Improving Plant Operations with Artificial Intelligence
image credit: © Igor Borisenko | Dreamstime.com
- Apr 14, 2021 10:17 am GMTApr 14, 2021 9:46 am GMT
- 230 views
Many utility operators desire greater flexibility in their plant operations. The developments in Artificial Intelligence (AI) and Machine Learning (ML) will enable these improvements, as well as helping to cut costs, reduce damaging emissions, and improve reliability in the face of a changing power mix that includes more renewables.
Renewable energy inputs, coupled with distributed energy systems and emerging energy storage networks, is making a huge impact on the business of electricity markets. Wind and solar electricity resources have been the most disruptive renewable energy technologies over the past few years and will continue to challenge the way power provision operates. The challenge for grid operators is managing these diverse electricity sources to match weather-dependent supply with end-users who expect more independence and flexibility to manage their energy consumption needs.
AI-based systems offer the opportunity to continuously optimize plant performance, instead of being limited to a static “design point” usually found in gas- and coal-fired power stations. These can be implemented as an add-on to the conventional control systems, so no massive changes to plant Digital Control Systems (DCS) are required.
AI-based control technology is intended to operate in parallel with the plant DCS. These systems are adaptive and will adjust operating parameters to the prevailing conditions. It continuously tunes the system to the optimal output. As the inputs and outputs depart from the optimal, it tests and returns them to an equilibrium that suits the conditions. This is a dynamic and changing process, and obviously there are humans in the loop who can override the AI if the need arises.
It appears that most coal- and gas-fired plants are capable of greater flexibility than their designers envisaged and the AI control systems can benefit from that. For example, ramp times to full load can be reduced significantly, operating temperatures and pressures optimized – ensuring greater reliability through fewer maintenance breaks and lengthening component lifespans.
The promise of AI is it will assist under-performing plants to improve their thermal efficiency while minimizing thermal stress to the equipment, reducing startup time, and improving operating flexibility for both coal-fired and gas plants. Flexible power facilities, particularly responsive plants with excellent ramp rates, high turn-down, and good load-following capabilities under AGC, are particularly valuable to a system operator. The relatively small investment in AI is likely to increase the ROI on the owner’s plant investment, so is where the smartest plant operators will be focusing their attention.