Johan Wall

The ongoing servitization journey of the manufacturing industries instills a through-life perspective of value, where a combination of products and services is delivered to meet expectations. Often described as a product-service system (PSS), these systems are poised with many complexity aspects, introducing uncertainties during the design phase. Incorporating changeability is one of the known strategies to deal with such uncertainties, where the system changes in the face of uncertainty to sustain value, thereby achieving value robustness. While the theme of dealing with multiple uncertainties has been discussed since the inception of PSS, changeability is still poorly addressed. To bridge this gap, an integrative literature review is performed to outline various complexities aspects and their link to uncertainty from a PSS perspective. Also, the state-of-the-art approach to achieving value robustness is presented via changeability incorporation. Subsequently, a reference framework is proposed to guide decision-makers in changeability incorporation in PSS, especially during the early design stages.

This paper presents an approach that utilizes artificial intelligence techniques to identify autonomous machine behavior patterns. The context for investigation involves a fleet of prototype autonomous haulers as part of a Product Service System solution under development in the construction and mining industry. The approach involves using deep learning-based object detection and computer vision to understand how prototype machines operate in different situations. The trained model accurately predicts and tracks the loaded and unloaded machines and helps to identify data patterns such as course deviations, machine failures, unexpected slowdowns, battery life, machine activity, number of cycles per charge, and speed. PSS solutions hinge on efficiently allocating resources to meet the required site-level output. Solution providers can make more informed decisions at the earlier stages of development by using the AI techniques outlined in the paper, considering asset management and reallocation of resources to account for unplanned stoppages or unexpected slowdowns. Understanding machine behavioral aspects in early-stage PSS development could enable more efficient and customized PSS solutions.

The shift towards Product-Service Systems (PSS) stresses the need to embed new and unique capabilities in Decision Support Systems, with the aim of helping the engineering team in handling the pool of information and knowledge available during decision events. Emerging from a multiple case study in the Swedish manufacturing industry, this paper describes the development of the Model-Driven Decision Arena (MDDA), an environment for collaborative decision-making that focuses on the early design phases of PSS. Based on the findings from multiple case studies, this paper illustrates the main goals of the MDDA, detailing its main functions, its physical environment, and its software architecture and models. This paper demonstrates the use of the MDDA in a case study related to the development of an asphalt compactor, presenting and discussing the results of verification activities conducted with industrial practitioners on the current MDDA prototype.

A data analysis method aiming to support cause and effect analysis in design exploration studies is presented. The method clusters and aggregates effects of multiple design variables based on the structural hierarchy of the evaluated system. The resulting dataset is intended as input to a visualization construct based on colour-coding CAD models. The proposed method is exemplified in a case study showing that the predictive capability of the created, clustered, dataset is comparable to the original, unmodified, one.

The ability to predict and control the outcome of the sheet metal forming process demands holistic knowledge of the product/process parameter influences and their contribution in shaping the output product quality. Recent improvements in the ability to harvest in-line production data and the increased capability to understand complex process behaviour through computer simulations open up the possibility for new approaches to monitor and control production process performance and output product quality. This research presents an overview of the common process monitoring and control approaches while highlighting their limitations in handling the dynamics of the sheet metal forming process. The current paper envisions the need for a collaborative monitoring and control system for enhancing production process performance. Such a system must incorporate comprehensive knowledge regarding process behaviour and parameter influences in addition to the current-system-state derived using in-line production data to function effectively. Accordingly, a framework for monitoring and control within automotive sheet metal forming is proposed. The framework addresses the current limitations through the use of real-time production data and reduced process models. Lastly, the significance of the presented framework in transitioning to the digital manufacturing paradigm is reflected upon.