Published by the ISA

ISA Transactions is a journal of advances and state-of-the-art in the science and engineering of measurement and automation, of value to leading-edge industrial practitioners and applied researchers.

The topics of measurement include: sensors, perception systems, analyzers, signal processing, filtering, data compression, data rectification, fault detection, inferential measurement, soft sensors, hardware interfacing, etc.; and any of the techniques that support them such as artificial intelligence, fuzzy logic, communication systems, and process analysis. The topics of automation include: statistical and deterministic strategies for discrete event and continuous process control, modelling and simulation, event triggers, scheduling and sequencing, system reliability, quality, maintenance, management, loss prevention, etc.; and any equipment, techniques and best practices that support them such as optimization, learning systems, strategy development, security, and human interfacing and training.

The intended audience is research and development personnel from academe and industry in the fields of control systems, process instrumentation, systems, and automation.

The journal seeks to bridge the theory and practice gap. This balance of interests requires simplicity of technique, credible demonstration, fundamental grounding, and connectivity to the state of the art in both theory and practice.

If you would like more information please visit the ISA Transactions society homepage

Special Issue on Soft Sensors for Advanced Process Modelling, Monitoring, Control, and Optimisation
截稿日期: 2025-06-01

With the increase in the complexity and regulatory constraints for industrial processes, it has become increasingly important to understand them. Unfortunately, in many cases, it may not be possible to obtain accurate, online measurements of the variables at the required sampling frequency required for control, monitoring, and optimisation. Thus, there is a need to develop and implement advanced soft sensors that provide information about the current state of the system using the available information. This special issue will provide the opportunity for both academic and industrial researchers to present their ideas and thoughts with the goal of finding common problems and solutions.

As industry faces the demands to be both economically profitable and environmentally safe, there has been a renewed interest in developing and implementing advanced methods for control, monitoring, and optimisation of complex industrial processes. Even though advanced, online measurement sensors have been developed, it is often the case that it remains difficult to accurately measure critical variables, such as concentration and density, especially for complex, nonideal fluids, where laboratory analysis is still used to obtain reliable values. However, laboratory analysis cannot provide sufficiently fast or frequent measurements in order to effectively monitor, control, or optimise the process. Therefore, other methods, namely soft sensors, which are mathematical descriptions that relate the desired process values with the readily available measurements, need to be developed. Soft sensors have been have used for some time now. However, each implementation of a soft sensor brings its own challenges that require new approaches and methods.

First, despite the advantages of machine learning and artificial intelligence, there is a pressing need to understand the limitations of these methods for soft sensors. One pressing issue is the lack of explainability of the models developed using machine learning or artificial intelligence. This means that it is not possible to know why the model gives the answer that it gives, which often arises from the fact that, if the original data were insufficient, the resulting model could provide inaccurate or wrong answers. Explainable artificial intelligence, where methods are implemented to understand what is being done, provide one solution. Furthermore, soft sensors are limited to the region described by the original data set. Extending soft sensors to new operating conditions requires the use of such methods as transfer learning, which needs to be explored.

Second, aging and process or equipment changes require that soft sensors once developed be updated or changed. Thus, online, real-time updating of soft sensors is required to take into consideration these changing conditions. For example, in model predictive control, using an outdated soft sensor will lead to a significant plant-model mismatch that will cause a corresponding degradation in the control performance. Unless the models are updated, the whole control strategy may well be turned off as being useless, despite the fact that a simple correction of the models would fix the problem. Thus, there is a need to develop methods that can detect plant-model mismatch and allow for the re-identification of a new model.

Third, the implication of using soft sensors for process monitoring, control, and optimisation has not often been considered. This includes such topics as the optimal configuration of the softsensor system or when will a soft sensor lead to unexpected or even undesired behaviour. Even if the soft sensor itself is properly designed, the overall system may still provide poor results since the overall configuration has not been properly designed. As well, a general framework on how to incorporate slowly sampled, but accurate values into the overall soft-sensor system needs to be developed. Thus, a proper framework for the use of soft sensors and their application needs to be developed.

Finally, industrial and academic researchers need to be brought together so that they can enrich each other’s approaches to the problem. The industrial problems facing industry need to be formulated and explained so that appropriate theoretical solutions can be found. Similarly, the theoretical results need to be properly formulated and tested so that the correct industrial application can be found.

Guest editors:

Prof. Yuri A.W. Shardt, Technical University of Ilmenau, 98684 Ilmenau, Germany. Email: yuri.shardt@tu-ilmenau.de
Prof. Xu Yang, University of Science & Technology Beijing, China. Email: yangxu@ustb.edu.cn
Prof. Fan Yang, Tsinghua University, Beijing 100084, China. Email: yangfan@tsinghua.edu.cn
Prof. Sanghong Kim, Tokyo University of Agriculture and Technology, Japan. Email: sanghong@go.tuat.ac.jp
Prof. Joseph Kwon, Texas A&M University, College Station, TX 77843-3251, USA. Email: kwonx075@tamu.edu

Special issue information:

This special issue will collect the research and applications currently being done in the area of soft-sensor development in both academia and industry. Topics of interest to this special issue include, but are not limited to:

⋅ Artificial intelligence in modelling and the development of soft sensors;
⋅ Soft sensors for process monitoring;
⋅ Soft sensors for control, including model predictive control and adaptive control;
⋅ Soft sensors for process optimisation;
⋅ Updating and maintaining soft sensors with changing conditions;
⋅ Detecting plant-model mismatch; 
⋅ Dual control and how it can be used to develop a unified framework for sensor development and control;
⋅ Applications of soft sensors in industry;
⋅ Real-time model-free learning methods;
⋅ Practical implementations of the above topics; and
⋅ Survey papers discussing the impact and implications of the methods in industry.

Manuscript submission information:

Important Dates

    Submission deadline: June 1st, 2025​
    Notification of first review: September 1st, 2025
    Submission of revised manuscript: November 1st, 2025
    Notification of final decision: January 1st, 2026

Manuscripts should be submitted using the ISA Transactions online submission system (https://www.editorialmanager.com/isatrans/default.aspx.) by selecting the Article Type of “SI: Soft Sensors”. All submitted manuscripts will be screened by the editorial office and peer reviewed according to the usual standards of this journal, and will be evaluated on the basis of originality, quality, and relevance to this Special Issue. 

Please refer to the Guide for Authors to prepare your manuscript: https://www.sciencedirect.com/journal/isa-transactions/publish/guide-for-authors.

For any further information, the authors may contact the Guest Editors.

Keywords:

Soft sensors; modelling; control; optimisation; Artificial Intelligence

Special Issue on Advances in health-aware control and prognostics
截稿日期: 2025-09-30

Health-aware control (HAC) is an advanced control strategy that integrates the health status of system components into the control system. It aims to optimize system performance while considering the degradation and remaining useful life (RUL) of critical components. By using the information coming from a prognostics and health management (PHM) module, HAC adjusts control actions to extend the lifespan of components and prevent failures. HAC is particularly valuable in industries where system reliability and longevity are crucial, such as aerospace, automotive, and manufacturing.

PHM can be performed using model-based or data-driven approaches. Model-based approaches rely on mathematical models that describe the physical behavior of a system. These models use known physics and engineering principles to predict future states and potential failures. They are highly accurate but require detailed knowledge of the system and can be complex to develop and maintain. Data-driven approaches, on the other hand, utilize historical and real-time data to predict system health and failures. Techniques such as machine learning and statistical analysis are employed to identify patterns and trends in the data. These methods are more flexible and can adapt to different systems without needing detailed physical models. However, they require large amounts of data and may be less interpretable compared to model-based approaches. Both approaches are essential in PHM, often complementing each other to provide robust and reliable predictions.

This special issue aims at bringing together cutting-edge research and innovative methodologies aimed at enhancing system reliability and performance, featuring papers about HAC, papers about PHM, and possibly papers about the integration of HAC with PHM, so as to obtain a control system that optimizes maintenance, predicts failures, and extends the lifespan of critical components. The collection of works in the special issue will be a valuable resource for researchers, engineers, and practitioners dedicated to improving system health and operational efficiency.

Guest editors:

Prof. Vicenç Puig (Executive Guest Editor)
Institut de Robòtica i Informàtica Industrial (IRI)
Universitat Politècnica de Catalunya (UPC)
Carrer Pau Gargallo 14, 08028 Barcelona, SPAIN
Email: vicenc.puig@upc.edu 

Dr. Damiano Rotondo (Corresponding Editor)
Department of Electrical Engineering and Computer Science (IDE)
Universitetet i Stavanger (UiS)
Kristine Bonnevies Vei 22, 4021 Stavanger, NORWAY
Email: damiano.rotondo@uis.no 

Dr. Francisco-Ronay López-Estrada
TURIX-Dynamics Diagnosis and Control Group
Tecnológico Nacional de México, I. T. Tuxtla Gutierrez
Carr. Panam Km 1080, 29050 Tuxtla Gutierrez, Chiapas, MEXICO
Email: frlopez@tuxtla.tecnm.mx 

Special issue information:

Potential topics of interest include, but are not limited, to the following:

• Control reconfiguration
• Health-monitoring techniques
• Predictive maintenance and repair strategies
• Statistical methods for reliability and safety
• Condition monitoring
• Prognosis and health management
• Health-aware control
• Applications to distributed systems, industrial processes, energy systems, unmanned vehicles, marine systems, chemical processes, robotics, mechatronics, etc.

Manuscript submission information:

Important Dates

• First Submission Deadline: 30 September 2025
• Notification of First Round Decision: 30 November 2025
• Revised Paper Submission Deadline: 28 February 2026
• Notification of Final Decision: 30 April 2026
• Final Paper Submission Deadline: 31 May 2026
• Tentative Publication Date: Late-2026

Manuscripts should be submitted using the ISA Transactions online submission system (https://www.editorialmanager.com/isatrans/default.aspx) by selecting the Article Type of “SI: health-aware control and prognostics”. All submitted manuscripts will be screened by the editorial office and peer reviewed according to the usual standards of this journal, and will be evaluated on the basis of originality, quality, and relevance to this Special Issue. 

Please refer to the Guide for Authors to prepare your manuscript: https://www.sciencedirect.com/journal/isa-transactions/publish/guide-for-authors.

For any further information, the authors may contact the Guest Editors.

Keywords:

(health-aware control) OR (remaining useful life) OR (prognostics) OR (health management)