Genetic optimization for engine combustion system calibration: A case study of optimization performance sensitivity to algorithm search parameters

The use of genetic optimization algorithms (GOA) has been shown to significantly reduce the resource intensity of engine calibration, motivating investigation into the development of these methods. The objective of this work was to quantify the sensitivity of GOA performance to the algorithm search parameter values, in a case study of engine calibration. A GOA was used to calibrate four combustion system control parameters for a direct-injection gasoline engine at a single operating condition, with an optimization goal to minimize brake specific fuel consumption (BSFC) for a specified engine-out NOx concentration limit. The calibration process was repeated for two NOx limit values and a wide range of values for five GOA search parameters, including the number of genes, mutation rate, and convergence criteria. Results indicated GOA performance is very sensitive to algorithm search parameter values, with converged calibrations yielding BSFC values from 1 to 14% higher than the global minimum value, and the number of iterations required to converge ranging from 10 to 3,000. Broadly, GOA performance sensitivity was found to increase as the NOx limit was decreased from 4,500 to 1,000 ppm. GOA performance was the most sensitive to the number of genes and the gene mutation rate, whereas sensitivity to convergence criteria values was minimal. Identification of one set of algorithm search parameter values which universally maximized GOA performance was not possible as ideal values depended strongly on engine behavior, NOx limit, and the maximum level of error acceptable to the user.

A Data Driven Artificial Intelligence Framework for Hydrogen Production Optimization in Waterflooded Hydrocarbon Reservoir

Hydrogen has become a very promising green energy source that can be easily stored and transported, and it has the potential to be utilized in a variety of applications. Hydrogen, as a power source, has the benefits of being easily transportable and stored over long periods of times, and does not lead to any carbon emissions related to the utilization of the power source. Thermal EOR methods are among the most commonly used recovery methods. They involve the introduction of thermal energy or heat into the reservoir to raise the temperature of the oil and reduce its viscosity. The heat makes the oil mobile and assists in moving it towards the producer wells. The heat can be added externally by injecting a hot fluid such as steam or hot water into the formations, or it can be generated internally through in-situ combustion by burning the oil in depleted gas or waterflooded reservoirs using air or oxygen. This method is an attractive alternative to produce cost-efficiently significant amounts of hydrogen from these depleted or waterflooded reservoirs. A major challenge is to optimize injection of air/oxygen to maximize hydrogen production via ensuring that the in-situ combustion sufficiently supports the breakdown of water into hydrogen molecules. In-situ combustion or fireflood is a method consisting of volumes of air or oxygen injected into a well and ignited. A burning zone is propagated through the reservoir from the injection well to the producing wells. The in-situ combustion creates a bank of steam, gas from the combustion process, and evaporated hydrocarbons that drive the reservoir oil into the producing wells. There are three types of in-situ combustion processes: dry forward, dry reverse and wet forward combustion. In a dry forward process only air is injected and the combustion front moves from the injector to the producer. The wet forward injection is the same process where air and water are injected either simultaneously or alternating. Artificial intelligence (AI) practices have allowed to significantly improve optimization of reservoir production, based on observations in the near wellbore reservoir layers. This work utilizes a data-driven physics-inspired AI model for the optimization of hydrogen recovery via the injection of oxygen, where the injection and production parameters are optimized, minimizing oxygen injection while maximizing hydrogen production and recovery. Multiple physical and data-driven models and their parameters are optimized based on observations with the objective to determine the best sustainable combination. The framework was examined on a synthetic reservoir model with multiple injector and producing wells. Historical injection and production were available for a time period of three years for various oxygen injection and hydrogen production levels. Various time-series deep learning network models were investigated, with random forest time series models incorporating a modified mass balance – reaction kinetics model for in-situ combustion performing most effectively. A robust global optimization approach, based on an artificial intelligence genetic optimization, allows for simultaneously optimization of an injection pattern and uncertainty quantification. Results indicate potential for significant reduction in required oxygen injection volumes, while maximizing hydrogen recovery. This work represents a first and innovative approach to enhance hydrogen recovery from waterflooded reservoirs via oxygen injection. The data-driven physics inspired AI genetic optimization framework allows to optimize oxygen injection while maximizing hydrogen production.

A Deep Learning Approach to Estimate the Respiratory Rate from Photoplethysmogram

This article describes the methodology used to train and test a Deep Neural Network (DNN) with Photoplethysmography (PPG) data performing a regression task to estimate the Respiratory Rate (RR). The DNN architecture is based on a model used to infer the heart rate (HR) from noisy PPG signals, which is optimized to the RR problem using genetic optimization. Two open-access datasets were used in the tests, the BIDMC and the CapnoBase. With the CapnoBase dataset, the DNN achieved a median error of 1.16 breaths/min, which is comparable with analytical methods in the literature, in which the best error found is 1.1 breaths/min (excluding the 8 % noisiest data). The BIDMC dataset seems to be more challenging, as the minimum median error of the literature’s methods is 2.3 breaths/min (excluding 6 % of the noisiest data), and the DNN based approach achieved a median error of 1.52 breaths/min with the whole dataset.

A Deep Learning Approach to Estimate the Respiratory Rate from Photoplethysmogram

This article describes the methodology used to train and test a Deep Neural Network (DNN) with Photoplethysmography (PPG) data performing a regression task to estimate the Respiratory Rate (RR). The DNN architecture is based on a model used to infer the heart rate (HR) from noisy PPG signals, which is optimized to the RR problem using genetic optimization. Two open-access datasets were used in the tests, the BIDMC and the CapnoBase. With the CapnoBase dataset, the DNN achieved a median error of 1.16 breaths/min, which is comparable with analytical methods in the literature, in which the best error found is 1.1 breaths/min (excluding the 8 % noisiest data). The BIDMC dataset seems to be more challenging, as the minimum median error of the literature’s methods is 2.3 breaths/min (excluding 6 % of the noisiest data), and the DNN based approach achieved a median error of 1.52 breaths/min with the whole dataset.

A simulation-based multi-objective genetic optimization framework for efficient building design in early stages: application for Vietnam's hot and humid climates

PurposeIn many countries, innovation in building design for improving energy performance, reducing CO2 emissions and minimizing life cycle cost has received much attention for sustainable development. This paper investigates the importance of optimization tools for enhancing the design performance in the early stages of Vietnam's cooling-dominated buildings in hot and humid climates using an integrated building design approach.Design/methodology/approachThe methodology of this study exploits the non-dominated sorting genetic algorithm (NSGA-II) optimization algorithm coupled with building simulation to research a trade-off between the optimization of investment cost and energy consumption. Our approach focuses on the whole optimization problem of thermal envelope, glazing and energy systems from preliminary design phases. The methodology is then tested for a case study of a non-residential building located in Hanoi.FindingsThe results show a considerable improvement in design performance by our method compared to current building design. The optimal solutions present the trade-off between energy consumption and capital cost in the form of a Pareto front. This helps architects, engineers and investors make important decisions in the early design stages with a large view of impacts of all factors on energy performance and cost.Originality/valueThis is one of the original research to study integrated building design applying the simulation-based genetic optimization algorithm for cooling-dominated buildings in Vietnam. The case study in this article is for a non-residential building in the north of Vietnam but the methodology can also be applied to residential buildings and other regions.

Research on Fan Operation Evaluation and Error State Judgment Relying on Improved Neural Network and Intelligent Computing

Fan, as the most commonly used mechanical equipment, is widely used. In order to solve the problem of fan bearing fault diagnosis, this paper analyzes the main factors affecting fan spindle speed and power generation in operation. The input and output parameters of the performance prediction model are determined. The performance prediction model of wind turbine is established by using generalized regression neural network, and the smoothing factor of GRNN is optimized by comparing the prediction accuracy of the model. Based on this model, the sliding data window method is used to calculate the residual evaluation index of wind turbine speed and power in real time. When the evaluation index continuously exceeds the pre-set threshold, the abnormal state of wind turbine can be judged. In order to obtain wind turbine blades with better aerodynamic performance, a blade aerodynamic performance optimization method based on quantum heredity is proposed. The B é zier curve control point is used as the design variable to represent the continuous chord length and torsion angle distribution of the blade, the blade shape optimization model aiming at the maximum power is established, and the quantum genetic algorithm is used to optimize the chord length and torsion angle of the blade under different constraints. The optimization results of quantum genetic algorithm and classical genetic algorithm are compared and analyzed. Under the same parameters and boundary conditions, the proposed blade aerodynamic optimization method based on quantum genetic optimization is better than the classical genetic optimization method, and can obtain better blade aerodynamic shape and higher wind energy capture efficiency. This method makes up for the shortcomings of traditional fault diagnosis methods, improves the recognition rate of fault types and the accuracy of fault diagnosis, and the diagnosis effect is good.

Electrochromic window integration in adaptive building envelopes in different climates: a genetic optimization of switchable glazing parameters to reduce energy consumptions in office buildings

During last decades, many efforts have been made to address challenges regarding building energy consumption. A particularly interesting and effective field of development in the building domain is represented by responsive technologies applied to transparent envelopes. Among these technologies, the electrochromic (EC) glazing is one of the most developed solutions thanks to its capability to dynamically modulate daylight and thermal radiation, simply applying a controlled external voltage. The aim of this study is to provide a methodology to analyse smart responsive technologies and optimize the properties of an ideal switchable glazing to find the best configuration for a medium office in different climatic zones. The genetic optimization considers a 5-elements genome, constituted of the following genes: i) solar heat gain coefficient in bleached (SHGCB) and ii) coloured state (SHGCC), iii) visible light transmittance in bleached (VLTB) and iv) coloured state (VLTC) and v) thermal transmittance (U). Moreover, different European cities were selected as representative of different climatic zones and results obtained give a set of ideal EC glazing configurations in the case of EC window controlled by daylighting sensors.

Multilayer radiation shield for satellite electronic components protection

In this paper, various multi-layer shields are designed, optimized, and analyzed for electron and proton space environments. The design process is performed for various suitable materials for the local protection of sensitive electronic devices using MCNPX code and the Genetic optimization Algorithm. In the optimizations process, the total ionizing dose is 53.3% and 72% greater than the aluminum shield for proton and electron environments, respectively. Considering the importance of the protons in the LEO orbits, the construction of the shield was based on designing a proton source. A sample shield is built using a combination of Aluminum Bronze and molybdenum layers with a copper carrier to demonstrate the idea. Comparisons of radiation attenuation coefficient results indicate a good agreement between the experimental, simulation, and analytical calculations results. The good specifications of the proposed multi-layer shield prove their capability and ability to use in satellite missions for electronic device protection.