Machine learning in process systems engineering: Challenges and opportunities

This paper investigates the oversimplification of the inherently complex systems engineering process in space life support. The standard systems engineering process steps are described. The International Space Station (ISS) life support system is explained with its goals and performance criteria. Although it is not usually emphasized, the essential function of developing a hierarchy of systems and subsystems is to simplify the design process. The System Complexity Metric (SCM) shows how this divide‐and‐conquer approach also reduces the system complexity. The complete systems engineering process has many detailed steps. It is often simplified because of the effort required and the human limitations on working memory and decision span. Systems analysis demands slow, logical, and focused thinking but is often bypassed in favor of quick, intuitive, subconscious “gut feel.” A study of 100 system designs found examples of 12 specific mental mistakes, such as ignoring stakeholder needs, and these mistakes are essentially oversimplifications of the systems engineering process. An analysis of space life support goals, options, criteria, and processes found 11 examples of oversimplifications in systems engineering, such as neglecting safety and cost. All these 11 oversimplifications could be traced to one or more of the 12 previously identified mental mistakes or other well‐known ones, such as ignoring sunk costs. Oversimplification of the systems engineering process is rarely noticed but is a common and harmful problem. A study of failures in 50 different space systems found that problems in systems engineering caused failures and often led to errors in design, development, and test that further contributed to failure. It seems that more diligent systems engineering could prevent many project problems and failures, but projects seem to be more guided by “gut feel” based on tradition, authority, and consensus than on the logical, rational systems engineering approach.

From Amundson, Aris, and Sargent to the future of process systems engineering

Thirty Years of International Symposia on Process Systems Engineering

Process systems engineering developments in Europe from an industrial and academic perspective

This study provides a comprehensive benchmarking of traditionalsystem identification and modern machine learning (ML) models forthe data-driven modeling of dynamical systems, with a focus on processsystems engineering (PSE) applications. To achieve this, we deployAutoSID, an automated end-to-end framework inspired by Machine LearningOperations (MLOps) principles. While AutoSID facilitates model selection,training, validation, and evaluation, its purpose here is to serveas a platform to investigate how well MLOps-inspired tools can beadapted for system identification tasks in PSE. Our investigationincludes a comparison of 12 diverse model architectures from the systemidentification, machine learning, and deep learning literature, evaluatedacross 11 PSE case studies under varying data regimes. We employ fourmodel search or hyperparameter optimization algorithms and three modelselection criteria to ensure a thorough assessment. Our findings highlightthe importance of model selection as the crucial step in system identification.Specifically, our results demonstrate the effectiveness of Bayesianoptimization with tree-structured parzen estimators (TPE) for balancedmodel selection, while k-fold cross-validation proves to be a robustmetric for performance evaluation during the selection process. Inlarge-scale data scenarios, where performance differences between k-fold cross-validation and information criteria are small,information criteria emerge as a computationally efficient alternative.Once the “best” model structure is decided, in termsof model performance, we find that ML models with balanced complexity,such as tree ensemble models, consistently achieve superior predictiveaccuracy and computational efficiency, outperforming both simplisticand overly complex models. These findings provide actionable insightsinto model selection and performance evaluation for PSE practitionersand demonstrate the potential of incorporating MLOps-inspired workflowsinto the system identification process.

Process systems engineering: From Solvay to modern bio- and nanotechnology.: A history of development, successes and prospects for the future

Completing its final development and early deployment on the Navy's multi-role aircraft, the F/A-18 E/F Super Hornet, the SHAred Reconnaissance Pod (SHARP) provides the war fighter with the latest digital tactical reconnaissance (TAC Recce) Electro-Optical/Infrared (EO/IR) sensor system. The SHARP program is an evolutionary acquisition that used a spiral development process across a prototype development phase tightly coupled into overlapping Engineering and Manufacturing Development (EMD) and Low Rate Initial Production (LRIP) phases. Under a tight budget environment with a highly compressed schedule, SHARP challenged traditional acquisition strategies and systems engineering (SE) processes. Adopting tailored state-of-the-art systems engineering process models allowd the SHARP program to overcome the technical knowledge transition challenges imposed by a compressed program schedule. The program's original goal was the deployment of digital TAC Recce mission capabilities to the fleet customer by summer of 2003. Hardware and software integration technical challenges resulted from requirements definition and analysis activities performed across a government-industry led Integrated Product Team (IPT) involving Navy engineering and test sites, Boeing, and RTSC-EPS (with its subcontracted hardware and government furnished equipment vendors). Requirements development from a bottoms-up approach was adopted using an electronic requirements capture environment to clarify and establish the SHARP EMD product baseline specifications as relevant technical data became available. Applying Earned-Value Management (EVM) against an Integrated Master Schedule (IMS) resulted in efficiently managing SE task assignments and product deliveries in a dynamically evolving customer requirements environment. Application of Six Sigma improvement methodologies resulted in the uncovering of root causes of errors in wiring interconnectivity drawings, pod manufacturing processes, and avionics requirements specifications. Utilizing the draft NAVAIR SE guideline handbook and the ANSI/EIA-632 standard: Processes for Engineering a System, a systems engineering tailored process approach was adopted for the accelerated SHARP EMD prgram. Tailoring SE processes in this accelerated product delivery environment provided unique opportunities to be technically creative in the establishment of a product performance baseline. This paper provides an historical overview of the systems engineering activities spanning the prototype phase through the EMD SHARP program phase, the performance requirement capture activities and refinement process challenges, and what SE process improvements can be applied to future SHARP-like programs adopting a compressed, evolutionary spiral development acquisition paradigm.

This is an era which the ELT telescopes define 'the new science' for astronomy. Thus, to make optimal contribution (i.e. valuable scientific output in an efficient, sustainable manner), a mid class telescope such as DAG 4m, must have a carefully designed Systems Architecture, which, in our opinion, could only be possible by means of a proper Systems Engineering (SE) process. From a Platonic perspective, the SE work must be started well before (at least conceptually), even the 'idea' of erecting an observatory. As can be seen from the experiences, this, however, never happens, and also it did not happen in our case. Regarding the facts given above, a SE process for DAG observatory has been initiated soon. As a bunch of constraints had already been formed, the work primarily focuses on the scientific instrumentation. This paper demonstrates various phases of the SE process carried until now. We will also discuss the methodologies/techniques that are planned to be used in the future.

Purpose: The most active and rapid development in today's world is happening in Smart cities. Smart Cities are changing very fast in every aspect, be it development, operations, and or maintenance points of view. Today's Smart Cities are aiming to be at an advanced stage of urbanization and fully exploiting digital infrastructure for rapid urban development. In order to make the cities better places to live and to offer more comfortable and enjoyable living for their residents, Smart Cities are using and employing various tools and technologies to make themselves smarter and more connected with their stakeholders using technology means. Industry 4.0, Digital Transformation, and various latest technologies such as 5G, Data Analytics, IoT, AI, and Machine Learning, Digital Twins, etc. are transforming and shaping up Smart Cities in never before style. In this paper, various such key technologies that are positively affecting Smart Cities are discussed at length. It is also highlighted in detail how these technologies are impacting Smart Cities development and operations. Finally, future research directions are also discussed in brief. Design/Methodology/Approach: Extensive exploration of available literature with research papers, conference papers, white papers, online blogs, dedicated websites, etc. on the research area and interactions with field researchers, subject matter experts, industry professionals is carried out to collect, analyse and process the collected data to find out the facts. The resulted facts and findings about the latest technologies used in Smart Cities is presented in this research paper. Findings/Result: After analysis of available literature and based on interactions with relevant stakeholders and based on own data analysis, it is identified that Smart City services are making use of various latest tools and technologies to solve their real-life challenges. Among vast list of technologies specifically IoT, Blockchain, Digital Twins, 5G, Contactless Technology, AI and ML are found the most significant and widely used technologies in Smart Cities development, operations, and maintenance activities. Originality/Value: It is found that not many research papers are available on analysis of future technologies used in Smart Cities. The data presented in this paper is genuine and original and completely based on systematic literature review, interactions with SME, Researchers and Industry experts and based on own data analysis which produced new findings. Paper Type: Technology oriented Research

This paper describes and expands upon the proposed System of Systems Engineering (SoSE) Process Framework for the Air Force Materiel Command first outlined in IEEE SoSE 2011. Through repeated uses, it became quickly understood that systems-of-systems processes were foundationally similar to but different from basic systems engineering processes. The SoSE Process Framework, supporting processes, and products provide a context to integrate across modern complex systems-of-systems. In defining the SoSE Process Framework we tailor existing systems engineering processes and add a minimal amount of SoS-level engineering to it. The four core SoSE processes, Architecture and Analysis, Test and Evaluation, Management and Governance together can help to successfully deliver integrated capabilities at the SoS and Enterprise level within the U.S. Air Force. The key concept introduced is the alignment of analysis and engineering efforts across the Enterprise System Engineering and Architecting realm, and the synchronization of decision making within the SoSE components. The paper concludes by discussing implications of the SoSE Process Framework, as well as recommendations for actions, products, key stakeholder decisions and future challenges.

Simultaneous and collaborative development of satellites and Information Systems to support their lifecycle processes

Data is the new oil. From the beginning of the 21st century, data is similar to what oil was in the 18th century, an immensely untapped valuable asset. This paper reviews recent advances in the field of optimization under uncertainty via a modern data lens and highlights key research challenges and the promise of data-driven optimization that organically integrates machine learning and mathematical programming for decision-making under uncertainty. A brief review of classical mathematical programming techniques for hedging against uncertainty is first presented, along with their wide spectrum of applications in Process Systems Engineering. we provide an introduction to the topic of uncertainty in machine learning as well as an overview of attempts so far at handling uncertainty in general and formalizing this distinction in particular. In line with the statistical tradition, uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions. Yet, due to the steadily increasing relevance of machine learning for practical applications and related issues such as safety requirements, new problems, and challenges have recently been identified by machine learning scholars, and these problems may call for new methodological developments.

The systems engineering process, applied across a typical system life‐cycle model, features design, or synthesis, as a core element. Creativity and innovation are required, to varying degrees, in all successful synthesis activities in systems engineering. The process of creativity and innovation in systems engineering is, however, poorly understood and is not adequately fostered. Educational institutions also place little emphasis on creativity and innovation in undergraduate teaching. This deficiency results in an engineering culture that is frequently resistant to the factors which promote creativity and innovation. This paper presents a phase‐model of creativity which maps onto the process of synthesis in the systems engineering life‐cycle. The paper serves as a framework for fostering creativity and innovation in systems engineers, at all levels, as well as for embedding a creativity culture in the systems engineering process.

All applications in current trends need to use Machine Learning and Big Data in this huge data world.Machine learning is a type of artificial intelligence that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so.Machine learning use historical data as input to predict new output values.Small Scale and even large developers cannot maintain Machine Learning Algorithms and other big data processing techniques all by themselves.To harvest, process and analyze the data we need a data processing engine.Our project is to provide them with a machine learning engine which runs on.a specified port on their servers which collects the data sets in real time.This which can be queried using a simple Query Language and analyze the database on the query.The purpose of our project is to create a Data Processing Engine for Big Data Analytics. Machine learning and Big Data plays a major role in the current huge data world. Our project is to maintain a dedicated machine learning and data processing engine, so that even small developers without the knowledge of machine learning and big data analysis can produce expected results based on Machine Learning to make their application smooth. All applications in current trends need to use Machine Learning and Big Data in this huge data world. Machine learning is a subset of artificial intelligence that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning uses historical data as input to predict new output values. Small Scale and even large developers cannot maintain Machine Learning Algorithms and other big data processing techniques all by themselves. To harvest, process and analyze the data we need a data processing engine. This project is to provide them a data processing engine which runs on a specified port on their servers which collects the data sets in real time. This can be queried using a simple Query Language and analyze the data and produce respected results using ML based on the query

The best practice of watershed management is through the understanding of the hydrological processes. As a matter of fact, hydrological processes are highly associated with stochastic, non-linear, and non-stationary phenomena. Hydrological processes simulation and modeling are challenging issues in the domains of hydrology, climate and environment. Hence, the development of machine learning (ML) models for solving those complex hydrological problems took essential place over the past couple decades. It can be observed, hydrological data availability has increased remarkably, and thus computational resources has led to a resurgence in ML models’ development. It has been witnessed huge efforts on the hydrological processes modeling using the facility of ML models and several review researches have been conducted. Literature studies approved the capacity of ML models in the field of hydrology over the classical “traditional models” based on their forecastability, flexibility, precision, generalization, and modeling execution convergence speed. However, although several potential merits were observed in ML model’s development, several limitations are allied such as the interpretability of those black-box models, the practicality of the ML models in watershed management, and difficulty to explain the physical hydrological processes. In this survey, an exhibition for all the published review articles on the development of ML models for hydrological processes and recognize all the research gaps and potential research direction. The ultimate aim of the current survey is to establish a new milestone for the interested hydrology, environment and climate researchers on the applications of ML models.