While capital intensive industries continue to utilize large numbers of capital assets at each stage of the production process, a failure in any of these assets could cause shutdowns, costing upwards to tens of thousands of dollars per hour in lost production.
To avoid failure and to keep equipment running, experienced service technicians must be vigilant in identifying any failures in the production process and quickly fixing them. However, due to the ongoing retirement of the baby boomer generation, along with a decreased interest in the service field, experienced technicians are dwindling.
To help fill the gap, businesses are turning to emerging technologies like the Internet of Things (IoT) and augmented reality (AR), which can transform the industrial maintenance and field service process by capturing data in real-time and instantly converting it into actionable information, allowing for failures to be diagnosed more quickly than ever before. This process is called predictive maintenance (PdM), and in some cases, problems can be fixed remotely by service technicians armed with diagnostic information and access to machine controls.
Sometimes a service technician is necessary, and that’s where augmented reality is best used. It complements the skill set of field technicians and increases their productivity by overlaying diagnostic information, service instructions, parts catalogs and other information directly over the technician’s view of the asset requiring service. For example, a technician wearing smart glasses can see an animation of the repair operation he or she is about to perform overlaid on the area of the machine where the operation is required. The combination of IoT and AR can ease the shortage of skilled industrial maintenance workers and increase the utilization of valuable capital assets.
To increase capital asset uptime, here are six simple steps that harness the power of IoT and AR, from initial detection to the problem to the resolution:
Connect your assets to the IoT. The first step is to equip capital assets with sensors and connect them to the IoT technology, so that their performance can be monitored and diagnosed remotely. Many capital assets are already equipped with thousands of sensors that monitor flow, pressure, vibration, voltage, current, speed and many other parameters and transmit data to the control system where it is used to make operating decisions.
Leverage analytics to detect impending problems. Machine learning systems can analyze the data stream from sensors to understand what’s going on deep inside complex machinery. Analysis of previous failures can be used to correlate sensor readings and the condition of critical components that might cause machine failures. Then, algorithms can predict when specific components might be nearing failure and monitor the condition of in-service equipment to determine when maintenance is required. This approach makes it possible to perform maintenance only when it is needed, as opposed to traditional time-based preventive maintenance, which generates production downtime and ties up skilled maintenance technicians long before maintenance is required.
Attempt to solve the problem remotely. Let’s suppose that the predictive maintenance system detects an existing or impending problem on the plant floor. Rather than spending the time and expense to send a service technician to the machine, a remote technician can first attempt to diagnose the problem based on the information available from the sensor data. Then the remote technician may be able to address some or all the possible causes remotely. For example, the remote technician may be able to recalibrate a sensor to see if that fixes the problem. Workflows can also be established to leverage predictive analytics to analyze the alert and identify possible causes.
Dispatch a technician. If the problem cannot be solved remotely, then a remote technician can change the status to “dispatch required.” The application will then automatically generate a work order, which will include all the information on the problem, generated by the predictive analytics. The field technician also has access to the same predictive analytics output and real-time sensor data as the remote technician, which can be used to select special tools and parts to bring on the service call to be more fully prepared.
Leverage AR to diagnose the problem on site. When the field technician arrives at the asset, he or she can use an AR application on his or her smartphone, tablet or smart glasses to see sensor readings and other diagnostic information. Access to this detailed information may make it possible to dispatch a less experienced and lower cost field technician. As the field technician’s view moves around the product, real-time diagnostic information provided by sensors for the area that he or she is viewing are visible on the screen. Based on a combination of the real-time data, previous predictive analytics and a knowledge base, the AR application can provide problem diagnoses, along with procedures to correct each one.
Order parts and complete solution. After the field technician determines how to solve the problem, he or she can aim the device with the AR application at the area of the asset where the problem lies and click to call up an exploded view of the assembly. Then the field technician can manipulate the exploded view and select the part needed for the repair. Ordering parts and billing can all be handled through the AR application, which will create a seamless experience for both parties.
Mission complete. By successfully implementing IoT into capital assets and leveraging AR to quickly solve the diagnostic, capital assets can improve in uptime, and maintenance costs will diminish.
Jeff Brown is Vice President for Global IoT and Embedded PC Sales at Dell EMC.The InformationWeek community brings together IT practitioners and industry experts with IT advice, education, and opinions. We strive to highlight technology executives and subject matter experts and use their knowledge and experiences to help our audience of IT ... View Full Bio