Analysis results
After you upload entity property files and event files, the product analyzes the information, trains the model based on the data that is uploaded, and then provides the analysis result. You can select an asset type to see the analyses for all equipment assets of that type.
On the asset pane, click the asset type menu and select an asset type.
Equipment assets are grouped by the following categories:
- All Assets
- All equipment assets, or all equipment assets of the selected type.
- Over Maintained
- Scheduled maintenance is long before the predicted failure of the asset.
- Well Maintained
- Scheduled maintenance is close to the predicted failure of the asset.
- Under Maintained
- Scheduled maintenance is long after the predicted failure of the asset.
- Needs Data
- More data is required to analyze the asset.
Each equipment asset appears on a separate card that provides important indicators of asset health:
- Top Driver
- Top driver is a sensitivity analysis that shows the strength of correlation between operating variables and failure for each equipment instance. Prescriptive Maintenance on Cloud ranks the drivers, indicates the current value of each driver, and provides an estimate of the remaining value before failure in the driver unit. For example, the top failure for a pump might be the cubic feet of water pumped since last repair. At the time of analysis, pump 2672 has pumped 40000 cubic feet of water. Prescriptive Maintenance on Cloud estimates that it pump another 10000 cubic feet before it fails. This value is intended as an estimate. When this estimate is produced, Prescriptive Maintenance on Cloud assumes that the values of the other drivers remain constant. The actual number of operating hours is influenced by the changes in other variables.
- Margin
- The number of days' difference between the next scheduled maintenance and the next predicted
failure of the asset. Attention: Negative margin means that the asset is predicted to fail before the next scheduled maintenance.
- Risk Factors
- Risk factors are characteristics of equipment that make them more or less susceptible to failure. Unlike drivers, which are continuous numeric variables, risk factors are categorical characteristics of the equipment. They are useful in explaining why different equipment instances that are used in a similar way have different failure rates. For example, pump 2672 has pumped 40000 cubic feet of water since the last repair, and can pump 10000 more cubic feet before failure. However, pump 8251 has also pumped 40000 cubic feet of water, but it can pump only 10 more cubic feet. Pump 2672 is used in a clean environment. Pump 8251 is used in a corrosive environment. The environment is shown as a risk factor with a clean environment shown as a positive contributor for pump 2672 and a corrosive environment is shown as a negative contributor for pump 8251.
- Graph
- The graph gives a concise visual reference of asset health:
- The gray horizontal bar indicates the total top driver count before the next predicted failure of the asset.
- The dark portion of the horizontal bar indicates the current top driver count. Attention: If the entire horizontal bar is dark, then the asset is already past its next predicted failure.
- The vertical bar indicates the current average top driver count for this asset type.
- The arrow at the end of the horizontal bar indicates whether the current top driver count is more than twice the average top driver count for this asset type.
You can sort the cards based on Margin, or filter the cards based on Top Driver or Asset Property Type.
Click a card to open a window that shows more analysis results for the asset, including the
following details:
- The number of days until the next scheduled maintenance date.
- All drivers (that is, variables that contribute to asset failure). A driver whose name ends with _LTD is derived from an existing field by accumulating between failure events.
- The maintenance history of the asset.
- A histogram of all drivers or a particular driver. Tip: Specify a time scale to view a particular period.