Ruchira Papers: Process Stability and Intelligent Control in Modern Paper Manufacturing

In an exclusive interview with Paper Mart, Ms. Ruchika Garg, Director, Ruchira Papers Limited, shares how the shift from traditional PID-based feedback control in PLC/DCS systems towards Advanced Process Control (APC), predictive analytics, and intelligent control is helping paper mills achieve greater process stability and quality consistency. The integration of APC, MPC, AI/ML, QCS, online measurement systems, smart instrumentation, machine vision, and condition monitoring is enabling mills to proactively identify process deviations and optimise operations. At Ruchira Papers, the installation of a Bellmer dilution control headbox, a Tri-Nip Press with shoe press, and the Honeywell Calcoil system has contributed to improved basis weight uniformity, dewatering, brightness, moisture consistency, and caliper profile control, demonstrating the measurable benefits of intelligent process control.

Paper Mart: Where does process variability remain most persistent in paper manufacturing today, and how does it affect quality and operating performance? Please tell us the process stages or parameters where tighter stability can deliver the greatest measurable gains.

Ruchika Garg: The two process parameters with the greatest impact on both product quality and overall mill performance are basis weight (GSM) stability and moisture stability. Basis weight (GSM) stability, particularly in the headbox/approach flow section, affects fibre consumption and product quality. Improving basis weight control can typically reduce fibre consumption by 0.3-0.8%, while also improving GSM uniformity, reducing broke, and ensuring consistent paper quality. Similarly, moisture stability in the press and dryer section plays an important role in influencing energy consumption, machine runnability, and final paper quality.

[bsa_pro_ad_space id=16]

Watch: Top Paper Companies 2023

PM: How has the approach to controlling process variability changed in recent years? In other words, how are mills moving beyond conventional automation and feedback control to achieve greater process stability? Please explain with examples.

RG: Traditionally, paper mills relied on PID-based feedback control in PLC/DCS systems, where corrective actions were taken only after a process deviation was detected. While effective for basic control, this approach often reacted too late to prevent quality variations. Today, mills are adopting Advanced Process Control (APC), predictive analytics, and Artificial Intelligence (AI)/ Machine Learning (ML)-based optimisation to minimise variability before it impacts production. These systems continuously analyse data from process sensors, quality scanners, and equipment condition monitoring systems to predict disturbances and optimise control actions in real time, enabling mills to achieve greater process stability and more consistent production performance.

PM: How are Advanced Process Control and Model Predictive Control being applied to reduce process variability? Where have they delivered measurable gains?

RG: Advanced Process Control (APC) and Model Predictive Control (MPC) are increasingly being used in paper mills to optimise multiple interacting process variables simultaneously. Unlike conventional PID control, MPC predicts future process behaviour and proactively adjusts control actions while considering process constraints. Key applications include basis weight control, moisture control, refining optimisation, recovery boiler and evaporator operations, and chemical dosing.

The application of advanced control strategies has delivered measurable gains, including 0.3–0.8% reduction in fibre usage, 2–8% reduction in steam consumption, and 1–3% reduction in refining energy. They have also resulted in reduced process variability and off-spec production, improved machine runnability with fewer sheet breaks, higher product quality, and improved Overall Equipment Effectiveness (OEE).

PM: What practical role are AI and machine learning playing in predicting and correcting process deviations before they affect production or quality?

RG: Artificial Intelligence (AI) and Machine Learning (ML) are enabling paper mills to move from reactive process control to predictive and proactive optimisation. By analysing large volumes of historical and real-time process data, AI and ML models can identify patterns, predict deviations, and recommend corrective actions before product quality or production is affected. Practical applications include predictive quality control, where AI predicts variations in basis weight, moisture, and caliper, allowing operators or APC systems to make adjustments before off-spec paper is produced.

Predictive maintenance uses ML to analyse vibration, temperature, and motor current data to detect early signs of bearing, roll, or pump failures, potentially reducing unplanned downtime by 20–40% in many applications. AI also supports process optimisation by continuously optimising refining energy, steam usage, and chemical dosing, which eventually led to improved efficiency while reducing operating costs. In addition, ML plays an important role in anomaly detection; it identifies abnormal process behaviour that may not trigger conventional alarms, allowing early intervention before a process upset occurs.

PM: How are online measurement, smart instrumentation, machine vision, and QCS improving real-time detection and control of process variation? Where do significant measurements or data gaps remain?

RG: Modern paper mills are using online measurement systems, smart instrumentation, machine vision, and Quality Control Systems (QCS) to continuously monitor critical process parameters, enabling the immediate detection of process deviations and automatic corrective action. Key technologies include Quality Control System (QCS), smart instrumentation, machine vision systems and online condition monitoring.

Despite these advances, several measurement and data gaps remain; online measurement of fibre quality, including fibre length, fibrillation, and fine content, is still limited. Similarly, real-time monitoring of wet-end chemistry and retention efficiency is not yet widely available, and pitch, stickies and deposits are difficult to detect before they impact the process. In addition, many mills still operate with isolated DCS, QCS, PLC, and condition monitoring systems, limiting the use of integrated analytics and plant-wide optimisation.

PM: Drives and motion control directly influence speed, tension, synchronisation, and machine stability. How are newer drive and control technologies helping mills reduce variability across the paper machine and associated processes?

RG: Modern paper mills adopt high-performance AC drives, digital servo systems, and integrated motion controllers to achieve precise speed, tension, and synchronisation across the entire paper machine. Unlike conventional drive systems, these technologies provide faster response, higher accuracy, and seamless coordination between multiple machine sections.

Key improvements include:

• Electronic line shafting replaces mechanical line shafts, ensuring precise synchronisation between the headbox, press, dryer, calendar, and reel sections.
• Advanced tension control maintains stable web tension throughout the machine, reducing wrinkles, web breaks, and reel defects.
• High-speed drive communication (e.g., Ethernet/IP, PROFINET, EtherCAT) enables real-time data exchange between drives, PLC/DCS, and QCS for coordinated control.
• Adaptive drive control automatically compensates for changes in roll diameter, machine load, and production speed, maintaining stable operation during grade changes.
• Integrated diagnostics and condition monitoring continuously monitor motor health, vibration, temperature, and torque, enabling predictive maintenance and reducing unexpected failures.

PM: How are automation, advanced control, and integrated process data helping mills achieve more consistent paper quality? Which quality parameters have benefited most?

RG: Modern paper mills combine automation such as PLC/DCS, Advanced Process Control (APC), Quality Control Systems (QCS), and integrated process data to continuously monitor, analyse, and optimise production. By integrating process measurements with quality data, control systems can automatically adjust operating parameters before quality deviations occur, resulting in more stable operation and reduced process variability.

The key improvements include real-time process optimisation using APC and QCS to automatically adjust headbox flow, stock consistency, steam pressure, and moisture control. Similarly, integrated process data from DCS, QCS, machine vision, and condition monitoring systems provides a complete view of machine performance, enabling faster decision-making and root cause analysis. Predictive analytics and AI further help to identify trends and recommend corrective actions before quality is affected at mills.

The quality parameters that have benefited most include basis weight (GSM), moisture, caliper (thickness), ash and coat weight, formation, and defect detection. Basis weight (GSM) control has improved MD and CD profile control with a 20–50% reduction in profile variation. More uniform moisture profiles help reduce curls, wrinkles, and dimensional instability, while better caliper consistency improves printability and converting performance. More accurate control of ash and coat weight contributes to improved product uniformity, while optimised stock preparation and headbox control support better fibre distribution and formation. In addition, machine vision systems identify holes, spots, streaks, and edge defects in real time, helping to reduce customer rejects.

PM: As control systems become more intelligent, how is the operator’s role in process control and decision-making changing?

RG: As paper mills adopt Advanced Process Control (APC), AI, and intelligent automation, the operator’s role is shifting from manual process control to process supervision and decision support. Instead of continuously adjusting process variables, operators now monitor system performance, validate automated recommendations, and manage abnormal situations.

The key changes include a shift from reactive to proactive operation, as operators receive predictive alerts before process deviations affect production or quality. A greater focus on optimisation, with routine control actions being handled automatically, allowing operators to focus on production efficiency, energy optimisation, and quality improvement. Data-driven decision-making is further supported by integrated dashboards that combine data from DCS, QCS, machine vision, and condition monitoring systems, enabling faster and more informed decisions.

The other important changes are exception-based management and improved collaboration, with operators intervening primarily during process upsets, equipment faults, or grade changes, while normal operations are maintained automatically. Also, with improved collaboration, operators work more closely with process engineers and maintenance teams by using real-time analytics and predictive maintenance information.

PM: What typically prevents a mill from achieving the full benefits of advanced automation and intelligent control? Please tell us more about issues such as legacy systems, data quality, system integration, instrumentation, workforce capabilities, etc.

RG: While advanced automation and intelligent control technologies offer significant benefits, many paper mills face practical challenges that limit their full potential. The most common barriers include:

• Legacy Control Systems: Older PLCs, DCSs, and drives often have limited communication capabilities, making it difficult to integrate modern APC, AI, and IIoT platforms.
• Poor Data Quality: Inaccurate or unreliable measurements due to sensor drift, calibration issues, or missing data reduce the effectiveness of advanced control algorithms.
• Limited System Integration: Process data is often distributed across DCS, PLC, QCS, machine vision, historians, and condition monitoring systems, preventing a unified view of plant performance.
• Instrumentation Gaps: Many critical process variables, particularly in the wet end and chemical dosing systems, are still measured manually or infrequently, limiting real-time optimisation.
• Workforce Skills: Successful implementation requires personnel with expertise in automation, data analytics, APC, and cybersecurity. A shortage of these skills can slow adoption and reduce long-term benefits.
• Change Management: Operators and maintenance teams may be hesitant to rely on automated decision-making without adequate training and confidence in the system.
• Cybersecurity and IT Infrastructure: Secure network architecture, reliable data storage, and robust cybersecurity are essential for connected automation systems but are often overlooked during modernisation.

Also Read: Paper Mart Emagazine Aug-Sep, 2026

PM: Can you share a recent implementation that measurably reduced variability or improved quality consistency? What results were achieved, and where should mills prioritise investment next?

RG: A recent improvement at our mill was the installation of a Bellmer dilution control headbox along with a Tri-Nip Press incorporating a shoe press. The dilution control headbox provides precise cross-direction (CD) basis weight control by adjusting stock consistency across the machine width, resulting in improved fibre distribution, better sheet formation, and reduced profile variation.

In addition, the shoe press significantly improved dewatering efficiency in the press section. This increased sheet dryness and enhanced paper brightness from approximately 39% to 43–44% before entering the dryer section. The improved dewatering also contributed to more stable machine operation, better moisture uniformity, and reduced steam demand in the dryer section.

Another key initiative was the installation of the Honeywell Calcoil system for caliper profile control. The system continuously monitors and adjusts the cross-direction caliper profile, resulting in a 50% reduction in 2-sigma variation, significantly improving sheet thickness, uniformity, product consistency, and overall quality.

The key results achieved include improved fibre formation and CD basis weight uniformity, increased press section brightness from 38% to 44–45%, and a 50% reduction in caliper profile 2-sigma variation following the installation of the Honeywell Calcoil system. Also, better moisture consistency entering the dryer section and improved sheet quality and machine runnability were achieved.

Future investment priorities should focus on Advanced Process Control (APC), AI-based process optimisation, online quality measurement (QCS), machine vision systems, and predictive maintenance, enabling mills to further reduce process variability, improve quality consistency, and enhance overall production efficiency.