Energy monitoring system helps plastic processing enterprises achieve rapid return on investment

The intelligent energy monitoring system integrates IoT sensors with an asset management platform to help plastic manufacturing enterprises achieve quantifiable cost reductions.

IoT monitoring solutions can help injection molding, extrusion, and blow molding manufacturers eliminate energy waste and optimize overall plant production efficiency.

Berend Booms, head of the Enterprise Asset Insights department at global intelligent asset management company Ultimo, said that the plastics processing industry is inherently energy-intensive.

“Every injection molding machine, extrusion machine, and chiller is a major energy consumer,” said Berend Booms. “The issue is not whether to conduct energy monitoring, but whether the data obtained from monitoring can truly be used for decision-making to achieve energy consumption reduction.”

Independent measuring instruments can only display energy consumption, while the Enterprise Asset Management (EAM) platform can dig into the reasons behind high energy consumption and provide corresponding solutions.

"Its value lies in integrating equipment status data with energy consumption data. That way, the same system can schedule preventive maintenance while also issuing an alert that a particular hydraulic press is consuming 20% more power than the same model on the neighboring production line," said Berend Booms.

Energy costs rank among the major operating expenses.

For plastic processing companies, excluding raw material and labor costs, energy costs are usually among the top three operating costs.

Berend Booms stated: “Injection molding, extrusion, and blow molding production involve high-temperature processes, hydraulic systems, compressed air supply, and cooling requirements, resulting in high energy consumption, most of which is continuous.”

What is even more complex is that energy is no longer a fixed corporate operating expense. Affected by current global socioeconomic turbulence, fluctuations in utility prices, peak electricity surcharges, and increasing regulatory pressure related to carbon emissions, energy is increasingly eroding corporate profits.

Energy efficiency is gradually becoming a mandatory requirement in supply chains. Brands and original equipment manufacturers (OEMs) will ask processors for emissions data, carbon footprints, and energy intensity metrics. Berend Booms mentioned that, from the perspective of production operations, energy consumption is closely tied to equipment operating conditions.

IoT monitoring solution for real-time energy consumption visualization.

Over the past several years, energy monitoring technologies in the plastics manufacturing industry have become increasingly mature. Berend Booms notes that processors can choose from multi-level monitoring technologies and that most companies use a combination of them.

The most basic approach is intelligent sub-metering, where IoT sensors are deployed at the equipment or circuit level to collect real-time electricity consumption data. This changes the old model of only checking the main meter at the end of the month and relying on guesswork to trace energy flow. Berend Booms said, "Sensors continuously transmit data to cloud dashboards and data lakes, allowing managers to view energy consumption by equipment type, production shift, production batch, or factory area."

Enterprise Asset Management (EAM) is a higher-level system that integrates energy data with complete equipment records, including maintenance records, operating conditions, equipment parameters, service life, and equipment status.

"The monitoring data is truly actionable here: when an injection molding machine's power consumption exceeds the baseline by 18%, it serves as a warning signal, and the enterprise must take timely action to prevent the situation from worsening," he stated.

The enterprise asset management platform associates abnormal energy consumption with equipment data. Once an abnormality indicates a maintenance risk, a maintenance work order can be automatically generated.

Predictive analytics and artificial intelligence models are increasingly used to analyze sensor data, identifying energy consumption patterns across devices, shifts, and plants that are difficult to detect manually. Berend Booms stated that these systems can identify energy waste caused by ineffective idle running of equipment, provide optimal startup timing recommendations to avoid peak electricity surcharges, and, by analyzing trends in equipment energy consumption changes, determine whether the equipment is more suitable for repair or direct replacement.

Finally, there is also virtual metering technology. Without installing physical meters on every circuit, enterprises can calculate the total energy consumption of a group of devices or the difference in energy consumption.

“这套嵌入在企业资产管理系统中的工具，对制造企业十分实用。企业无需投入六位数成本大规模部署传感器，就可以拿到有实际参考价值的能源数据。”Berend Booms补充道，效果最好的方案，往往是多种技术分层组合落地。

Common Misconceptions About Intelligent Monitoring Systems

Many people hold the fixed belief that IoT energy monitoring solutions are only suitable for large manufacturing companies with ample budgets. Berend Booms says the situation has now changed. The cost of IoT sensors has declined, and cloud-based enterprise asset management platforms offer subscription models, making them affordable for small and medium-sized plastic processing companies as well.

"A factory with eight injection molding machines conducts energy monitoring at the equipment level, and the benefits obtained are comparable to those of a large factory with eighty machines," he said. "There is no need to deploy it throughout the entire plant from the beginning. Even if only the five highest energy-consuming machines are monitored, the information obtained is enough to prove that this investment is worthwhile."

Some people confuse IoT energy monitoring systems with building management systems. Building management systems generally track energy consumption at the level of an entire building or at the circuit breaker level, and can only show how much energy is consumed in a certain area of the plant. IoT energy monitoring, however, can accurately measure energy usage down to a single device, and can further break down energy consumption by different shifts and different batches of raw materials.

Another common view is that energy saving mainly depends on shutting down equipment. However, processing enterprises need their equipment to keep running continuously for production.

Berend Booms表示：“真正的机会在于消除非生产时段的能源浪费；优化工艺参数，在保障产品品质的前提下降低不必要能耗；在设备性能下滑造成生产效率损失前及时发现；通过更科学的排产管控用电峰期附加费用。”

Some people also believe that equipment upgrades must be completed first before energy monitoring can be meaningful. Berend Booms points out that, in reality, the vast majority of IoT energy monitoring projects in manufacturing are implemented on existing outdated equipment.

“Modern sensor technology is designed precisely for retrofitting old equipment. For an injection molding machine that has been in use for twenty years, its energy consumption data is often more valuable than that of a new machine—older equipment is more prone to performance degradation, and monitoring systems are well suited to capturing such problems.”

落地实践重塑工厂运营模式

When discussing the impact of implementing IoT monitoring solutions on plastic processing plants and on-site management personnel, Berend Booms said that the first thing maintenance personnel notice is the newly gained visibility into data that was previously lacking.

"In the past, discovering that last month's electricity bill surged by 12% would require a lot of time to review and find the cause; now we can see in real-time which shift and which equipment has abnormal energy consumption. The work mode has shifted from post-event investigation to proactive management."

Previously, maintenance personnel either waited for equipment to fail and shut down or performed scheduled maintenance at fixed intervals; now they receive alerts for abnormal energy consumption, enabling them to identify potential faults in advance.

Berend Booms gives an example: "The power consumption during the heating stage of the extruder suddenly increases, or the energy consumption of the hydraulic press per cycle continues to rise over several weeks. These signals can provide early warnings of failures, preventing sudden breakdowns that could lead to significant losses."

Factory managers and operations leaders can derive long-term strategic value from IoT monitoring.

“Investment decisions are no longer based on data but on subjective judgment about which piece of equipment ‘looks’ overheated; instead, they rely on actual energy consumption curves spanning a production cycle of up to 18 months. For multi-site enterprises, it is also possible to conduct benchmarking analyses across shifts and across plants,” said Berend Booms. “In the long run, manufacturers can renegotiate utility contracts, apply for energy-efficiency subsidies, and produce the environmental, social, and governance (ESG) reports that customers increasingly require, all based on real load data rather than estimates.”

Case: Achieving Significant Cost Reduction

iFactoryAI stated that a mid-sized plastics manufacturing company reduced its energy costs by 24% through data-driven optimization. The company operates 48 injection molding machines on a three-shift schedule, while utility expenses had risen 19% year over year. Electricity costs from hydraulic injection molding machines, compressed air units, and process cooling systems accounted for nearly 22% of the company’s total production costs. After deploying the iFactory monitoring platform to capture granular energy consumption data at the equipment, production line, and utility levels, the company identified more than $340,000 in annual energy waste within just six months. As a result, the plant’s overall energy intensity fell by 24%, and the platform paid for itself in 3.2 months.

Berend Booms introduced that the energy savings of enterprises come from multiple aspects.

A significant portion comes from eliminating waste during non-production periods: for example, equipment left on standby over the weekend while heating and hydraulic systems continue to run at full load; valves are already closed, yet the compressed air system is still running; and chillers undergo pointless repeated start-stop cycles.

He added that controlling the additional fees for peak electricity consumption often results in the fastest return on investment. Industrial electricity prices typically include demand charges based on peak power consumption over a 15-minute period. By staggering the startup times of equipment and scheduling high-energy-consuming processes during off-peak hours, processing enterprises can significantly reduce their demand charges.

The savings brought by predictive maintenance are not directly reflected in energy expenditures, but rather in reduced downtime, lower scrap rates, and extended equipment service life.

“After the enterprise asset management platform connects energy data with equipment status, the resulting economic benefits will cover multiple cost centers,” said Berend Booms.

But the true value of technology ultimately depends on the users. For enterprises to shift from reactive maintenance to proactive handling based on energy consumption anomalies, it is essential to have employee training, recognition from frontline personnel, and support from management.

Berend Booms stated: "Implementing projects on the ground requires investment in purchasing sensors, completing system integration, and allocating manpower to configure the system, as well as building new workflows based on data. Older equipment still poses integration challenges. Most IoT sensors can be retrofitted onto old equipment, but debugging and integration consume time, and the data quality output by old equipment is inconsistent. Enterprises need to allow for a learning and debugging period, first validating the data before making decisions based on it."

Overcoming implementation challenges

Berend Booms believes that the primary challenge is the integration of the IoT monitoring system.

Many plastic factories operate equipment from multiple generations and eras simultaneously, and many companies think it would be better to wait until the entire plant has been fully modernized before starting monitoring.

A more reasonable approach is to start with the equipment that has the highest energy consumption and critical importance, and then gradually expand. Retrofit sensor technology has made significant progress, enabling the addition of monitoring capabilities to old equipment without the need to replace the original control system.

The second challenge is data quality.

“Internet of Things sensors can generate massive amounts of data very quickly. Without clearly defining monitoring objectives and business needs, large volumes of data can instead become a burden,” said Berend Booms. “The industry best practice is to first clarify which business questions the enterprise wants to answer before deploying sensors.”

These questions may include: Which pieces of equipment consume the most energy? What does the normal energy consumption curve look like for each process line? What kinds of anomalies should trigger the initiation of the response procedure?

The third obstacle is accountability. Energy monitoring work spans multiple departments, including maintenance, production, reliability, and finance, and there is often a lack of regular communication between teams within the factory. Booms suggests that factories implementing IoT monitoring projects should designate a reliability engineer, energy manager, production director, or other responsible person to take the lead, with the authority to implement the various recommendations provided by the data.

Workflow integration is another major challenge.

“If data cannot connect with business processes, it is very difficult to truly change people’s behavior,” said Berend Booms. “In successfully implemented projects, energy-consumption alerts are directly integrated with the work order management system. Once an energy-use anomaly is identified, the follow-up handling steps are already predefined. This integration between IoT monitoring and enterprise asset management determines whether a project merely performs data monitoring or truly delivers operational improvement.”

智能监测技术未来发展方向

Berend Booms stated that future technological development will focus on three main directions: deep integration, intelligent analysis, and automation.

"In the short term, the integration of energy monitoring and predictive maintenance will continue to deepen. Currently, many factories treat the two as independent systems. The new generation of enterprise asset management platforms will take energy consumption data as one of the core equipment status monitoring signals, just like vibration, temperature, and cycle time. Among the many failure modes of plastic equipment, changes in power consumption are one of the earliest and most reliable signals of equipment performance degradation."

Pattern recognition work that previously required experienced engineers to perform manually will be accelerated by artificial intelligence. The next generation of enterprise asset management systems will leverage larger equipment and energy datasets to optimize anomaly detection, helping maintenance teams distinguish and prioritize issues.

Berend Booms mentioned that digital twins and simulation tools will be more widely used in larger and more advanced factories. Companies can view virtual energy consumption models of their facilities in real-time, simulate the impacts of production scheduling adjustments and equipment upgrades before formal implementation, and conduct various scenario analyses in conjunction with real electricity prices.

Finally, reporting requirements from customers and regulators will further amplify the commercial value of energy data. Processing enterprises with a robust energy monitoring system will gain an advantage under increasingly stringent customer ESG requirements and regulatory rules.

"Data collected today to enhance operational efficiency will be used for compliance reporting in the future, helping enterprises create differentiated competitive advantages," said Berend Booms.