Model Of Production Process Research Articles

Reinforcement learning and digital twin-driven optimization of production scheduling with the digital model playground

Abstract The significance of digital technologies in the context of digitizing production processes, such as Artificial Intelligence (AI) and Digital Twins, is on the rise. A promising avenue of research is the optimization of digital twins through Reinforcement Learning (RL). This necessitates a simulation environment that can be integrated with RL. One is introduced in this paper as the Digital Model Playground (DMPG). The paper outlines the implementation of the DMPG, followed by demonstrating its application in optimizing production scheduling through RL within a sample process. Although there is potential for further development, the DMPG already enables the modeling and optimization of production processes using RL and is comparable to commercial discrete event simulation software regarding the simulation-speed. Furthermore, it is highly flexible and adaptable, as shown by two projects, which distribute the DMPG to a high-performance cluster or generate 2D/3D-Visualization of the simulation model with Unreal. This establishes the DMPG as a valuable tool for advancing the digital transformation of manufacturing systems, affirming its potential impact on the future of production optimization. Currently, planned extensions include the integration of more optimization algorithms and Process Mining techniques, to further enhance the usability of the framework.

Deep Reinforcement Learning-Based Process Control in Biodiesel Production

The control of complex industrial processes has been a forefront research topic. Biodiesel production, as a typical complex industrial reaction process, exhibits multivariable coupling, nonlinearity, and high latency, making it challenging for traditional control methods to achieve real-time control under varying operating conditions. To address this issue, this paper proposes a control method based on the twin delayed deep deterministic policy gradient (TD3) algorithm, which dynamically adjusts process parameters to achieve the adaptive optimization control of complex processes. A simplified biodiesel production process model was established to simulate the actual production process. Subsequently, a controller based on the TD3 algorithm was designed and implemented for this model. To evaluate the performance of the proposed controller, comparative experiments were conducted with traditional controllers and deep deterministic policy gradient (DDPG) controllers. The effects of different control strategies were analyzed through simulation experiments. The results demonstrate that the proposed controller achieves the objectives while exhibiting a lower overshoot and shorter settling time and fully validates the effectiveness of the proposed control strategy in terms of both the dynamic and steady-state performance in the production process.

Joint optimization of condition-based production and maintenance with mutual production-deterioration dependencies

Production control and maintenance scheduling are the two major cost-effective methodologies in the manufacturing systems. The existing literature considers these processes in isolation or with unidirectional dependencies. To fill this gap, we propose an integrated control model of maintenance and production process considering the mutual influence between production and deterioration in a single-machine system. By leveraging condition monitoring data, we enhance decision-making effectiveness and develop a comprehensive framework based on an infinite-horizon Markov decision process. We establish and prove the monotonic structural properties of total profit and maintenance actions relative to machine state, and develop an improved value iteration algorithm to reduce the computational space. Numerical experiments demonstrate the performance of our model in maximizing profits compared to traditional condition-based maintenance and condition-based production approaches. Sensitivity analysis further highlights key parameters influencing optimal policies, providing valuable insights for practical applications.

Cooperativism as pedagogy: Conversation with Gustavo Machado a lecturer and researcher from Facultad de Ciencias Sociales de la Universidad de la República

This conversation with Gustavo Machado discusses the role of cooperativism as a pedagogical process in Uruguay. Machado emphasizes how cooperatives serve as models for housing production and transformative social learning processes, embedding collective action and mutual aid into daily life. He distinguishes between housing, habitat, and inhabitation, advocating for a broader understanding of living that transcends physical structures and integrates social, cultural, and communal dimensions. Our conversation delves into the political significance of cooperatives in the face of neoliberalism, positioning them as alternatives to market-based housing models. Machado discusses the challenges cooperatives face, such as state regulation and the need for flexibility in adapting to changing life circumstances. He also reflects on his personal experiences growing up in a cooperative during Uruguay's dictatorship, which shaped his political and professional views. The article highlights the intersection of cooperativism with broader social movements, such as gender equality and mental health, and the importance of international dialogue in expanding cooperative housing models across Latin America.

Some Bivariate Replacement Policies Under Partial Product Process in an Alternative Repair Model

A common assumption in replacement problems is that the repair of a failed system may yield a functioning system, which may be either as good as new (complete repair) or as old as just prior to failure (partial repair). In this paper, we study the partial product process and replacement model for a deteriorating system under various conditions and a repairable system of an alternative repair model, called the Negligible Or Non-Negligible (NONN) repair times introduced by Thangaraj and Rizwan [2001] to develop a new repair model, some replacement policies (T;N) and (T+;N) with NONN repair times where T is the working age of the system and N is the number of failures of the system and T+ is the system replaced at the first failure point after the cumulative operating time exceeds T are studied. Furthermore, explicit expressions for the long-run average cost of the policies are derived. Optimal replacement policies for the deteriorating systems using partial product process is developed.

A Universal Framework for Skill-Based Cyber-Physical Production Systems

In the vision of smart manufacturing and Industry 4.0, it is vital to automate production processes. There is a significant gap in current practices, where the derivation of production processes from product data still heavily relies on human expertise, leading to inefficiencies and a shortage of skilled labor. This paper proposes a universal framework for skill-based cyber–physical production systems (CPPS) that formalizes production knowledge into machine-processable formats. Key contributions include a novel conceptual model for skill-based production processes and an automated method to derive production plans from high-level CPPS skills for production planning and execution. This framework aims to enhance smart manufacturing by enabling more efficient, transparent, and automated production planning, thereby addressing the critical gap in current manufacturing practices. The framework’s benefits include making production processes explainable, optimizing multi-criteria systems, and eliminating human biases in process selection. A case study illustrates the framework’s application, demonstrating its current capabilities and potential for modern manufacturing.

Application of artificial intelligence and red-tailed hawk optimization for boosting biohydrogen production from microalgae

Enhancing biohydrogen production from microalgae is crucial in addressing environmental and energy challenges. It provides a sustainable, clean energy source while reducing greenhouse gas emissions. Moreover, it advances microalgae-based biotechnology, enabling innovative biofuel production and ecological revitalization. The main target of this study is to develop a robust ANFIS model to simulate the biohydrogen production process from microalgae within photobioreactors. The study focuses on enhancing hydrogen yield by optimizing three critical process parameters: sulfur concentration (%), run time (hours), and wet biomass concentration (g/L). Initially, an adaptive neuro-fuzzy inference system (ANFIS) model for biohydrogen production process is constructed based on empirical data. Subsequently, the red-tailed hawk algorithm (RTH) is used to determine the optimal values for the process parameters, corresponding to maximum hydrogen yield. The performance of ANFIS model in predicting hydrogen yield is assessed using root mean square error (RMSE) and coefficient-of-determination (R2) values. The obtained RMSE values for training and testing data are 2.8477 × 10−05 and 1.2807, respectively, while the corresponding R2 values are 1.0 and 0.9911 for training and testing. The introduction of fuzzy logic into the model significantly improves its predictive accuracy, as evidenced by the drop in RMSE from 10.79 with ANOVA to 0.7159 with ANFIS, representing a substantial 93.4 % decrease. The remarkable precision of the ANFIS model, indicated by its low RMSE and high R2 values, underscores the success of the modeling stage. The combination between ANFIS with the RTH technique yields impressive results, leading to a hydrogen yield enhancement of 6.87 % and 26.65 % when compared to both measured data and ANOVA.

Smart Industrial Internet of Things Framework for Composites Manufacturing.

Composite materials are increasingly important in making high-performance products. However, contemporary composites manufacturing processes still encounter significant challenges that range from inherent material stochasticity to manufacturing process variabilities. This paper proposes a novel smart Industrial Internet of Things framework, which is also referred to as an Artificial Intelligence of Things (AIoT) framework for composites manufacturing. This framework improves production performance through real-time process monitoring and AI-based forecasting. It comprises three main components: (i) an array of temperature, heat flux, dielectric, and flow sensors for data acquisition from production machines and products being made, (ii) an IoT-based platform for instantaneous sensor data integration and visualisation, and (iii) an AI-based model for production process forecasting. Via these components, the framework performs real-time production process monitoring, visualisation, and prediction of future process states. This paper also presents a proof-of-concept implementation of the framework and a real-world composites manufacturing case study that showcases its benefits.

An experimentally validated model for a multivariate drying industrial process

Modeling of industrial production processes is becoming increasingly challenging due to their large number of variables. These variables often are highly correlated and introduce nonlinear and complex features. In this paper, we are interested to model an industrial dicalcium phosphate (DCP) drying process. Attempting to solve this issue is motivated by the need to improve several production conditions, such as minimizing the consumption of natural gas and reducing the pollution rate. In fact, applying an advanced control approach requires a dynamic model for the monitored plant. This work proposes a multivariable mathematical model for the DCP dryer within the Tunisian Chemical Group factory. A steady-state model has been reproduced using Aspen Plus software tool to implement the different functionalities of the system as well as involved reactions. Indeed, since the main operation in the drying process is the combustion reaction of the liquified petroleum gas (LPG) in the furnace that produce the necessary heat to reach a target value of temperature at the dryer outlet, we focus on determining a dynamic model for the furnace. To do so, we have proposed two approaches. The first is based on the Aspen dynamic tool. The second is based on the left matrix fraction description (LMFD) identification approach. The obtained results have been successfully validated using real measurements.

STATISTICAL EVALUATION OF PERFORMANCE INDICATORS OF PHOTOVOLTAIC PLANTS AS A SOURCE OF ENERGY FOR WATER DESALINATION IN THE AZOV-BLACK SEA REGION OF UKRAINE

The application of statistical methods for the analysis of random processes to obtain quantitative estimates for the performance indicators of photovoltaic plants as a stochastic energy source is considered. The power generation process is represented by a set of daily random functions with their respective trends and stochastic components. One hour was taken as the minimum stationari-ty interval of trend’s statistical characteristics. A time period of 16 years was studied to obtain statistically stable estimates. The meteorological database SARAH2 was used as a source of hourly data on the density of solar irradiance, ambient temperature and wind speed in the middle part of the Azov-Black Sea region of Ukraine. For mathematical modelling of power generation and electricity production processes, specialized software PVGIS version 5.2 of the European Commission was used. Hourly quantitative estimates of expected daily power generation trends for each month of the year, as well as their correlation functions, were computed. Algorithms were developed and levels of probabilistic assurance for hourly generated power were evaluated. Statistical estimates of the expected daily, monthly, and annual volumes of electricity production by photovoltaic power plants were studied, taking into account the meteorological conditions in the said region.

Automated machine learning methodology for optimizing production processes in small and medium-sized enterprises

Machine learning can be effectively used to generate models capable of representing the dynamic of production processes of small and medium-sized enterprises. These models enable the estimation of key performance indicators, and are often used for optimizing production processes. However, in most industrial applications, modeling and optimization of production processes are currently carried out as separate tasks, manually in a very costly and inefficient way. Automated machine learning tools and frameworks facilitate the path for deriving models, reducing modeling time and cost. However, optimization by exploiting production models is still in infancy. This work presents a methodology for integrating a fully automated procedure that embraces automated machine learning pipelines and a multi-objective optimization algorithm for improving the production processes, with special focus on small and medium-sized enterprises. This procedure is supported on embedding the generated models as objective functions of a reference point based non-dominated sorting genetic algorithm, resulting in preference-based Pareto-optimal parametrizations of the corresponding production processes. The methodology was implemented and validated using data from a manufacturing production process of a small manufacturing enterprise, generating highly accurate machine learning-based models for the analyzed indicators. Additionally, by applying the optimization step of the proposed methodology it was possible to increase the productivity of the manufacturing process by 3.19 % and reduce its defect rate by 2.15 %, outperforming the results obtained with traditional trial and error method focused on productivity alone.

The economic production quantity model for an imperfect production process by control chart design

The Economic Production Quantity (EPQ) plays a crucial role in the manufacturing process. The traditional EPQ model operates under the assumption that Non-Conforming (NC) items are not produced, and the process remains under control. However, real-world scenarios often involve the production of NC products, leading to process deviations. This study introduces a model that optimizes the design of a control chart to incorporate NC products into the EPQ model. The model integrates inventory and quality-related costs to minimize the expected total cost by determining EPQ, sample size, and control limit. The solution methodology employs direct search techniques to solve this problem. The sensitivity analysis results demonstrate the significant cost reduction achieved by the proposed model compared to the classical EPQ model. The numerical examples presented in the study show an average cost reduction of approximately 21 percent, highlighting the potential effectiveness of the model in cost reduction efforts.

Techno-economic and life cycle analysis of synthetic natural gas production from low-carbon H2 and point-source or atmospheric CO2 in the United States

Synthetic natural gas (SNG) is of great interest in reducing fossil energy consumption while maintaining compatibility with existing NG infrastructure and end-use applications equipment. SNG can be produced using clean H2 generated from renewable or nuclear energy and CO2 captured from stationary sources or the atmosphere. In this study, we develop an engineering process model of SNG production using Aspen Plus® and production scales reported by the industry. We examine the levelized cost and life cycle greenhouse gas (GHG) emissions of SNG production under various CO2 supply scenarios. Considering the higher cost of H2 transportation compared with CO2 transportation, we assume that CO2 feedstock is transported via pipeline to the H2 production location, which is collocated with the SNG plant. We also evaluate the cost of CO2 captured from the atmosphere, assuming the direct air capture process can occur near the SNG facility. Depending on the CO2 supply chain, the levelized cost of SNG is estimated to be in the range of $45–76 per million British thermal units (MMBtu) on a higher heating value (HHV) basis. The SNG production cost may be reduced to $27–57/MMBtu-HHV by applying a tax credit available in the United States for low-carbon H2 production (45 V). With a lower electricity price of 3ȼ/kWh for water electrolysis and accounting for a 45 V tax credit, the SNG cost reaches parity with the cost of fossil NG. Depending on the CO2 supply chain, SNG can reduce life cycle GHG emissions by 52–88 % compared with fossil NG.

Rent formation and distortions due to quotas in biological production processes

Production licenses with use restrictions that limit output are commonly used to regulate biological production processes. Such regulations are vulnerable to rent formation and production distortions that can end up subsidizing harmful environmental behavior. This paper develops a partial equilibrium model for a biological production process and use the model to study the impact of production quotas in Norwegian salmon aquaculture. Results suggest substantial regulatory rents capitalized in license values. Production has intensified leading to excessive stocking of fish per license, a shorting of the production period, and smaller produced fish. Our findings provide important insights for quota policies in food production, especially for cases where quotas are motivated by harmful environmental effects.

The transition to electrified vehicles: Evaluating the labor demand of manufacturing conventional versus battery electric vehicle powertrains

The shift from traditional internal combustion engine vehicles (ICEVs) to electric vehicles (EVs) has raised concerns about displacement of automotive manufacturing labor. Prior studies have mixed findings, and have been hindered by a lack of shop floor-level data on the labor hours required for ICEV and EV manufacturing. We collect detailed data from leading automotive manufacturers on the production process steps and labor inputs required to build key ICEV and battery electric vehicle (BEV) powertrain components. Our novel data set covers 252 process steps, with data on a further 78 process steps from the existing literature. We build a production process model that estimates the labor hours required to produce ICEV and BEV powertrain components at different production volumes and labor efficiency levels. We find that, accounting for production and assembly of battery packs, the labor intensity required for the manufacturing of BEV powertrain components is larger than for ICEV powertrain components. This difference in labor intensity holds even when comparing the highest-efficiency estimates for BEV production with the lowest efficiency-estimates for ICEVs. This finding depends on our shop-floor operations modeling approach and could not be derived from recent approaches focusing on part counts. Our results imply that vehicle electrification could lead to more automotive manufacturing jobs, at least in the short- to medium-term. While there are potential jobs to support transitions for incumbent automotive workers, the feasibility of these transitions will depend on geographic co-location of new battery production capacity with current ICEV production sites, and on matching between the skills of the automotive workforce and the demands of new EV jobs.

Process modelling of biodiesel production process using genetic programming

Biodiesel production is a complex process that involves a number of process parameters. These process parameters must be carefully optimized to increase its yield. In this paper, a process model for biodiesel production is developed by using genetic programming (GP). A case study on biodiesel production from palm oil transesterification is selected from the literature to analyze the proposed methodology. The dataset from literature is based on a central composite design (CCD) with four process parameters (namely methanol-to-oil ratio (x1), catalyst loading (x2), reaction time (x3) and reaction temperature (x4)). The FAME yield % is the target response. The available CCD data is divided into dedicated training (90 %) and testing (10 %) sets to analyze and evaluate the predictive power of the GP metamodel. The GP metamodel is trained using the tuned parameters and validated on the testing data using various statistical metrics. A high accuracy with an R2 of 0.9676 for training data and 0.8834 for testing data is obtained. This study shows that the GP metamodel is a robust and accurate approach to model biodiesel production processes.

Cascading Propagation Path of Vinyl Chloride Process Risk Based on Complex Network

In the production of vinyl chloride, small parameter fluctuations may lead to large-scale cascade fluctuations, causing serious economic losses and casualties, in order to ensure the safety and stability of production, it is necessary to study the cascade fluctuation propagation path of vinyl chloride production process. In this paper, a complex network model of vinyl chloride production process is constructed based on complex network theory, and the concept of comprehensive degree considering network direction is introduced to identify important nodes in the network: secondly, the fluctuation overload propagation probability and material hazard degree of the edge are used to define the fluctuation overload propagation intensity of the edge; finally, according to the fluctuation overload propagation intensity, the risk propagation path of cascading fluctuations under different overload modes is obtained by using ant colony algorithm, it provides a basis for the prevention of cascade overload and the selection and protection of key monitoring nodes.

Technological scheme of wood resources utilization model development

In the present work the justification of the urgency of solving the issue of environmental friendliness of materials produced from wood resources is given. The analysis of the production technology of semifinished wood-fiber products is carried out at the current stage of development of the board industry. The estimation of board formation properties of the wood fiber mass produced in disk blade grinding machines is given, and the inefficiency of the used equipment is substantiated. The expediency of using the equipment with cavitation effect as the second grinding stage in the production of wood pulp was substantiated. As a result, the purpose of the present work was the development of the technology for the production of the semifinished wood fiber product with the use of a rotor-pulsation apparatus as the second stage of the wood pulp mill. To achieve the goal, an analysis of modern technologies used in the production of fiberboard was carried out. The model of technological scheme of production of wood fiberboards by wet method in the environment of AnyLogic program package was developed. Based on the technological scheme developed, a dynamic model of the fiberboard production process was built using a rotor-pulsation apparatus in the second stage of wood pulp milling. In the course of research, statistical analysis methods and simulation modelling of technological processes were applied. The results obtained can find application in the production of fiberboard, as well as in the improvement of technological processes at the enterprises of the forest complex.

BALANCING EFFICIENCY AND FLEXIBILITY – A SIMULATION OF LINE CONFIGURATIONS

Purpose: The purpose of the study is to examine the impact of production line configurations on operational efficiency using simulation tools. Analyzing various scenarios with a variable number of production lines allows for an assessment of how infrastructure modifications affect system performance, resource management, and operational flexibility. Design/methodology/approach: The study was conducted using FlexSim software, which enables the modeling and analysis of production processes. Key steps included: collecting operational data, developing a simulation model, validating the model, and analyzing the results for three configurations: one, two, and three production lines. Model validation was performed by comparing simulation results with real-world operational data. Findings: The findings indicate that a single production line ensures high operational efficiency (around 98%), but its rigidity limits adaptability under changing conditions. Adding a second production line results in a moderate decrease in efficiency (approximately 1.2%), while significantly enhancing flexibility and resource management capabilities. Three production lines offer the highest flexibility; however, efficiency drops to approximately 80%, which may cause challenges related to underutilized resources and increased operational costs. The optimal solution, balancing flexibility and efficiency, is the addition of a second production line. Adding a third line may only be justified under conditions of significant demand growth. Research limitations/implications: The study's limitations stem from the simplifications in the model, such as the assumption of constant production parameters and the exclusion of market variability. Future research should consider dynamic market conditions and a more comprehensive cost analysis. Originality/value: The study introduces an innovative approach by applying computer simulation to evaluate the efficiency of different production line configurations. The insights provided in the article are valuable for production engineers and managers, assisting them in making informed decisions about optimizing production systems.

Transfer of synthesis, logistic and recycling processes in nature to industrial processes

In biological structures, where logistic, synthesis and recycling processes take place, one finds compartments for these different processes. These are arranged in a specific order so that there is optimal synthesis, transformation, logistics, freedom from interference and flexibility of action. Between the compartments run fast transport systems, microtubules or roads, along which information, molecules etc. are transported. Because production, transport and recycling processes run in every living cell, or numerous macroscopic logistical pathways between cells have been evolved and optimized, various biological functional and design structures can serve as models for industrial production processes. In the context of biointelligent production concepts, input and output of material, energy and information, resource-optimized biological production processes and recycling of materials are interesting aspects with transfer potential. In this paper, numerous examples from nature and approaches to transfer the principles to industrial production processes are presented. Some of them have already proven their effectiveness and efficiency, others have yet to do so. The hypothesis is that further optimization potential can be tapped if principles that have been successfully applied for millions of years are transferred to human processes that have only been developed over decades or centuries.