Revisiting optical scattering with machine learning (SPARKLE)

Lead Research Organisation: University of Nottingham
Department Name: Faculty of Engineering

Abstract

The surface topography of a component part can have a profound effect on the function of the part. In tribology, it is the surface interactions that influence such quantities as friction, wear and the lifetime of a component. In fluid dynamics, it is the surface that determines how fluids flow and it affects such properties as aerodynamic lift, therefore, influencing efficiency and fuel consumption of aircraft. Examples of the relationships between the topography of a surface and how that surface functions in use can be found in almost every manufacturing sector, both traditional and high-tech. To control surface topography, and hence the function and/or performance of a component, it must be measured and useful parameters extracted from the measurement data. There are a large number instruments that can measure surface topography, but many of them cannot be used realistically for real-time in-process applications due to the need for scanning in either the lateral axes and/or the vertical axis. There have been developments in area-integrating (scattering) methods for measuring surface topography that can be fast enough to use during a manufacturing process, but these are limited in the height range of surface topography with which they can be used.

In conventional machining, there has been a significant research effort to determine the surface topography of the machined parts during the manufacturing process. The dominant technology for this has been machine vision approaches, where a relationship between a texture parameter and an aspect of the measured field from an intensity sensor is determined. Such approaches have two major drawbacks: 1. they are usually applied to surfaces with geometrical features over a limited range and 2. they do not have the benefit of a physical model of the measurement process, i.e. they are purely empirical. As an example, the measurement and characterisation of the surface topography of additive manufactured parts remains a significant challenge, especially where measurement speed may be an issue. Typical metal additive manufactured surfaces have a large range of surface features, with the dominant features often being the weld tracks with typical wavelengths of a few hundred micrometres and amplitudes of a few tens of micrometres; such structures are beyond what can be measured effectively with existing commercial approaches.

In the proposed project, we aim to demonstrate that it is possible to measure rough and structured, machined or additive surfaces using a simple, cost-effective real-time measurement system. This will involve the development of a fully rigorous three-dimensional optical scattering model, which will be combined with a machine learning approach to mine optical scattering data for topographic information that is not within the range of commercial scattering instruments. The proposed system could be mounted into a machining or additive operation without slowing down the process, therefore, reducing the cost of many advanced products that require engineered surfaces. To demonstrate the commercial potential of the project outputs, we have several advanced manufacturing partners who will supply industrially relevant case studies and one partner who could act as the commercial exploitation route for the instrument.

Planned Impact

Advanced manufacturing is an important technology for societal change. Metrology is an underlying requirement of a progressive society and it has impact at every stage of a products life, from manufacturing through use, to eventual disposal. The better an object can be measured the better it can be made, and the better it can provide its function. Metrology plays a critical role in underpinning the development and optimisation of all new manufacturing processes and is key to the digital manufacturing revolution we are currently experiencing, the so-called "4th Industrial Revolution" or "Industry 4.0". According to a report by Frost and Sullivan, by 2025 the EU will generate revenue of up to $821 million from the dimensional metrology sector alone. The report predicts the revenue will reach $2.9 billion for the entire world market. This work will be of significant benefit to researchers or industrialists interested in the development, design or manufacture of difficult-to-produce high-value products. As stated in Innovate UK's 'High Value Manufacturing Strategy 2012-2015', the high value manufacturing industry is now worth £151 billion to the UK balance of payments and sustains 1.6 million UK jobs. Moreover, high precision and surface-engineered products and processes and integration with macro-scale devices, were identified as one of the most significant process and service technologies to influence the UK manufacturing landscape in the next 20 years. The additive manufacturing of functional metal parts is a key technology in this new paradigm, and in the development of high value manufacturing in the UK in general - globally the AM market forecast is £67 billion by 2020, with £5.7 billion in market share and 63,000 sustained jobs for the UK (UK Additive Manufacturing Steering Group 2016 Additive manufacturing UK, September 2016). A key element of this project will be to ensure the basic technology capability is embedded into multiple manufacturing applications to capitalise upon process speed and manufacturing quality for UK and international industry, resulting in more efficient manufacturing and ultimately better quality, more innovative products. The specific branch of metrology covered by this project is surface metrology and most manufactured parts rely on some form of control of their surface characteristics. The surface topography of a part can affect how two bearing parts slide together, how fluids interact with the part, or how the part looks and feels. The need to control, and hence, measure surface features during manufacturing becomes increasingly apparent when surface features are the dominant functional features of a part.

The project partners: Renishaw, Xaar, Zeeko and ZYGO, stand to benefit significantly from the project. They are keenly aware of the need to bring metrology in advanced manufacturing up to speed with other technological developments and are actively developing their own expertise in in-process measurement. This work will be greatly supported by their experience, as likewise this work will provide them with a detailed understanding of a novel measurement approach. Valuable IP generated by the project should be effectively exploited, and the partners are ideally situated to do so. Developing and selling manufacturing systems is a very competitive market, even a small edge in performance could mean a multi-million pound market advantage in global sector worth £151 billion. ZYGO are well-placed to take the instrument to market.

Publications

10 25 50
 
Description We have found that it is possible to detect defetcs and surface topography changes on a manufactured product very quickly. Most current methods involve time-consuming measurerments using 3D imaging systems. The time-consuming step is converting the scattered light into tompography information that can be analysed. We have demonstrated that it is possible to just use the scattered light, combined with a machine learning method to hubnt for defects ultra-fast, without slowing down the manufacturing process. The machine learning process has to use a time-consuming method of optical modelling (or experimental data) to teach an algorithm, but this is then used very quickly during manufacturing. We now have a PhD student taking this work to the next step, where a small amount of data is used with a surface simulation technique to speed up the training phase. We then hope to pass this IP to a spin-out company (Taraz Metrology) and produce a commercial instrument.
Exploitation Route We will pass this IP to a spin-out company (Taraz Metrology) and produce a commercial instrument that can be used in a number of manufacturing processes to speed up the measurement (and quality control) processes.
Sectors Aerospace

Defence and Marine

Agriculture

Food and Drink

Electronics

Manufacturing

including Industrial Biotechology

Transport

 
Description Hard Problem solution with Imperial College London 
Organisation Imperial College London
Country United Kingdom 
Sector Academic/University 
PI Contribution Development of measurement systems to allow hard problem to be solved (i.e. which defects matter in powder bed fusion)
Collaborator Contribution Access to PBF machine with integrated metrology
Impact None yet due to covid
Start Year 2019
 
Description Hard Problem solution with Imperial College London 
Organisation Imperial College London
Country United Kingdom 
Sector Academic/University 
PI Contribution Development of measurement systems to allow hard problem to be solved (i.e. which defects matter in powder bed fusion)
Collaborator Contribution Access to PBF machine with integrated metrology
Impact None yet due to covid
Start Year 2019
 
Description Hong Kong Polytechnic 
Organisation Hong Kong Polytechnic University
Country Hong Kong 
Sector Academic/University 
PI Contribution Visit in early 2019 to give basic metrology lectures and discuss collaboration. Visit by Mingyu Liu in late 2019 to carry out on-line experiments on a diamond turning machine with SPARKLE prototype sensor (paper under review)
Collaborator Contribution Access to diamond turning and other machining facilties.
Impact Paper submitted.
Start Year 2019
 
Description Renishaw machine 
Organisation Renishaw PLC
Country United Kingdom 
Sector Private 
PI Contribution Developing technology for integration
Collaborator Contribution Renishaw are gifting us a working powder bed fusion machine on which to build and integrate the optics
Impact None yet
Start Year 2020
 
Title SURFACE TOPOGRAPHY SENSING 
Description Method for surface measurement using scattering and machine learning 
IP Reference GB1816526.6 
Protection Patent application published
Year Protection Granted 2018
Licensed Yes
Impact None yet