Skip to content Skip to footer

Case Study: Condition-based Monitoring and Cognitive Operational Control of the Chiller Plant

1

Background and Problem Statement

The chilled water plants are traditionally regulated and monitored by a predetermined control strategy  where energy efficiency is a major concern. In addition, emergency maintenance calls in general and  summer season, in particular, have been a major concern in the industry. A chilled water plant owner  located in Houston leveraged Ranial Systems’ platform to address these issues, gain energy efficiency  and minimized ongoing maintenance overheads.  

 

 

2

Approach

During the brainstorming sessions with the client, Ranial Systems identified the pain points of the  traditional chiller plant control strategy. It was noted that while the operational model aims to fulfill the  required cooling load demand, the predefined setpoint temperature defined within the PLC/SCADA  system results in considerable energy wastage within the operating environment. Chillers are sequentially  switched on one after another whenever the building cooling load demand increases, and often the part load of the operating chillers rises above a pre-set value.  

Ranial has introduced its Cognitive edge computing and AI based condition monitoring platform to enable  predictive operational control strategy. The aim was to improve the performance of chiller plants using  real-time predictive operational intelligence and autonomous controls without any additional high-priced  equipment procurement. The target-state solution should minimize the manual supervision and improve  energy efficiency. 

 

3

Solution

Ranial Systems collected historical data from the existing Historian and fed those inputs to the cognitive  algorithm for the purpose of training the AI agent. It correlated the outdoor temperature, cooling demand,  chilled water supply & return temperatures, chilled water flow rate, and energy consumption data speeded  over the Summer, Spring & Fall usage patterns.  

Upon testing the model performance, the models were deployed on the edge (site controller). The security  requirements, specifications of the edge devices, and maintenance strategy were mutually discussed and  agreed upon.  

The offered CognitIoT™ solution supports multi-protocol integration (Modbus, BACnet, and OPC to  communicate with the industrial assets and offers extensible communication/intelligence infrastructure  through highly scalable AI-powered edge computing runtime. The interoperability and self-healing of  endpoint IoT systems ensure resilient and low-latency interactions with PLC/SCADA systems. The  cognitive edge runtime intercepts the sensory feeds to gain situational awareness to facilitate requisite  control operations. The flexibility in integration with legacy control system infrastructure allowed Ranial  systems to leverage such intelligence at the point of action with minimal hardware and software upgrades  in the existing control systems. CognitIoT™ could integrate with multiple PLC/SCADA systems in a  protocol-agnostic way and, offer real-time monitoring and site management functions through a  centralized web-based console, while the edge controller performs the autonomous operations at the  plant. 

4

Implementation

The following workflow was designed to implement the predictive control strategy for the existing chilled  water plant.

 

An edge controller preloaded with the AI agent was installed in the control room linked to the PLC/SCADA  system over Modbus. Platform middleware and infrastructure tuning, AI/ ML modules, and monitoring  dashboard customization were performed in line with the client’s requirement.

5

Result

In an implementation cycle of two months, Ranial systems rolled out the cost-effective solution by  integrating existing PLC/SCADA systems, incrementally trained the model, and testing all possible  scenarios prior to go-live.  

The implemented system could improve up to ~8% energy efficiency of the chilled water plant. The edge  native solution with cloud-based monitoring, Ranial Systems could achieve 30% saving on recurring  maintenance costs.

Leave a comment