Water services produce large quantities of data (to be viewed in real time and then historicized): the real challenge is to transform this raw data into information useful for decision-making and continuous improvement: Proficy CSense is the solution proposed by GE Digital for analytics of the Water&Wasterwater sector, thanks to a series of preconfigured applications that will make integration into your architectures simple and rapid.

Not everyone can afford the figure of the data scientist within their team and for this reason General Electric has taken the field with a solution to bypass this problem: your ANALITYCS system will not have to be built from scratch and you will have all the tools to do it in complete autonomy.

The advantages of punctual monitoring in the world of WATER brings significant improvements in terms of:

  • Cost reduction
  • Efficiency improvement
  • Increased accuracy for demand planning
  • Decrease unplanned donwtime
  • Improved management of chemicals and quality analysis data
Increase performance with ANALYTICS

Industrial analytics is now more accessible for water utilities: thanks to ready-to-use templates and adapted to specific use cases GE Digital's Proficy CSense it will be yours PLUG&PLAY application for ANALITYCS in the WATER World. Using a self-service user interface, engineers can combine data across industrial data sources and quickly identify problems, uncover root causes, predict future performance, and automate actions to continuously improve quality, utilization , productivity and uptime.

In a recent example, GE Digital helped a mid-sized water utility predict pump failure up to 16 days in advance using Proficy CSense. This was achieved without writing a single line of code and resulted in a trend graph that helps engineers identify faults.

The component identified as the cause of the pump failure was a critical corroding bolt – however it was difficult to visually inspect based on its location. As the bolt wore away, its threads would loosen and lose contact, allowing the impeller to oscillate. The extra vibrations created by this movement would have caused more damage to the engine and its coupling. Eventually, the bolt head would separate, resulting in the impeller popping out of the housing and causing catastrophic failure. The result is that this cheap bolt puts this very expensive pump out of action for weeks.

It was a dangerous (however small) "point of failure" which had to be eliminated.

Using analytics and a trained data model, you are now monitoring vibration signal patterns and changes and can detect future failures. The result is that the water company has two weeks to schedule preventive maintenance against wasted resources in unplanned downtime, resulting in downtime of just one day versus weeks.

I want to remind you once again that all this was possible without writing a single line of code and using readily available historical data. The magic happened when the “GE Digital water algorithms”.

In this case, text-based maintenance records were ingested. Analysis of these records revealed two instances of pump failure and the correlation of vibration changes that had previously been overlooked. Using this insight, the data was cleaned up and a statistical method known as “principal component analysis” was used to find the minimum number of tags needed to accurately predict failures while reducing extraneous data noise. We didn't need hundreds of data points or dozens of data sources. We just needed the right dataset that was readily available.

This new information was then combined with ready-to-use learning models to train the algorithm for optimal and repeatable performance. Viewing the resulting data easily identifies anomalies which can then be fed into preventive maintenance scheduling.

Explore possibilities with analytics

This example of how GE Digital and this water utility company were able to predict, demonstrating that it is possible to pump the precise amount of water required, where it is required, according to specification, while keeping operating costs as low as possible.

If you're collecting and storing data from your operations, the opportunities are endless. To spark your imagination, here are some use cases where analytics can have a huge impact:

  • Optimization of the use of chemicals (for example, ammonia)
  • Reduction of energy costs based on the use of assets in processes
  • Improved water demand accuracy and flow optimization
  • Prediction of property failures

Now that you've seen that analysis is within your reach, where do you want to take it?

For more information on this topic watch the video, Analytics in Water. Success Without Becoming a Data Scientist.

Source:

Analytics That Engineers in Water Can Really Use, article by Patrick Bean, Senior Solution Architect, GE Digital.