The technology organization at Volvo Construction Equipment (VCE) aims topredict and verify the performance of machines like Wheel loaders (WL) andArticulated haulers (AH) to enhance product development, requirements engineering,and customer service, etc. Hence, it is needed to virtualize machinesand components using the existing sensors on the machines and infrastructureof the central server. Over the years, virtualization has been achieved throughthe use of digital twins (DTs) across different industries, but realizing it ondynamically complex construction machines (CE) has its own challenges. It isalso an important step in this digital transformation journey for VCE and otherCEs.This PhD thesis describes and investigates how the digital twin (DT) needs tobe developed for machines like AH, and more specifically for WL, and can begeneralized for other CEs. Further, a variety of actions are needed to incorporateinto the framework of the DT. The framework needs to support different machinesand their predictive journey, which can be different based on their usage andwhere they are being used.This DT is the virtual replica of the physical machines that feed the twins(simulation model) with data from sensors and edge-based algorithms. Thealgorithms are built using a machine learning (ML) model. The algorithmsthat are implemented into machines are often called machine logs or virtualsensors. Further, a high-fidelity simulation supports the different force-drivenmaneuvers of different machine operators. A new co-simulation frameworkhas been developed that integrates the operators’ model of the wheel loader(WL) and its interaction with the power source model, i.e., the drive train, thehydraulics, and the material. By using the simulations and physical machinedata, visualizations are built to illustrate the results, which support variousdepartments in providing customers with predictive services.The edge-based virtual sensors align well with their accuracy in predictingdifferent failures in the machines. Furthermore, the results show that the cosimulationmodel aligns well with measurement data, validating the model’saccuracy in different types of machine operator driving. The integration of virtualsensors, machine logs, simulation, and results visualization paves the way for asuccessful DT of the machines.The results are useful for engineers in product development, sales, and theaftermarket to create services and develop existing and future machines.The successful validation of the framework also paves the way for futureresearch to enhance the virtual simulation techniques for WL and AH machineperformances with different types of machine operators. It also paves the wayand inspires to improve ML algorithms on the edge and, therefore, create servicesunder the shadow of DTs for VCE and other CEs.
Manoranjan Kumar (Thu,) studied this question.