scholarly journals Increased resilience for manufacturing systems in supply networks through data-based turbulence mitigation

2021 ◽  
Author(s):  
Dennis Bauer ◽  
Markus Böhm ◽  
Thomas Bauernhansl ◽  
Alexander Sauer
Keyword(s):  
Manufacturing Systems ◽  
Control Method ◽  
Great Influence ◽  
Learning System ◽  
Effective Control ◽  
Sufficient Information ◽  
Short Term ◽  
Data Format ◽  
Supply Networks ◽  
Manufacturing Control

AbstractIn manufacturing systems, a state of high resilience is always desirable. However, internal and external complexity has great influence on these systems. An approach is to increase manufacturing robustness and responsiveness—and thus resilience—by manufacturing control. In order to execute an effective control method, it is necessary to provide sufficient information of high value in terms of data format, quality and time of availability. Nowadays, raw data is available in large quantities. An obstacle to manufacturing control is the short-term handling of events induced by customers and suppliers. These events cause different kinds of turbulence in manufacturing systems. If such turbulences could be evaluated in advance, based on data processing, they could serve as aggregated input data for a control system. This paper presents an approach how to combine turbulence evaluation and the derivation of measures into a learning system for turbulence mitigation. Integrated in manufacturing control, turbulence mitigation increases manufacturing resilience and strengthens the supply network’s resilience.

scholarly journals Influenza-like illness prediction using a long short-term memory deep learning model with multiple open data sources

2020 ◽  
Vol 76 (12) ◽  
pp. 9303-9329 ◽  
Author(s):  
Chao-Tung Yang ◽  
Yuan-An Chen ◽  
Yu-Wei Chan ◽  
Chia-Lin Lee ◽  
Yu-Tse Tsan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Air Quality ◽  
Short Term Memory ◽  
Control Method ◽  
Visual Presentation ◽  
Health Care Facilities ◽  
Emergency Department Visits ◽  
Effective Control ◽  
Short Term ◽  
Influenza Like Illness

Abstract The influenza problem has always been an important global issue. It not only affects people’s health problems but is also an essential topic of governments and health care facilities. Early prediction and response is the most effective control method for flu epidemics. It can effectively predict the influenza-like illness morbidity, and provide reliable information to the relevant facilities. For social facilities, it is possible to strengthen epidemic prevention and care for highly sick groups. It can also be used as a reminder for the public. This study collects information on the influenza-like illness emergency department visits to the Taiwan Centers for Disease Control, and the PM2.5 open-source data from the Taiwan Environmental Protection Administration's air quality monitoring network. By using deep learning techniques, the relevance of short-term estimates and the outbreak calculation method can be determined. The techniques are published by the WHO to determine whether the influenza-like illness situation is still in a stage of reasonable control. Finally, historical data and future forecasted data are integrated on the web page for visual presentation, to show the actual regional air quality situation and influenza-like illness data and to predict whether there is an outbreak of influenza in the region.

scholarly journals A New Model Predictive Control Method for Eliminating Hydraulic Oscillation and Dynamic Hydraulic Imbalance in a Complex Chilled Water System

Energies ◽  
2021 ◽  
Vol 14 (12) ◽  
pp. 3608
Author(s):  
Yang Yuan ◽  
Neng Zhu ◽  
Haizhu Zhou ◽  
Hai Wang
Keyword(s):  
Model Predictive Control ◽  
Predictive Control ◽  
Control Method ◽  
Water System ◽  
Energy Performance ◽  
Effective Control ◽  
New Model ◽  
Chilled Water ◽  
Chilled Water System ◽  
Hydraulic Oscillation

To enhance the energy performance of a central air-conditioning system, an effective control method for the chilled water system is always essential. However, it is a real challenge to distribute exact cooling energy to multiple terminal units in different floors via a complex chilled water network. To mitigate hydraulic imbalance in a complex chilled water system, many throttle valves and variable-speed pumps are installed, which are usually regulated by PID-based controllers. Due to the severe hydraulic coupling among the valves and pumps, the hydraulic oscillation phenomena often occur while using those feedback-based controllers. Based on a data-calibrated water distribution model which can accurately predict the hydraulic behaviors of a chilled water system, a new Model Predictive Control (MPC) method is proposed in this study. The proposed method is validated by a real-life chilled water system in a 22-floor hotel. By the proposed method, the valves and pumps can be regulated safely without any hydraulic oscillations. Simultaneously, the hydraulic imbalance among different floors is also eliminated, which can save 23.3% electricity consumption of the pumps.

scholarly journals Control Strategy Based on Arm-Level Control for Output and Circulating Current of MMC in Stationary Reference Frame

Energies ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 4160
Author(s):  
Waqar Uddin ◽  
Tiago D. C. Busarello ◽  
Kamran Zeb ◽  
Muhammad Adil Khan ◽  
Anil Kumar Yedluri ◽  
...  
Keyword(s):  
Reference Frame ◽  
Control Method ◽  
Second Harmonic ◽  
Harmonic Component ◽  
Effective Control ◽  
Level Control ◽  
Circulating Current ◽  
Stationary Reference Frame ◽  
Pr Controller ◽  
Dc Component

This paper proposed a control method for output and circulating currents of modular multilevel converter (MMC). The output and circulating current are controlled with the help of arm currents, which contain DC, fundamental frequency, and double frequency components. The arm current is transformed into a stationary reference frame (SRF) to isolate the DC and AC components. The AC component is controlled with a conventional proportional resonant (PR) controller, while the DC component is controlled by a proportional controller. The effective control of the upper arm and lower arm ultimately controls the output current so that it delivers the required power to the grid and circulating current in such a way that the second harmonic component is completely vanished leaving behind only the DC component. Comparative results of leg-level control based on PR controller are included in the paper to show the effectiveness of the proposed control scheme. A three-phase, five-level MMC is developed in MATLAB/Simulink to verify the effectiveness of the proposed control method.

Mechanism and Effect of Nanoparticles on Controlling Fines Migration in Unconsolidated Sandstone Formations

SPE Journal ◽  
2021 ◽  
pp. 1-13
Author(s):  
Xin Zhao ◽  
Zhengsong Qiu ◽  
Jian Gao ◽  
Xiaoxia Ren ◽  
Jia Li ◽  
...  
Keyword(s):  
Interaction Energy ◽  
Control Method ◽  
Effective Control ◽  
Attractive Potential ◽  
Surface Element ◽  
Pore Surface ◽  
Microscopic Mechanism ◽  
Fines Migration ◽  
Favorable Conditions ◽  
Physical And Chemical

Summary Pore throat blockage due to fines migration during drilling and completion is one of the leading causes of damage to unconsolidated sandstone reservoirs. Therefore, it is necessary to explore an effective control method for fines migration. Five types of nanoparticles in suspension with aqueous NaCl solutions of six different ionic strengths were chosen. Their ability to control the migration of quartz and kaolinite fines in quartz sand as the porous medium is discussed in this work. Results show that nanoparticles can effectively adsorb and fix fines, thus successfully suppressing their migration. Among these nanoparticles, Al2O3 showed the best performance, and nanoparticle suspensions with higher ionic strengths were preferable. A surface element integration method was used to establish a mathematical model for calculating the interaction energy between the formation fines and the rock pore surface with adsorbed nanoparticles. Through atomic force microscopy and zeta potential measurements, the effect of nanoparticle adsorption on the heterogeneity of the pore surface was analyzed in terms of roughness and electrical properties. The interaction energy between the formation fines and the heterogeneous pore surface was calculated; it revealed the microscopic mechanism of how nanoparticles control fines migration. The results indicated that the nanoparticles form an adsorption layer, which enhances the physical and chemical heterogeneities of the pore surface and provides favorable conditions for the adsorption and fixation of fines. As a result, the interaction energy curves of the fines and the pore surface shift downward, and their repulsive barriers decrease or even disappear, exhibiting higher attractive potential energy. These variations promote adsorption and fixation of fines at the pore surface, as confirmed by the experimental results reported in this work, thus successfully preventing formation damage.

A Two-Layer Long Short-Term Memory Network for Bottleneck Prediction in Multi-Job Manufacturing Systems

2018 ◽  
Author(s):  
Xingjian Lai ◽  
Huanyi Shui ◽  
Jun Ni
Keyword(s):  
Manufacturing Systems ◽  
Short Term Memory ◽  
Complex Dynamics ◽  
State Of The Art ◽  
Short Term ◽  
Term Memory ◽  
Future Production ◽  
Effective Manner ◽  
Long Short Term Memory ◽  
Factory Floor

Throughput bottlenecks define and constrain the productivity of a production line. Prediction of future bottlenecks provides a great support for decision-making on the factory floor, which can help to foresee and formulate appropriate actions before production to improve the system throughput in a cost-effective manner. Bottleneck prediction remains a challenging task in literature. The difficulty lies in the complex dynamics of manufacturing systems. There are multiple factors collaboratively affecting bottleneck conditions, such as machine performance, machine degradation, line structure, operator skill level, and product release schedules. These factors impact on one another in a nonlinear manner and exhibit long-term temporal dependencies. State-of-the-art research utilizes various assumptions to simplify the modeling by reducing the input dimensionality. As a result, those models cannot accurately reflect complex dynamics of the bottleneck in a manufacturing system. To tackle this problem, this paper will propose a systematic framework to design a two-layer Long Short-Term Memory (LSTM) network tailored to the dynamic bottleneck prediction problem in multi-job manufacturing systems. This neural network based approach takes advantage of historical high dimensional factory floor data to predict system bottlenecks dynamically considering the future production planning inputs. The model is demonstrated with data from an automotive underbody assembly line. The result shows that the proposed method can achieve higher prediction accuracy compared with current state-of-the-art approaches.

scholarly journals Small time scale plankton structure variations at the entrance of a tropical eutrophic bay (Guanabara Bay, Brazil)

2012 ◽  
Vol 60 (4) ◽  
pp. 405-414 ◽  
Author(s):  
Mariana Guenther ◽  
Isabel Lima ◽  
Glenda Mugrabe ◽  
Denise Rivera Tenenbaum ◽  
Eliane Gonzalez-Rodriguez ◽  
...  
Keyword(s):  
Surface Layer ◽  
Photosynthetic Efficiency ◽  
Great Influence ◽  
Small Time ◽  
Guanabara Bay ◽  
Short Term ◽  
Mesozooplankton Biomass ◽  
Trophic Pathways ◽  
Se Brazil ◽  
Almost All

The dynamics of the plankton compartments at the entrance of Guanabara Bay (SE Brazil) were assessed during a short-term temporal survey to estimate their trophic correlations. Size-fractioned phytoplankton (picoplankton: < 2µm, nanoplankton: 2-20µm and microplankton: > 20µm) biomass and photosynthetic efficiency, composition and abundance of the auto-and heterotrophic nano-and microplankton, and mesozooplankton were evaluated at a fixed station for 3 consecutive days at 3-h intervals, in the surface and bottom (20m) layers. The variability of almost all plankton compartments in the surface layer was directly dependent on temperature, indicating the great influence of the circulation at the entrance of the bay on plankton structure. In the surface layer, the mesozooplankton seems to be sustained by both autotrophic nano-and picoplankton, this last being channeled through the microzooplankton. Near the bottom, both auto-and heterotrophic microplankton are probably supporting the mesozooplankton biomass. Our findings thus suggest that the entrance of Guanabara bay presents a multivorous food web, i.e., a combination of both grazing and microbial trophic pathways.

scholarly journals Trust between Humans and Learning Machines: Developing the Gray Box

2017 ◽  
Vol 139 (06) ◽  
pp. S9-S13 ◽  
Author(s):  
James C. Christensen ◽  
Joseph B. Lyons
Keyword(s):  
Situation Awareness ◽  
Task Allocation ◽  
Intelligent Agent ◽  
Semantic Space ◽  
Learning Systems ◽  
Learning System ◽  
Sufficient Information ◽  
Learning Technology ◽  
Learning Machines ◽  
Potential Impact

This article explores the notion of the ‘Gray Box’ to symbolize the idea of providing sufficient information about the learning technology to establish trust. The term system is used throughout this article to represent an intelligent agent, robot, or other form of automation that possesses both decision initiative and authority to act. The article also discusses a proposed and tested Situation Awareness-based Agent Transparency (SAT) model, which posits that users need to understand the system’s perception, comprehension, and projection of a situation. One of the key challenges is that a learning system may adopt behavior that is difficult to understand and challenging to condense to traditional if-then statements. Without a shared semantic space, the system will have little basis for communicating with the human. One of the key recommendations of this article is that there is a need to provide learning systems with transparency as to the state of the human operator, including their momentary capabilities and potential impact of changes in task allocation and teaming approach.

Sign in / Sign up

Export Citation Format

Share Document