Asset Selection for Your Monitron Pilot
Updated: Jan 14
The Most Critical Decision for Achieving High ROI...
In this post we provide a framework for asset selection for a POC or Pilot. Reference our earlier post, 10 Ways to Boost the ROI of Your PdM Program. This blog content is based on our direct experience with over 14 Pilots and POCs, multiple PdM platforms. With Monitron we have helped our clients achieve an ROI of 60x profits/cost. This blog post is complementary to the Amazon Monitron Documentation located here...
WHY IT MATTERS: Asset selection in the Pilot is the most critical decision to catch some pending failures and then estimate savings from a planned repair. This is especially important if the objective is to demonstrate the platform ROI in a Pilot, typically over a 90 day monitoring period. Here, the objective is to identify assets with a high probability of failure that also have a cost of failure.
You can always use experienced judgement if you do not have a large number of sensors, or the CMMS data to support this approach.
DecisionIQ can provide this analysis as part of its support for funded Pilots.
We present here a systematic methodology to select assets for a pilot in four stages:
Stage 1: Build a list of candidate assets.
Secure an Excel export from your CMMS – for each asset a 1-2 year work order (WO) history that contains WO type, description of repair and ideally: downtime hours and maintenance hours.
If you don’t have a WO history, you can build a list from an asset hierarchy, but systematicaly ranking assets will be more challenging, as discussed in Step 3 below.
Example CMMS Export
Stage 2: Filter out assets that do not meet the following requirements:
A high cost of failure as determined by unplanned downtime hours.
Is rotating equipment with bearings including motors, pumps, compressors, gearboxes, fans.
Operates at near constant speed (+/- 10%) of operation.
Conditions of failure can be observed through vibration and/or temperature condition data.
Failure occurs in a process of degradation over time, preferably over five days or more.
Asset accepts physical mounting of the sensor directly on the equipment itself. For Monitron, the surface is glue compatible. Only exception to this is stainless steel or extremely hot operation.
Gateway will be in range of sensor (20-30 meters). Monitron uses low power Bluetooth. Factor Bluetooth signal attenuation from metal shrouds, cages and electromagnetic fields.
For gateway connection to internet, AWS cloud, there must be internet access available via Wi-Fi or ethernet.
The equipment operating environment is within vibrating and/or temperature limits of the sensor.
Stage 3: Score candidate assets (An Excel pivot makes this fast):
For each asset count unplanned maintenance events identified as either: emergency WOs (EM) or preventative maintenance (PM) or corrective maintenance (CM) WOs where an emergency repair was performed. So careful reading of the WO description is important.
For these events, total unplanned downtime hours and assocaited maintenance cost.
High availability assets that never have an EM WO present a special case. These are usually mission critical assets that have a very high cost of failure. To achieve this uptime, they are typically heavily loaded with PM cycles. Flag assets that for a year have 6x or more PMs than all other WOs combined. Putting a sensor on these assets is unlikely to indicate a failure during the Pilot and are not the best choice for predicting a failure. They can be used to verify monitoring, but will lower the overall ROI of the Pilot.
Rank candidate assets by WO count and/or unplanned downtime hours. Sort from highest to lowest.
Step 4: Assign sensors to assets
Overlay the planned sensor purchase to get the list of assets for sensor assignments For example, if there are 25 sensors in the Pilot, assign these sensors to the top 25 assets in the scoring table above.
PRIOR POST: Your Monitron Pilot, How to Execute for Maximum ROI
NEXT POST: Your Monitron Pilot, Building the Asset Hierarchy
GetIQ.ai is a blog about building AI solutions for augmenting decision making and empowering people that make them. It's authored by the engineers at DecisionIQ.
ABOUT DECISIONIQ: We are "boots on the ground" factory engineers expert at the adoption of AI and machine learning into operations. As consultants and system integrators we bring our experience in a mix of a well structured programs that enable our clients to produce winning results and maximum ROI. You will learn to use AI to build competitive advantage by increasing plant uptime, quality and yield. With 24 POCs, Pilots and 16 deployments we have achieved for our client’s ROIs as high as 60x and a cumulative $22 million in savings.
AN AWS PARTNER: We provide capability in design of AI solutions for industrial applications. We work with the AWS Industrial IoT services stack, cloud migrations and Amazon Monitron Pilots and deployments. For qualifying customers, many of these capabilities are eligible for AWS subsidized funding.
©Copyright 2023, DecisionIQ, Inc.