In view of the nonlinear and time-varying characteristics existing in industrial processes, this paper proposes an integrated soft sensor model based on probabilistic slow feature analysis (PSFA) and least squares sup...
详细信息
ISBN:
(纸本)9798350387780;9798350387797
In view of the nonlinear and time-varying characteristics existing in industrial processes, this paper proposes an integrated soft sensor model based on probabilistic slow feature analysis (PSFA) and least squares support vector regression (LSSVR) to achieve real-time measurement of quality variables. First, the PSFA method was used to effectively capture the slow feature vector of the process and solve the slow time-varying problem;then, the LSSVR method is utilized to establish the relationship between slow features and quality variables, thereby achieving online prediction of quality indicators. Finally, a numerical case and cobalt oxalate synthesis processdata were applied to demonstrated the effectiveness of this propose approach.
This study details data mining techniques in the design of transportation information system (TIS) database, which are widely used by transport companies in China. The objective is to examined how the information syst...
详细信息
In high-energy physics experiments, dataanalysis is an important step in interpreting experimental results. However, there are problems such as low efficiency and low accuracy in the dataanalysis of high-energy phys...
详细信息
Performing accurate and timely Scanning Electron Microscope (SEM) image analysis to identify wafer defects is crucial as it directly impacts manufacturing yield. In this paper, a machine learning (ML) based approach f...
详细信息
ISBN:
(纸本)9781510672178;9781510672161
Performing accurate and timely Scanning Electron Microscope (SEM) image analysis to identify wafer defects is crucial as it directly impacts manufacturing yield. In this paper, a machine learning (ML) based approach for analyzing SEM images (from wafer inspection machines) to locate and classify wafer defects is proposed. A state-of-the-art one-stage objection detection model called YOLOv8 (You Only Look Once version 8) is used as it offers a good balance between accuracy and inference speed. Experimental results confirm that an ensemble model composed of multiple YOLOv8 models can predict 6 types of defects with a mean Average Precision (mAP) of 0.789 (at IoU=0.5) for unseen test data consisting of real-world SEM images from 5 wafer fabs that have varying image qualities.
process models have long-since been used to capture business processes for documentation, communication, analysis, and enactment purposes. Most of the commonly used modeling languages, e.g., BPMN, focus on the control...
详细信息
Current stochastic nonlinear model predictive control (SNMPC) hinges on the lack of high-fidelity models that describe the system behavior and the lack of tractable solution methods that handle chance constraints. Mot...
详细信息
Current stochastic nonlinear model predictive control (SNMPC) hinges on the lack of high-fidelity models that describe the system behavior and the lack of tractable solution methods that handle chance constraints. Motivated by this, a model-and data-driven predictive control approach using Gaussian processes (GP-MDPC) is synthesized in this paper. It exploits GPs to learn the unknown dynamics and apply Taylor expansion for uncertainty propagation through probabilistic modeling. A backoff approximation method is explored to reformulate the chance constraints into tractable expressions. Finally, a finite-horizon stochastic optimal control problem (FH-SOCP) is formulated. Copyright (C) 2024 The Authors.
Biomechanical analysis studies the mechanical structure, function and movement of biological systems using mechanical methods. Recent research shows that more researchers tend to use Physics Informed Neural Networks (...
详细信息
Biomechanical analysis studies the mechanical structure, function and movement of biological systems using mechanical methods. Recent research shows that more researchers tend to use Physics Informed Neural Networks (PINN) instead of finite elements for biomechanical analysis because it greatly shortens the analysis time. However, most existing approaches have two shortcomings: (1) Random initialization of small samples leads to the local optimal solution;(2) Single attribute leads to stress deviation. To tackle the shortcomings mentioned above, we proposed a biomechanical analysis method to obtain the global optimal solution in small sample CT data sets and automatically distinguish bone components. Specifically, to solve the problem that small sample CT data easily produces local optimal solutions and leads to poor generalization ability, we try to purposefully reconstruct the initialization weight matrix and design an initialization weight method based on spinal CT image features to alleviate this problem and thus improve the generalization ability of the model. To distinguish different bone compositions, a bone composition differentiation method based on PINN was designed, which can automatically distinguish different bone compositions. At the same time, leveraging the acquired global optimal solution and the adaptive matching parameters of the bone components, we employ multiple sets of physical rules to constrain feature mapping through numerical regression. This approach enhances the accuracy of biomechanical analysis. Extensive experiments on three representative thoracic and lumbar spine datasets achieved an accuracy of 91.09%, demonstrating the effectiveness of the method. The training and testing time for each sample does not exceed 8ms, demonstrating the technique's applicability.
Measurement data acquired from an industrial heat exchanger (HE) can provide a reliable inference on its dynamics and performance. Harnessing the information available on the acquired data, the data-driven modeling te...
详细信息
As a new type of geographic data source, real 3D models can effectively complement the lack of facade and environmental information in traditional aerial remote sensing data captured from only downward perspective. Cu...
详细信息
This paper presents the development, validation, and application of a numerical model to simulate the process of refueling hydrogen-powerd heavy-duty vehicles, with a cascade hydrohen refueling station design. The mod...
详细信息
This paper presents the development, validation, and application of a numerical model to simulate the process of refueling hydrogen-powerd heavy-duty vehicles, with a cascade hydrohen refueling station design. The model is implemented and validated using experimental data from SAE J2601. The link between the average pressure ramp (APRR) and flow rate, which is responsible for the dynamic evolution of the refueling process, was analyzed. Various simulations were conducted, with a vehicle tank of 230 L and nominal pressure of 35 MPa typical of tanks adopted in heavy-duty vehicles, varying the ambient temperature between 0 and 40 degrees C, the cooling temperature of the hydrogen by the system cooling between -40 and 0 degrees C and the APRR between 2 and 14 MPa/min. The study found that if the ambient temperature does not exceed 30 degrees C, rapid refueling can be carried out with not very low pre-cooling temperatures, e.g. -20 degrees C or - 10 degrees C, guaranteeing greater savings in station management. Cooling system thermal power has been investigated, through the analyses in several scenarios, with values as high as 38.2 kW under the most challenging conditions. For those conditions, it was shown that energy savings could reach as much as 90 %. Furthermore, the refueling process was analyzed taking into account SAE J2061/2 limitations and an update was proposed. An alternative strategy was proposed such that the settings allow a higher flow rate to be associated with a given standard pressure ramp. This approach was designed to ensure that the maximum allowable pressure downstream of the pressure control valve, as specified by the refueling protocol, is reached exactly at the end of the refueling process. It has been observed that the adoption of this strategy has significant advantages. In the case of refueling with higher APPR, refueling is about 20 s faster with a single tank, with limited increases in temperature and pressure within it.
暂无评论