P4A, your gateway to most advanced asset monitoring methods

P4A is taking online asset monitoring and data analytics to whole new levels. Where most companies still focus on using the available asset data to configure simple degradation trends and set alarms based on single data to protect your process, we are truly turning your asset data into actionable intelligence and help maintenance experts and asset managers to efficiently and effectively diagnose faults, identify the cause(s) and automatically track recurring defects.

Beside our online monitoring solution we also propose specific services for advanced troubleshooting and digital asset twin models. All together it really allows you to move to predictive maintenance and start automating your decision-making process.

The P4A Wintell platform supports the following 3 approaches:

The P4A Wintell platform is an advanced asset monitoring system. The main features of the system are data processing, centralization, automatic analysis and visualization in a secure environment. Based on the data collected in real time (SCADA data and vibrations data), the P4A  models (algorithms) allow you to:

This automatic analysis of the available data allows you to turn them into actionable intelligence. The objective is to provide the end user with clear and valuable information helping you to take objective decisions to improve the reliability/availability and performance on 3 levels:

The intelligence extracted from the data allows you to mitigate the consequences of drifts, to optimize the maintenance operations and to increase the availability and the effectiveness of the equipment under surveillance.

In addition to fault prediction, the P4A Wintell platform also assists the enduser to manage unexpected faults. These defects can, for example, be electrical with a very fast propagation making any prediction useless.

When a machine suddenly triggers, you require high frequency data. They can be retrieved either through the machine PLC that usually generates a file called “trigger log” linked to the error or by setting up a specific acquisition system triggering when the fault occurs. This file contains all the data acquired (digital and Boolean) at high frequency (ms) over a period of a couple of minutes before and after the error. In order to assist the expert with his data analysis to identify the probable root causes and solutions, these files can be uploaded on the P4A Wintell asset monitoring platform allowing intervention at two levels:

1. “Unknown” (or non-modelable) fault: In this case, the objective is to assist the expert by means of analytics tools to enable a faster identification of the cause(s) of the failure and therefore a faster resolution thereof (reduction of downtime). To achieve this, the goal is to isolate and propose solutions based on the automatic analysis of all the data in the “trigger logs”.
2. Known defect: When a defect has already been identified following a previous analysis, the aim is to model it in order to automize future detection of the same defect and consequently also the actions plan to correct the defect. The objectives pursued are:

Another option proposed by P4A is to build digital twins of equipment through physical modeling of the asset in order to simulate the operation of these equipment in real-time based on live operational data. It is thus possible to continuously compare the output from the model (twin) to those of the operational equipment and consequently detect any drift (in degradation or performance), diagnose the cause(s) and decide when to act (from short to long term) depending of the urgency and criticality.

Many digital twin solutions currently available analyze the entire process. The disadvantage of this approach is that in case of drift, it is usually not possible to specifically identify the cause(s) and provide recommendations for an intervention.

The drift can be caused either by the product processed and the operational / environmental conditions of the process, or by equipment used in the process. The goal of adding specific digital twins for equipment is to fill this gap by specifically identifying equipment drifts in the production process as well as their cause(s) and to recommend interventions.

In addition, we can use our analytics tools and the operator’s process knowledge to help identify process-related causes of anomalies (in degradation or performance) as well as recommendations for interventions on the short, medium and long term to restore them and improve the process.