Energy Consumption

Assembly Line

Artificial intelligence optimally controls your plant

Date:

Topics: energy consumption, reinforcement learning, machine learning, industrial control system

Organizations: Siemens

Until now, heating systems have mainly been controlled individually or via a building management system. Building management systems follow a preset temperature profile, meaning they always try to adhere to predefined target temperatures. The temperature in a conference room changes in response to environmental influences like sunlight or the number of people present. Simple (PI or PID) controllers are used to make constant adjustments so that the measured room temperature is as close to the target temperature values as possible.

We believe that the best alternative is learning a control strategy by means of reinforcement learning (RL). Reinforcement learning is a machine learning method that has no explicit (learning) objective. Instead, an “agent” with as complete a knowledge of the system state as possible learns the manipulated variable changes that maximize a “reward” function defined by humans. Using algorithms from reinforcement learning, the agent, meaning the control strategy, can be trained from both current and recorded system data. This requires measurements for the manipulated variable changes that have been carried out, for the (resulting) changes to the system state over time, and for the variables necessary for calculating the reward.

Read more at Siemens Ingenuity

Why more manufacturers are turning to microgrids

Date:

Author: Brent Tracy

Topics: energy consumption, sustainability

Microgrids offer manufacturers a flexible platform to head off these issues — ensuring power is reliable, enabling renewable energy for sustainability goals, controlling energy costs and attracting customers and investors that want manufacturers to continuously raising the bar on ESG performance. A microgrid can help control energy generation, usage and cost stability.

A well-designed microgrid can bring efficient, low-cost power as well as reliability and resiliency benefits to critical infrastructure. A microgrid with robust controls and up-to-date cybersecurity supports operational flexibility while providing predictable costs optimized for both efficiency and sustainability.

An investment in a microgrid can act as insurance for continued growth, success and innovation. A power disruption brings vulnerability, loss of time and money — a microgrid puts you back in charge.

Read more at Plant Engineering

Thermal Process Modeling to Save Energy

Date:

Authors: V. Mendoza, J. Gonzalez

Topics: energy consumption, finite element method

Vertical: Primary Metal

Organizations: Carpenter Technology

The thermal schedule for heating workpieces is often determined by simple rules and experience in industrial production. Thus, a finite element method (FEM) based simulation of heating ingots in heat treatment furnaces is of great importance to thermal optimization. FEM modeling allows for the prediction and control of temperature uniformity — and ultimately microstructure, residual stresses, workpiece properties, and reducing energy consumption.

Read more at Carpenter Technology Blog

Reducing Energy Costs by 8% by Optimizing Autogenous Mills

Date:

Topics: digital transformation, energy consumption

Vertical: Mining, Pulp and Paper

Organizations: METRON

The grinding process alone accounts for 80% of the energy consumption. It consists of pulverizing limestone blocks to obtain the calcium carbonate used as a mineral filler in paper pulp.

Mills are the plant’s main equipment:

  • 5 x 355 kW autogenous mills operating without prior crushing;
  • 20 electric mills of various powers between 250 and 355 kW.

The case presented concerns only the autogenous mills, which are the most energy-consuming.

Read more at METRON Blog

How SparkCognition Improved Production Efficiency for a Beverage Manufacturer

Date:

Topics: machine health, energy consumption

Vertical: Beverage

Organizations: SparkCognition

We developed seven new deep learning models to detect anomalies in resource consumption, machine status/health, and overall efficiency. (As always with a Total Plant solution, these models were tailored to the specific data, technical context, and business goals and strategies of the client.)

Once developed, the models were deployed into our AI platform for execution and KPI-driven reporting. Another key new function we delivered: predictive analysis, to anticipate problems before they occur, based on patterns detected in current and historical data, and notify the beverage manufacturer in time to take preventative action.

Finally, the results of the AI-powered analysis were delivered via a configurable dashboard that provides at-a-glance insight into the plant’s efficiency, including new KPIs reflecting water usage, water balance, power consumption, heat generation, and waste levels. This information can also now be streamed whenever, wherever, and to whomever the manufacturer requires, now or in the future.

Read more at SparkCognition

How Honeywell's CEO is turning the legacy manufacturer into a SaaS player

Date:

Author: Joe Williams

Topics: energy consumption, sustainability

Organizations: Honeywell, Microsoft, SAP

Cumulatively, it marked a significant step forward in Adamczyk’s vision to turn Honeywell from a legacy industrial manufacturer into a top software provider for sectors like real estate, life sciences and aviation.

“The one common fiber across all our businesses is we are a controls company,” he told Protocol at an event on Tuesday. “When you’re a controls company, you’re connected to everything, you’re connected to all the systems in that building, in that aircraft. We use that data to drive controls, but we could use that data to drive energy savings, to drive efficiency.”

Read more at Protocol