There are three major steps involved in this process
Identifying PdM data
Transmission of data and connecting to Senseye PdM
Review of findings from Senseye PdM
Throughout the whole process you’ll be supported either by a team from Senseye or from one of our Partners, all with a vast knowledge of condition monitoring and predictive maintenance, and with excellent skills in both data and assets.
Identifying Data for senseye pdm
Data for Senseye PdM comprises two simple groups:
Condition Monitoring Data
The key requirement for effective PdM is to provide online condition monitoring data in the form of time-series data values. Directly related to, or influenced by, the health of the asset or machine being monitored, this data ranges in complexity and quality and will reflect the monitoring needs coming from asset reliability studies. It can be as simple as peaks in motor current during operation or high-precision vibration measures known as ‘condition indicators’.
Over 80% of the condition monitoring data with which customers use Senseye PdM can be classed as simple and, in many cases, puts existing control or process measurement to a secondary purpose, removing the need for additional sensors. Imagine being able to monitor hundreds of assets with no additional hardware costs. Many of our customers do exactly that.
The second set of data is concerned with maintenance, and is important for providing context to the condition monitoring data. Using maintenance data coming directly from your Computerised Maintenance Management Systems (CMMS) or entered via our Work Event user interface, Senseye PdM’s analytics are able to make use of this data and integrate it into the automated data analysis flow.
The condition monitoring data you are collecting may be stored in one of the following:
IIoT Platform (e.g. ThingWorx or Mindsphere)
Data Historian (e.g. OSISoft PI or Wonderware)
In-house platforms (e.g. SQLServer or AZURE)
If you don’t yet have condition monitoring data available, we’ll assist you with the use of Senseye Stream or support your in-house team in transforming raw sensor data so that it’s suitable for predictive maintenance.
Given the prolific use of CMMS and EAM systems to perform maintenance work recording it’s likely you already have a solution in place, with valuable information our solution can use. However, we know this is not always the case, and it is possible to make maintenance work event entries directly into the Senseye PdM application using our simple user interface.
Data Transmission and Connectivity
Senseye PdM is a trusted and proven solution that helps you predict the attention required for your assets, at scale. Developed specifically for you as a maintenance manager and your team, many Fortune 100 industrial companies already depend on our solution.
There are several alternatives for data transmission and connectivity as Senseye PdM has an open architecture that enables connectivity to many data sources through a range of integrated data platforms. Alternatively, we can provide solutions as simple as file transfer or direct API pushes, all of which will be under your control.
We also provide access to a suite of interfaces that enable integration with your other asset management tools such as CMMS. Our open architecture enables the simple integration of maintenance systems so there is no need for duplication in recording by the maintenance team.
Reviewing PdM findings
Once data transmission and connectivity has been established, a period of familiarization begins. After users have interacted with Senseye PdM, the results are reviewed to confirm they show potential signs of machine failure. These findings are discussed with the Senseye team and, where opportunities for greater success are identified, these will be implemented. In a short period, you will be completely self-sufficient and soon looking to extend your coverage by adding more assets and sites.
As a highly scalable cloud-based solution Senseye PdM deployment scales with your needs.
Most of our clients typically start with a sub-set of assets in a single plant to gain an understanding of Senseye PdM in use and establish best practice. With phases measured in weeks and months, this quickly becomes a wider plant rollout leading to multi-site deployments. Initial deployments can be up and running in weeks, with benefits proven in just 3 to 6 months of use, and scaling to full site development and multi-site deployment following on over the next 6 to 8 months.