A conceptual framework of predictive manufacturing begins with data that can be sourced via remote monitoring devices, reports Susan Fearn Ringsell.
Anyone who has ever been stranded at the roadside with a stationary car would have to reluctantly acknowledge that a proactive maintenance plan is always better than a reactive remedy. Yet finding the time and resources for regular servicing and health checks is not always simple.
Could the burgeoning Internet of Things (IoT) provide an answer? IoT, which aims to add intelligence and connectivity to almost any device or machine, is envisioned by many as a transformative force for change in the manufacturing world; from the introduction of advanced robots in the workplace to smart components that communicate their own assembly instructions to the production line.
For production managers in an industrial environment, the dilemma is particularly acute, since the consequences of critical machinery failure not only include the time and cost associated with repairs, but the grave prospect of production downtime
Stef Lievens, business line manager, Atlas Copco
This growing trend is reflected by the latest findings of manufacturers’ organisation EEF which predicts that companies are planning to invest more in internet-connected capital equipment over the next five years.
“For production managers in an industrial environment, the dilemma is particularly acute, since the consequences of critical machinery failure not only include the time and cost associated with repairs, but the grave prospect of production downtime,” says Stef Lievens, business line manager for compressor technique service operations at Atlas Copco Compressors UK.
New conditions
The process of monitoring a parameter of condition in machinery allows for maintenance to be scheduled (most commonly used on rotating equipment and other machinery such as pumps and motors).
An underlying component of condition monitoring is visual inspection. “Motion amplification is a new technology,” explains Keith Gallant, condition monitoring technologies manager, Reliability Maintenance Solutions. “It is a non-contact optical measurement of vibration, with wide-ranging applications from rotating equipment to pipework.”
“Using a portable handheld device, maintenance staff can establish the health of less critical machines such as motors, compressors and pumps by collecting and analysing vibration data from sensors
Cranford Johnstone, reliability solutions manager, Emerson
On the other hand, route-based condition monitoring provides a periodic analysis of equipment.
“Using a portable handheld device, maintenance staff can establish the health of less critical machines such as motors, compressors and pumps by collecting and analysing vibration data from sensors,” says Cranford Johnstone, reliability solutions manager, Emerson Automation Systems.
This solution is also used to ensure precise alignment and balance of these machines. Meanwhile real-time, online monitoring solutions are usually applied on larger and more critical plant equipment and provide both prediction and protection capabilities.
Using a prediction monitoring solution, potential problems can be identified earlier, enabling scheduled maintenance during periods of downtime. “For example,” says Johnstone, “problems could arise due to misalignment, imbalance, bearing defects or insufficient lubrication.”
Data and beyond
Wireless vibration sensors have expanded the range of online monitoring applications by enabling cost effective data collection from remote and hard to reach equipment. Plus the cost of sensing equipment and infrastructure is now much lower.
Johnstone explains: “The question is not which equipment can I afford to place sensors on, but instead, how can I make best use of the data collected?” Wireless, cloud computing, data analytics and smart mobility are expected to provide growth opportunities.
“The trend toward collecting and sending data to service providers with the capability to analyse the data remotely is increasing,” adds Johnstone.
The industrial Internet of Things (IIoT) is enabling plants to generate unprecedented amounts of data from their assets, but this information must not only be gathered but also analysed
Cranford Johnstone, reliability solutions manager, Emerson
Data can be collected and transmitted to a remote analysis centre using continuous online monitoring technology, portable (offline) instrumentation, or wireless transmitters, where advanced diagnostics and prognostics can be performed.
“The industrial Internet of Things (IIoT) is enabling plants to generate unprecedented amounts of data from their assets, but this information must not only be gathered but also analysed,” concludes Johnstone.
Optimal productivity
In addition to supporting preventative maintenance, technology is helping plant managers optimise productivity and keep running costs down. It is little wonder that the onset of smart monitoring is reaching every corner of manufacturing practice, and the compressor room is no exception.
The on-site servicing of compressor systems has traditionally followed two paths: the proactive route undertaken on a regulated basis, whereby users take out service contracts to ensure regular planned visits from a service technician; or alternatively taking appropriate action only when an unforeseen problem requires an immediate intervention.
“This latter scenario,” explains Lievens, “means the plant operator has to keep a continuous eye on running hours and performance parameters, calling for service when needed. If left too late there is an inherent risk of excessive energy consumption and possible mechanical breakdown.”
Offering an answer to this is a monitoring programme for compressors that intelligently gathers, compares and analyses data to help compressed air users increase maintenance and service efficiency.
“Making smart use of connectivity, data monitoring and business intelligence, SmartLink helps customers get a better view of their maintenance needs, maintain production uptime and improve their operating costs, wherever possible, by minimising energy consumption,” adds Lievens.
Tapio Torikka, senior data scientist at Bosch Rexroth, explains that diagnosing wear and tear in industrial applications is an extremely complex task.
Statistically, there is only a 13% probability of an issue being detected by chance, while an expert monitoring the system by traditional means has a 43% chance of detecting it.
“The Bosch Rexroth system [ODiN] acquires all the necessary information from the sensor data and machine learning methods, then converts this into knowledge. The health index therefore not only shows the state of the assembly currently being monitored, but also gradual changes to upstream and downstream mechanical or hydraulic systems.
“If movements take longer or require more power, this indicates wear and tear. ODiN gives corresponding instructions in its regular health index reports and helps to create specific recommendations for action.
“Even ODiN cannot fully eliminate the risk of plant downtime, but we can reduce the risk so significantly that the costs for the system are generally already recouped after the first prevented downtime,” adds Torikka.
Future performance
Remote condition monitoring is an example of fledgling IoT technology that is already having an impact.
However, it is with the addition of control that the full potential of the IoT can be realised in the future.
The eventual goal is progression towards full remote or automated control, based on the machine-acquired data – and with the IoT evolving rapidly, that’s not too far off. The IoT changes data into actionable information. It enables a constant stream of performance information to provide real-time insights on production processes.
The strategy focuses on creating cyber-physical systems, the communication technologies, software, sensors and processors that have the potential to communicate and interact with each other in an intelligent way to gain competitive edge
Stef Lievens, business line manager, Atlas Copco
Big Data provides an infrastructure for transparency in the manufacturing industry and acts as the input into predictive tools and preventive strategies, unravelling uncertainties such as inconsistent component performance and availability. Predictive manufacturing, as an applicable approach toward near-zero downtime and transparency, requires vast amounts of data and advanced prediction tools for a systematic process of data into useful information.
“The strategy focuses on creating cyber-physical systems, the communication technologies, software, sensors and processors that have the potential to communicate and interact with each other in an intelligent way to gain competitive edge,” explains Lievens.
Remote monitoring, as a component of the larger IoT trend, provides the gateway to integrated industry – the concept that ultimately allows entire production lines to reconfigure themselves autonomously.
As such, small-batch and one-off production in large-scale plants becomes commercially viable – achieving the goal of transforming the factory from cost centre to profit centre.
