Use Data Analytics to Comply with HSE Regulations

Clean water is one of the most essential requirements for human health, environmental sustainability and economic development. Due to population growth, urbanization and climate change, this vital resource has become more scarce than ever in many communities around the world. In order to meet the increasing demand, there is a growing need for societies to shift toward a more circular economy, but it comes at a cost. Instead of automatically discharging wastewater, many experts believe it needs to be captured, treated and distributed back to the consumer. Water reuse and wastewater treatment are intrinsically energy intensive, due to the need to move large volumes of water using pumps and electric motors, and then treating the water to meet stringent regulatory requirements. In conventional wastewater treatment plants (WWTPs) aeration is one of the biggest energy consumers for treating wastewater. Other significant energy consumers include filtration and disinfection processes depending on application. To cope with increasing energy consumption and to reduce the carbon footprint in water industries, novel technologies need to be implemented. Innovative technologies in water reuse facilities often come with drawbacks like increased complexity and reliance on instrumentation. These challenges in energy management are not unique to the water industry. They are also of critical concern in other industries including the chemical, food and beverage, metals and mining, pharmaceutical, and oil and gas.

Energy management has become more important in recent years due to established regulations to reduce greenhouse gas emissions on an international, national and local scale. To achieve these goals and to comply with regulations, the oil and gas industry in particular is rapidly adopting the International Organization for Standardization (ISO) 50001 standard to improve energy performance and to make climate part of their corporate strategy. Most companies have formalized their energy management programs and use automation and control technologies to help minimize energy costs. It is clear, however, that many companies need to take their efforts to the next level by monitoring and optimizing energy use in real time and leveraging Industrial Internet of Things (IIoT)-generated data. For many years process data has been retained and maintained within corporate histories. All of this data can be unlocked and leveraged for continuous improvement of processes and to lower the carbon footprint. To some extent, data analytics has been used by major companies for their larger on-site energy issues, but this requires significant resources. Interestingly, these time-consuming, centrally led, data modeling projects are less suited for process-related optimization projects that require subject matter expertise. In recent years, new tools have become available that place advanced analytics in the hands of subject matter experts, including process and field engineers. These tools enable such experts to solve energy process-related cases independently and positively contribute to corporate goals for reducing carbon footprints.

Energy Management 4.0

Global interest in Industry 4.0 has accelerated digital transformation in the process manufacturing industry, including those that are water-related. Many companies have engaged in technology pilots to explore options for reducing costs, to increase overall equipment effectiveness (OEE) and to help conform to enforced regulations. Anaerobic membrane bioreactors (AnMBR) are used in WWTPs to separate and treat sludge from wastewater, generating biogas as a byproduct. This technology can drastically reduce the energy consumption in large plants by generating renewable energy on-site. Microbial electrical systems can be used to generate electricity while treating wastewater with microbial fuel cells (MFC), for instance, but this is still in its early stages of development. Aeration is a key consumer in wastewater facilities, and a lot of research has been conducted in an effort to optimize these processes. To give some examples, membrane aerated biofilm reactors are an emerging technology in which oxygen is transferred much more efficiently. Optimizing the configuration and hydrodynamics in large bioreactors can provide better mixing. Better mixing consequently leads to less energy consumption for aeration and can even result in less production of strong greenhouse gases like nitrous oxides and methane. Disinfection and filtration processes can contribute significantly to the total energy consumption. This depends largely on the level of water quality standards required for the application. Novel technologies like ultraviolet (UV) treatment using LEDs can reduce the energy consumption. Also, improved membrane technologies like ultrafiltration and reverse osmosis are gaining more attention for reducing the energy impact of the system. One of the best ways to leverage these new innovations is to apply advanced industrial analytics to production data, generated by sensors. Every piece of data provides unique opportunities for improving energy efficiency. Since data is only as valuable as the solutions it unlocks, understanding its potential is key. Complex optimization problems are frequently tackled by a limited group of data scientists who use the data for building and validating mathematical models. For instance, computational fluid dynamics (CFD) modeling is gaining much more traction in the water industry. Another strategy is to empower subject matter experts such as process, operation and maintenance engineers, who have deep knowledge about the production process itself. If they can quickly access, search and analyze the historical time series data, they will be able to answer relevant questions for their day-to-day jobs, without having to rely on data scientists. Hypothesis generating and hypothesis testing using descriptive, discovery, diagnostic and even predictive analytics has proven its value already in many other industries.

Practical Use Cases

Before starting any energy management project, it is crucial to define the problem and identify the high energy consumers. Using descriptive analytics, one can benchmark optimal operating conditions. Such benchmarks can be used to assess cost-saving opportunities and set priorities for optimization projects. Optimal operating conditions can be used to configure monitors, using discovery analytics. Leaks can be detected if levels in tanks decrease abnormally fast. Alerts can be received when sensors need to be replaced or calibrated. When flow control valves start to wear out or get plugged, this information can be captured within the data. Fouled membranes cause increased hydraulic head losses. This change of behavior is expressed in time-series data and can be identified by the appearance of different operating windows in scatter plots. These anomalies can be detected and used as a premise to prompt people in the field to take action, as was seen at PWN, a water company in the Netherlands.

A Water Company Case Study

PWN used time-series data to calculate hydraulic head to analyze and monitor the performance of their water network. It became clear that the hydraulic head losses were increased after construction works (see Image 1). This descriptive analysis enabled the engineers to distinguish between the two operating zones. A similar approach can be used to optimize pumps by comparing the actual performance curve to the manufacturer’s performance curves, providing insights to the energy efficiency of the pumps. The installed system can be monitored live and used to better predict maintenance needs. Covestro, a chemical company, initiated three major energy savings projects for their polyether plant in Antwerp as part of the energy savings goals and ISO 50001 directives. Self-service analytics solutions were implemented for online detection, logging and explaining unexpected energy consumption and for comparing the results with the reference year 2013. The latter is illustrated in Image 2, where the averages of steam consumptions and production rates for four consecutive years are compared. Using specific formulas and calculated tags, various energy consumers are monitored and controlled. Through monitoring the performance against the reference year, it is shown that the energy consumption is effectively decreased year over year, meeting their corporate goals. More importantly, with a growing knowledge and insight into the production process, Covestro is continuously improving overall performance. Diagnostic analytics can help the process engineers troubleshoot and gain more insight into processes. Comparing different regeneration cycles in ion-exchangers can help the investigation into the effect of multiple process parameters on performance. By overlaying multiple runs, hypotheses can be tested with historical data. An example of this is the monitoring and quantification of the effect of feed composition, temperature, or pH on the quality of the biogas production in AnMBR systems. Visualizing the relevant data in the correct way helps engineers to gain new insights. For instance, Evides, a Dutch water company, found that a significant amount of energy could be saved by using a redundant reverse osmosis skid to deliver the same production rate. This became clear after preprocessing and filtering the relevant data of a reverse osmosis unit at an industrial WWTP in Antwerp, Image 3.

Conclusion

In order to meet the needs for a global increase in water demand, there is a growing need for societies to shift toward a more circular economy. Instead of just discharging wastewater, it needs to be captured, treated and distributed back to the consumer, but this takes a lot of energy and increases significantly the carbon footprint. With the ever-evolving environmental regulations, the water industry is having to think of new ways to increase energy efficiency. Energy management is not new. Indeed, many companies have a structured energy management program in place. However, such programs often require the use of data scientists, stalling the time it takes to find process solutions and often overlooking insights that subject matter experts can offer. New self-service analytics tools bring the subject matter experts to the forefront of the analytical process by enabling them to analyze, monitor and predict process and asset performance. This can significantly contribute to meeting organizational carbon footprint goals—especially when process knowledge is needed to improve operational performance and asset reliability. Typically, these improvements come together with an improved overall profitability and increased safety. Therefore, it is critical to raise data analytical awareness in all energy intensive industries to reduce the carbon footprint.