Fusing human knowledge and technology to perfect processes

Paul Boughton

Mass manufacturing of productssuch as aluminium platerequires millions of Euros worth of investment every yearand aluminium plate producers naturally seek to maximise the productivity and profitability of rolling mills.

Now scientists at the universities of Reading and Leicester in the UK have teamed up with Alcoa to develop new state-of-the-art ‘fused expert system’ that has shown through plate rolling trials how mills could work at optimum performance levels.

Dr Will Browne of Reading’s School of Systems Engineeringtogether with professor Ian Postlethwaite and Dr Liqun Yao from Leicestercreated the system that fuses the human and computer knowledge of a rolling mill and uses that combined understanding to produce high quality plates of aluminium – potentially saving manufacturers millions of Euros. The system is described in the latest issue of Engineering Applications of Artificial Intelligence.

“The UK is one of the world leaders in metals productionbutfor supervisory and plant-wide control systemsit had lost ground by failing to embrace new technologies” said Postlethwaite. “This project redressed this situation through the development of a generic knowledge-based system for supervisory control of rolling mills” added Browne.

Aluminium plates used in the manufacture of aeroplanes and shipsfor exampleare produced by passing an initial aluminium slab through a giant mangle – a four-high rolling stand - many times so that it is flattened into a thin final plate. A large number of factors may affect the quality of the final plate – the number of passesplate temperatureplate widthand so forth – and as much background knowledge as possible is needed to ensure that the plates are near perfectwith no waves.

“With even the most advanced supervisory control systemnot all plant knowledge is fully utilised” said Browne. “Howeverour new system makes a much improved use of both the human knowledge of the plant and technological data. It predicts and diagnoses quality problems before and during rolling and this leads to superior product shape and shape predictionand improved explanations of product quality defectscoupled with suggested remedy actions. Ultimatelythe development of this knowledge-based system can improve the operational efficiency of plants manufacturing hot band aluminium plate by increasing productivity and yield."

The Engineering and Physical Sciences Research Council-funded research followed on from groundbreaking work by the University of Leicester and involved the combining of knowledge-elicitation and data-mining techniques to develop the fused expert system. Knowledge-elicitation involves establishing important facts and heuristics (rules of thumb) from plant expertswhile data-mining is the process of analysing dataoften utilising advanced artificial intelligence techniquesin order to identify patterns or relationships.

“The fusion of these two techniques produced an expert system that successfully rolled aluminium plate without significant shape defects” said Browne. “The methodology is transferable to all the other plate alloys and it is applicable to many other industrial problems. The system could be used in many areas of industrial processingsuch as drink cans or wallpaper and we hope thatwith the aid of industrial sponsorshipwe will be able to take the technology even further forward” he concluded.

Safety buses poised for growth

Meanwhilethe relatively small global market for distributed/remote I/O (DRI/O) using safety buses/networks is about to enjoy a period of higher growth according to a recent study from Venture Development Corporation (VDC).

Launched in 1971VDC (www.vdc-corp.com) is an independent technology market research and strategy consulting firm that specialises in a number of industrialembeddedcomponentretail automationRFIDAIDCdatacom/telecomand defence markets.

Its new study Industrial Distributed/Remote I/O: Global Market Demand Analysis and User Requirement Analysis4th Editionindicates that safety buses/networks accounted for 1.3 per cent of global DRI/O shipments in 2005 and forecasts 2010 shipments to be 2.3 per cent. That will be a rise in value from US$42.1 today to US$99.4 in 2010.

Distributed/remote I/O for use in PLC system applications had the highest utilisation of safety buses/networks. On the other end of the spectrumonly a fractional share of products for PC-based systems are equipped with safety bus capabilities.

“PLC system applications are the most attractive for safety buses” says VDC analyst Jake Millette. “This is due to the high level of shipments for equipment and machinery in discrete manufacturing compared to process controls. The development and promotion of safety buses by PLC suppliers such as Siemens has also led to a greater adoption.”

In 2005PROFIsafe accounted for the largest share of the overall market and of distributed/remote I/O for use with DCSs and PLCs. This lead is expected to be held in 2010. AS-i Safety at Work accounted for the second largest share of the overall market in 2005 and either led or was among the leaders for each product type. HoweverDeviceNet Safetyjust barely behind AS-i Safety at Work in 2005is forecast to take second place by 2010.

VDC’s study concludes that the safety bus/network arena will become more crowded in coming years: “Ethernet/IP Safety is close to release and the Safetybus p Club is developing its SafetyNet protocol. These reflect the general trend to Ethernet solutions in the safety bus/network market.” 

"