Machine Learning-Based Design Concept Evaluation

2020 ◽  
Vol 142 (3) ◽  
Author(s):  
Bradley Camburn ◽  
Yuejun He ◽  
Sujithra Raviselvam ◽  
Jianxi Luo ◽  
Kristin Wood
Keyword(s):  
Machine Learning ◽  
Technology Development ◽  
Empirical Evaluation ◽  
Learning Technologies ◽  
Design Concept ◽  
Third Party ◽  
Large Set ◽  
Design Concepts ◽  
Automated Method ◽  
Concept Evaluation

Abstract In order to develop novel solutions for complex systems and in increasingly competitive markets, it may be advantageous to generate large numbers of design concepts and then to identify the most novel and valuable ideas. However, it can be difficult to process, review, and assess thousands of design concepts. Based on this need, we develop and demonstrate an automated method for design concept assessment. In the method, machine learning technologies are first applied to extract ontological data from design concepts. Then, a filtering strategy and quantitative metrics are introduced that enable creativity rating based on the ontological data. This method is tested empirically. Design concepts are crowd-generated for a variety of actual industry design problems/opportunities. Over 4000 design concepts were generated by humans for assessment. Empirical evaluation assesses: (1) correspondence of the automated ratings with human creativity ratings; (2) whether concepts selected using the method are highly scored by another set of crowd raters; and finally (3) if high scoring designs have a positive correlation or relationship to industrial technology development. The method provides a possible avenue to rate design concepts deterministically. A highlight is that a subset of designs selected automatically out of a large set of candidates was scored higher than a subset selected by humans when evaluated by a set of third-party raters. The results hint at bias in human design concept selection and encourage further study in this topic.

Exploiting Critical Path Method for Evaluation of Conceptual Design

2010 ◽  
Vol 97-101 ◽  
pp. 4429-4432 ◽  
Author(s):  
Mei Yan Wang ◽  
Lian Guan Shen ◽  
Yi Min Deng
Keyword(s):  
Conceptual Design ◽  
Critical Path ◽  
Design Concept ◽  
Design Evaluation ◽  
Critical Path Method ◽  
Design Concepts ◽  
Critical Design ◽  
Concept Evaluation ◽  
Design Requirements

Conceptual design is a critical design phase during which initial design solutions, called design concepts, are developed. These design concepts must be evaluated to ensure they satisfy the specified design requirements and the most appropriate design concept must be selected. It is often difficult for the designer, especially for the novice, to make an appropriate design concept evaluation and selection. Existing work on design evaluation lacks an effective tool for evaluating the temporal performance of the design concepts. To address this problem, a Critical Path Method (CPM) from project management is adapted for design evaluation, whereby a CPM network is converted from a causal behavioral process (CBP) and the methodologies relating to CPM are also applied to design improvement. A case study of a lever-clamp assembly system is also presented to illustrate as well as validate the method.

Design Concept Evaluation and Selection: A Decision Making Approach

2012 ◽  
Vol 155-156 ◽  
pp. 1122-1126 ◽  
Author(s):  
Rizwan Ullah ◽  
De Qun Zhou ◽  
Peng Zhou
Keyword(s):  
Decision Making ◽  
Fuzzy Sets ◽  
Product Design ◽  
Information Entropy ◽  
Entropy Method ◽  
Design Concept ◽  
Computationally Efficient ◽  
Design Concepts ◽  
Concept Evaluation ◽  
Multi Attribute Decision Making

This study proposes a multi-attribute decision making based approach for product design concept evaluation and selection. The technique for order preference by similarity to ideal solution (TOPSIS) is combined with fuzzy sets and information entropy. While the fuzzy sets theory is employed to capture the associated vagueness in the expert judgment, the combination of information entropy method with multi-attribute decision making makes the approach computationally efficient. We present the results of the evaluation of design concepts which demonstrate the feasibility and practicability of the approach. The proposed approach will result in considerable time and cost saving by identifying the most promising product design concepts and short-listing for further design and development activities.

Using Parameterized Pareto Sets to Model Design Concepts

2007 ◽  
Author(s):  
Richard J. Malak ◽  
Christiaan J. J. Paredis
Keyword(s):  
Conceptual Design ◽  
Pareto Set ◽  
Design Concept ◽  
Design Solution ◽  
Large Set ◽  
Specific Design ◽  
Design Problems ◽  
Design Concepts ◽  
Pareto Sets ◽  
The Many

Decisions made during conceptual design can have a major impact on the success of a design project, and designers must take care to select a concept that leads to a desirable design solution. However, the inherently imprecise nature of design concepts complicates decision making. A single concept relates to a large set of specific design implementations, each of which has a different level of desirability based on the tradeoffs designers are willing to make. Thus, designers must consider tradeoffs across the many possible implementations of a design concept in order to decide between concepts rigorously. To accomplish this efficiently, designers require an abstract understanding of the characteristics of a design concept. In this paper, we describe an approach to modeling design concepts that is based on an extension of the notion of a Pareto set, called a parameterized Pareto set. Using this construct, designers can generate a model based on information about prior implementations of a design concept in a way that includes tradeoff information while being independent of implementation details and reusable for different design problems. We demonstrate the approach on the conceptual design of a gearbox. The example involves two different design scenarios that serve to demonstrate the reusability of the model and effectiveness of the overall approach.

scholarly journals Simulation-based design concept evaluation for ambulance patient compartments

SIMULATION ◽  
2015 ◽  
Vol 91 (8) ◽  
pp. 691-714 ◽  
Author(s):  
Deogratias Kibira ◽  
Y Tina Lee ◽  
Jennifer Marshall ◽  
Allison Barnard Feeney ◽  
Larry Avery ◽  
...  
Keyword(s):  
Homeland Security ◽  
Occupational Safety ◽  
Service Providers ◽  
Design Concept ◽  
Design Standards ◽  
Department Of Homeland Security ◽  
Design Concepts ◽  
Concept Evaluation ◽  
Simulation Based ◽  
Standards And Guidelines

To address the inadequacy of ambulance design standards, the Department of Homeland Security Science and Technology Directorate, the National Institute of Standards and Technology, the National Institute for Occupational Safety and Health, and BMT Designers and Planners have collaborated to develop new design standards for ambulance patient compartments. This paper presents a simulation-based approach to evaluate and guide improving patient compartment designs that conform to developed requirements for better performance and safety of ambulance users. Those requirements address hazards stemming from (1) the inability of providers to remain safely restrained while treating patients, and (2) the musculoskeletal damage from awkward body postures. An initial design was developed through the axiomatic design approach with inputs from stakeholders such as emergency medical service providers and ambulance manufacturers. The design was imported into a human task simulation tool. It was tested for performance to identify areas for further improvements, which resulted in a second design concept. This paper shows how computer simulation was used to evaluate the effectiveness of the two successive design concepts in enabling providers to perform a range of medical care tasks while remaining seated and restrained. We also evaluated the musculoskeletal effect of these designs on the providers. The results showed that using a simulation-based evaluation produced patient compartments that better meet user requirements when compared with traditional designs. This research produced a set of requirements and recommendations that we believe will lead to better design standards and guidelines for the next generation of ambulances.

Adsorption Isotherm Predictions for Multiple Molecules in MOFs Using the Same Deep Learning Model

2019 ◽  
Author(s):  
Ryther Anderson ◽  
Achay Biong ◽  
Diego Gómez-Gualdrón
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Molecular Simulation ◽  
Large Scale ◽  
Learning Model ◽  
Operating Conditions ◽  
Small Subset ◽  
Screening Methods ◽  
Large Set ◽  
Metal Organic

<div>Tailoring the structure and chemistry of metal-organic frameworks (MOFs) enables the manipulation of their adsorption properties to suit specific energy and environmental applications. As there are millions of possible MOFs (with tens of thousands already synthesized), molecular simulation, such as grand canonical Monte Carlo (GCMC), has frequently been used to rapidly evaluate the adsorption performance of a large set of MOFs. This allows subsequent experiments to focus only on a small subset of the most promising MOFs. In many instances, however, even molecular simulation becomes prohibitively time consuming, underscoring the need for alternative screening methods, such as machine learning, to precede molecular simulation efforts. In this study, as a proof of concept, we trained a neural network as the first example of a machine learning model capable of predicting full adsorption isotherms of different molecules not included in the training of the model. To achieve this, we trained our neural network only on alchemical species, represented only by their geometry and force field parameters, and used this neural network to predict the loadings of real adsorbates. We focused on predicting room temperature adsorption of small (one- and two-atom) molecules relevant to chemical separations. Namely, argon, krypton, xenon, methane, ethane, and nitrogen. However, we also observed surprisingly promising predictions for more complex molecules, whose properties are outside the range spanned by the alchemical adsorbates. Prediction accuracies suitable for large-scale screening were achieved using simple MOF (e.g. geometric properties and chemical moieties), and adsorbate (e.g. forcefield parameters and geometry) descriptors. Our results illustrate a new philosophy of training that opens the path towards development of machine learning models that can predict the adsorption loading of any new adsorbate at any new operating conditions in any new MOF.</div>

scholarly journals Predicting Future Occurrence of Acute Hypotensive Episodes Using Noninvasive and Invasive Features

2021 ◽  
Vol 186 (Supplement_1) ◽  
pp. 445-451
Author(s):  
Yifei Sun ◽  
Navid Rashedi ◽  
Vikrant Vaze ◽  
Parikshit Shah ◽  
Ryan Halter ◽  
...  
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Real World ◽  
Short Term Memory ◽  
Model Performance ◽  
Learning Technologies ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Continuous Map

ABSTRACT Introduction Early prediction of the acute hypotensive episode (AHE) in critically ill patients has the potential to improve outcomes. In this study, we apply different machine learning algorithms to the MIMIC III Physionet dataset, containing more than 60,000 real-world intensive care unit records, to test commonly used machine learning technologies and compare their performances. Materials and Methods Five classification methods including K-nearest neighbor, logistic regression, support vector machine, random forest, and a deep learning method called long short-term memory are applied to predict an AHE 30 minutes in advance. An analysis comparing model performance when including versus excluding invasive features was conducted. To further study the pattern of the underlying mean arterial pressure (MAP), we apply a regression method to predict the continuous MAP values using linear regression over the next 60 minutes. Results Support vector machine yields the best performance in terms of recall (84%). Including the invasive features in the classification improves the performance significantly with both recall and precision increasing by more than 20 percentage points. We were able to predict the MAP with a root mean square error (a frequently used measure of the differences between the predicted values and the observed values) of 10 mmHg 60 minutes in the future. After converting continuous MAP predictions into AHE binary predictions, we achieve a 91% recall and 68% precision. In addition to predicting AHE, the MAP predictions provide clinically useful information regarding the timing and severity of the AHE occurrence. Conclusion We were able to predict AHE with precision and recall above 80% 30 minutes in advance with the large real-world dataset. The prediction of regression model can provide a more fine-grained, interpretable signal to practitioners. Model performance is improved by the inclusion of invasive features in predicting AHE, when compared to predicting the AHE based on only the available, restricted set of noninvasive technologies. This demonstrates the importance of exploring more noninvasive technologies for AHE prediction.

scholarly journals Design, Manufacturing and Test of CFRP Front Hood Concepts for a Light-Weight Vehicle

Polymers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 1374
Author(s):  
Paul Bere ◽  
Mircea Dudescu ◽  
Călin Neamțu ◽  
Cătălin Cocian
Keyword(s):  
Automotive Industry ◽  
Design Concept ◽  
Torsional Stiffness ◽  
Material Structure ◽  
Black Metal ◽  
Design Concepts ◽  
Metal Design ◽  
Body Components ◽  
Cost Efficient ◽  
Transversal Stiffness

Composite materials are very often used in the manufacture of lightweight parts in the automotive industry, manufacturing of cost-efficient elements implies proper technology combined with a structural optimization of the material structure. The paper presents the manufacturing process, experimental and numerical analyses of the mechanical behavior for two composite hoods with different design concepts and material layouts as body components of a small electric vehicle. The first model follows the black metal design and the second one is based on the composite design concept. Manufacturing steps and full details regarding the fabrication process are delivered in the paper. Static stiffness and strain values for lateral, longitudinal and torsional loading cases were investigated. The first composite hood is 254 times lighter than a similar steel hood and the second hood concept is 22% lighter than the first one. The improvement in terms of lateral stiffness for composite hoods about a similar steel hood is for the black metal design concept about 80% and 157% for the hood with a sandwich structure and modified backside frame. Transversal stiffness is few times higher for both composite hoods while the torsional stiffness has an increase of 62% compared to a similar steel hood.

scholarly journals Design of a dynamic and self-adapting system, supported with artificial intelligence, machine learning and real-time intelligence for predictive cyber risk analytics in extreme environments – cyber risk in the colonisation of Mars

2021 ◽  
Author(s):  
Petar Radanliev ◽  
David De Roure ◽  
Kevin Page ◽  
Max Van Kleek ◽  
Omar Santos ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Real Time ◽  
Cyber Security ◽  
Extreme Environments ◽  
Learning Technologies ◽  
Cyber Attacks ◽  
Edge Computing ◽  
Mathematical Formulas ◽  
Cyber Risk

AbstractMultiple governmental agencies and private organisations have made commitments for the colonisation of Mars. Such colonisation requires complex systems and infrastructure that could be very costly to repair or replace in cases of cyber-attacks. This paper surveys deep learning algorithms, IoT cyber security and risk models, and established mathematical formulas to identify the best approach for developing a dynamic and self-adapting system for predictive cyber risk analytics supported with Artificial Intelligence and Machine Learning and real-time intelligence in edge computing. The paper presents a new mathematical approach for integrating concepts for cognition engine design, edge computing and Artificial Intelligence and Machine Learning to automate anomaly detection. This engine instigates a step change by applying Artificial Intelligence and Machine Learning embedded at the edge of IoT networks, to deliver safe and functional real-time intelligence for predictive cyber risk analytics. This will enhance capacities for risk analytics and assists in the creation of a comprehensive and systematic understanding of the opportunities and threats that arise when edge computing nodes are deployed, and when Artificial Intelligence and Machine Learning technologies are migrated to the periphery of the internet and into local IoT networks.

scholarly journals NLOS Multipath Classification of GNSS Signal Correlation Output Using Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2503
Author(s):  
Taro Suzuki ◽  
Yoshiharu Amano
Keyword(s):  
Machine Learning ◽  
Satellite System ◽  
Training Data ◽  
Support Vector ◽  
Positioning Errors ◽  
Automated Method ◽  
Global Navigation Satellite ◽  
Better Than ◽  
Signal Correlation

This paper proposes a method for detecting non-line-of-sight (NLOS) multipath, which causes large positioning errors in a global navigation satellite system (GNSS). We use GNSS signal correlation output, which is the most primitive GNSS signal processing output, to detect NLOS multipath based on machine learning. The shape of the multi-correlator outputs is distorted due to the NLOS multipath. The features of the shape of the multi-correlator are used to discriminate the NLOS multipath. We implement two supervised learning methods, a support vector machine (SVM) and a neural network (NN), and compare their performance. In addition, we also propose an automated method of collecting training data for LOS and NLOS signals of machine learning. The evaluation of the proposed NLOS detection method in an urban environment confirmed that NN was better than SVM, and 97.7% of NLOS signals were correctly discriminated.

Sign in / Sign up

Export Citation Format

Share Document