Path Enhanced Bidirectional Graph Attention Network for Quality Prediction in Multi-stage Manufacturing Process

2021 ◽  
pp. 1-1
Author(s):  
Donghao Zhang ◽  
Zhenyu Liu ◽  
Weiqiang Jia ◽  
Hui Liu ◽  
Jianrong Tan
Keyword(s):  
Manufacturing Process ◽  
Quality Prediction ◽  
Attention Network ◽  
Multi Stage

Dynamic Quality Prediction of Manufacturing Process Based on Extreme Learning Machine

2014 ◽  
Vol 889-890 ◽  
pp. 1231-1235
Author(s):  
Jun Guo ◽  
Yi Bing Li ◽  
Bai Gang Du
Keyword(s):  
Extreme Learning Machine ◽  
Manufacturing Process ◽  
Manufacturing Processes ◽  
Manufacturing Cost ◽  
Quality Prediction ◽  
Proposed Model ◽  
Machine Learning Approach ◽  
Learning Machine ◽  
Dynamic Quality ◽  
Quality Categories

In many manufacturing processes, the abnormal changes of some key process parameters could result in various categories of faulty products. In this paper, a machine learning approach is developed for dynamic quality prediction of the manufacturing processes. In the proposed model, an extreme learning machine is developed for monitoring the manufacturing process and recognizing faulty quality categories of the products being produced. The proposed model is successfully applied to a japanning-line, which improves the product quality and saves manufacturing cost.

scholarly journals Acetone-butanol-ethanol fermentation from different pulp and paper manufacturing process side-streams

BioResources ◽  
2020 ◽  
Vol 15 (4) ◽  
pp. 9265-9290
Author(s):  
Sandra Sandar ◽  
Ming Yang ◽  
Ossi Turunen ◽  
Jouko Vepsäläinen ◽  
Ari Pappinen ◽  
...  
Keyword(s):  
Enzymatic Hydrolysis ◽  
Manufacturing Process ◽  
Paper Industry ◽  
Pulp And Paper ◽  
Dilute Acid Pretreatment ◽  
Acid Pretreatment ◽  
Diverse Range ◽  
Paper Manufacturing ◽  
Multi Stage ◽  
Acetone Butanol Ethanol

The pulp and paper industry produces a diverse range of side-streams from multi-stage processes, but these remain underutilized despite their high potential for use as biofuels. This study investigated acetone-butanol-ethanol (ABE) fermentation by Clostridium acetobutylicum DSM 1731 from the side-streams of three different stages of the pulp and paper manufacturing process (PI, PII, and PIII). Biomass specimens with and without water washing were pretreated with 0.2% H2SO4 at 180 °C for 10 min, followed by enzymatic hydrolysis, to obtain fermentable sugars. The results showed that the produced ABE solvent concentrations were 12.8 g/L, 5.2 g/L, and 6.3 g/L from PI, PII, and PIII, respectively. The butanol yields of PI, PII, and PIII were 0.25, 0.18, and 0.19 g/g sugars, respectively. Among the tested side-streams, PI was shown to have potential as a feedstock for butanol production without prewashing prior to dilute acid pretreatment, enzymatic hydrolysis, and microbial fermentation.

Selection of Part Orientation for Multi-Axis Hybrid Manufacturing Process

2009 ◽  
Author(s):  
Jianzhong Ruan ◽  
Jun Zhang ◽  
Frank Liou
Keyword(s):  
Manufacturing Process ◽  
Search Space ◽  
Deposition Process ◽  
Hybrid Manufacturing ◽  
Optimal Orientation ◽  
Multi Stage ◽  
Build Time ◽  
Speed Up ◽  
Computation Algorithm ◽  
Selection Of

In regular 3 axis layered manufacturing processes, the build direction is fixed throughout the process. Multi-axis laser (more than 3-axis motion) deposition process, the orientation of the part can affect the non-support buildability in the multi-axis hybrid manufacturing process. However, each orientation that satisfies the buildability and other constraints may not be unique. In this case, the final optimal orientation is determined based on build time. The build time computation algorithm for multi-axis hybrid system is presented in this paper. To speed up the exhaustive search for the optimal orientation, a multi-stage algorithm is developed to reduce the search space.

scholarly journals Systematic and Model-Assisted Process Design for the Extraction and Purification of Artemisinin from Artemisia annua L.—Part II: Model-Based Design of Agitated and Packed Columns for Multistage Extraction and Scrubbing

Processes ◽  
2018 ◽  
Vol 6 (10) ◽  
pp. 179 ◽  
Author(s):  
Axel Schmidt ◽  
Maximilian Sixt ◽  
Maximilian Huter ◽  
Fabian Mestmäcker ◽  
Jochen Strube
Keyword(s):  
Manufacturing Process ◽  
Process Model ◽  
Artemisia Annua ◽  
Scale Up ◽  
Plug Flow ◽  
Process Models ◽  
Extraction Column ◽  
Model Parameters ◽  
Multi Stage ◽  
Extraction And Purification

Liquid-liquid extraction (LLE) is an established unit operation in the manufacturing process of many products. However, development and integration of multistage LLE for new products and separation routes is often hindered and is probably more cost intensive due to a lack of robust development strategies and reliable process models. Even today, extraction columns are designed based on pilot plant experiments. For dimensioning, knowledge of phase equilibrium, hydrodynamics and mass transport kinetics are necessary. Usually, those must be determined experimentally for scale-up, at least in scales of DN50-150 (nominal diameter). This experiment-based methodology is time consuming and it requires large amounts of feedstock, especially in the early phase of the project. In this study the development for the integration of LLE in a new manufacturing process for artemisinin as an anti-malaria drug is presented. For this, a combination of miniaturized laboratory and mini-plant experiments supported by mathematical modelling is used. System data on extraction and washing distributions were determined by means of shaking tests and implemented as a multi-stage extraction in a process model. After the determination of model parameters for mass transfer and plant hydrodynamics in a droplet measurement apparatus, a distributed plug-flow model is used for scale-up studies. Operating points are validated in a mini-plant system. The mini-plant runs are executed in a Kühni-column (DN26) for extraction and a packed extraction column (DN26) for the separation of side components with a throughput of up to 3.6 L/h, yield of up to 100%, and purity of 41% in the feed mixture to 91% after washing.

scholarly journals Quality Prediction of Discrete Manufacturing Process Based on CGAN&Catboost Hybrid Model

2021 ◽  
Vol 1757 (1) ◽  
pp. 012072
Author(s):  
Peng Xu ◽  
Zhichen Ren ◽  
Yili Shen ◽  
Wendi Yu ◽  
Lianghua He
Keyword(s):  
Hybrid Model ◽  
Manufacturing Process ◽  
Quality Prediction ◽  
Discrete Manufacturing

Multi-Stage Fusion and Multi-Source Attention Network for Multi-Modal Remote Sensing Image Segmentation

2021 ◽  
Vol 12 (6) ◽  
pp. 1-20
Author(s):  
Jiaqi Zhao ◽  
Yong Zhou ◽  
Boyu Shi ◽  
Jingsong Yang ◽  
Di Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Rapid Development ◽  
Remote Sensing Data ◽  
Semantic Segmentation ◽  
Sensor Technology ◽  
Feature Maps ◽  
Attention Network ◽  
Modal Data ◽  
Sensing Data ◽  
Multi Stage

With the rapid development of sensor technology, lots of remote sensing data have been collected. It effectively obtains good semantic segmentation performance by extracting feature maps based on multi-modal remote sensing images since extra modal data provides more information. How to make full use of multi-model remote sensing data for semantic segmentation is challenging. Toward this end, we propose a new network called Multi-Stage Fusion and Multi-Source Attention Network ((MS) 2 -Net) for multi-modal remote sensing data segmentation. The multi-stage fusion module fuses complementary information after calibrating the deviation information by filtering the noise from the multi-modal data. Besides, similar feature points are aggregated by the proposed multi-source attention for enhancing the discriminability of features with different modalities. The proposed model is evaluated on publicly available multi-modal remote sensing data sets, and results demonstrate the effectiveness of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document