The matching and fusion of visible and infrared images of power equipment are essential for real-time monitoring. Nevertheless, the computation of an accurate transform model between images for alignment remains a tough challenge due to notable changes in spectrum, resolution, and intensity between visible and infrared images. To address this issue, this paper proposes a hierarchical matching algorithm for visible and infrared images of power equipment based on multi-scale local normalized filtering. First, the input image is preprocessed by multi-scale local normalized filtering to enhance the image structures. Then, the contours of the filtered image are extracted by the Canny operator. A k-cosine curvature-based multi-scale corner detection algorithm is used to detect the feature points on the contours and the scale-invariant PIIFD is constructed for each feature point. Finally, a hierarchical matching strategy is proposed for feature matching, and the consistency check algorithm is applied to eliminate the false matches. The experiment is carried out on four groups of visible and infrared images of power equipment. The results show that our method can effectively achieve a large number of correct matches despite of scale and viewpoint changes.

Dense and accurate matching for visible and infrared images of power equipment is crucial to intelligent diag-nosis system of power grid, but existing matching methods usually fail in aligning visible and infrared image pairs because of significant intensity, resolution and viewpoint differences. In this paper, we propose a matching algorithm based on phase congruency and scale-invariant feature to address this problem. The proposed method consists of four steps. First, the maximum moment map of phase congruency of input image is computed based on phase congruency theory, which is then used to enhance the raw image. Second, Canny operator and contour tracking method are employed to detect image contours and scale-invariant feature points are extracted by the curvature scale space (CSS) corner detector. Third, the novel histogram of phase congruency orientation (HPCO) descriptors based on phase congruency information are computed for all feature points. Finally, a set of prelimi-nary matches is obtained by the bidirectional matching, and refinement procedures are implemented to achieve dense and accurate matching results. We conduct the experiments on public available dataset. Experimental re-sults show that the proposed method can robustly match feature points in visible and infrared image pairs of power equipment in spite of intensity, resolution and viewpoint differences, and achieve favorable performance compared to state-of-the-art approaches.

针对火电机组锅炉燃烧过程中预测NOx排放过程存在的非线性和时序性特点,提出一种基于核主成分分析(KPCA)和注意力机制(AM)的门控循环神经网络(GRU)氮氧化物预测模型.首先选用KPCA对模型的输入变量进行降维,消除冗余变量;其次,将筛选的变量数据作为GRU的输入,并采用网格搜索优化GRU的超参数;最后,引入AM计算权值,实现区分输入特征功能,提高NOx预测模型精度.通过某330 MW电站锅炉实际数据对AGRU预测模型仿真验证,并将AGRU模型、GRU模型和BP神经网络模型的预测结果进行对比.结果表明:基于AGRU的NO,预测模型的均方根误差和平均绝对误差较BP神经网络和GRU模型均有减少,可精准预测非线性时序燃烧过程的NOx排放.

针对发电机组主蒸汽温度控制系统惯性大、时滞长、扰动大的特点,结合比例积分微分(PI)控制和动态矩阵控制(DMC)的优点,提出一种基于PI-DMC的发电机组主蒸汽温度串级前馈预测控制策略.以控制量为燃料量、被控量为主蒸汽温度,利用遗忘因子递推最小二乘法对主蒸汽温度控制系统模型参数进行辨识;通过对模型施加单位阶跃信号得到预测模型,并通过反馈校正在线修正预测值;对目标函数实时滚动优化得到当前时刻控制量,并设定控制权重对PI和DMC进行优化组合.仿真结果表明:与串级PID和DMC控制相比,提出的控制策略在模型适配且施加干扰时,调节时间约 20 s、超调量仅6.47%;在模型失配且施加干扰时,调节时间约 30 s、超调量为 6.03%.工程应用结果表明:相较于工业现场原控制策略,提出的控制策略控制精度提高了66.91%,同时汽包液位的控制精度提高了47.23%,符合现场设计要求.

Robust feature matching for multi-source images of power equipment is critical for automatic diagnosis of power grid. However, classical image matching methods may not be suitable for this challenging task due to different resolution, spectrum and viewpoint between multi-source images. To solve this problem, a robust multi-source image matching algorithm is presented. First, the maximum moment map of phase congruency of input image is computed to enhance the raw image. Then, Canny operator and contour tracking method are employed to detect contour map of enhanced image. A set of feature points on contours is extracted by the curvature scale space corner detector. Second, a robust method is presented to assign main orientation to each feature point based on the local contour information, and a scale-invariant PIIFD descriptor is computed for feature point description. Finally, the bidirectional matching procedure is implemented to achieve feature correspondence and matching results are refined by both geometric and photometric information. We conduct the experiments on pairs of visible and infrared images of power equipment, and the results can demonstrate the effectiveness of our methods.

The classification method of steel surface defects with high performance and easy to be embedded in the detection equipment is one of the keys to ensure the quality of hot rolled strip. However, the development of deep convolutional neural networks (CNNs) in many real-world applications is largely hindered by their high computational cost, especially in industrial production, although it has good classification accuracy compared with machine learning-based methods in image recognition. Therefore, in this work, we present a lightweight network FCCNet based on the convolutional neural network to facilitate its application in the detection system. To compensate for the accuracy loss caused by the network downsizing, a knowledge distillation (KD) method using a larger trained network (teacher network) to teach a smaller network (student network) is adopted to improve the performance of our model. As a result, our method achieves a classification accuracy of 99.44%, precision of 99.46%, recall of 99.45%, and an F1 score of 99.45% on the NEU-CLS dataset, using only 0.03 MB parameters. These results show that the FCCNet is lighter than other existing classic CNNs with good performance for surface defects classification of hot-rolled steel strip, and it has the potential to be applied in the actual production line.

针对污水处理中和反应过程pH值控制具有强干扰和模型参数易变等特点,利用内模控制方法的设定值响应和干扰响应之间相互独立的优点,提出一种基于内模控制和神经网络逆模型相结合的pH值优化控制策略.通过在系统中插入低通滤波器,并采用RBF神经网络在线辨识被控对象的逆模型,提高污水处理pH值控制的鲁棒性和抗干扰能力,有效解决中和反应pH值控制过程中模型参数易变的问题.MATLAB仿真结果表明:与常规PID控制和不带滤波器的神经内模控制策略相比,提出的优化控制策略超调量最多降低17.4％,调节时间最多减少113.6 s,有效提高了系统鲁棒性和抗干扰能力.工程应用表明:使用所提策略后,pH值控制偏差在±0.2以内,系统的控制精度和稳定性显著提高.

针对燃煤发电机组风烟系统大惯性、大滞后、参数不稳定等特点,提出一种基于发电机组的滑模自抗扰控制策略.选择模糊径向基函数(RBF)算法辨识模型,以梯度下降法和遗传算法分别对神经网络权值进行粗调和细调,通过扩张状态观测器估计系统内外部扰动,将非线性状态误差反馈控制律与滑模控制策略相结合以克服系统惯性、滞后和扰动的问题,并设计Lyapunov函数验证控制系统稳定性.仿真结果表明,滑模自抗扰控制与串级比例-积分-微分(PID)控制、滑模控制和自抗扰控制相比,在模型适配的情况下,所设计的控制策略在 38 s达到设定值,无超调量;当向系统施加 20%的反向阶跃干扰时,系统调节时间为 39.5 s,超调量为 3.4%.在模型失配情况下的调节时间为 43.2 s,无超调量;当向系统施加 20%的反向阶跃干扰时,系统调节时间为 46.4 s,超调量为 3.87%.工程应用结果表明,一次风量控制偏差在±10 000 m3/h以内,相比串级PID控制策略波动范围降低 21%,系统抗干扰能力和鲁棒性得到有效提升.

针对加热炉炉温控制的目标多变、干扰因素多等问题,提出基于萤火虫算法(firefly algorithm)优化预期动态(desired dynamic equation,DDE)二自由度PID控制策略.将非线性鲁棒控制器(Tornambe Controller)中的不确定因素和外部干扰项利用观测器近似替换,运用预期动态法构建动态特性方程,推导出带有预期动态特性方程系数和观测器参数的二自由度PID等价形式.在判定系统稳定性后确定待优化参数选值范围,进而通过萤火虫优化算法选取最优参数.研究结果表明:与常规PID和二自由度PID控制相比,模型适配时所提出的控制策略使调节时间最多减少38 s,超调量最多降低15%,系统抗干扰性良好.使用所提策略后,炉温控制偏差小于±20℃,炉温波动降低60%,系统稳定性和抗干扰能力明显提高.

The main steam temperature is an important parameter of thermal power boiler. In view of the problem that the traditional PID control algorithm cannot meet the expectation of good control quality of the main steam temperature, an improved linear active disturbance rejection controller based on RBF neural network recognizer is designed to adjust the main steam temperature of the boiler. The control quantity formula in the linear ADRC system is improved as increment type, and add a tracking differentiator, Moreover, the Jacobian information of main steam temperature is identified online by the RBF network to realize the self-tuning of the weight coefficients of the control variables which can reduce the difficulty of parameter setting of controller. The proposed algorithm is applied to the main steam temperature control system of power boiler,and the experimental results show that this method can controls the main steam temperature fluctuation range to ± 5°C and has strong robustness and short adjusting time.

针对火力发电机组因结构复杂、指标众多且难以量化导致的燃烧检测仪器综合性能评价难以实现的问题,提出了一种基于信息熵-灰色模糊融合模型的火电机组燃烧检测仪器综合性能评价方法,建立了信息熵-灰色模糊评价模型.以发电机组飞灰含碳量工程范例的3种检测方式对比验证所提方法,采用模糊数学量化仪器性能、适用性能、风险性能3类语言标度,以从优隶属度规范化11项指标建立模型输入,用灰色关联系数矩阵综合考量输入量之间的耦合关联度,以熵权法替代传统专家法,剔除赋权过程的主观影响.对比结果表明,3种方案的二级指标权重在去人为干扰环境下,分别占总体的14.63％、58.51％、26.86％,对最优结果1的隶属度分别达到0.4265、0.6642和0.9673.与单因素分析方法相比,该模型在评价结果上具有一致性,而在多数据分析和去人为干扰中表现出更好的综合评价效能.

针对锅炉飞灰含碳量在线测量参数多变、惯性大等问题,设计一种改进型BP神经网络飞灰含碳量预测模型.通过主元分析法分析各燃烧工况与飞灰含碳量的关系,利用信息熵将标准BP神经网络中的误差函数进行改进,以抑制输入样本中的干扰噪声,并采用主元分析法筛选模型中输入参数,精简网络模型.结合所提出的改进型BP-WA(BP神经网络-狼群算法)优化控制策略对锅炉燃烧运行工况进行优化控制仿真研究,结果表明:采用改进型BP-WA优化控制策略优化飞灰含碳量前后,锅炉飞灰含碳量预测与标准BP网络模型方法相比,均方误差降低0.0121;飞灰含碳量降低3.50％,提升了锅炉运行的稳定性.

For computer numerical control (CNC) machine tools, thermal error is currently compensated according to a single fixed point on the worktable. When the worktable is in motion, the thermal error obviously differs across the worktable due to manufacturing, assembly, and other factors from driving and supporting devices. This causes the thermal error compensation by the single-point (SP) method to have great uncertainty for the whole worktable. To solve this problem, this paper proposes a sub-regional (SR) method to compensate for the thermal error of a worktable. The SR method divides the worktable into different regions and establishes a thermal error compensation model for each region, which are then combined to compensate for the thermal error of the whole worktable. The influence of the number of regions on the compensation effect of the SR method was analyzed theoretically and validated experimentally to provide a basis for determining a reasonable number of regions. The prediction effects of the SR method were compared with the SP method. And the compensation effects of the SR method were compared with a two dimensional thermal error map compensation method. The experimental results showed that the SR method has high prediction accuracy and stability and has better compensation effect in practical application for the whole worktable.

该文针对燃煤锅炉烟气含氧量传统测量方法误差大、效率低和成本高等缺点,利用隐式广义预测控制方法对控制系统进行设计,通过遗传算法对目标函数进行在线滚动优化,以此来实现对烟气含氧量的实时控制.从现场的运行工况来看,将烟气含氧量控制在2％左右,符合现场的设计要求.

针对火力发电机组燃气锅炉主汽温控制系统存在的强干扰和不确定性问题,利用滑模控制对系统参数变化和扰动不灵敏的优点,提出一种基于反演滑模控制和自适应算法相结合的主汽温优化控制策略.将主汽温控制过程中存在的干扰和不确定性归结为系统的总干扰,通过设计李雅普诺夫函数和虚拟控制量,逐步回推出反演滑模控制一级减温粗调控制器;在此基础上,采用自适应算法对系统总干扰进行估计,并设计出自适应反演滑模控制二级减温细调控制器.MATLAB仿真结果表明:与常规PID和反演滑模控制策略相比,所提策略的调节时间可减少126.9 s,超调量可降低20.1％,系统抗干扰及鲁棒性能得到有效提升.工程应用结果表明:所提策略的主汽温控制偏差小于±4℃,系统稳定性和抗干扰能力显著提高.

The modeling and compensation method is a common method for reducing the influence of thermal error on the accuracy of machine tools. The prediction accuracy and robustness of the thermal error model are two key performance measures for evaluating the compensation effect. However, it is difficult to maintain the prediction accuracy and robustness at the desired level when the ambient temperature exhibits strong seasonal variations. Therefore, a year-round thermal error modeling and compensation method for the spindle of machine tools based on ambient temperature intervals (ATIs) is proposed in this paper. First, the ATIs applicable to the thermal error prediction models (TEPMs) under different ambient temperatures are investigated, where the C-Means clustering algorithm is utilized to determine ATIs. Furthermore, the prediction effect of different numbers of ATIs is analyzed to obtain the optimal number of ATIs. Then, the TEPMs corresponding to different ATIs in the annual ambient temperature range are established. Finally, the established TEPMs of ATIs are used to predict the experimental data of the entire year, and the prediction accuracy and robustness of the proposed ATI model are analyzed and compared with those of the low and high ambient temperature models. The prediction accuracies of the ATI model are 20.6% and 41.7% higher than those of the low and high ambient temperature models, respectively, and the robustness is improved by 48.8% and 62.0%, respectively. This indicates that the proposed ATI method can achieve high prediction accuracy and robustness regardless of the seasonal temperature variations throughout the year.

针对火力发电机组燃气锅炉主汽温控制系统大惯性、大时滞、扰动大等特点,提出一种基于隐式广义预测控制(implicit generalized predictive control,IGPC)的主汽温预测控制策略.以主汽温为被控量,减温水流量为控制量,设计应用于燃气发电锅炉主汽温控制系统的隐式广义预测控制策略,通过建立主汽温预测模型,使用滚动优化对目标函数进行输出预测,构建最优控制律,并采用反馈校正在线修正预测值.仿真结果表明,与常规的串级比例积分微分(proportional-integral-derivative,PID)控制、动态矩阵控制和Smith预估补偿控制策略相比,在模型适配施加干扰的情况下,所设计的控制策略在67s左右达到设定值,超调量仅为4.28％;在模型失配情况下,施加干扰的调节时间为78.8s,超调量仅为8.66％.工程应用结果表明:主汽温控制偏差在±7℃左右,其稳定性得到了较大的改善,有效满足燃气发电锅炉主汽温控制系统的实际要求,该策略提高了控制系统的鲁棒性.

为进一步提高关节臂式坐标测量机等高机动性精密测量设备的测量精度,使用D-H矩阵法建立其关节坐标转换数学模型并据此推导出参数误差模型.针对非线性多参数标定问题,通过变换分析消除了最小二乘法求解时矩阵中的冗余参数,降低了计算的复杂性.设定判定准则并实现最小二乘法和模拟退火算法的混合,提出了一种基于混合优化算法的参数标定方法,解决了LM算法的初值设定和SA算法的搜索效率逐步降低的问题.实验结果表明:关节臂式测量机参数经混合优化算法标定后,参数的误差范围有了显著的缩小,单点重复性误差的平均值减小了1.746 mm,长度误差的平均值减小了0.941 mm,测量误差得到了进一步的抑制.

为了提高数控机床热误差补偿模型的预测精度与稳健性,对主成分算法在数控机床主轴热误差建模中的应用进行了研究。首先,根据主成分算法原理,提出基于主成分分析的温度敏感点选择算法和热误差建模算法。然后,以一台三轴立式加工中心为对象进行全年温度范围内的主轴热误差测量实验,并基于实验数据建立主轴热误差主成分回归（Principal Component Regression,PCR）模型。进而,将所建立的PCR模型与多元线性回归模型、BP神经网络模型和岭回归模型的预测精度与稳健性进行比对分析,实验结果表明PCR模型在该四种模型中具有最高的预测精度和稳健性,分别达到6.8μm和2.4μm。最后,使用所建立的PCR模型对按照转速图谱运行的机床主轴热误差进行预测,预测精度和稳健性分别为6.12μm和3.43μm。并将PCR模型嵌入到热误差补偿控制器中进行热误差补偿实验,以验证本文建模算法的有效性。

针对燃气发电锅炉存在的纯滞后、大惯性和参数模型易变等问题,设计了一种改进粒子群优化(PSO)的主汽压模糊广义预测控制策略.利用遗忘因子递推最小二乘法(FFRLS)辨识出主汽压模型,并引入广义预测控制(GPC),通过多步预测、滚动优化和实时反馈技术克服系统惯性、时滞和参数时变问题.为改善主汽压控制系统的稳定性和动态响应品质,对G PC算法中的控制加权系数进行模糊自校正设计.引入改进粒子群算法对广义预测控制的控制量增量进行寻优,求取最优控制律.仿真结果表明:与改进PSO-GPC策略和动态矩阵控制(DMC)策略相比,在施加扰动情况下,所提改进PS O-模糊G PC策略在模型适配与失配时稳定时间分别最多减少94.5 s和132 s,超调量分别最多降低5.1％ 和8％.工程运用表明:所提控制策略主汽压控制偏差低于±0.15 MPa,系统受模型失配影响更小,稳定性和抗扰动能力明显提升.