Investigating Grey-Box Modeling for Predictive Analytics in Smart Manufacturing

Zhuo Yang ◽  
Douglas Eddy ◽  
Sundar Krishnamurty ◽  
Ian Grosse ◽  
Peter Denno ◽  

This paper develops a two-stage grey-box modeling approach that combines manufacturing knowledge-based (white-box) models with statistical (black-box) metamodels to improve model reusability and predictability. A white-box model can use various types of existing knowledge such as physical theory, high fidelity simulation or empirical data to build the foundation of the general model. The residual between a white-box prediction and empirical data can be represented with a black-box model. The combination of the white-box and black-box models provides the parallel hybrid structure of a grey-box. For any new point prediction, the estimated residual from the black-box is combined with white-box knowledge to produce the final grey-box solution. This approach was developed for use with manufacturing processes, and applied to a powder bed fusion additive manufacturing process. It can be applied in other common modeling scenarios. Two illustrative case studies are brought into the work to test this grey-box modeling approach; first for pure mathematical rigor and second for manufacturing specifically. The results of the case studies suggest that the use of grey-box models can lower predictive errors. Moreover, the resulting black-box model that represents any residual is a usable, accurate metamodel.

Energies ◽  
2021 ◽  
Vol 14 (23) ◽  
pp. 7865
Saeid Shahpouri ◽  
Armin Norouzi ◽  
Christopher Hayduk ◽  
Reza Rezaei ◽  
Mahdi Shahbakhti ◽  

The standards for emissions from diesel engines are becoming more stringent and accurate emission modeling is crucial in order to control the engine to meet these standards. Soot emissions are formed through a complex process and are challenging to model. A comprehensive analysis of diesel engine soot emissions modeling for control applications is presented in this paper. Physical, black-box, and gray-box models are developed for soot emissions prediction. Additionally, different feature sets based on the least absolute shrinkage and selection operator (LASSO) feature selection method and physical knowledge are examined to develop computationally efficient soot models with good precision. The physical model is a virtual engine modeled in GT-Power software that is parameterized using a portion of experimental data. Different machine learning methods, including Regression Tree (RT), Ensemble of Regression Trees (ERT), Support Vector Machines (SVM), Gaussian Process Regression (GPR), Artificial Neural Network (ANN), and Bayesian Neural Network (BNN) are used to develop the black-box models. The gray-box models include a combination of the physical and black-box models. A total of five feature sets and eight different machine learning methods are tested. An analysis of the accuracy, training time and test time of the models is performed using the K-means clustering algorithm. It provides a systematic way for categorizing the feature sets and methods based on their performance and selecting the best method for a specific application. According to the analysis, the black-box model consisting of GPR and feature selection by LASSO shows the best performance with test R2 of 0.96. The best gray-box model consists of SVM-based method with physical insight feature set along with LASSO for feature selection with test R2 of 0.97.

2019 ◽  
Vol 29 (Supplement_4) ◽  
S Ram

Abstract With rapid developments in big data technology and the prevalence of large-scale datasets from diverse sources, the healthcare predictive analytics (HPA) field is witnessing a dramatic surge in interest. In healthcare, it is not only important to provide accurate predictions, but also critical to provide reliable explanations to the underlying black-box models making the predictions. Such explanations can play a crucial role in not only supporting clinical decision-making but also facilitating user engagement and patient safety. If users and decision makers do not have faith in the HPA model, it is highly likely that they will reject its use. Furthermore, it is extremely risky to blindly accept and apply the results derived from black-box models, which might lead to undesirable consequences or life-threatening outcomes in domains with high stakes such as healthcare. As machine learning and artificial intelligence systems are becoming more capable and ubiquitous, explainable artificial intelligence and machine learning interpretability are garnering significant attention among practitioners and researchers. The introduction of policies such as the General Data Protection Regulation (GDPR), has amplified the need for ensuring human interpretability of prediction models. In this talk I will discuss methods and applications for developing local as well as global explanations from machine learning and the value they can provide for healthcare prediction.

2009 ◽  
Lori Katz ◽  
Andrei Novac ◽  
Bita Ghafoori ◽  
Toni Pusateri

1988 ◽  
Vol 16 (2) ◽  
pp. 62-77 ◽  
P. Bandel ◽  
C. Monguzzi

Abstract A “black box” model is described for simulating the dynamic forces transmitted to the vehicle hub by a tire running over an obstacle at high speeds. The tire is reduced to a damped one-degree-of-freedom oscillating system. The five parameters required can be obtained from a test at a given speed. The model input is composed of a series of empirical relationships between the obstacle dimensions and the displacement of the oscillating system. These relationships can be derived from a small number of static tests or by means of static models of the tire itself. The model can constitute the first part of a broader model for description of the tire and vehicle suspension system, as well as indicating the influence of tire parameters on dynamic behavior at low and medium frequencies (0–150 Hz).

Qing Yang ◽  
Xia Zhu ◽  
Jong-Kae Fwu ◽  
Yun Ye ◽  
Ganmei You ◽  

2021 ◽  
Vol 17 (3) ◽  
pp. 1-38
Lauren Biernacki ◽  
Mark Gallagher ◽  
Zhixing Xu ◽  
Misiker Tadesse Aga ◽  
Austin Harris ◽  

There is an increasing body of work in the area of hardware defenses for software-driven security attacks. A significant challenge in developing these defenses is that the space of security vulnerabilities and exploits is large and not fully understood. This results in specific point defenses that aim to patch particular vulnerabilities. While these defenses are valuable, they are often blindsided by fresh attacks that exploit new vulnerabilities. This article aims to address this issue by suggesting ways to make future defenses more durable based on an organization of security vulnerabilities as they arise throughout the program life cycle. We classify these vulnerability sources through programming, compilation, and hardware realization, and we show how each source introduces unintended states and transitions into the implementation. Further, we show how security exploits gain control by moving the implementation to an unintended state using knowledge of these sources and how defenses work to prevent these transitions. This framework of analyzing vulnerability sources, exploits, and defenses provides insights into developing durable defenses that could defend against broader categories of exploits. We present illustrative case studies of four important attack genealogies—showing how they fit into the presented framework and how the sophistication of the exploits and defenses have evolved over time, providing us insights for the future.

2021 ◽  
Vol 11 (10) ◽  
pp. 4631
Yu Chen ◽  
Xiaoqing Ji ◽  
Zhongyong Zhao

The accurate establishment of the equivalent circuit model of the synchronous machine windings’ broadband characteristics is the basis for the study of high-frequency machine problems, such as winding fault diagnosis and electromagnetic interference prediction. Therefore, this paper proposes a modeling method for synchronous machine winding based on broadband characteristics. Firstly, the single-phase high-frequency lumped parameter circuit model of synchronous machine winding is introduced, then the broadband characteristics of the port are analyzed by using the state space model, and then the equivalent circuit parameters are identified by using an optimization algorithm combined with the measured broadband impedance characteristics of port. Finally, experimental verification and comparison experiments are carried out on a 5-kW synchronous machine. The experimental results show that the proposed modeling method identifies the impedance curve of the circuit parameters with a high degree of agreement with the measured impedance curve, which indicates that the modeling method is feasible. In addition, the comparative experimental results show that, compared with the engineering exploratory calculation method, the proposed parameter identification method has stronger adaptability to the measured data and a certain robustness. Compared with the black box model, the parameters of the proposed model have a certain physical meaning, and the agreement with the actual impedance characteristic curve is higher than that of the black box model.

Energies ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 6749
Reda El Bechari ◽  
Stéphane Brisset ◽  
Stéphane Clénet ◽  
Frédéric Guyomarch ◽  
Jean Claude Mipo

Metamodels proved to be a very efficient strategy for optimizing expensive black-box models, e.g., Finite Element simulation for electromagnetic devices. It enables the reduction of the computational burden for optimization purposes. However, the conventional approach of using metamodels presents limitations such as the cost of metamodel fitting and infill criteria problem-solving. This paper proposes a new algorithm that combines metamodels with a branch and bound (B&B) strategy. However, the efficiency of the B&B algorithm relies on the estimation of the bounds; therefore, we investigated the prediction error given by metamodels to predict the bounds. This combination leads to high fidelity global solutions. We propose a comparison protocol to assess the approach’s performances with respect to those of other algorithms of different categories. Then, two electromagnetic optimization benchmarks are treated. This paper gives practical insights into algorithms that can be used when optimizing electromagnetic devices.

Symmetry ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 102
Mohammad Reza Davahli ◽  
Waldemar Karwowski ◽  
Krzysztof Fiok ◽  
Thomas Wan ◽  
Hamid R. Parsaei

In response to the need to address the safety challenges in the use of artificial intelligence (AI), this research aimed to develop a framework for a safety controlling system (SCS) to address the AI black-box mystery in the healthcare industry. The main objective was to propose safety guidelines for implementing AI black-box models to reduce the risk of potential healthcare-related incidents and accidents. The system was developed by adopting the multi-attribute value model approach (MAVT), which comprises four symmetrical parts: extracting attributes, generating weights for the attributes, developing a rating scale, and finalizing the system. On the basis of the MAVT approach, three layers of attributes were created. The first level contained six key dimensions, the second level included 14 attributes, and the third level comprised 78 attributes. The key first level dimensions of the SCS included safety policies, incentives for clinicians, clinician and patient training, communication and interaction, planning of actions, and control of such actions. The proposed system may provide a basis for detecting AI utilization risks, preventing incidents from occurring, and developing emergency plans for AI-related risks. This approach could also guide and control the implementation of AI systems in the healthcare industry.

Sign in / Sign up

Export Citation Format

Share Document