Big data can drive big energy savings
Most manufacturing managers understand the value of keeping close tabs on the amount of energy consumed in production processes. They know, for instance, that saving energy can improve a company’s competitive position by lowering its operating costs, keeping it in compliance with government regulations, and burnishing its image among environmentally conscious consumers.
However, many manufacturers still struggle to pinpoint exactly what parts of their factories are energy hogs.
There are numerous reasons manufacturers find it difficult to accurately measure plant floor energy use, but chief among them is a lack of adequate tools the accomplish the task. Fortunately for manufacturers, innovative technologies are emerging in other industries can be applied to energy management problems in industrial settings. More specifically, the answer to controlling consumption—and thus the cost—of energy on the plant floor lies in the Big Data revolution.
Data science and innovative analytical algorithms are helping companies improve business operations by tapping into vast amounts of data stored in disparate systems and then leveraging previously unrealized data correlations. Big Data capabilities are empowering companies to quickly analyze massive amounts of data, driving improved operational decision making. Managers can more easily identify and diagnose operational problems. Then management can prescribe appropriate business decisions and actions.
So how does all this apply to industrial energy management? Consider the top four energy management challenges confronting manufacturers, according to a recent survey of more than 100 executives conducted by LNS Research:
- Energy metrics are not effectively measured
- Disparate systems and data sources
- Lack of culture supporting energy management
- Lack of visibility into performance.
Having visibility and detailed knowledge of ongoing energy consumption patterns at each machine or industrial process is the first critical step for initiating a systematic approach to industrial energy management, and improving a company’s competitive position. However, there are other factors hindering industrial energy management.
Costly time lags
Industrial environments are extremely complex. They are very technical and unique in their operations, organization and culture. No two factories, even within the same company making the same products, are alike. Product variations, inconsistent equipment and process efficiencies, unplanned downtime, preventive maintenance routines, and changing production schedules are facts of life.
The two most common approaches to determining how much energy is used on factory floors are:
- Physical plant audits by energy engineers and auditors who may install temporary meters and data loggers, survey equipment and their power ratings, evaluate operating schedules and calculate energy use.
- Installation of costly metering systems: this includes designing, tendering, procuring, installing, and configuring automated metering systems (which may require production interruptions).
The drawbacks with both traditional approaches include the extensive amount of time and labor they require, the need for large upfront capital investments, plus a lack of scalability across a single plant or enterprise.
Plant audits capture energy metrics only for a limited time period, and are not directly correlated to production output and mix, which frequently change over time. The long duration of time necessary to perform and document plant audits or to deploy sub-metering solution projects can delay plant the initiation of energy-saving actions.
Manufacturing operations typically do not set aside separate budgets for energy efficiency. Energy management projects compete for funding against projects related to production efficiency, manufacturing yields, and quality. And the expected ROI for energy related projects is often more demanding than those tied to production. For these reasons and the perceived difficulty in quantifying ROI and indirect benefits (due to the lack of meaningful data), industrial energy management projects are difficult to get financed.
It’s a frustrating and costly closed-loop cycle. Without an intelligent energy management system, how can plant managers have the data to measure energy performance, know their significant energy uses (SEUs) and establish a baseline for improvement? How after energy conservation measures are implemented, can decision makers then verify the savings and the return on investment without the energy metrics?
A new approach is needed to tackle this problem. That’s where Big Data comes in. To understand how this technology transfer can work, it’s important to remember that industrial energy costs go beyond electricity. They include the five components known as WAGES:
For commercial buildings, Big Data and energy analytic software as a service (SaaS) platforms are driving innovative energy management developments. By analyzing readily accessible data sets – weather, GIS, and 15 minute or hourly interval electricity consumption – “Virtual” or “No Touch” Energy Audits aim to determine how a building is consuming energy. These software systems then provide end-use operational insights and recommendations for improvement without ever contacting the building itself.
First Fuel and Retroficiency, both Boston-area companies, are among the technology providers who are pioneering this science for commercial buildings.
These energy assessment tools are proving effective in helping corporate real estate managers accurately identify and target buildings by their energy efficiency potential. Capital can then be more effectively deployed to yield the optimal ROI across a property portfolio.
There are tremendous untapped opportunities in manufacturing data that is not being leveraged to drive reduced energy consumption. Data science and analytics are providing manufacturers with capabilities to pinpoint operational improvements and achieve savings on the factory floor.
The Industrial Internet, the Internet of Things and Big Data are trends that manufacturers can no longer afford to ignore. The world is speeding in this direction and Big Data can provide manufacturers with business intelligence, analysis and relevant energy metrics. This intelligence can help manufacturers overcome the challenges associated with implementing energy conservation programs due to an inability to get their hands on meaningful data.
Click to the next page to see a smart energy graphic and read about manufacturing pilot programs and other potential applications.
(Continued from page 1)
Manufacturing pilot programs
In a pilot program, a multi-national manufacturer found it could cut energy costs by 20% in a single plant by using a manufacturing virtual audit platform from LinkCycle. The factory in which the pilot took place houses more than 80 injection molding machines manufacturing various plastic products that customers use for food storage. Before the pilot, the plant was consuming approximately $3 million worth electricity each year.
Plant personnel provided LinkCycle two readily available data sets:
- 15 minute interval data from the electric utility meter
- Machine-level production data by shift.
Without ever stepping into the plant, LinkCycle’s Cloud/Software as a Service (SaaS) business intelligence platform was able to calculate both fixed and variable electricity consumption for each machine by product SKU. Thus, the manufacturer avoided the high costs associated with a physical plant audit or installations of a sub-metering system. The statistical accuracy of the results were found to be greater than 90%, matching available sub-meter data from several injection molding machines.
By attaining detailed energy visibility for shop floor operations and knowing the electricity profile of each machine, plant management can save electricity through a more systematic approach to industrial energy management. By arming executives with the same data as plant functional managers and operators, operational strategies which include energy conservation measures and improved asset management initiatives can be put in place. Such strategies include:
- Scheduling production on machines which are more efficient
- Diagnosing, troubleshooting and repairing less efficient machines
- Reducing machine idling times through better production scheduling
- For machines with high energy profiles, moving production to off-peak shifts when electricity prices decline
- For machines with energy profile volatility, troubleshooting and scheduling maintenance and/or process control tuning
- Avoiding peak demand pricing penalties
- Allocating energy cost per unit to bills of material.
In the pilot, the plant’s 20% reduction in energy waste translates to lower manufacturing costs. Other potential benefits include improvements in schedule or production attainment and overall equipment efficiency. Deploying LinkCycle’s SaaS solution across its global plants will allow the enterprise to uncover energy saving opportunities at a greater scale faster and at much lower cost.
Other potential applications
Manufacturers across a spectrum of industries (CPG, food processing, and chemicals) have validated the virtual audit technology for process, batch, discrete and hybrid operations. Some factors to consider when investigating virtual audit technology for manufacturing settings are summarized below:
The technology is nearly ideal for plants with the following characteristics:
- High volume production
- Continuous, batch, discrete, and hybrid manufacturing
- Complex facilities with multiple to several hundred production lines
- Production facility with its own utility interval meter.
Virtual audits may not work well in plants with these characteristics:
- Low production volume
- High degree of customization, not repetitive output (i.e. job shops)
- Singular production line (i.e. glass production)
- A lot of work in process (i.e. aircraft manufacturers)
- No meter for production area (i.e. meter includes large laboratory, pilot plant or R&D space).
Manufacturing energy intelligence can reveal patterns of energy waste, pinpoint savings opportunities and indicate declining equipment performance. The vast untapped amounts of manufacturing data have in the past been too distributed and disconnected to provide meaningful information which can lead to operational improvements. Innovations in Big Data science and predictive analytics are correlating data sets in new ways to reveal the “where and how much it costs” of energy consumption patterns coming from production.
An industrial energy management system based on these new and innovative methods will give manufacturers timelier and less expensive energy-related metrics. With this information in hand, manufacturing managers can fine tune their operations in ways that will lower energy costs while improving productivity and boosting the overall corporate bottom line.
– Chris Davis is vice president of sales and marketing for LinkCycle Inc., www.linkcycle.com, a technology supplier that helps manufacturers leverage previously unknown data correlations in factories to improve operational decision making and plant efficiencies. He can be reached at email@example.com. Edited for the CFE Media Industrial Energy Management section in February as a Digital Edition Exclusive. Send comments to firstname.lastname@example.org.
- Manufacturers find it difficult to accurately measure plant floor energy use, primarily because they lack adequate tools accomplish the task.
- The answer to controlling consumption—and thus the cost—of energy on the plant floor lies in the Big Data revolution.
- Advanced analytic technologies make it easier for plant managers to identify and diagnose operational problems.
Isn’t it time to at least investigate a new form of technology with the potential for fine-tuning your plant operations in ways that will lower energy costs while improving productivity and boosting the overall corporate bottom line?