Anomaly detection in todays industrial environments is an ambitious challenge to detect possible faults/problems which may turn into severe waste during production, defects, or systems components ...damage, at an early stage. Data-driven anomaly detection in multi-sensor networks rely on models which are extracted from multi-sensor measurements and which characterize the anomaly-free reference situation. Therefore, significant deviations to these models indicate potential anomalies. In this paper, we propose a new approach which is based on causal relation networks (CRNs) that represent the inner causes and effects between sensor channels (or sensor nodes) in form of partial sub-relations, and evaluate its functionality and performance on two distinct production phases within a micro-fluidic chip manufacturing scenario. The partial relations are modeled by non-linear (fuzzy) regression models for characterizing the (local) degree of influences of the single causes on the effects. An advanced analysis of the multi-variate residual signals, obtained from the partial relations in the CRNs, is conducted. It employs independent component analysis (ICA) to characterize hidden structures in the fused residuals through independent components (latent variables) as obtained through the demixing matrix. A significant change in the energy content of latent variables, detected through automated control limits, indicates an anomaly. Suppression of possible noise content in residuals—to decrease the likelihood of false alarms—is achieved by performing the residual analysis solely on the dominant parts of the demixing matrix. Our approach could detect anomalies in the process which caused bad quality chips (with the occurrence of malfunctions) with negligible delay based on the process data recorded by multiple sensors in two production phases: injection molding and bonding, which are independently carried out with completely different process parameter settings and on different machines (hence, can be seen as two distinct use cases). Our approach furthermore i.) produced lower false alarm rates than several related and well-known state-of-the-art methods for (unsupervised) anomaly detection, and ii.) also caused much lower parametrization efforts (in fact, none at all). Both aspects are essential for the useability of an anomaly detection approach.
Robotic manipulation and automation have gained increasing popularity in the food manufacturing industry due to their potential benefits for enhancing hygiene standards, enforcing quality ...consistency, promoting product traceability, and reducing labor costs. As a majority of robotic manipulation, the pick-and-place operation plays a crucial role in food handling applications. However, the reproducibility and comparability of results have put a dilemma that hinders further advancement in this field, especially for those unstructured scenarios. To tackle such thorny issues, this article proposes a benchmarking framework for system-level evaluation of robotic-assisted food handling under the line production environment. A typical food handling scenario, including a pick-and-place operation and a packing operation, is presented as the benchmark task, where food items are supposed to be picked from the tray and placed in the serving dish. A robotic system incorporating a high-speed Delta robot, vision system, conveyor belt, and end-effector is developed as the testbed for the benchmarking implementation. Finally, five variants of the robotic system with different end-effectors are evaluated using the proposed benchmarking framework. Comparative studies illustrate the performance of various benchmarked systems and validate the applicability of the benchmarking strategy for the food handling context. Videos of our experiments are available at https://youtu.be/SBAOoswnjWM .
Tremendous efforts have been made toward large-area Cu(In,Ga)Se2-based photovoltaic module fabrication with some successful commercialisation cases using a co-evaporation system. However, ...comprehensive implementation of the technology has been hindered due to the technological difficulties in film uniformity for scaled-up deposition. However, the quantitative impact analysis on these topics is a matter of commercial confidentiality, and it has not been possible to provide precise accounts of the processes currently used. In this technical report, an attempt has been made to statistically identify the quantitative impact of the uniformity of Cu(In,Ga)Se2 layer on the J-V characteristics of the large-area panels (120 cm × 60 cm) fabricated from a pilot in-line evaporation system. Given the assumption that reproducibility for the other process steps is high, the results deliver important grounds for setting the control limits of the compositional uniformity for quality assurance towards a highly efficient CIGS PV manufacturing line.
Display omitted
•The impact of the large-area (120 cm × 60 cm) CIGS film uniformity on the J-V characteristics was statistically identified.•Cu/(In + Ga) ratio in the range of 0.88–0.92 has limited influence on the efficiency of CIGS solar panels.•The RSM analysis revealed that the impact of Cu/III becomes predominant when its non-uniformity is over 4%.•The within-panel statistics revealed that the non-uniformity of the efficiency appears to be led mainly by variability in Jsc and FF.
Civilization, and therefore also enterprises, have been creating and developing over thousands of years. Previous practices in the production of consumer goods have changed: from primitive tools to ...highly innovative production facilities and lines. The purpose of the study is to present the genesis of the establishment and development of business enterprises, which is often the basis of the production of the final product. During the study, the periods of development of business enterprises and how the methods of production of goods changed were examined. Henry Ford is examined as an example, who contributed to the prosperity of the automobile industry by developing mass production. It is known that over the years, the ways of producing goods have changed a lot. The scientific problem is to investigate how the methods of producing goods have changed and what impact this has had on the entire industry. Main research methods: analysis and synthesis of literature and documents, process modeling.
The consequences of implementing a Hot Wire Chemical Vapor Deposition (HWCVD) chamber into an existing in-line or roll-to-roll reactor are described. The hardware and operation of the HWCVD ...production reactor is compared to that of existing roll-to-roll reactors based on Plasma Enhanced Chemical Vapor Deposition. The most important consequences are the technical consequences and the economic consequences, which are both discussed. The technical consequences are adaptations needed to the hardware and to the processing sequences due to the different interaction of the HWCVD process with the substrate and already deposited layers. The economic consequences are the reduced investments in radio frequency (RF) supplies and RF components. This is partially offset by investments that have to be made in higher capacity pumping systems. The most mature applications of HWCVD are moisture barrier coatings for thin film flexible devices such as Organic Light Emitting Diodes and Organic Photovoltaics, and passivation layers for multicrystalline Si solar cells, high mobility field effect transistors, and silicon heterojunction cells (also known as heterojunction cells with intrinsic thin film layers). Another example is the use of Si in thin film photovoltaics. The cost perspective per unit of thin film photovoltaic product using HWCVD is estimated at 0.07€/Wp for the Si thin film component.
•Review of consequences of implementing Hot Wire CVD into a manufacturing plant•Aspects of scaling up to large area and continuous manufacturing are discussed•Economic advantage of introducing a HWCVD process in a production system is estimated•Using HWCVD, the cost for the Si layers in photovoltaic products is 0.08€/Wp.
Process mining technology has been widely used to optimize the processes of various organizations, especially in enterprises. It facilitates cooperation between departments and prompts efficient ...process design and resource scheduling in the production workshop. However, as a data-driven approach, the lack of production logs hinders the development of enterprise process mining research. Therefore, we introduce a new benchmark dataset named TV-ALP to provide effective data support for the combination of process mining and workshop production. The dataset comes from the field survey experience and product operation instructions, which highly restores the operation of the production workshop and details the processing of television (TV) sets in the assembly line. We compare TV-ALP with other public datasets for detailed statistical analysis and provide benchmark performance for the remaining time prediction task. The experimental results show that TV-ALP can meet the requirements of process mining and analysis research in terms of both scale and quality. In addition, while maintaining the data commonality of public datasets, it also emphasizes the importance of role information and supports a series of role-based log studies. The complete dataset is accessible for download at
https://github.com/Zzou-Sdust/TV-ALP-dataset.
A drawback of multiple lymphaticovenular anastomoses (LVAs) is the need for at least two microsurgeons and the same number of microscopes. In practice, many hospitals find it difficult to access such ...resources. We have developed a novel line production system (LPS) to address this problem. We assessed whether or not the LPS is better than the conventional dual microscope (DM) system when performing multiple LVAs.
An LPS group, wherein a novice microsurgeon used loupes to dissect lymphatics and an expert microsurgeon used a microscope to perform the LVAs, and a DM (control) group, wherein the surgeons used microscopes to perform the LVAs. We recorded the lymphatic detection rate through the loupes and the diameter of the detected lymphatics. We also investigated the impact of using the LPS by comparing the number and quality of LVAs and improvement in lymphedema between the study groups.
The mean lymphatic detection rate was 81%±15.60%, and the mean size of lymphatics was 0.44 ± 0.12 mm in the LPS. The number of LVAs/h in LPS was significantly higher than that in DM (2.15 ± 0.20 vs. 1.38 ± 0.17; p < 0.01). The number of successful LVAs/h in LPS was significantly higher than that in the DM (2.08 ± 0.22 vs. 0.84 ± 0.14; P < 0.01). Mean rate of improvement in LEL index was significantly higher than that in DM (9.36 ± 1.85 vs. 6.93 ± 1.73; P < 0.01).
The number and quality of the LVAs increase using the LPS, which leads to further improvement in lymphedema, with fewer microscopes and microsurgeons and a shorter operating time.
The demand of customer-specific products leads to a fundamental change to manufacturing facilities. To adapt the facilities to new product types, frequently occurring functionality changes in ...industrial automation systems are expected. Functionality changes are primarily implemented by software changes. These software changes within the operation phase can be implemented, for instance, by over-the-air software updates or ad hoc integration of new components. The effects of these changes are often difficult to estimate, especially in distributed automation systems. This mainly poses a challenge on production line operators, who are required to validate their automation systems after functionality changes have been executed. The goal of this contribution is to assist production line operators in the validation process of their automation systems after software changes. Formal verification methods can support the operators, due to its fully automated execution. However, the creation process of the behavior models needed for the formal verification is complex and error-prone. This is why formal verification is usually not used. Hence, a model-based technique is presented to automate this creation process. By means of this, the subsystem affected by the software change is automatically identified and subsequently a suitable input to a model-based verification tool is generated. The concept is based on the generation of a system model by composing the Petri net models of components within the automation system. In order to identify affected components, an impact analysis is performed, starting from the component in which a modification occurred. Followingly, a tailored subsystem is composed using the component models necessary for verification. This subsystem is applied to verify the system requirements for the affected components. To evaluate the applicability of the concept in the field of industrial automation, a distributed automation system was implemented. A service-oriented, OPC-UA-based, control network is thereby used to implement a technical process. Furthermore, a configuration interface enables change of the components at runtime. This emulates over-the-air updates and ad hoc networking. The concept is implemented with the demonstrator “TestIAS.” This test device detects software changes within the automation system and verifies them automatically according to the model-based approach presented. An empirical evaluation was performed with ten different reconfiguration scenarios showing functional changes. In addition, based on the time measurements of the time saving due to the impact analysis, the efficiency enhancement is substantiated.