Machine Learning and Data-Driven Techniques for the Control of Smart Power Generation Systems:An Uncertainty Handling Perspective

Due to growing concerns regarding climate change and environmental protection,smart power generation has become essential for the economical and safe operation of both conventional thermal power plants and sustainable energy.Traditional first-principle model-based methods are becoming insufficient when faced with the ever-growing system scale and its various uncertainties.The burgeoning era of machine learning(ML)and data-driven control(DDC)techniques promises an improved alternative to these outdated methods.This paper reviews typical applications of ML and DDC at the level of monitoring,control,optimization,and fault detection of power generation systems,with a particular focus on uncovering how these methods can function in evaluating,counteracting,or withstanding the effects of the associated uncertainties.A holistic view is provided on the control techniques of smart power generation,from the regulation level to the planning level.The benefits of ML and DDC techniques are accordingly interpreted in terms of visibility,maneuverability,flexibility,profitability,and safety(abbreviated as the“5-TYs”),respectively.Finally,an outlook on future research and applications is presented.

Novel Oxygen Storage Components Promoted Palladium Catalysts for Emission Control in Natural Gas Powered Engines

A three-way catalyst comprised novel oxygen storage components for emission control in natural gas powered engines was prepared. The addition of novel oxygen storage components to the Pd/γ-Al2O3 catalysts resulted in improved activities of the fresh and aged catalyst by lowering the light-off temperature for methane in natural gas engines exhaust.

Finite-time Stability of Heating Furnace Temperature Control System

A finite-time stabilization controller for the heating furnace temperature control system is proposed.Based on the extended Lyapunov finite-time stability theory and power integral method,a finite-time stable condition of the heating furnace temperature control system is given.The temperature of the heating furnace is directed by the finite-time stabilization controller to make it stable in finite time.And the quality and quantity of slabs is improved.The simulation example is presented to illustrate the applicability of the developed results.

Charging System of ECRH High-Voltage Power Supply and its Control System

High-voltage power supply (HVPS) of Electron Cyclotron Resonance Heating (ECRH) for HT-7 and HT-7U is presently being constructed. The high voltage (100 kV) energy of HVPS is stored in the capacitor banks, and they can power one or two gyrotrons. All the operation of the charging system will be done by the control system, where the field signals are interfaced to programmable logic controller (PLC). The use of PLC not only simplifies the control system, but also enhances the reliability. The software written by using configuration software installed in the master computer allows for remote and multiple operator control, and the status and data information is also remotely available.

Most Suitable Power System Stabilizer Selection for the Improvement of Dynamic Stability

A method of enhancing power system stability for a single machine to infinite bus power system is presented. The technique used compromises the effectiveness of Proportional-Integral-Derivative controller （PID）. In order to satisfy the damping characteristics for the proposed power system over a wide range of operating interval, rotational speed, torque angle and terminal voltage signals of the synchronous machine are utilized as control signals of the system. It is well known that these variables have significant effects on damping the generators shaft mechanical oscillations, it＇ll be so easy to validate the most suitable controller as seen from the simulation results.

Auto-Ignition and Heat Release Correlations for Controlled Auto-Ignition Combustion in Gasoline Engines

Auto-ignition and heat release correlations for controlled auto-ignition(CAI)combustion were derived from extensive in-cylinder pressure data of a four-stroke gasoline engine operating in CAI combustion mode.Abundant experiments were carried out under a wide range of air/fuel ratio,speed and residual gas fraction to ensure that the combustion correlations can be used in the entire CAI engine operation range.Furthermore,a more accurate method to compute the residual gas fraction was proposed by calculating the working fluid temperature at the exhaust valve close timing in the experiments.The heat release correlation was described in two parts,one is for the first slower heat release process at low temperature,and the other is for the second faster heat release process at high temperature.Finally the heat release correlation was evaluated on the single cylinder gasoline engine running with CAI combustion by comparing the experimental data with the 1-D engine simulation results obtained with the aid of the GT-Power simulation program.The results show that the predicted loads and ignition timings match closely with the measurements.

基于Simulink的E-Power自卸车发动机控制方法

E-Power作为一种新兴混动技术,能够将发动机运行与车辆驱动解耦,实现能量的高效利用。文章介绍一种E-Power自卸车发动机控制方法,该方案充分考虑发电机的工作效率和电池充放电功率限值的条件,通过Simulink模型搭建发动机控制策略。实车CHTC-D循环试验结果表明,按照该控制方法进行发动机驱动,可以平稳控制发动机起停,起到节油效果。

Recent advance on the efficiency at maximum power of heat engines

This review reports several key advances on the theoretical investigations of efficiency at maximum power of heat engines in the past five years. The analytical results of efficiency at maximum power for the Curzon-Ahlborn heat engine, the stochastic heat engine constructed from a Brownian particle, and Feynman＇s ratchet as a heat engine are presented. It is found that： the efficiency at maximum power exhibits universal behavior at small relative temperature differences; the lower and the upper bounds might exist under quite general conditions; and the problem of efficiency at maximum power comes down to seeking for the minimum irreversible entropy production in each finite-time isothermal process for a given time.

Progress in Research and Development of Molten Chloride Salt Technology for Next Generation Concentrated Solar Power Plants

Concentrated solar power(CSP)plants with thermal energy storage(TES)system are emerging as one kind of the most promising power plants in the future renewable energy system,since they can supply dispatchable and low-cost electricity with abundant but intermittent solar energy.In order to significantly reduce the levelized cost of electricity(LCOE)of the present commercial CSP plants,the next generation CSP technology with higher process temperature and energy efficiency is being developed.The TES system in the next generation CSP plants works with new TES materials at higher temperatures(>565℃)compared to that with the commercial nitrate salt mixtures.This paper reviews recent progressin research and development of the next generation CSP and TES technology.Emphasis is given on theadvanced'TES technology based on molten chloride salt mixtures such as MgCl_(2)/NaCl/KCl which hassimilar thermo-physical properties as the commercial nitrate salt mixtures,higher thermal stability(>800℃),and lower costs(<0.35USD·kg^(-1)).Recent progress in the selection/optimization of chloridesalts,determination of molten chloride salt properties,and corrosion control of construction materials(eg.,alloys)in molten chlorides is reviewed.

H∞ control of novel active steering integrated with electric power steering function

Based on the traditional active steering system, a novel active steering system integrated with electric power steering function was introduced, which can achieve the functions of both active steering and electric power steering. In view of the interference from road random signal and sensor noise in the novel active steering system, the H∞ control model of the novel active steering system was built. With satisfying steering feel, good robust performance and steering stability being the control objectives, the H∞ controller for the novel active front steering (AFS) system was designed. The simulation results show that the novel AFS system with H∞ control strategy can attenuate the road interference quickly, and there is no resonance peak in the bode diagram. It can make the driver obtain more useful information in the low frequency range, and attenuate the road interference better in the high frequency range, thus the driver can get more satisfying road feeling. Therefore, the designed H∞ controller can synthesize the advantages of both robust performance and robust stability, and has certain contribution to the design of novel AFS system.

Research on H_2 speed governor for diesel engine of marine power station

The frequency stability of a marine power system is determined by the dynamic characteristic of the diesel engine speed regulation system in a marine power station. In order to reduce the effect of load disturbances and improve the dynamic precision of a diesel engine speed governor, a controller was designed for a diesel engine speed regulation system using H2 control theory. This transforms the specifications of the system into a standard H2 control problem. Firstly, the mathematical model of a diesel engine speed regulation system using an H2 speed governor is presented. To counter external disturbances and model uncertainty, the design of an H2 speed governor rests on the problem of mixed sensitivity. Computer simulation verified that the H2 speed governor improves the dynamic precision of a system and the ability to adapt to load disturbances, thus enhancing the frequency stability of marine power systems.

计及需求响应的光热电站参与深度调峰的分层优化调度策略

从源、荷两侧挖掘系统调峰潜力,建立计及需求响应的光热电站参与深度调峰的分层优化调度模型。上层从负荷侧出发,提出一种基于负荷分类的价格需求响应模型,可有效缓解系统调峰压力;中层从电源侧出发,利用光热电站灵活的调节特性在深度调峰时段协调火电机组参与辅助调峰,构建以运行总成本最小为目标函数的日前调度模型;下层提出一种基于模型预测控制的日内动态调整模型,在滚动优化的同时,通过状态反馈环节实时调整光热电站储热装置充放热修正日前调度计划。仿真结果表明,所提调度策略在降低系统调峰成本的同时能有效抑制风光以及负荷的短时功率波动,在保证系统安全稳定运行的前提下提升风光消纳率。

基于反向传播神经网络PID的高功率微波炉温度控制

针对现有10 kW高功率工业微波炉,采用继电器作为控制执行器,在使用传统控制方法加热时,温度存在较大超调和明显振荡,系统温度稳定性较低,为解决上述问题将反向传播神经网络PID(BPNNPID)控制引入到该装置微波加热温度控制中,并以自来水为加热对象进行仿真对比与实验验证。首先,利用现有输入输出实验数据,建立工业微波炉温度控制模型;其次,运用MATLAB/SIMULINK搭建高功率工业微波炉温度控制系统并进行仿真对比实验;最后,实验验证BPNNPID控制方法在加热5 kg自来水时工业微波炉的温度控制性能,实验结果表明,较常规PID、模糊PID控制,该方法在微波加热过程中对媒质温度控制超调更小且未发生明显温度振荡,有效改善了高功率工业微波炉工作时的系统温度稳定性,有助于提高产品质量和安全性能。

汽油机冷机间歇性抖动问题的研究

汽油机冷起动后,催化器需快速达到较高温度,才能具有一定的转化效率。此阶段的控制策略往往是通过提高转速、减小点火提前角、加浓混合气等手段使排气温度迅速升高,但会影响到NVH性能和驾驶性。针对某汽油机催化器加热阶段严重的抖动问题,首先通过对源头和传递路径进行分析和排查,确认起燃阶段燃烧稳定性差是引起抖动的根本原因;然后对相关硬件进行排查,对多组控制参数下的座椅振动、燃烧稳定性进行扫描试验以及对排放进行摸底试验,寻求出一套排放和NVH性能均达标的控制参数;最后通过调整挡位转速控制策略,解决起步阶段突兀的驾驶性问题,使该汽油车型冷机怠速工况各性能指标均达标。

准气体动力循环Power MEMS气体静压轴承

为追求微细尺度条件下超高能量密度的目标,提出了Power MEMS准气体动力循环发动机的概念。鉴于Power MEMS准气体动力循环发动机能够自行提供高压气源的结构特征以及气体静压轴承在性能上的优点,提出了将气体静压轴承应用于该Power MEMS发动机的研究和Power MEMS准气体动力循环发动机中气体静压径向轴承和止推轴承的结构形式的选择,指出了微细尺度下气体静压轴承的设计要点;运用气体静压润滑的基本原理对气体轴承的结构及运行参数进行了分析,获取了径向轴承和止推轴承的参数设计;通过气体轴承静态性能的计算,从承载能力方面验证了将所设计的气体轴承应用于Power MEMS准气体动力循环发动机中的可行性。

热电联供电厂厂级供热集中智能管控系统开发及应用研究

为了解决多台机组供热负荷调节分散、供热系统压力波动大、供热经济性差的问题,首先提出基于MODBUS通信方式下多台机组供热单元互联控制的厂级供热集中智能管控系统;然后,结合机组实际性能试验数据建立机组性能仿真模型,获得不同电负荷下冷热再抽汽量与煤耗量的关系;最后,考虑机组安全运行边界,建立适用于多台机组热负荷经济分配的数学模型,以厂级总耗煤量最低寻优为目标,获得各机组热负荷分配方案,并成功在某装机6台、总容量3320 MW燃煤电厂实现了工程示范应用。结果表明:厂级供热集中智能管控系统可采用流量指令方式在机组安全运行边界内对各机组供热流量进行自动调节;全厂对外供热流量在50~400 t/h之间变化时,厂级供热集中智能管控系统可将供热母管压力控制在设定值的±0.03 MPa以内;通过对总供热负荷智能寻优分配,全厂总煤耗量可降低0.13~3.53 t/h。

串联式混合动力车辆动力单元载荷补偿策略研究

为解决串联式混合动力车辆动力单元突加重载时发动机转矩负荷率过高导致运行异常的问题,设计了一种基于模糊控制的载荷补偿策略,通过控制发电机转矩来调节发动机转矩负荷率,避免发动机在临界条件工作。仿真和试验结果表明,该策略有效改善了动力单元工作特性,使其可以稳定平滑地过渡到预期工作点,提高了动力单元工作的鲁棒性。

基于Fluent的IGBT模块散热器的优化设计

随着新能源电动汽车功率控制器中的IGBT模块向着微型化、集成化方向发展,功率密度增大会导致芯片发热量大幅度增加,降低模块的可靠性。优化英飞凌IGBT模块的散热器结构,以提高散热器的散热性能。设计开口角度为63.256°供冷却液流通的进口和出口,在散热器前、中、后位置设计直径为4~5.5 mm、叉分式排布的扰流柱。利用ANSYS仿真软件,通过计算流体动力学(CFD)的流固耦合传热计算模型进行仿真分析。仿真结果表明,采用新型叉分式结构散热器的IGBT模块的最高温度为85.10℃,最低温度为65.28℃,平均温度为78.81℃,均低于传统均分式结构散热器模块。搭建实验平台对IGBT模块散热器的散热性能进行检测,实验结果表明新型叉分式结构散热器散热效果良好,有助于提升IGBT模块的可靠性。

回收船舶柴油机余热的双回路有机朗肯循环系统性能分析

为了降低船舶二氧化碳排放,利用双回路有机朗肯循环(DORC)系统对船舶柴油机的排烟和缸套冷却水余热进行回收发电。通过夹点温差法构建热力学模型,高温回路用于回收排烟热量,低温回路用于回收缸套冷却水热量和高温回路冷凝热。分析9对工质组合时DORC系统的冷凝器热力学参数对系统性能的影响,结果表明:随着高温回路的冷凝温度和冷凝热负荷的增高,低温回路蒸发压力和净输出功呈现升高趋势,在高温回路冷凝热负荷为715.2 kW~1 241.2 kW时,系统总净输出功呈现先升高后降低的趋势。当高温回路采用环乙烷,低温回路采用一氯三氟丙烯(反式)为工质时,系统总净输出功可达到410.6 kW。

大功率涡扇发动机负载下基于加速度调节的航空三级式电机起动控制策略研究

针对某大功率航空涡扇发动机电起动过程中,存在的因特殊负载力矩特性对地面电源瞬时功率需求变化等会影响起动可靠性,引起电源保护等问题,提出了基于加速度调节的三级式电机起动控制策略。在保证发动机起动成功的前提下,对不同速度范围内加速度进行合理规划,减小起动初始阶段的转矩冲击,降低对地面电源的功率需求。通过对该负载情况下仿真分析和台架起动试验,验证了所提起动控制方法的有效性,为航空三级式电机起动/发电系统在涡扇发动机上的应用提供了参考。