adopt IRPA, informing decision-making, resource allocation, and strategy development. The final process analysis framework highlights the importance of accuracy, level of human involvement in a task, and standardization as the main three primary factors for successful IRPA adoption. Three major secondary factors were identified: digital data input, integration with existing systems, and the cost of adopting new technologies. This research contributes to the added value to existing knowledge and serves as a foundation for future research in IRPA adoption.
24 November 2021 in Engineer: Journal of the Institution of Engineers, Sri Lanka
The building industry is strongly reliant on materials, which account for 55%-60% of its expenses. However, due to outdated and time-consuming approaches, inadequate inventory management prevails. This is where developing technologies such as Deep Learning (DL) might help uncover solutions. Surprisingly, very little scientific research on DL has been conducted for this purpose. As a result, this study looks into the prospect of automating construction warehouse management by employing CNN for object detection and counting. During the initial investigation, 23 studies out of 26 used Convolutional Neural Networks (CNN) for image processing and object detection. Secondly, a model was developed and compared its accuracy to that of human counting and discovered that the model outperformed people. Industry professionals were interviewed to discuss the findings. Industry professionals highlighted the advantages and disadvantages of using such an automated system in construction warehouses. In conclusion, this study shows that the CNN base model outperforms people in counting materials, and the proposed automated inventory management system has significant industry potential.