System In Production Environment Research Articles

Failure Prediction of Automated Guided Vehicle Systems in Production Environments through Artificial Intelligence

Modern industrial systems demand intricate connectivity and automation, especially in the realm of shop floor processes and intralogistics. Automated Guided Vehicle (AGV) systems are characterized by their potential for seamlessly networking value creation areas. However, failures and disruptions in AGV systems and adjacent facilities can lead to production halts, adversely affecting delivery reliability and quality. A substantial portion of the downtime stems from manual troubleshooting, underscoring the pivotal importance of the response time from maintenance staff. This paper introduces an approach employing a neural network with long short-term memory for forecasting and predictive maintenance to enhance AGV system reliability and availability in production environments. By analysing historical data, identifying patterns, and predicting potential failures or maintenance needs in AGV components and neighbouring facilities, the proposed AI-based forecasting ensures timely preventive measures. A case study shows the effectiveness of this approach in significantly improving AGV system performance, minimizing disruptions, and enhancing operational availability. This research contributes to smart manufacturing by providing a practical solution for optimizing availability of the concerned AGV system through advanced AI-based forecasting strategies.

Solving line balancing and AGV scheduling problems for intelligent decisions using a Genetic-Artificial bee colony algorithm

Due to the rapid advancement of technology, the demand for electronic devices in various sectors such as consumer electronics, automotive, telecommunications, healthcare, and industrial applications, as well as customized printed circuit board (PCB) products, has significantly increased. Balancing the PCB assembly line is crucial for improving productivity to meet market demand, which means balancing the workload distributed among various assembly stations on the assembly line. However, the workload balancing depends on material-handling systems in production environments that facilitate the transportation of raw materials to the buffer storage of the assembly stations. In the PCB assembly system, the material handling is carried out using automated guided vehicles (AGVs). This paper studies the assembly line balancing and AGV scheduling collectively because of their dependency on each other. A mixed integer linear programming (MILP) model is formulated to balance the workload distribution among stations and schedule the AGVs. An existing intelligent platform of the real-life PCB industry is considered to solve this integrated problem with intelligent decisions. The platform includes three layers modules: physical layer, data management layer and application service layer. A novel genetic artificial bee colony (GABC) algorithm is proposed and embedded with an application service layer to optimize the current problem and give optimum solutions for the real-life physical layer. The proposed GABC algorithm incorporates the operators of the genetic algorithm (GA) i.e., crossover and mutation into the search process of the ABC algorithm. Additionally, the greedy selection feature is employed in GABC which significantly enhances the exploitation capabilities, leading to faster convergence, higher-quality solutions, and improved robustness. The performance of the proposed GABC algorithm is tested based on different parameters by comparing the results with GA, ABC and PSO algorithms. Experimental analysis indicates that the proposed GABC algorithm outperforms the compared algorithms. Therefore, the yielded solutions in terms of prompt responses help managers to expedite the production through intelligent decision-making based on customer demands.

Optimized Energy-Flexible Operation Strategies of Air Conditioning Systems in Production Environments

Rising energy prices and regulatory requirements are forcing both large manufacturing companies and small and medium-sized enterprises to minimize costs and emissions associated with energy supply. To operate the considered systems more efficiently overall, numerous energy efficiency measures have already been successfully implemented in recent years. This is particularly the case for the cross-industry air conditioning systems that are the focus of this paper. However, due to the growing share of renewable energies and the resulting fluctuating electricity prices and CO2 emissions factors, energy flexibility measures are becoming increasingly relevant. In this context, flexibility measures allow industrial system operators to benefit from these fluctuations, primarily using energy storages and optimized operation strategies. However, the implementation of energy flexibility measures requires high data availability, a good understanding of the system, and flexibility in production planning. To be able to effectively use the existing energy flexibility potentials, air conditioning systems are examined, that contain widely used cross-section technologies. In this paper, a method to enable optimized energy-flexible operation of industrial air conditioning systems is presented. A common feature of manufacturing sites is a similar topology of the thermal supply infrastructure across industries. The complex overall system is divided into several subsystems, e.g., cooling supply system, ventilation system and the production hall. Production processes typically release waste heat into the indoor air of the production hall, which then must be cooled. By accounting for thermal and electrical output and optimizing the operation strategy using mathematical optimization, both operating costs and CO2 emissions associated with energy provision can be significantly reduced. The presented use case reveals that operational cost savings of up to 18 % and a reduction of CO2 emission associated with energy supply of up to 16 % can be realized by optimizing the cooling supply system on its own.

Research Directions for Merging Geospatial Technologies with Smart Manufacturing Systems

Abstract As industrial Internet of Things concepts and technologies continue to be retrofitted onto existing manufacturing infrastructure, geospatial considerations, such as asset localization, registration, and tracking, become more critical to ensure better flexibility, capability understanding, and agility. In response, there have been efforts to merge state-of-the-art Geographical Information Systems and Smart Manufacturing Systems in production environments. However, these solutions are often product- or platform-centric and proprietary, such as (i) computer vision technologies embedded on an automatic guided vehicle and (ii) point cloud translation after 3-D scan within a Product Lifecycle Management solution. Standards exist for various steps and functions within these computer-supported pipelines, but little work exists that tests their scalability and robustness. This paper aims to critically evaluate the current state of the integration of Smart Manufacturing Systems and Geographic Information Science and Technology and identifies the potential overlap between the two fields and lists opportunities for further collaboration. The methodological approach of this paper is two-fold: we utilize (a) a survey with experts in both fields and (b) an algorithmic literature meta-analysis. The results reveal that both fields have concepts that could mutually support each other and that smart manufacturing could benefit from Geographic Information technologies—especially from a standardized representation of indoor environments. The results show a great number of potential overlaps and thus present a preliminary roadmap to foster the integration.

Energy efficiency of Heating, Ventilation and Air Conditioning systems in production environments through model-predictive control schemes: The case of battery production

In the German industry Heating, Ventilation and Air Conditioning (HVAC) systems account for 11 %–20 % of the final energy consumption. Usually HVAC systems are dimensioned based on static extreme values and thus during most of the operation time, HVAC systems tend to be overdimensioned. In addition, the extensive literature review of 40 papers shows that often topics on model-based energy efficiency improvement are commonly performed for office or residential buildings, but rather rarely for production environments. Furthermore, the performance of control schemes for energy efficiency improvement are rarely compared with each other or incompletely compared with each other. In this publication, we use the framework of a Cyber–Physical Production System (CPPS) to compare the performance of four main control schemes, ranging from simple time-based control to model-predictive control, which has not been done in the context of battery production before. Over a fixed observation period, the four control schemes are transparently compared with each other in a case study using the example of the Battery LabFactory Braunschweig (BLB). Compared to the initial state, a significant reduction in final energy demand can be achieved with all examined control approaches, which is even up to 37.29% in case of the model-predictive control. Surprisingly, even simple control approaches, without any predictions, have a good energetic saving potential of up to 20.22% compared to the initial state, which is why they are initially recommended for practical implementation. Moreover, we publish all source code of the control schemes, in order to encourage the implementation of energy efficiency measures in further applications not restricted to battery production.

Understanding augmented reality adoption trade-offs in production environments from the perspective of future employees: A choice-based conjoint study

The implementation of augmented reality (AR) systems in production environments is associated with a variety of advantages, such as productivity gains, lower costs and reduced operating times. Despite these potential benefits, the lack of user acceptance due to issues such as privacy concerns constitutes a barrier to diffusion in workplace environments. In order to better understand the issues surrounding AR acceptance, we employed a conjoint study to empirically examine the trade-offs that future employees perceive when being involved in adopting such systems. Using a hierarchical Bayes estimation, we discover that functional benefits such as productivity gains and safety enhancement are the main adoption drivers. In contrast, future employees indeed perceive monitoring through head-worn AR devices as negative. However, a complementary cluster analysis indicates that not all respondents share a negative view of monitoring, and one third are likely to share their performance data with employers. We identify three groups with significantly different utility patterns. Furthermore, we monetize the value of privacy to determine compensation payments. The results may help employers, decision-makers, software solution providers as well as researchers in the information systems domain to better understand the factors surrounding acceptance of AR assistance systems. To the best of our knowledge, we are the first to address this issue using conjoint analysis.

CyProF – Insights from a Framework for Designing Cyber-Physical Systems in Production Environments

There is little experience in integrating cyber-physical systems (CPS) in production environments nowadays. A coordinated framework with reference architecture, methodology and procedural model can support the adaption of CPS by providing a pre-defined structure and guidelines. This paper describes such a framework, named CyProF, for designing CPS-based solutions in production environments. Engineers are supported by this framework in handling the complexity during the design phase. Additionally, this paper explains how the framework was used in a use case to reduce engineering efforts for a CPS-based demonstrator.

Glocalized cyber physical production systems

Current developments in automation technology deal with “cyber physical systems”. These cyber physical systems have sensors and actors and can make decisions based on their own intelligence as well as partially adapt to changing conditions. For a versatile and networked production cyber physical systems are of limited value. Precisely where the available sensors and actuators have to be combined flexibly due to ever new conditions, these systems find their limits because of their insularity. Limited computing hardware resources and lacking interfaces confine the possibilities of cyber physical systems in production environment. This paper explains how cyber physical systems need to be developed further in order to meet the requirements of a versatile and networked production plant.