Implementation of PdM strategy for gas turbine

Goals

Predict whether the current level of contamination of turbine components will allow the machine to run smoothly

Reduction of unplanned downtime, more efficient organization of work

Results

Development of a system that monitors the performance of the expansion turbine to predict whether the current contamination of the turbine components allows the turbine to restart smoothly after a scheduled shutdown

Challenge

The plant has two twin turbines with a capacity of about 9 MW, each powered by blast furnace gas, which is a byproduct of the smelter furnace. The gas thus supplied, after a purification process, contains a trace amount of impurities, which then settle on the turbine components.

As a result, increased vibration occurs during turbine startup, and as a result, the machine cannot be started. The reason for the startup problems is that the maximum vibration allowed during machine startup is exceeded. The consequence of the occurrence of such vibrations is unplanned downtime and the need to call in external service to clean dirty components.

Solution

The implementation used the anomaly detection module available in the RSIMS Module solution. The implementation used a transform of the raw vibration signals, the value of which reflects the contamination status of the turbine components. Exceeding the transform's limit value informs about possible problems with turbine startup during the next startup attempt.

CASE 1 / Sensor data analysis

In the case presented here, the RSIMS Module application was able to detect an improperly performed turbine rotor cleaning service, and as a result, experts were able to observe a sudden increase in vibration on one of the sensors (the graphic above is an example). The consequence of detecting the sudden increase was to call the turbine component cleaning service again to perform the cleaning service again.

The result of this work was a reduction in the vibration of the expansion turbine rotor to a level below the alarm threshold. This reduced the risk of uneven accumulation of dirt on the rotor leading to an even greater increase in vibration and ultimately the inability to start the turbine.

Benefits

The solution is able to predict up to 100% of potential failures resulting from contamination of turbine components. Implementing RSIMS Module provides faster and more accurate insight into plant operation than any other monitoring system used to date.

By predicting whether a turbine will be able to start up after an impending shutdown, the customer has gained the ability to:

Possibility to organize turbine cleaning work in advance

Savings from minimized waiting time for external service

Constant monitoring allows you to control the correctness of services provided by subcontracting companies

Ability to predict up to 100% of potential failures resulting from contamination of turbine components

Faster and more accurate insight into the operation of the installation

About company

ReliaSol is a company established in response to the growing need to increase the efficiency of machines and installations in industry.

We provide software and services that accelerate the digital transformation process. The applications we create combine real data from machines, sensors, event reports and automate drawing conclusions. The result of their work is data visualization, event prediction and monitoring of the optimal operating range of machines and entire production lines.

We will be happy to answer your questions

Reliability Solutions Sp. z o. o.
ul. Królewska 57, 30-081 Kraków, Polska