{"title":"Special Section on Risk and Uncertainties in Offshore Wind and Wave Energy Systems","authors":"V. Pakrashi, Jimmy Murphy, B. Hazra","doi":"10.1115/1.4052359","DOIUrl":"https://doi.org/10.1115/1.4052359","url":null,"abstract":"","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"33 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87174593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Akrouche, M. Sallak, E. Châtelet, F. Abdallah, Hiba Haj Chhade
An essential step in the safe design of systems is choosing the system configuration that will maximize the overall availability of the system and minimize its overall cost. The main objective of this paper is to propose an optimization method of multi-state system availability in the presence of both aleatory and epistemic uncertainties, to choose the best configuration for the system in terms of availability, cost, and imprecision. The problem is formulated as follows: let us consider several configurations of a system, with each configuration consisting of components with different working states, and imprecise failure and repair rates provided in the form of intervals. The aim is to find the best configuration regarding the system's imprecise availability, cost, and imprecision. First, the imprecise steady availability of each configuration is computed by using an original method based on Markovian approaches combined with interval contraction techniques. Then an objective function incorporating cost, the lower and upper bounds of availability, and imprecision is defined and computed to provide the best configuration. To illustrate the proposed method, a use case is discussed.
{"title":"An Interval Approach for the Availability Optimization of Multi-State Systems in the Presence of Aleatory and Epistemic Uncertainties","authors":"J. Akrouche, M. Sallak, E. Châtelet, F. Abdallah, Hiba Haj Chhade","doi":"10.1115/1.4052461","DOIUrl":"https://doi.org/10.1115/1.4052461","url":null,"abstract":"\u0000 An essential step in the safe design of systems is choosing the system configuration that will maximize the overall availability of the system and minimize its overall cost. The main objective of this paper is to propose an optimization method of multi-state system availability in the presence of both aleatory and epistemic uncertainties, to choose the best configuration for the system in terms of availability, cost, and imprecision. The problem is formulated as follows: let us consider several configurations of a system, with each configuration consisting of components with different working states, and imprecise failure and repair rates provided in the form of intervals. The aim is to find the best configuration regarding the system's imprecise availability, cost, and imprecision. First, the imprecise steady availability of each configuration is computed by using an original method based on Markovian approaches combined with interval contraction techniques. Then an objective function incorporating cost, the lower and upper bounds of availability, and imprecision is defined and computed to provide the best configuration. To illustrate the proposed method, a use case is discussed.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"1 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83169919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Spencer T Hallowell, S. Arwade, B. Diaz, C. Aubeny, Casey M. Fontana, D. DeGroot, Melissa E. Landon
One of many barriers to the deployment of floating offshore wind turbines is the high cost of vessel time needed for soil investigations and anchor installation. A multiline anchor system is proposed in which multiple floating offshore wind turbines (FOWTs) are connected to a single caisson. The connection of multiple FOWTs to a single anchor introduces interconnectedness throughout the wind farm. Previous work by the authors has shown that this interconnectedness reduces the reliability of the FOWT below an acceptable level when exposed to survival loading conditions. To combat the reduction in system reliability an overstrength factor (OSF) is applied to the anchors functioning as an additional safety factor. For a 100 turbine wind farm, single-line system reliabilities can be achieved using the multiline system with an OSF of 1.10, a 10% increase in multiline anchor safety factors for all anchors in a farm.
{"title":"Harmonizing the Mooring System Reliability of Multiline Anchor Wind Farms","authors":"Spencer T Hallowell, S. Arwade, B. Diaz, C. Aubeny, Casey M. Fontana, D. DeGroot, Melissa E. Landon","doi":"10.1115/1.4052423","DOIUrl":"https://doi.org/10.1115/1.4052423","url":null,"abstract":"\u0000 One of many barriers to the deployment of floating offshore wind turbines is the high cost of vessel time needed for soil investigations and anchor installation. A multiline anchor system is proposed in which multiple floating offshore wind turbines (FOWTs) are connected to a single caisson. The connection of multiple FOWTs to a single anchor introduces interconnectedness throughout the wind farm. Previous work by the authors has shown that this interconnectedness reduces the reliability of the FOWT below an acceptable level when exposed to survival loading conditions. To combat the reduction in system reliability an overstrength factor (OSF) is applied to the anchors functioning as an additional safety factor. For a 100 turbine wind farm, single-line system reliabilities can be achieved using the multiline system with an OSF of 1.10, a 10% increase in multiline anchor safety factors for all anchors in a farm.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"20 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78654595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Ye, M. Mahmoudi, K. Karayagiz, L. Johnson, R. Seede, I. Karaman, R. Arróyave, A. Elwany
Modeling and simulation for additive manufacturing (AM) are critical enablers for understanding process physics, conducting process planning and optimization, and streamlining qualification and certification. It is often the case that a suite of hierarchically linked (or coupled) simulation models is needed to achieve the above task, as the entirety of the complex physical phenomena relevant to the understanding of process-structure-property-performance relationships in the context of AM precludes the use of a single simulation framework. In this study using a Bayesian network approach, we address the important problem of conducting uncertainty quantification (UQ) analysis for multiple hierarchical models to establish process-microstructure relationships in laser powder bed fusion (LPBF) AM. More significantly, we present the framework to calibrate and analyze simulation models that have unmeasurable variables, which are quantities of interest predicted by an upstream model and necessary for the downstream model in the chain that are difficult or impossible to observe experimentally. We validate the framework using a case study on predicting the microstructure of binary nickel-niobium alloys processed using LPBF as a function of processing parameters. Our framework is shown to be able to predict segregation of niobium with up to 94.3% prediction accuracy in test data.
{"title":"Bayesian Calibration of Multiple Coupled Simulation Models for Metal Additive Manufacturing: A Bayesian Network Approach","authors":"J. Ye, M. Mahmoudi, K. Karayagiz, L. Johnson, R. Seede, I. Karaman, R. Arróyave, A. Elwany","doi":"10.1115/1.4052270","DOIUrl":"https://doi.org/10.1115/1.4052270","url":null,"abstract":"\u0000 Modeling and simulation for additive manufacturing (AM) are critical enablers for understanding process physics, conducting process planning and optimization, and streamlining qualification and certification. It is often the case that a suite of hierarchically linked (or coupled) simulation models is needed to achieve the above task, as the entirety of the complex physical phenomena relevant to the understanding of process-structure-property-performance relationships in the context of AM precludes the use of a single simulation framework. In this study using a Bayesian network approach, we address the important problem of conducting uncertainty quantification (UQ) analysis for multiple hierarchical models to establish process-microstructure relationships in laser powder bed fusion (LPBF) AM. More significantly, we present the framework to calibrate and analyze simulation models that have unmeasurable variables, which are quantities of interest predicted by an upstream model and necessary for the downstream model in the chain that are difficult or impossible to observe experimentally. We validate the framework using a case study on predicting the microstructure of binary nickel-niobium alloys processed using LPBF as a function of processing parameters. Our framework is shown to be able to predict segregation of niobium with up to 94.3% prediction accuracy in test data.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"18 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83809677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Levelised Cost of Energy (LCoE) is the most common metric used in renewable energy assessments. However, this can be a very complex calculation with numerous methodologies depending on the perspective taken. Inputs including costs, energy production are generally forecasts and predictions based on publicly available information; therefore they are key areas of uncertainty. Elements of the calculation are site or region specific such as the tax rate or inclusion of grid connection costs. The business case and financial assumptions applied will be very project specific e.g. the discount rate applied. These numerous variables and uncertainties must be fully understood in order to effectively apply the metric or review and compare LCoEs. Therefore, this paper provides a comprehensive set of LCoE methodologies that provide a reference basis for researchers. A case study demonstrates the application of these methods and the variation in results illustrates the importance of correctly selecting the discount rate and cash flow based on the perspective and motivation of the user. Sensitivity studies further investigates the potential impact of key variables and areas of uncertainty on results. Analysis indicates that the energy production and discount rate applied will have the most significant impact on LCoE, followed by CAPEX costs. While the key areas of uncertainties cannot necessarily be solved, this paper promotes consistency in the application and understanding of the metric, which can help overcome its limitations.
{"title":"Levelized Cost of Energy Assessment for Offshore Wind Farms–An Examination of Different Methodologies, Input Variables, and Uncertainty","authors":"F. D. McAuliffe, Miriam Noonan, Jimmy Murphy","doi":"10.1115/1.4052269","DOIUrl":"https://doi.org/10.1115/1.4052269","url":null,"abstract":"\u0000 Levelised Cost of Energy (LCoE) is the most common metric used in renewable energy assessments. However, this can be a very complex calculation with numerous methodologies depending on the perspective taken. Inputs including costs, energy production are generally forecasts and predictions based on publicly available information; therefore they are key areas of uncertainty. Elements of the calculation are site or region specific such as the tax rate or inclusion of grid connection costs. The business case and financial assumptions applied will be very project specific e.g. the discount rate applied. These numerous variables and uncertainties must be fully understood in order to effectively apply the metric or review and compare LCoEs. Therefore, this paper provides a comprehensive set of LCoE methodologies that provide a reference basis for researchers. A case study demonstrates the application of these methods and the variation in results illustrates the importance of correctly selecting the discount rate and cash flow based on the perspective and motivation of the user. Sensitivity studies further investigates the potential impact of key variables and areas of uncertainty on results. Analysis indicates that the energy production and discount rate applied will have the most significant impact on LCoE, followed by CAPEX costs. While the key areas of uncertainties cannot necessarily be solved, this paper promotes consistency in the application and understanding of the metric, which can help overcome its limitations.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"77 1 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76036074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The use of three-dimensional (3D) printing for lattice structures has led to advances in diverse applications benefitting from mechanically efficient designs. Three-dimensional printed lattices are often used to carry loads, however, printing defects and inconsistencies potentially hinder performance. Here, we investigate the design, fabrication, mechanics, and reliability of lattices with repeating cubic unit cells using probabilistic analysis. Lattices were designed with 500 μm diameter beams and unit cell lengths from 0.8 mm to 1.6 mm. Designs were printed with stereolithography and had average beam diameters from 509 μm to 622 μm, thereby demonstrating a deviation from design intentions. Mechanical experiments were conducted and demonstrated an exponential increase in yield stress for lattice relative density that facilitated probabilistic failure analysis. Sensitivity analysis demonstrated lattice mechanics were most sensitive to fluctuations for beam diameter (74%) and second to lattice yield stress (8%) for lattices with 1.6 mm unit cells, while lattices with smaller 1.0 mm unit cells were most sensitive to yield stress (48%) and second to beam diameter (43%). The methodological framework is generalizable to further 3D printed lattice systems, and findings provide new insights linking design, fabrication, mechanics, and reliability for improved system design that is crucial for engineers to consider as 3D printing becomes more widely adopted.
{"title":"Fabrication, Mechanics, and Reliability Analysis for Three-Dimensional Printed Lattice Designs","authors":"N. Kulkarni, S. Ekwaro-Osire, P. Egan","doi":"10.1115/1.4051747","DOIUrl":"https://doi.org/10.1115/1.4051747","url":null,"abstract":"\u0000 The use of three-dimensional (3D) printing for lattice structures has led to advances in diverse applications benefitting from mechanically efficient designs. Three-dimensional printed lattices are often used to carry loads, however, printing defects and inconsistencies potentially hinder performance. Here, we investigate the design, fabrication, mechanics, and reliability of lattices with repeating cubic unit cells using probabilistic analysis. Lattices were designed with 500 μm diameter beams and unit cell lengths from 0.8 mm to 1.6 mm. Designs were printed with stereolithography and had average beam diameters from 509 μm to 622 μm, thereby demonstrating a deviation from design intentions. Mechanical experiments were conducted and demonstrated an exponential increase in yield stress for lattice relative density that facilitated probabilistic failure analysis. Sensitivity analysis demonstrated lattice mechanics were most sensitive to fluctuations for beam diameter (74%) and second to lattice yield stress (8%) for lattices with 1.6 mm unit cells, while lattices with smaller 1.0 mm unit cells were most sensitive to yield stress (48%) and second to beam diameter (43%). The methodological framework is generalizable to further 3D printed lattice systems, and findings provide new insights linking design, fabrication, mechanics, and reliability for improved system design that is crucial for engineers to consider as 3D printing becomes more widely adopted.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"1 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81910700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Piyush Pandita, Sayan Ghosh, V. Gupta, Andrey Meshkov, Liping Wang
Accurate identification and modeling of process maps in additive manufacturing remains a pertinent challenge. To ensure high quality and reliability of the finished product researchers, rely on models that entail the physics of the process as a computer code or conduct laboratory experiments, which are expensive and oftentimes demand significant logistic and overheads. Physics-based computational modeling has shown promise in alleviating the aforementioned challenge, albeit with limitations like physical approximations, model-form uncertainty, and limited experimental data. This calls for modeling methods that can combine limited experimental and simulation data in a computationally efficient manner, in order to achieve the desired properties in the manufactured parts. In this paper, we focus on demonstrating the impact of probabilistic modeling and uncertainty quantification on powder-bed fusion (PBF) additive manufacturing by focusing on the following three milieu: (a) accelerating the parameter development processes associated with laser powder bed fusion additive manufacturing process of metals, (b) quantifying uncertainty and identifying missing physical correlations in the computational model, and (c) transferring learned process maps from a source to a target process. These tasks demonstrate the application of multifidelity modeling, global sensitivity analysis, intelligent design of experiments, and deep transfer learning for a meso-scale meltpool model of the additive manufacturing process.
{"title":"Application of Deep Transfer Learning and Uncertainty Quantification for Process Identification in Powder Bed Fusion","authors":"Piyush Pandita, Sayan Ghosh, V. Gupta, Andrey Meshkov, Liping Wang","doi":"10.1115/1.4051748","DOIUrl":"https://doi.org/10.1115/1.4051748","url":null,"abstract":"\u0000 Accurate identification and modeling of process maps in additive manufacturing remains a pertinent challenge. To ensure high quality and reliability of the finished product researchers, rely on models that entail the physics of the process as a computer code or conduct laboratory experiments, which are expensive and oftentimes demand significant logistic and overheads. Physics-based computational modeling has shown promise in alleviating the aforementioned challenge, albeit with limitations like physical approximations, model-form uncertainty, and limited experimental data. This calls for modeling methods that can combine limited experimental and simulation data in a computationally efficient manner, in order to achieve the desired properties in the manufactured parts. In this paper, we focus on demonstrating the impact of probabilistic modeling and uncertainty quantification on powder-bed fusion (PBF) additive manufacturing by focusing on the following three milieu: (a) accelerating the parameter development processes associated with laser powder bed fusion additive manufacturing process of metals, (b) quantifying uncertainty and identifying missing physical correlations in the computational model, and (c) transferring learned process maps from a source to a target process. These tasks demonstrate the application of multifidelity modeling, global sensitivity analysis, intelligent design of experiments, and deep transfer learning for a meso-scale meltpool model of the additive manufacturing process.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"24 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90415307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xufeng Huang, Tingli Xie, Zhuo Wang, Lei Chen, Qi Zhou, Zhen Hu
Melt pool modeling is critical for model-based uncertainty quantification (UQ) and quality control in metallic additive manufacturing (AM). Finite element (FE) simulation for thermal modeling in metal AM, however, is tedious and time-consuming. This paper presents a multifidelity point-cloud neural network method (MF-PointNN) for surrogate modeling of melt pool based on FE simulation data. It merges the feature representations of the low-fidelity (LF) analytical model and high-fidelity (HF) FE simulation data through the theory of transfer learning (TL). A basic PointNN is first trained using LF data to construct a correlation between the inputs and thermal field of analytical models. Then, the basic PointNN is updated and fine-tuned using the small size of HF data to build the MF-PointNN. The trained MF-PointNN allows for efficient mapping from input variables and spatial positions to thermal histories, and thereby efficiently predicts the three-dimensional melt pool. Results of melt pool modeling of electron beam additive manufacturing (EBAM) of Ti-6Al-4V under uncertainty demonstrate the efficacy of the proposed approach.
{"title":"A Transfer Learning-Based Multi-Fidelity Point-Cloud Neural Network Approach for Melt Pool Modeling in Additive Manufacturing","authors":"Xufeng Huang, Tingli Xie, Zhuo Wang, Lei Chen, Qi Zhou, Zhen Hu","doi":"10.1115/1.4051749","DOIUrl":"https://doi.org/10.1115/1.4051749","url":null,"abstract":"\u0000 Melt pool modeling is critical for model-based uncertainty quantification (UQ) and quality control in metallic additive manufacturing (AM). Finite element (FE) simulation for thermal modeling in metal AM, however, is tedious and time-consuming. This paper presents a multifidelity point-cloud neural network method (MF-PointNN) for surrogate modeling of melt pool based on FE simulation data. It merges the feature representations of the low-fidelity (LF) analytical model and high-fidelity (HF) FE simulation data through the theory of transfer learning (TL). A basic PointNN is first trained using LF data to construct a correlation between the inputs and thermal field of analytical models. Then, the basic PointNN is updated and fine-tuned using the small size of HF data to build the MF-PointNN. The trained MF-PointNN allows for efficient mapping from input variables and spatial positions to thermal histories, and thereby efficiently predicts the three-dimensional melt pool. Results of melt pool modeling of electron beam additive manufacturing (EBAM) of Ti-6Al-4V under uncertainty demonstrate the efficacy of the proposed approach.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"10 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75127166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Laser powder bed fusion (LPBF) process is one of popular additive manufacturing techniques for building metal parts through the layer-by-layer melting and solidification process. To date, there are plenty of successful product prototypes manufactured by the LPBF process. However, the lack of confidence in its quality and long-term reliability could be one of the major reasons prevent the LPBF process from being widely adopted in industry. The existing LPBF process is an open loop control system with some in situ monitoring capability. Hence, manufacturing quality and long-term reliability of the part cannot be guaranteed if there is any disturbance during the process. Such limitation can be overcome if a feedback control system can be implemented. This article studies the control effectiveness of the proportional-integral-derivative (PID) control and the model predictive control (MPC) for the LPBF process based on a physics-based machine learning model. The control objective is to maintain the melt pool width and depth at required level under process uncertainties from the powder and laser. A sampling-based dynamic control window approach is further proposed for MPC as a practical approach to approximate the optimal control actions within limited time constraint. Control effectiveness, pros, and cons of the PID control and the MPC for the LPBF process are investigated and compared through various control scenarios. It is demonstrated that the MPC is more effective than the PID control under the same conditions, but the MPC demands a valid digit twin of the LPBF process.
{"title":"Model Predictive Control of Melt Pool Size for the Laser Powder Bed Fusion Process Under Process Uncertainty","authors":"Zhimin Xi","doi":"10.1115/1.4051746","DOIUrl":"https://doi.org/10.1115/1.4051746","url":null,"abstract":"\u0000 Laser powder bed fusion (LPBF) process is one of popular additive manufacturing techniques for building metal parts through the layer-by-layer melting and solidification process. To date, there are plenty of successful product prototypes manufactured by the LPBF process. However, the lack of confidence in its quality and long-term reliability could be one of the major reasons prevent the LPBF process from being widely adopted in industry. The existing LPBF process is an open loop control system with some in situ monitoring capability. Hence, manufacturing quality and long-term reliability of the part cannot be guaranteed if there is any disturbance during the process. Such limitation can be overcome if a feedback control system can be implemented. This article studies the control effectiveness of the proportional-integral-derivative (PID) control and the model predictive control (MPC) for the LPBF process based on a physics-based machine learning model. The control objective is to maintain the melt pool width and depth at required level under process uncertainties from the powder and laser. A sampling-based dynamic control window approach is further proposed for MPC as a practical approach to approximate the optimal control actions within limited time constraint. Control effectiveness, pros, and cons of the PID control and the MPC for the LPBF process are investigated and compared through various control scenarios. It is demonstrated that the MPC is more effective than the PID control under the same conditions, but the MPC demands a valid digit twin of the LPBF process.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"1998 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72756218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Regression models are widely used as data-driven methods for predicting a continuous target variable. From a set of input variables, regression models predict a deterministic point value for the target variable. But the deterministic point value prediction is not always sufficient because a target variable value often varies due to diverse sources of uncertainty. For instance, in the fused deposition modeling process, the inconsistent results of replications are associated with natural randomness, environmental condition, and noisy process parameters. The point value estimation is not sufficient to represent the variability in this kind of scenario. Instead of point estimation, the interval prediction of a target variable is more useful in this application. In this paper, linear optimization-based techniques are proposed to predict conservative confidence intervals for linear and polynomial regression models. Two linear optimization models, one for ordinary least squares (OLS) regression and the other for weighted least squares (WLS) regression, are proposed. The proposed methods are implemented on several datasets, including an experimental fused deposition modeling dataset to demonstrate the effectiveness of the proposed methods. The results show that the proposed method is useful for the fused deposition modeling process where the level of uncertainty or the lack of knowledge of uncertainty sources is high. The proposed method can also be leveraged to the Bayesian neural network (BNN), where the optimization techniques for interval prediction will be nonlinear optimization instead of linear optimization.
{"title":"Conservative Confidence Interval Prediction in Fused Deposition Modeling Process With Linear Optimization Approach","authors":"Arup Dey, Nita Yodo","doi":"10.1115/1.4051750","DOIUrl":"https://doi.org/10.1115/1.4051750","url":null,"abstract":"\u0000 Regression models are widely used as data-driven methods for predicting a continuous target variable. From a set of input variables, regression models predict a deterministic point value for the target variable. But the deterministic point value prediction is not always sufficient because a target variable value often varies due to diverse sources of uncertainty. For instance, in the fused deposition modeling process, the inconsistent results of replications are associated with natural randomness, environmental condition, and noisy process parameters. The point value estimation is not sufficient to represent the variability in this kind of scenario. Instead of point estimation, the interval prediction of a target variable is more useful in this application. In this paper, linear optimization-based techniques are proposed to predict conservative confidence intervals for linear and polynomial regression models. Two linear optimization models, one for ordinary least squares (OLS) regression and the other for weighted least squares (WLS) regression, are proposed. The proposed methods are implemented on several datasets, including an experimental fused deposition modeling dataset to demonstrate the effectiveness of the proposed methods. The results show that the proposed method is useful for the fused deposition modeling process where the level of uncertainty or the lack of knowledge of uncertainty sources is high. The proposed method can also be leveraged to the Bayesian neural network (BNN), where the optimization techniques for interval prediction will be nonlinear optimization instead of linear optimization.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"24 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2021-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74216398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：