AI/ML
Modcon’s Industrial AI solutions complement our analytic hardware and leverage the data it generates together with other data sources operated by our customers. One aspect of our Industrial AI capabilities relates to maintaining the spectrometric models for our NIR analysers. A proprietary patent-pending Machine Learning application has been developed to automatically identify the most suitable samples for model building while excluding the outliers.
Rich process data, including the measurements provided by our NIR analysers and other online analytic solutions, allows the building of the Digital Twin of the process, precisely replicating the actual process dynamics. These high-fidelity process models allow answering the “what if” questions that lead to finding the optimal process setpoints for various process states. The Energy Conservation solution leverages this modelling ability through an online, DRL-based, optimising multivariate process controller.
AI Energy Conservation
MODCON AI Energy Conservation extends the AI-driven control techniques of the MODCON AI CDU Optimization Suite to various industries, offering significant improvements in energy efficiency. Traditionally, industries have relied on legacy technologies like Real-Time Optimization (RTO) and Advanced Process Control (APC) to optimize industrial processes. However, these technologies rely on first principles models, which can struggle to represent complex or variable processes, leading to inefficiencies, especially in energy-intensive operations.
The MODCON AI Energy Conservation system addresses this challenge using data-driven and hybrid models, combining machine learning with traditional methods. Data-driven models do not rely on explicit physical laws but learn from historical data to predict and control processes more accurately. This approach is particularly useful for industries where unpredictable factors like raw material variations, fluctuating environmental conditions, or unmeasured parameters influence the process dynamics.
Industries like petrochemical refining, pulp and paper, water treatment, and others rely on energy-intensive processes that require significant heating, cooling, and pumping. Even small inefficiencies in these processes can significantly increase energy consumption and costs. Legacy optimization systems often struggle to identify and correct these inefficiencies, especially when operating conditions change. Using hybrid models, MODCON AI Energy Conservation continuously adapts to process variations, identifying inefficiencies and recommending real-time adjustments to reduce energy use.
The system excels in detecting hidden inefficiencies that accumulate over time. These inefficiencies, such as suboptimal equipment settings or unaccounted process variations, can significantly impact energy consumption but often go unnoticed with traditional methods. The AI-based system learns from ongoing data, making precise adjustments to optimize energy usage.
MODCON AI Energy Conservation’s hybrid modeling approach offers scalability across industries. The system optimizes energy consumption in petrochemical plants by adjusting key parameters based on real-time data. In water treatment and pulp and paper production, the system improves energy efficiency by optimizing chemical reactions, filtration, and pumping systems without compromising quality.
Overall, MODCON AI Energy Conservation represents a significant advancement in energy optimization. By combining data-driven models with traditional optimization techniques, the system allows industries to reduce energy consumption, cut costs, and support sustainability efforts. As energy efficiency becomes increasingly crucial in industrial operations, this AI-driven solution provides a reliable way to unlock energy savings and improve operational performance.
CDU Optimisation Suite uses our MOD 4100 Crude Oil analyser to allow the AI-based CDU controller to adapt to changing feedstock. The controller relies on a high-precision rectification column model, complementing the first principles model with data-driven correction based on historical process data. Working in the paradigm of optimising control, the CDU controller, implemented using the Deep Reinforcement Learning technology, iteratively nudges the process from its present state to the one aligned with the optimisation criteria.
CDU Optimisation Suite
MODCON AI CDU Optimization Suite is a state-of-the-art system that enhances crude oil distillation processes by leveraging AI models to replicate complex relationships between technological parameters. The suite optimizes the distillation process, identifying the most appropriate setpoints to ensure efficient operation and minimize costs. Its strength lies in adapting to crude oil’s fluctuating properties, which significantly impact the distillation process.
Crude oil’s composition varies, and these variations affect the distillation dynamics, such as boiling points and component separability. Efficient process control requires real-time adjustments based on these fluctuations. The challenge becomes more pronounced during “crude switch” periods, when the feedstock composition changes, leading to variations in oil properties.
The MODCON 4100 Crude Oil NIR Analyzer is critical in addressing these fluctuations. It provides real-time data on crude oil’s composition, viscosity, and other vital properties, feeding this information directly into the AI-driven control model of the MODCON AI CDU Optimization Suite. This allows the suite to continuously adjust the distillation process to align with the crude oil’s current properties, even during transitions between different feedstocks.
Combining the AI suite and the MODCON 4100 Crude Oil NIR Analyzer ensures the distillation process remains optimized during feedstock changes. The AI models adapt to fluctuations by predicting and adjusting for changes in crude oil composition, reducing the risk of inefficiencies. This results in improved consistency of refined products, such as gasoline and diesel, while minimizing energy use and operational costs.
By integrating AI-driven control with real-time analysis of crude oil properties, the MODCON AI CDU Optimization Suite provides a comprehensive solution that enhances distillation process efficiency and sustainability in the oil and gas industry.
In addition to optimizing the distillation process, the MODCON AI CDU Optimization Suite offers significant benefits in terms of operational flexibility and scalability. The system’s ability to adjust to varying crude oil compositions in real time ensures that refineries can handle a wide range of feedstocks without compromising performance. This adaptability is particularly valuable in environments where crude oil sources are diverse, and the demand for refined products fluctuates. The suite’s integration with existing refinery infrastructure further enhances its value, providing a seamless connection between real-time crude analysis, process control, and operational decision-making. By continuously learning from the data supplied by the MODCON 4100 Crude Oil NIR Analyzer, the AI model becomes increasingly effective at predicting the optimal process parameters, leading to long-term improvements in the quality of refined products and overall plant efficiency. Ultimately, this system reduces operational costs and supports sustainability goals by optimizing energy consumption and reducing waste.
The in-depth understanding of the process obtained through its precise data-driven model is a solid foundation for detecting divergencies between the model prediction and actual measurements of various process parameters. The trends in these divergencies over time, coupled with process parameters anomalies detection, indicate the process health and serve as process health markers.
Process Health Analysis
Process Health Analysis is a vital aspect of modern industrial operations, allowing for the early detection of issues and preventing potential failures before they cause significant damage. This approach establishes what constitutes normal process behavior by learning the relationships between process parameters through data-driven or hybrid models. With this knowledge, the system can continuously monitor real-time performance and identify deviations from expected behavior, signaling potential faults or equipment deterioration.
Early detection of deviations is crucial in industries like chemical processing, manufacturing, and energy, where even small changes can lead to significant disruptions or safety hazards. By catching these issues early, operators can take corrective actions, such as adjusting process parameters or scheduling maintenance, to prevent costly breakdowns and reduce downtime. In addition, Process Health Analysis helps ensure consistent product quality by identifying trends that could affect the final output.
This approach also supports predictive maintenance, optimizing schedules based on real-time process data rather than relying on fixed intervals or historical data. Companies can reduce unexpected failures and unnecessary downtime by focusing maintenance efforts on equipment showing early signs of deterioration. Additionally, monitoring the entire system’s health allows for identifying inefficiencies, improving energy use, reducing waste, and enhancing overall performance.
In summary, Process Health Analysis is essential for maintaining efficient, safe, cost-effective operations. It enables early fault detection, reduces downtime, optimizes maintenance, and ensures consistent product quality, ultimately supporting operational efficiency and long-term strategic decision-making.
Process Health Analysis also plays a key role in enhancing sustainability by minimizing waste and energy consumption. Even slight inefficiencies can result in higher resource use in industries with energy-intensive processes, leading to increased costs and environmental impact. By continuously monitoring the health of the process and identifying potential issues early, the system can help optimize resource utilization, ensuring that energy is used more effectively and that production processes are as efficient as possible. Additionally, predicting equipment degradation allows for more precise scheduling of replacements or upgrades, preventing premature replacements and ensuring that resources are utilized to their full potential. This reduces operational costs and environmental footprint, aligning with broader sustainability goals. By integrating Process Health Analysis into operations, companies improve their bottom line and demonstrate a commitment to more responsible and sustainable manufacturing practices.
Modcon leverages its decades-long expertise in smart sensors to create a range of medical solutions based on the contactless evaluation of vital signs. Coupled with advanced algorithmic and Machine Learning models, we allow the end-user multiple self-service and triage capabilities and niche applications developed in cooperation with clinicians from the leading hospitals.
AI Medical Technology
Since the COVID-19 pandemic, Modcon has been developing contactless vital signs evaluation technology based on image photoplethysmography (PPG), which uses light absorption in the skin to assess key physiological signals like heart rate (HR), heart rate variability (HRV), blood pressure (BP), and oxygen saturation (SpO2). This technology eliminates physical contact, making it ideal for remote monitoring and telemedicine. It utilizes advanced algorithms and machine learning models to process physiological data, ensuring accuracy even in varying lighting conditions or motion artifacts. As a result, the system delivers real-time, reliable health monitoring.
Modcon’s technology supports several vital signs, providing a comprehensive health assessment. HR and HRV offer insights into cardiovascular health, BP helps detect hypertension, and SpO2 levels monitor respiratory function. The system is currently undergoing evaluation with an international customer, which will help refine the product for global use.
In addition to contactless monitoring, Modcon has developed another innovative application in collaboration with a children’s hospital, funded by a public grant, focused on suicide risk detection in adolescents. By analyzing physiological signals, the system helps identify early signs of suicidal behavior, providing healthcare professionals with an important tool for early intervention.
These advancements highlight Modcon’s commitment to improving healthcare through noninvasive, scalable, and AI-driven technologies. With applications in physical and mental health monitoring, Modcon is poised to significantly impact healthcare delivery, enabling earlier detection of health issues and improving patient outcomes globally.
Modcon’s innovative healthcare technologies are part of a broader movement toward more personalized and accessible care. Modcon’s contactless vital signs evaluation system offers a practical and scalable solution for healthcare providers as the demand for remote monitoring solutions grows, particularly in light of the pandemic. The ability to monitor patients remotely reduces the need for frequent in-person visits, making healthcare more accessible, especially for individuals in remote or underserved areas. This technology also has the potential to enhance preventative care by providing continuous, real-time data that can help identify health issues before they become critical. By leveraging AI and machine learning, Modcon enables a more proactive approach to healthcare, allowing for early interventions and personalized treatment plans to improve overall patient health and reduce healthcare costs. Modcon’s contributions are paving the way for more efficient, data-driven, and patient-centered care as the healthcare industry continues to evolve.