Taking control of maintenance

Poor maintenance strategies have a tangible impact on the bottom line. From the millions of pounds of food loss through refrigeration failure every year to customer perception and brand value, asset underperformance and downtime continues to wreak significant business damage. Yet for most organisations – and their front-line staff – the continued reliance upon reactive maintenance models results in a spiralling lack of control over asset performance, repair and lifecycle.

Despite the adoption of basic planned preventative maintenance (PPM) strategies in many sectors, the painful reality for those tasked with delivering customer-facing services is that the problems are often only recognised when catastrophic machine failure occurs, for example, when the ice in a freezer melts all over the aisle, or the only cash machine for miles is out of service. Furthermore, although a clear process for contacting qualified maintenance engineers will be implemented, the predominantly manual process is far from efficient. How long does it take for an engineer to arrive? Does the engineer have the right skills and parts to achieve an immediate fix? If not, how many visits are required to do this – and at what price? The cost of the vast inefficiencies across the fault-to-fix process, alongside the impact of machine failure and asset downtime, has a considerable impact on the bottom line.

The ability to apply IoT solutions to acquire real-time performance and operational data from assets, alongside work order data from internal bureaus and 3rd party contractor systems, provides a clear opportunity to leverage this data to inform processes and fundamentally transform maintenance models.

IoT Enabled Insight

A truly intelligent approach combines IoT technology with Machine Learning and AI to accurately understand individual asset performance, business processes and workflows, and utilise that insight to effectively manage maintenance resource.

To enable an efficient maintenance strategy, an effective IoT solution must enrich the collected real-time asset performance data with an understanding of individual asset specifications and behaviour. Contextualising the real-time data with benchmarked performance and expected life cycle enables a deeper insight and understanding of asset performance, as opposed to having only singular data points and linear threshold breaches.

This learned, deeper understanding can be further enriched through identifying irregular fluctuations and anomalies, dynamically monitoring asset behaviour and understanding the patterns that indicate a potential future issue. Utilising a sophisticated monitoring approach will drive informed preventative maintenance that has the ability to prioritise and assign tasks based on risk and impact factors. This will encourage a shift from reactive to predictive regimes and can drive a vast reduction in critical machine failures due to early fault identification, enhancing data-driven energy management strategies and ultimately improving asset uptime and availability to unlock an enhanced consumer experience. With machine learning capabilities, future predictions can be enriched with past asset actuality to further establish an increasingly robust system.

Asset Centric Model

For many industries, including food retail and Financial (ATM) Service providers, this presents a platform to enable a fundamental rethink of maintenance strategies and, critically, provides asset owners the opportunity to regain control over the process, turning the current maintenance model on its head.

Real-time monitoring of asset performance and the enabled asset communication eradicates the manual and inefficient processes normally needed to achieve a fix, such as contacting and managing third-party maintenance providers through to intelligent auto-dispatch. Through further enriching work order systems with Original Equipment Manufacturer (OEM) and third-party data, the individual assets are equipped with all the necessary information required by engineers when a fix is needed. Critical information, such as specific machine parts and engineer skill set requirements, can be combined with GPS location, schedules, shift patterns and Service Level Agreements to ensure the most appropriate individual is deployed to site, vastly improving fault-to-fix times.

In addition, an increase in first time fix rates is driven through enhanced spare part acquisition management, enabled by the asset’s ability to inform an engineer of fault specifications and required parts ahead of site attendance, ensuring engineers arrive prepared.

For example, in the Financial Services sector, if an ATM machine is alerting with a fault, the sophisticated dispatch system raises a work order that considers the location and skillset of the engineer, in addition to whether they have the tools and spare parts required, in context of the contractor SLA. This ensures the work order is assigned to the engineer that is most likely to achieve a first-time-fix, and any site visits are as efficient and effective as possible.  

Spanning across the end-to-end process, the asset is then able to inform the work order system whether it has been effectively repaired and, when integrated with contractor systems, automatically raise an invoice once the repair has been completed. The only human interaction required throughout this whole process is the physical fix to the asset. This eradication of manual processes enables a reduction of back office costs, and will drive efficiencies throughout the entire process.

The increased visibility that an effective IoT solution can unlock over an estate – and the performance of assets within it – can further enable preventative work. When an engineer is on site for a call-to-fix, assets that have identified as performing lower than optimal but not to the criticality needed to raise an alarm, can also be attended to, utilising early identification. This can reduce further maintenance resource requirements and spend on call-outs, whilst enabling the creation of a sustained predictive maintenance model that incrementally reduces maintenance costs over time and ensures a prolonged asset life cycle.

Taking a supermarket as a use case, if an engineer is attending a site to fix a faulty refrigeration unit, and the system highlights another refrigeration case on site is demonstrating behaviours that indicate signs of impending failure, an automated work order can be raised for the attending engineer to perform preventative work, avoiding a future call out to fix that asset when the failure occurs, preventing refrigeration downtime and in this case, avoiding stock loss and product unavailability.

Taking Back Control

An IoT solution that has the ability to connect to any machine or device across an entire estate to enable an asset-centric view releases the retailer from the monopolised OEM market and prevents maintenance regimes from being dictated by contractors. With full visibility and control over their estate, a platform for contractor and engineer choice is provided, enabling the retailer to align maintenance strategies to business priorities, such as engineer skill set and availability alongside, fundamentally, cost to the business. However, the platform can also drive an improved existing contractor relationship, as the retailer gains insight into work orders and competition rates as well as integration to contractor systems, which can help establish better informed communication between the two parties.

Furthermore, an informed approach can transform the efficiency of maintenance teams and engineer resource. With early fault identification, performance level visibility, and the ability to utilise GPS positioning and engineer scheduling insight, undertaking preventative repair enables an increased level of productivity. This intelligent resourcing will maximise the output of the engineering team and increases the number of jobs performed each day, subsequently resulting in a reduction of labour costs for the retailer.

Conclusion

For any machine-rich environment with mission critical assets, the ability to take control of the maintenance process is fundamental to growth and evolution. By taking an asset-centric view, organisations and operational teams are no longer at the mercy of third-party contractors: work orders are driven by priority and efficiency, and the entire process is consolidated and automated.  Furthermore, this data can inform wider decisions around procurement processes, such as whether a comprehensive or pay-as-you-go approach is more appropriate, whilst providing increased flexibility and releasing value and insights for future asset investment.

Critically, organisations can reclaim control over the management of their consumer-facing assets; a customer wouldn’t think to blame a contractor when the product they want isn’t available or their local cash machine isn’t working – they blame the brand. By leveraging IoT to automate maintenance processes to ensure the right engineer with the correct skills and the necessary parts is deployed to site before a fault becomes catastrophic, companies can drastically minimise asset downtime, transform maintenance costs and protect brand integrity.