Enhanced Interactive Parallel Coordinates using Machine Learning and Uncertainty Propagation for Engineering Design

Abstract

The design process of an engineering system requires thorough consideration of varied specifications, each with potentially large number of dimensions. The sheer volume of data, as well as its complexity, can overwhelm the designer and obscure vital information. Visualisation of big data can mitigate the issue of information overload but static display can suffer from overplotting. To tackle the issue of overplotting and cluttered data, we present an interactive and touch-screen capable visualisation toolkit that combines Parallel Coordinates and Scatter Plot approaches for managing multidimensional engineering design data. As engineering projects require a multitude of varied software to handle the various aspects of the design process, the combined datasets often do not have an underlying mathematical model. We address this issue by enhancing our visualisation software with Machine Learning methods which also facilitate further insights into the data. Furthermore, various software within the engineering design cycle produce information of different level of fidelity (accuracy and trustworthiness), as well as with different speed. The induced uncertainty is also considered and modelled in the synthetic dataset and is also presented in an interactive way. This paper describes a new visualisation software package and demonstrates its functionality on a complex aircraft systems design dataset.

Optimisation of aero-manufacturing characteristics of aircraft ribs

“…• Apply for any positive integer N variables • Be the same for any N • Have complexity of the representation increase linearly with N • Give rise to a number of efficient geometrical algorithms For the purposes of this study, parallel coordinates visualised through the Cambridge Advanced Modeller 2 software [22] were only used to help visualise and understand the relationships from the optimisation results, where different pareto points were observed.…”

Using Parallel Coordinates in Optimization of Nano-Particle Drug Delivery

“…The approach has been previously demonstrated successfully in a number of different real-world applications [20], and in particular in aerospace design problems [26]. A view of the Software environment CAM-PCX ( [27]) is shown in Figure 2. The dataset represents the 48 points that shape the Pareto front of the optimization problem described in Section 2.…”

“…In the view in the left of Figure 2 we can see the Parallel Coordinates representation and in the right we can see the two Scatter plots of the decision-making space (upper), and of the parameter space (lower). The user can interactively explore the data in either view, as described in [27].…”

Multi-Domain Design Assessment for Aerospace Components Including Weld Accessibility

“…The present work requires the integration and extension of several state of the art design related modelling and simulation capabilities following Model Based Systems Engineering (MBSE) principles Pagliuca et al (2019). Hence a brief literature review on modelling based design methodology and simulation for manufacturability in design is appended.…”

“…Hence a brief literature review on modelling based design methodology and simulation for manufacturability in design is appended. Recently, multidisciplinary design systems have been reported from a UK-based research project, APROCONE (Piotrowski et al, 2019), representing state of the art technologies for interactive decision making for design experiments. To advance the assessment of manufacturability there is a need to replace, or expand, the predominately qualitative practices in Design for Manufacturing (DFM) with simulation based and quantified methods, such as proposed by Söderberg et al (2018).…”