Data-driven Optimization Technique Research Articles

An intelligent data-driven investigation and optimization integrated with an eco-friendly thermal design approach for a marine diesel engine to study its waste-to-liquefied hydrogen generation potential

The waste heat generated by vehicles, especially heavy-duty engines, has motivated the current research to propose a novel thermal design for a ship's engine. Hence, the suggested system comprises an organic-flash power plant, a bi-evaporator cooling subsystem, a thermal desalination cycle, a water electrolysis-based hydrogen generation unit, and a Claude unit for liquefying hydrogen. The innovative aspects associated with the proposed design include utilizing a novel cascade heat recovery process aimed at reduced irreversibility for the engine's waste and the integration of bi-evaporator technology and Claude unit to facilitate the process of waste-to-liquefied hydrogen generation for a marine engine for improved handling. In addition, the research includes an intelligent study that comprehensively analyzes and optimizes the proposed system in terms of long-term sustainability and economic feasibility. For this purpose, a data-driven optimization technique is implemented using artificial neural networks in combination with multi-objective grey wolf optimization. The aims of the research encompass the optimization of the sustainability index and unit cost of liquefied hydrogen. The research findings indicate that the vapor generator’s terminal temperature difference exerts the most substantial influence on performance metrics, as evidenced by a mean sensitivity index of 0.368. Also, the mentioned objective functions exhibit values of 1.139 and 7.60 $/kg, respectively. Besides, the optimum exergy destruction rate is 124.3 kW, the total investment cost rate is 4.94 $/year, the specific cost of products is 74.87 /GJ, the payback period is 2.2 years, and the net present value is 7.48 M$.

Research on the Optimization of Multi-Class Land Cover Classification Using Deep Learning with Multispectral Images

With the advancement of artificial intelligence, deep learning has become instrumental in land cover classification. While there has been a notable emphasis on refining model structures to improve classification accuracy, it is imperative to also emphasize the pivotal role of data-driven optimization techniques. This paper presents an in-depth investigation into optimizing multi-class land cover classification using high-resolution multispectral images from Worldview3. We explore various optimization strategies, including refined sampling strategies, data band combinations, loss functions, and model enhancements. Our optimizations led to a substantial increase in the Mean Intersection over Union (mIoU) classification accuracy, improving from a baseline of 0.520 to a final accuracy of 0.709, which represents a 35.2% enhancement. Specifically, by optimizing the classic semantic segmentation network in four key aspects, we improved the mIoU by 15.5%. Further improvements through changes in data combinations, sampling methods, and loss functions led to an overall 17.2% increase in mIoU. The proposed model optimization methods enabled the OUNet to outperform the baseline model by providing more precise edge detection and feature representation, while reducing the model parameters scale. Experimental evidence shows that in the application of multi-class land surface classification, increasing the quantity and diversity of samples, avoiding data imbalance issues, is equally valuable for improving overall classification accuracy as it is for enhancing model performance.

Flame transfer function shaping for robust thermoacoustic systems: Application to a kinematic flame model

This work presents a data-driven optimization technique for the optimization of the flame response within a low-order acoustic network model. The methodology exploits the Nyquist criterion to compute a measure of thermoacoustic robustness at targeted frequencies, which serves as an objective value for the optimized system. The method is demonstrated using a simple Rijke tube model coupled with a [Formula: see text]-equation solver to model flame dynamics. The approach is shown to efficiently increase the stability margin of the system by modifying the flame transfer function. The methodology is applied to two examples, based on which possible scenarios are discussed and the potential and limitations associated with the practical implementation of the method are analyzed.

Constrained Bayesian Optimization under Partial Observations: Balanced Improvements and Provable Convergence

The partially observable constrained optimization problems (POCOPs) impede data-driven optimization techniques since an infeasible solution of POCOPs can provide little information about the objective as well as the constraints. We endeavor to design an efficient and provable method for expensive POCOPs under the framework of constrained Bayesian optimization. Our method consists of two key components. Firstly, we present an improved design of the acquisition functions that introduce balanced exploration during optimization. We rigorously study the convergence properties of this design to demonstrate its effectiveness. Secondly, we propose Gaussian processes embedding different likelihoods as the surrogate model for partially observable constraints. This model leads to a more accurate representation of the feasible regions compared to traditional classification-based models. Our proposed method is empirically studied on both synthetic and real-world problems. The results demonstrate the competitiveness of our method for solving POCOPs.

Exploring the Layout Optimization of Commercial Service Space Affecting Energy Consumption in Communities Using Machine Learning

The current design of commercial service spaces in many communities faces issues like incoherence, irrational resource allocation, and low utilization rates. These challenges contribute to increased energy consumption in communities, hindering the overall sustainable development of cities. As a representative community space in the urban environment, the commercial space within the campus requires continuous energy input. Its energy-efficient layout aligns with the principles of sustainable development. This paper uses the university campus as a case study to examine energy-efficient commercial space layout and community practices for environmental protection. Various factors influence the layout of inter-community commercial spaces, and the parameters for measuring the layout structure are diverse, considering the large sample size. Employing machine learning and big data processing to quantify development indicators across various industries and optimize their structure, resource allocation, and energy use has emerged as a viable tool for sustainable urban planning practices. This research seeks to utilize machine learning and data-driven optimization techniques to formulate a comprehensive framework for the sustainable allocation and design of business service spaces within communities. Firstly, we conduct a comprehensive investigation, which includes data collected by applying questionnaire surveys and field research, to assess and model the factors influencing the spatial layout of commercial services on university campuses. Secondly, the AEL machine learning model is constructed by combining the analytic hierarchy process to determine subjective weights, the entropy weight method to calculate objective weights, and the Lagrange algorithm to determine comprehensive weights. Thirdly, we assess and improve the layout of commercial service spaces. Then, by training and testing the Neural Network Model, we apply cases to ensure the accuracy of the machine learning calculation results. Qualitative analysis elucidates the varying factors influencing the sustainable layout of different commercial spaces. Quantitative analysis indicates that, within university campuses, the distance between commercial service spaces and residence halls is a crucial factor in fostering a more sustainable layout. Other significant factors include their location along major student routes and proximity to teaching areas. This study makes contributions not only to the specific field of optimizing commercial service space in communities but also to the broader discourse on sustainable urban development. It advances our understanding of the complex dynamics involved in crafting urban environments that are both efficient and environmentally friendly. Beyond theoretical considerations, the study provides practical solutions and recommendations applicable to implementing tangible improvements in resource allocation. These contributions aim to foster urban environments that are not only environmentally conscious but also economically viable.

Reinforcement learning as data-driven optimization technique for GMAW process

Welding optimization is a significant task that contributes to enhancing the final welding quality. However, the selection of an optimal combination of various process parameters poses different challenges. The welding geometry and quality are influenced differently by several process parameters, with some exhibiting opposite effects. Consequently, multiple experiments are typically required to obtain an optimal welding procedure specification (WPS), resulting in the waste of material and costs. To address this challenge, we developed a machine learning model that correlates the process parameters with the final bead geometry, utilizing experimental data. Additionally, we employed a reinforcement learning algorithm, namely stochastic policy optimization (SPO), with the aim to solve different optimization tasks. The first task is a setpoint‐based optimization problem that aims to find the process parameters that minimize the amount of deposited material while achieving the desired minimum level of penetration depth. The second task is an optimization problem without setpoint in which the agent aims to maximize the penetration depth and reduce the bead area. The proposed artificial intelligence-based method offers a viable means of reducing the number of experiments necessary to develop a WPS, consequently reducing costs and emissions. Notably, the proposed approach achieves better results with respect to other state-of-art metaheuristic data-driven optimization methods such as genetic algorithm. In particular, the setpoint‐based optimization problem is solved in 8 min and with a final mean percentage absolute error (MPAE) of 2.48% with respect to the 42 min and the final 3.42% of the genetic algorithm. The second optimization problem is also solved in less time, 30 s with respect to 6 min of GA, with a higher final reward of 5.8 from the proposed SPO algorithm with respect to the 3.6 obtained from GA.

Faux-Data Injection Optimization for Accelerating Data-Driven Discovery of Materials

Artificial intelligence is now extensively being used to optimize and discover novel materials through data-driven search. The search space for the material to be discovered is usually so large, that it renders manual optimization impractical. This is where data-driven search and optimization enables us to resourcefully locate an optimal or acceptable material configuration with desirable target properties. One such prominent data-driven optimization technique is Bayesian optimization (BO). Among the mechanics of a BO is the use of a machine learning (ML) model that learns about the scope of the problem through data being acquired on the fly. In this way a BO becomes more informative, directing the search more exquisitely by providing informative suggestions for locating a suitable material candidate for further evaluation. The candidate material is suggested by proposing parameters such as its composition and configuration, which are then evaluated either by physically synthesizing the material and testing its properties or through computational methods such as through density functional theory (DFT). DFT enables researchers to exploit massively parallel architectures such as high-performance computing (HPC) which a traditional BO might not be able to fully leverage due to their typical sequential data-acquisition bottleneck. Here, we tackle such shortcomings of BO and maximize the utilization of HPC by enabling BO to suggest multiple candidate material suggestions for DFT evaluations at once, which can then be distributed in multiple compute nodes of an HPC. We achieve this objective through a batch optimization technique based on faux-data injection in the BO loop. In the approach at each candidate suggestion from a typical BO loop, we “predict” the outcome, instead of running the actual experiment or DFT calculation, forming a “faux-data-point” and injecting it back to update an ML model. The next BO suggestion is therefore conditioned on the actual data as well as faux-data, to yield the next candidate data-point suggestion. The objective of this methodology is to simulate a time-consuming sequential data-gathering process and approximate the next k-potential candidates, quickly. All these k-potential candidates can then be distributed to run in parallel in an HPC. Our objective in this work is to test the theory if faux-data injection methodology enables us accelerate our data-driven material discovery workflow. To this end, we execute computational experiments by utilizing organic–inorganic halide perovskites as a case study since the optimality of the results can be easily verified from our previous work. To evaluate the performance, we propose a metric that considers and consolidates acceleration along with the quality of the results such as the best value reached in the process. We also utilize a different performance indicator for situations where the desired outcome is not material with optimal properties but rather a material whose properties satisfy some minimum requirements. We use these performance indicators to compare this BO-based faux-data injection method (FDI-BO) with different baselines. The results show that based on our design constraints, the FDI-BO approach enabled us to obtain around two- to sixfold acceleration on average compared to the sequential BO.

Parametric data-driven optimization approach on plasmonic based ring resonator

In this paper, a plasmonic based ring resonator is being investigated. The metallic portion of plasmonic waveguide is chosen to be silver while the insulating material is air. The structure is numerically analyzed through Finite Difference in Time Domain (FDTD) method. To accurately model the relationship between the design parameter (radius of the ring) and the resonance condition of the resonator, a Machine Learning (ML) approach is applied. The ML model is trained on a dataset and tested for obtained results. The simulated results show that the proposed model is able to achieve the accuracy of prediction. The data driven optimization technique is being used for finding out the appropriate resonance condition of ring resonator. The proposed model is able to achieve good prediction accuracy (>90 %). The predicted result can be utilized in designing desired plasmonic devices like sensors, splitter, optical gates etc.

RiRiShun Logistics: Home Appliance Delivery Data for the 2021 Manufacturing & Service Operations Management Data-Driven Research Challenge

To support the 2021 Manufacturing & Service Operations Management (M&SOM) Data-Driven Research Challenge, RiRiShun Logistics (a Haier group subsidiary focusing on logistics service for home appliances) provides MSOM members with logistics operational-level data for data-driven research. This paper provides a detailed description of the data associated with over 14 million orders from 149 clients (the consigners) associated with 4.2 million end consumers (the recipients and end users of the appliances) in China, involving 18,000 stock keeping units operated at 103 warehouses. Researchers are welcomed to develop econometric models, data-driven optimization techniques, analytical models, and algorithm designs by using this data set to address questions suggested by company managers. History: This paper has been accepted as part of the 2021 M&SOM Data-Driven Research Challenge. Funding: This work was supported by the National Natural Science Foundation of China [Grants 72091215/72091210, 71871207, 71991464/71991460, and 71921001]. Supplemental Material: Data and the online appendix are is available at https://doi.org/10.1287/msom.2021.0994 .

Recovery of energy losses using an online data-driven optimization technique

This paper investigates the energy loss due to rotor aging for a wind turbine and its recovery. Energy loss for a wind turbine is caused by formation of dust and bugs, and corrosion and erosion of the surface of the rotor by sand and rain. We present a real-time data-driven optimization algorithm that uses dither and demodulation signals to recover the energy loss by extracting online the sensitivity of the function of interest to optimize. We use a viscid–inviscid model to represent aerodynamic performance loss of the rotor due to aging. We employ time-domain aeroservoelastic simulation of the CART3 wind turbine of the National Renewable Energy Laboratory to provide a comprehensive assessment of aging and its recovery. We also investigate the impact of aging on structural loads and levelized cost of energy. Using annual energy production and WindPACT cost models of the National Renewable Energy Laboratory, the levelized cost of energy enables an overall assessment of aging and its recovery. To evaluate the impact of the energy loss recovery on structural loading, ultimate and fatigue loads for power production design load case are used. The results of this study show 6.9% reduction in the annual energy production due to aging for a class C wind condition based on IEC61400 standard. This energy loss increases the levelized cost of energy by 7.5%. Our online optimization algorithm can recover 1.7% of the energy losses, and it results in 2.0% reduction in the levelized cost of energy. Results of the ultimate loads indicate that an aged rotor reduces structural loading on most components except the main shaft where the bending moment shows an increase of 5.3%. Rotor aging also reduces the fatigue loads in most components except the tower bottom fore-aft moment with an increase of 5.5%. The statistical inference of the results shows that the proposed optimization algorithm is effective in recovering aging related energy losses of wind turbines with a confidence level of 84% based on the sampled data in this study.

Extremum Seeking Control With Sporadic Packet Transmission for Networked Control Systems

Extremum seeking control (ESC) is a data-driven optimization technique that can steer a dynamic plant toward an extremum of an unknown but measurable input to steady-state output. In the context of networked control systems, a new implementation method for ESC inspired by the well-known Luus–Jaakola algorithm is proposed. The main motivation is to minimize the communication burden associated with the search phase of ESC. In the proposed method, the controller only requires a notification of a change registered at the sensor, rather than the full information available at the sensor. This event-based approach leads to sporadic packet transmission. In addition, the proposed method is able to directly account for constraints while seeking the desired extremum. The constraints may be of the inequality or equality type. The algorithm's behavior is illustrated on a networked water pump control system.

A spatio-temporal kernel density estimation framework for predictive crime hotspot mapping and evaluation

Predictive hotspot mapping plays a critical role in hotspot policing. Existing methods such as the popular kernel density estimation (KDE) do not consider the temporal dimension of crime. Building upon recent works in related fields, this article proposes a spatio-temporal framework for predictive hotspot mapping and evaluation. Comparing to existing work in this scope, the proposed framework has four major features: (1) a spatio-temporal kernel density estimation (STKDE) method is applied to include the temporal component in predictive hotspot mapping, (2) a data-driven optimization technique, the likelihood cross-validation, is used to select the most appropriate bandwidths, (3) a statistical significance test is designed to filter out false positives in the density estimates, and (4) a new metric, the predictive accuracy index (PAI) curve, is proposed to evaluate predictive hotspots at multiple areal scales. The framework is illustrated in a case study of residential burglaries in Baton Rouge, Louisiana in 2011, and the results validate its utility.

Real-time control using Bayesian optimization: A case study in airborne wind energy systems

This paper presents a framework by which a data-driven optimization technique known as Bayesian Optimization can be used for real-time optimal control. In particular, Bayesian Optimization is applied to the real-time altitude optimization of an Airborne Wind Energy (AWE) system, for the purpose of maximizing net energy production. Determining the optimal operating altitude of an AWE system is challenging, as the wind speed constantly varies with both time and altitude. Furthermore, without expensive auxiliary equipment, the wind speed is only measurable at the AWE system’s operating altitude. In this work, Gaussian Process modeling and Bayesian Optimization are used in real-time to optimize the AWE system’s operating altitude efficiently, without the use of auxiliary wind profiling equipment. Specifically, the underlying objective function is modeled by a Gaussian Process (GP); then, Bayesian Optimization utilizes the predictive uncertainty information from the GP to determine the best subsequent operating altitude. In the AWE application, context-dependent Bayesian Optimization is used to handle the time-varying nature of the wind shear profile (wind speed vs. altitude). Using real wind data, our method is validated against three baseline approaches. Our simulation results show that the Bayesian Optimization method is successful in significantly increasing power production over these baselines.

Data-Based Multiobjective Plant-Wide Performance Optimization of Industrial Processes Under Dynamic Environments

This paper provides a method for automatically selecting optimal operational indices for unit processes in an industrial plant using measured data and without knowing dynamical models of the unit process. A dynamic multiobjective optimization problem is defined to find operational indices that lead to plant-wide production indices close to their target values. A case-based reasoning (CBR) technique is also employed, which uses the stored experience of a human expert to determine appropriate operational indices for given target production indices. The solutions of the optimization problem and CBR technique are combined to form baseline operational indices. The dynamic models of the production indices, however, are time varying and affected by disturbances and online corrections of these baseline operational indices are required. To this end, reinforcement learning (RL) is used to provide a data-driven optimization technique to compensate for disturbances and model approximation errors and variations. The data-driven RL approach is used in two different time scales. The samples of the predicted production indices are used at a fast sampling rate, i.e., at each sample time, and the samples of actual production indices are used at a slower sampling rate, i.e., after each operational run, to correct the baseline operational indices. The effectiveness of this automated decision procedure has been demonstrated by successful implementation of the proposed approach on a large mineral processing plant in Gansu Province, China.

On Optimizing Anomaly Detection Rules for Gas Turbine Health Monitoring

Gas turbine health monitoring is a critical process in preventing costly unplanned maintenance and secondary damage. To monitor gas turbine health, control signals are typically collected and analyzed using anomaly detection rules and models to assess failure likelihood based on observed data patterns. An analytic designer will often deal with rule optimization tasks in order to maximize failure detection and reduce false alarms. Manual tradeoff analysis is typically time consuming and suboptimal. In this paper, we attempt to address this issue by introducing a strategy for automatic and efficient rule optimization. By focusing on optimizing rule parameters while keeping rule structure intact, we maximize the rule performance by integrating domain knowledge with data driven optimization techniques. Realizing that automated rule tuning can be computationally expensive and infeasible to complete in reasonable time, we will leverage our recently-developed scalable learning framework - iScale that allows for automatically distributing rule tuning tasks to a large number of cloud computers, which not only dramatically speeds up tuning process, but also enables us to handle big size of historical data for tuning. We also explore different search methods to make rule tuning more efficient and effective and finally demonstrate our rule optimization strategy by a real-world application.