Project aims for 'plug-and-play' PdM for manufacturing SMEs

1 min read

SamsonVT and RS Components are embarking on an R&D project to produce an affordable machine learning-enabled predictive maintenance (PdM) solution for manufacturing SMEs.

(Image: AdobeStock)

The partnership is supported by Innovate UK, which has awarded a joint R&D grant to support the technology’s development.

The ADX project will focus on the application of anomaly detection for improved maintenance, engineering and decision making – and will see SamsonVT integrate data extraction, criticality assessment, machine learning (ML) and root cause analysis with its existing condition monitoring platform, SamsonBASE.

Sam Burgess, CEO at SamsonVT, a Manchester-based Industry 4.0 technology start-up, said SamsonBASE is currently a one-off bespoke process, and the development of ADX will make the technology a scalable, reusable product capable of using standard manufacturing environment equipment to harvest and process relevant data to detect anomalies within machinery.

“Customers will have access to SamsonBASE’s technology in a new ‘plug-and-play’ style,” he said. “The addition of Criticality Assessment (CA) will enable better decision making to ensure key assets are identified and prioritised for maintenance. Outputs of ADX will feed directly into Root Cause Analysis (RCA) ensuring repeat incidents are reduced and, in some cases, prevented altogether.”

Burgess added that automation also means that customers can add assets easier, get online quicker and start avoiding downtime sooner. The addition of CA and RCA will improve overall value and ROI.

In 2017 The Engineer reported that machinery downtime costs British manufacturers around £180bn every year, representing three per cent of all working days. It is estimated that the implementation of a PdM solution would save SMEs 65 per cent of these costs.

Machine downtime costs UK manufacturers £180bn a year

By ensuring machinery is neither under nor over maintained, PdM helps to optimise maintenance resources, reduce the unnecessary replacement of parts and minimise the ancillary damage repair costs caused when parts fail in situ.

Most SMEs are yet to adopt this approach due to the high implementation costs. The ADX project seeks to address this problem by significantly reducing this cost burden.

SMEs will be able to use their existing network of sensors, hardware, and equipment – provided they have been harnessing data for a minimum of three to six months – and do not require highly trained personnel to interpret the findings.

“In most cases, customers will already have their own PLC hardware installed which will be reading data from machines,” said Burgess. “This can simply be outputted by the development team to our cloud-based system for analysis.”