Souma Chowdhury

New Modular Product-Platform-Planning Approach to Design Macroscale Reconfigurable Unmanned Aerial Vehicles

The benefits of a family of macroscale reconfigurable unmanned aerial vehicles to meet distinct flight requirements are readily evident. The reconfiguration capability of an unmanned-aerial-vehicle family for different aerial tasks offers a clear cost advantage to end users over acquiring separate unmanned aerial vehicles dedicated to specific types of missions. At the same time, it allows the manufacturer the opportunity to capture distinct market segments, while saving on overhead costs, transportation costs, and after-market services. Such macroscale reconfigurability can be introduced through effective application of modular product-platform-planning concepts. This paper advances and implements the Comprehensive Product Platform Planning framework to design a family of three reconfigurable twin-boom unmanned aerial vehicles with different mission requirements. The original Comprehensive Product Platform Planning method was suitable for scale-based product-family design. In this paper, important modifi...

Comprehensive Product Platform Planning (CP 3 ) Framework: Presenting a Generalized Product Family Model

Development of a family of products that satisfies different sectors of the market introduces significant challenges to today’s manufacturing industries – from development time to aftermarket services. A product family with a common platform paradigm offers a powerful solution to these daunting challenges. The Comprehensive Product Platform Planning (CP 3 ) framework formulates a flexible product family model that (i) seeks to eliminate traditional boundaries between modular and scalable families, (ii) allows the formation of sub-families of products, and (iii) yield the optimal depth and number of platforms. In this paper, the CP 3 framework introduces a solution strategy that obviates common assumptions; namely (i) the identification of platform/non-platform design variables and the determination of variable values are separate processes, and (ii) the cost reduction of creating product platforms is independent of the total number of each product manufactured. A new Cost Decay Function (CDF) is developed to approximate the reduction in cost with increasing commonalities among products, for a specified capacity of production. The Mixed Integer Non-Liner Programming (MINLP) problem, presented by the CP 3 model, is solved using a novel Platform Segregating Mapping Function (PSMF). The proposed CP 3 framework is implemented on a family of universal electric motors.

Uncertainty Quantication in Surrogate Models Based on Pattern Classication of Cross-validation Errors

This paper advances the Domain Segmentation based on Uncertainty in the Surrogate (DSUS) framework which is a novel approach to characterize the uncertainty in surrogates. The leave-one-out cross-validation technique is adopted in the DSUS framework to measure local errors of a surrogate. A method is proposed in this paper to evaluate the performance of the leave-out-out cross-validation errors as local error measures. This method evaluates local errors by comparing: (i) the leave-one-out cross-validation error with (ii) the actual local error estimated within a local hypercube for each training point. The comparison results show that the leave-one-out cross-validation strategy can capture the local errors of a surrogate. The DSUS framework is then applied to key aspects of wind resource assessment and wind farm cost modeling. The uncertainties in the wind farm cost and the wind power potential are successfully characterized, which provides designers/users more condence when using these models.

Adaptive Model Refinement in Surrogate-based Multiobjective Optimization

Surrogate-Based Optimization (SBO), while providing a computationally-efficient alternative to expensive high-fidelity optimization of complex systems, is often plagued by the low reliability of the optimum values obtained thereof. Model refinement techniques are one of the most recognized means to increasing the reliability of the optimum solutions while preserving the computational efficiency of SBO. One such method is the recently developed Adaptive Model Refinement (AMR) technique, which decides when to refine and the desired extent of the refinement, for single-objective optimization using any type of surrogate models (i.e., a model independent approach). In this paper, we make fundamental modifications to the AMR technique to extend its applicability to multiobjective problems, both in the case of problems involving multiple and single high-fidelity source codes or simulations. The AMR technique is designed to work particularly with population-based optimization algorithms. In AMR, the reconstruction of the model is performed by sequentially adding a batch of new samples at any given iteration (of SBO), when a refinement metric is met. This metric is formulated by comparing (1) the uncertainty associated with the outputs of the current model, and (2) the distribution of the latest fitness function improvement over the population of candidate designs. Conservative, non-conservative, and balanced approaches are explored for multiobjective implementation, in terms of the fraction of objectives for which the model refinement metric has been satisfied. In the case of an affirmative decision for model refinement, the history of the fitness function improvement is used to determine the desired fidelity for the upcoming iterations of SBO. The location of the new samples in the input space is determined based on the smallest hypercube enclosing the entire population of candidate designs, the smallest hypercube enclosing the current set of non-dominated designs, and a distance-based criterion that minimizes the correlation between the current sample points and the new points. A multiobjective implementation of GA algorithm is used in conjunction with Kriging surrogate model to apply the new AMR method. The performance of the new multiobjective AMR method is investigated by applying it to a structural wind blade design problem.

Adaptive radio and transmission power selection for Internet of Things

Research efforts over the last few decades produced multiple wireless technologies, which are readily available to support communication between devices in various Internet of Things (IoT) applications. However, none of the existing technologies delivers optimal performance across all critical quality of service (QoS) dimensions under varying environmental conditions. Using a single wireless technology therefore cannot meet the demands of varying workloads or changing environmental conditions. This problem is exacerbated with the increasing interest in placing embedded devices on the users body or other mobile objects in mobile IoT applications. Instead of pursuing a one-radio-fits-all approach, we design ARTPoS, an adaptive radio and transmission power selection system, which makes available multiple wireless technologies at runtime and selects the radio(s) and transmission power(s) most suitable for the current conditions and requirements. Experimental results show that ARTPoS can significantly reduce the power consumption, while maintaining desired link reliability.

Optimal Metamodeling to Interpret Activity-Based Health Sensor Data

Wearable sensors are revolutionizing the health monitoring and medical diagnostics arena. Algorithms and software platforms that can convert the sensor data streams into useful/actionable knowledge are central to this emerging domain, with machine learning and signal processing tools dominating this space. While serving important ends, these tools are not designed to provide functional relationships between vital signs and measures of physical activity. This paper investigates the application of the metamodeling paradigm to health data to unearth important relationships between vital signs and physical activity. To this end, we leverage neural networks and a recently developed metamodeling framework that automatically selects and trains the metamodel that best represents the data set. A publicly available data set is used that provides the ECG data and the IMU data from three sensors (ankle/arm/chest) for ten volunteers, each performing various activities over one-minute time periods. We consider three activities, namely running, climbing stairs, and the baseline resting activity. For the following three extracted ECG features – heart rate, QRS time, and QR ratio in each heartbeat period – models with median error of <25% are obtained. Fourier amplitude sensitivity testing, facilitated by the metamodels, provides further important insights into the impact of the different physical activity parameters on the ECG features, and the variation across the ten volunteers.

Optimal Scheduling of Preventive Maintenance for Offshore Wind Farms

The maintenance cost of wind farms is one of the major factors influencing the profitability of wind projects. During preventive maintenance, the shutdown of wind turbines results in downtime wind energy losses. Appropriate determination of when to perform maintenance and which turbine(s) to maintain can reduce the overall downtime losses significantly. This paper uses a wind farm power generation model to evaluate downtime energy losses during preventive maintenance for a given group of wind turbines in the entire array. Wakes effects are taken into account to accurately estimate energy production over a specified time period. In addition to wind condition, the influence of wake effects is a critical factor in determining the selection of turbine(s) under maintenance. To minimize the overall downtime loss of an offshore wind farm due to preventive maintenance, an optimal scheduling problem is formulated that selects the maintenance time of each turbine. Weather conditions are imposed as constraints to ensure the safety of maintenance personnel, transportation, and tooling infrastructure. A genetic algorithm is used to solve the optimal scheduling problem. The maintenance scheduling is optimized for a utility-scale offshore wind farm with 25 turbines. The optimized schedule not only reduces the overall downtime loss by selecting the maintenance dates when wind speed is low, but also considers the wake effects among turbines. Under given wind direction, the turbines under maintenance are usually the ones that can generate strong wake effects on others during certain wind conditions, or the ones that generate relatively less power being under excessive wake effects.

Surrogate-based Design Optimization with Smart Sequential Sampling

Surrogate-based design is an effective approach for modeling computationally expensive system behavior. In such application, it is often challenging to characterize the expected accuracy of the surrogate. In addition to global and local error measures, regional error measures can be used to understand and interpret the surrogate accuracy in the regions of interest. This paper develops the Regional Error Estimation of Surrogate (REES) method to quantify the level of the error in any given subspace (or region) of the entire domain, when all the available training points have been invested to build the surrogate. In this approach, the accuracy of the surrogate in each subspace is estimated by modeling the variations of the mean and the maximum error in that subspace with increasing number of training points (in an iterative process). A regression model is used for this purpose. At each iteration, the intermediate surrogate is constructed using a subset of the entire training data, and tested over the remaining points. The evaluated errors at the intermediate test points at each iteration are used for training the regression model that represents the error variation with sample points. The effectiveness of the proposed method is illustrated using standard test problems. To this end, the predicted regional errors of the surrogate constructed using all the training points are compared with the regional errors estimated over a large set of test points.