Repairing complex, mission-critical equipment quickly and accurately is a top priority when uptime is essential to success. Every hour of downtime increases service costs and reduces revenue opportunities. Fortunately, industrial businesses with IoT-connected devices now have a vastly superior alternative to archaic manual repair processes. Called adaptive diagnostics, this advanced approach harnesses equipment data to enhance troubleshooting processes. As a result, companies are able to perform a real-time, detailed assessment of a problem and its causes, accompanied by structured servicing workflows that quickly lead technicians to the right resolution.
Here’s how it works: IoT software sifts through petabytes of real-time and historical data to determine a problem’s root causes — examining fault codes, interrelated operating conditions and repair history. It then ranks probable causes and produces an optimized repair plan that can be integrated into other enterprise workflow applications, such as parts, maintenance and service warranty systems.
With adaptive diagnostics, technicians arrive at an asset armed with detailed and accurate information about the problem, the right parts to address it, and the interactive guidance they need to rapidly fix it right the first time. This is in stark contrast to manual approaches where a technician arrives at an asset to make a visual inspection, thumbs through a manual for repair ideas or may call over a more senior technician for their advice.
Over time, as your asset datasets grow and technicians feed repair input back to the software, businesses are able to build a knowledge base of proven troubleshooting paths, enabling technicians of any skill level to fix the most complex failure scenarios.
Based on experiences with industrial businesses, there are five critical ways adaptive diagnostics is helping improve repair of mission-critical equipment:
- Helps technicians troubleshoot issues faster: Evaluates real-time conditions, contextual data and past failure events for probable root causes, with corresponding “confidence levels.”
- Cuts to the source of a problem sooner: Suggests the most effective fix for a problem based on historical fault resolutions, probable causes and current conditions.
- Speeds time to resolution, continually improves diagnostics: Uses two-way interaction to give technicians relevant repair steps, then receives and incorporates results to guide the next steps.
- Triggers enterprise workflows with ERP systems: e.g., automatically orders parts through a parts management system, reports technician time to a workforce management database.
- Reduces overhead for technician training: Enables easy creation and management of an IoT-connected electronic service manual; as the ESM grows, probable-cause prediction and resolution recommendations improve.
Adaptive diagnostics in the wild
One company I’ve worked with, a heavy-duty trucking business, wanted to improve the uptime and reliability of its vehicles. This would help eliminate unplanned downtime, which is expensive, disruptive and can potentially tarnish service reputations. Adaptive analytics helped the company eliminate these expenses, which cut directly into revenue mile profits.
For decades, the trucking company’s vehicle engines have displayed warning lights for a variety of conditions, but they failed to provide drivers with sufficient information to determine whether the issue was an imminent failure that would disable the truck or a minor condition. The trucks needed to be taken to service centers where technicians could use equipment connected directly to the truck that could help diagnose a single condition, but didn’t take into consideration related events or conditions that might accelerate mean time to repair and get the truck back on the road more quickly.
This manual approach ate into uptime as technicians spent hours troubleshooting and fixing problems. Finally, lengthy and imprecise warranty processing resulted in high warranty costs for the business and lengthy reimbursement periods for its third-party service centers.
With adaptive diagnostics, the trucking company was able to tie multiple relevant data sources together with business logic to create a user-friendly, holistic IoT system that scales to hundreds of thousands of trucks. Fleet operators and drivers can now schedule truck service at times and locations that minimize disruption thanks to the insight provided by predictive failure analytics. As a result of this improved repair process, revenue miles have increased, providing faster ROI on truck investment.
Adaptive diagnostics is ideal for any business that wants to minimize downtime of equipment that is under repair. By improving repair turnaround and accuracy, faulty equipment gets back online faster, at lower cost, for better operational efficiencies.
All IoT Agenda network contributors are responsible for the content and accuracy of their posts. Opinions are of the writers and do not necessarily convey the thoughts of IoT Agenda.