If a solvable problem is currently unsolved, then something important to a solution is most likely being overlooked. From this simple observation we derive the obscure features hypothesis: every innovative solution is built upon at least one commonly overlooked or new (i.e., obscure) feature of the problem. By using a new definition of a feature as an effect of an interaction, we are able to accomplish five things. First, we are able to determine where features come from and how to search for new ones. Second, we are able to construct mathematical arguments that the set of features of an object is not computably enumerable. Third, we are able to characterize innovative problem solving as looking for a series of interactions that produce the desired effects (i.e., the goal). Fourth, we are able to construct a precise problem-solving grammar that is both human and machine friendly. Fifth, we are able to devise a visual and verbal problem-solving representation that both humans and computers can contribute to as they help counteract each other's problem-solving weaknesses. We show how computers can counter some of the known cognitive obstacles to innovation that humans have. We also briefly discuss ways in which humans can return the favor. We conclude that a promising process for innovative problem solving is a human–computer collaboration in which each partner assists the other in unearthing the obscure features of a problem.

The central objective of the present author's research is to develop a system supporting the design of a technological process (a computer-aided process planning system) that functions similarly to a human expert in the field in question. The use of neural networks makes the creation of such a system possible. The proposed method uses a system of three blocks of neural networks, and involves the creation of neural networks to be used for the selection of machines, tools, and machining parameters. These networks are built for each process operation separately; that is, a set of neural networks is created for each selection. For the construction of models, different types of neural networks (multilayer networks with error backpropagation, radial basis function, and Kohonen) with different structures were employed, and the networks that made the best selections were identified. A method was also developed for the elimination of defects occurring during the production process. When a defect comes to light, this method suggests changes to the technological process, thus improving the quality of that process. Guidelines for the elimination of defects are produced in the form of decision rules. Such a computer-aided process planning system will be especially useful for process engineers who do not yet have sufficient experience in the design of technological processes, or who have only recently joined a particular manufacturing enterprise and are not fully familiar with its machines and other means of production (tools and instrumentation). It should be emphasized that such a system performs an advisory role, and it is always the process engineer who makes the final decision. The neural network models were tested on real data from an enterprise. A computer-aided process planning system based on rules and neural network models enables the intelligent design of technological processes.

We present a novel and trainable gesture-based system for next-generation intelligent interfaces. The system requires a non-contact depth sensing device such as an RGB-D (color and depth) camera for user input. The camera records the user's static hand pose and palm center dynamic motion trajectory. Both static pose and dynamic trajectory are used independently to provide commands to the interface. The sketches/symbols formed by palm center trajectory is recognized by the Support Vector Machine classifier. Sketch/symbol recognition process is based on a set of geometrical and statistical features. Static hand pose recognizer is incorporated to expand the functionalities of our system. Static hand pose recognizer is used in conjunction with sketch classification algorithm to develop a robust and effective system for natural and intuitive interaction. To evaluate the performance of the system user studies were performed on multiple participants. The efficacy of the presented system is demonstrated using multiple interfaces developed for different tasks including computer-aided design modeling.

Complex engineered systems design is a collaborative activity. To design a system, experts from the relevant disciplines must work together to create the best overall system from their individual components. This situation is analogous to a multiagent system in which agents solve individual parts of a larger problem in a coordinated way. Current multiagent models of design teams, however, do not capture this distributed aspect of design teams – instead either representing designers as agents which control all variables, measuring organizational outcomes instead of design outcomes, or representing different aspects of distributed design, such as negotiation. This paper presents a new model which captures the distributed nature of complex systems design by decomposing the ability to control design variables to individual computational designers acting on a problem with shared constraints. These designers are represented as a multiagent learning system which is shown to perform similarly to a centralized optimization algorithm on the same domain. When used as a model, this multiagent system is shown to perform better when the level of designer exploration is not decayed but is instead controlled based on the increase of design knowledge, suggesting that designers in multidisciplinary teams should not simply reduce the scope of design exploration over time, but should adapt based on changes in their collective knowledge of the design space. This multiagent system is further shown to produce better-performing designs when computational designers design collaboratively as opposed to independently, confirming the importance of collaboration in complex systems design.

In this paper, we report on a data analysis process for the automated classification of mechanical components. In particular, here, we describe, how to implement a machine learning system for the automated classification of parts belonging to several sub-categories. We collect models that are typically used in the mechanical industry, and then we represent each object by a collection of features. We illustrate how to set-up a supervised multi-layer artificial neural network with an ad-hoc classification schema. We test our solution on a dataset formed by 2354 elements described by 875 features and spanned among 15 sub-categories. We state the accuracy of classification in terms of average area under ROC curves and the ability to classify 606 unknown 3D objects by similarity coefficients. Our parts’ classification system outperforms a classifier based on the Light Field Descriptor, which, as far as we know, actually represents the gold standard for the identification of most types of 3D mechanical objects.

In the current work, the effects of design (groove depth and groove width) and operational (temperature and velocity) parameters on aerodynamic performance parameters (coefficient of drag and coefficient of lift) of an isolated passenger car tire have been investigated. The study is conducted by using neural network-based Monte-Carlo analysis on computational fluid dynamics (CFD). The computer experiments are designed to obtain the causal relationship between tire design, operational, and aerodynamic performance parameters. The Reynolds-averaged Navier–Stokes equations-based Realizable K-ε model has been employed to analyze the variations in flow patterns around an isolated tire. The design parameters are varied over wide range and full factorial design, while considering temperature and velocity is completely explored to draw conclusive results. The multi-layer perceptron type neural network with the back-propagation algorithm is trained to map any non-linearity in causal relationships. The sensitivity analysis is performed to find the relationship between control variables and performance indicators. The importance of control variable is determined by both sensitivity and significance analyses and the paired interaction analysis is performed between selected control variables to find the interactive behavior of corresponding variables. The design parameter of groove width with 6.8% and 41% reduction in drag and lift coefficient, respectively, and conventionally overlooked operational parameter of velocity with 4% and 35% impact on drag and lift coefficient, respectively, are found to be the most significant variables. The air trapped between the longitudinal grooves and the road is found to follow the beam theory. The interaction of the groove depth and width is found to be significant with respect to coefficient of lift based on the air beam concept. The interaction of groove width and velocity is found to be significant with respect to both coefficients of lifts and drag.

Traditionally, design opportunities and directions are conceived based on expertise, intuition, or time-consuming user studies and marketing research at the fuzzy front end of the design process. Herein, we propose the use of the total technology space map (TSM) as a visual ideation aid for rapidly conceiving high-level design opportunities. The map is comprised of various technology domains positioned according to knowledge proximity, which is measured based on a large quantity of patent data. It provides a systematic picture of the total technology space to enable stimulated ideation beyond the designer's knowledge. Designers can browse the map and navigate various technologies to conceive new design opportunities that relate different technologies across the space. We demonstrate the process of using TSM as a rapid ideation aid and then analyze its applications in two experiments to show its effectiveness and limitations. Furthermore, we have developed a cloud-based system for computer-aided ideation, that is, InnoGPS, to integrate interactive map browsing for conceiving high-level design opportunities with domain-specific patent retrieval for stimulating concrete technical concepts, and to potentially embed machine-learning and artificial intelligence in the map-aided ideation process.

Benchmarking function modeling and representation approaches requires a direct comparison, including the inferencing support by the different approaches. To this end, this paper explores the value of a representation by comparing the ability of a representation to support reasoning based on varying amounts of information stored in the representational components of a function structure: vocabulary, grammar, and topology. This is done by classifying the previously developed functional pruning rules into vocabulary, grammatical, and topological classes and applying them to function structures available from an external design repository. The original and pruned function structures of electromechanical devices are then evaluated for how accurately market values can be predicted using the graph complexity connectivity method. The accuracy is found to be inversely related to the amount of information and level of detail. Applying the topological rule does not significantly impact the predictive power of the models, while applying the vocabulary rules and the grammar rules reduces the accuracy of the predictions. Finally, the least predictive model set is that which had all rules applied. In this manner, the value of a representation to predict or answer questions is quantified.