The least squares support vector regression (LS-SVR) is usually used for the modeling of single output system, but it is not well suitable for the actual multi-input-multi-output system. The paper aims at the modeling...
详细信息
The least squares support vector regression (LS-SVR) is usually used for the modeling of single output system, but it is not well suitable for the actual multi-input-multi-output system. The paper aims at the modeling of multi-output systems by LS-SVR. The multi-output LS-SVR is derived in detail. To avoid the inversion of large matrix, the recursive algorithm of the parameters is given, which makes the online algorithm of LS-SVR practical. Since the computing time increases with the number of training samples, the sparseness is studied based on the pro-jection of online LS-SVR. The residual of projection less than a threshold is omitted, so that a lot of samples are kept out of the training set and the sparseness is obtained. The standard LS-SVR, nonsparse online LS-SVR and sparse online LS-SVR with different threshold are used for modeling the isomerization of C8 aromatics. The root-mean-square-error (RMSE), number of support vectors and running time of three algorithms are compared and the result indicates that the performance of sparse online LS-SVR is more favorable.
Distillation columns are normally controlled at a pre-designed condition, which is the optimal for a specified feed condition. In reality, however, the feeds may vary in their flow rates, temperatures, or compositions...
详细信息
Distillation columns are normally controlled at a pre-designed condition, which is the optimal for a specified feed condition. In reality, however, the feeds may vary in their flow rates, temperatures, or compositions, which results in the distillation process operating at non-optimal values. Therefore, it is ideal to optimally adjust the operations in conjunction with the real feed variation. The online hardware measurement of the feed status, however, is basically impossible for most columns. A method using the temperature measurements along the distillation column to detect the feed variations is proposed in this paper. Verification is conducted through simulations under different conditions. Both derivative-based and derivative-free optimization methods are discussed for the soft-sensor establishment.
In this paper, a robust control method is proposed for rejecting the periodic disturbance. Cooperating with predictive function control (PFC), iterative learning (IL) is used to deal with the period mismatch, that is,...
详细信息
In this paper, a robust control method is proposed for rejecting the periodic disturbance. Cooperating with predictive function control (PFC), iterative learning (IL) is used to deal with the period mismatch, that is, iterative learning control (ILC) is used to handle the periodic errors while PFC doing its job of system process control. Simulation results shows that the IL-PFC algorithm achieves significant improvement in rejecting periodic disturbance over the repetitive control scheme.
Performance monitoring of model predictive control systems (MPC) has received a great interest from both academia and industry. In recent years some novel approaches for multivariate control performance monitoring hav...
详细信息
ISBN:
(纸本)9783902661548
Performance monitoring of model predictive control systems (MPC) has received a great interest from both academia and industry. In recent years some novel approaches for multivariate control performance monitoring have been developed without the requirement of process models or interactor matrices. Among them the prediction error approach has been shown to be a promising one, but it is k-step prediction based and may not be fully comparable with the MPC objective that is multi-step prediction based. This paper develops a multi-step prediction error approach for performance monitoring of model predictive control systems, and demonstrates its application in an industrial MPC performance monitoring and diagnosis problem.
A flowrate measurement method for air-water two-phase flow is developed using an Electrical Resistance Tomography (ERT) sensor and a Venturi meter. With the conductance values measured by the ERT sensor, the real-time...
详细信息
ISBN:
(纸本)9781424433520
A flowrate measurement method for air-water two-phase flow is developed using an Electrical Resistance Tomography (ERT) sensor and a Venturi meter. With the conductance values measured by the ERT sensor, the real-time flow pattern is identified and the voidage is also calculated. The Butterworth correlation is applied to calculate the mass quality from the voidage value, and then six Venturi measurement correlations are introduced to predict the mass flowrate of two-phase flow. The flow pattern classifier is constructed by using the partial least square (PLS) method and the Least Squares Support Vector Machine (LS-SVM) classification method. The voidage measurement models are developed by using the PLS method and the LS-SVM regression method for different flow patterns. Experiment results verify that this measurement method is effective. The research work also shows that among the six Venturi measurement correlations the Collins correlation always performs the best for the flow condition in this work.
A measurement system is developed for the parameter detection and flow characterization of gas-liquid two-phase flow in micro-channel. Electrical capacitance measurement system and optical measurement system are desig...
详细信息
ISBN:
(纸本)9781424433520
A measurement system is developed for the parameter detection and flow characterization of gas-liquid two-phase flow in micro-channel. Electrical capacitance measurement system and optical measurement system are designed for the micro-channels with different inner diameters of 4.0 mm, 3.1 mm and 1.8 mm respectively. In experiment, bubble flow, stratified flow, slug flow and annular flow are observed. PSD (Power Spectrum Density) and PDF (Probability Density Function) methods are used to analyze the capacitance and optical signals. The results show that the stratified flow can not be observed in the pipe with inner diameter of 1.8 mm, and that the PSD and PDF curve can be used to characterize different flow regimes of gas-liquid two-phase flow in micro-channel. So the constructed measurement system is effective, and can be used to analyze flow characteristics and identify flow regime of gas-liquid two-phase flow in micro-channel.
Terahertz time-domain spectroscopy (THz-TDS) was used for the detection of cyfluthrin content in N-hexane solvent with the concentration range of 0.5-10 μg/mL. The absorbance of the solution form cyfluthrin was obtai...
详细信息
Terahertz time-domain spectroscopy (THz-TDS) was used for the detection of cyfluthrin content in N-hexane solvent with the concentration range of 0.5-10 μg/mL. The absorbance of the solution form cyfluthrin was obtained in the frequency range between 0.5-1.5 THz. Two kinds of multivariate linear regression models were then built between the absorbance and the concentration of 15 samples, using partial least squares (PLS) and principle component regression (PCR) methods. The number of factors leading to the least root-mean-square error of cross validation (RMSECV) was 2 for PCR and 9 for PLS respectively. Compared to the PCR model, the PLS model proves to be more effective, with the RMSECV as low as 0.565 μg/mL. Results show that the THz-TDS plus PLS method is very promising for the further pesticide residue detection in food safety control, with the characteristics of being nondestructive and laborsaving compared to other analytical tools.
Based on a hybrid flowmeter and a dominant phase identifier, a new system is proposed for oil-water two-phase flow measurement. The hybrid flowmeter consists of an oval gear flowmeter and a Venturi meter. The dominant...
详细信息
Based on a hybrid flowmeter and a dominant phase identifier, a new system is proposed for oil-water two-phase flow measurement. The hybrid flowmeter consists of an oval gear flowmeter and a Venturi meter. The dominant phase identifier is utilized to overcome the influence of oil fraction on the measurement results. In the practical measurement process, the total volume flowrate and the differential pressure of the two-phase flow are firstly obtained by the oval gear flowmeter and the Venturi meter, respectively. Meanwhile, the dominant phase of the oil-water two-phase flow is identified. Then the meter coefficient of the Venturi meter is selected according to the dominant phase identification result. Finally, the total volume flowrate and the total mass flowrate of the two-phase flow are obtained. The preliminary research results show that the proposed system is effective in measuring oil-water two-phase flow.
Computation by self-assembly of DNA is an efficient method of executing parallel DNA computing, in which information is encoded in DNA tiles and a large number of tiles can be self-assembled via sticky end association...
详细信息
The remarkable characteristic of lighting system based on digital addressable lighting interface is panorama supervised which results from feedback control. This paper proposes the three-state feedback mechanism and t...
详细信息
ISBN:
(纸本)9781424437597
The remarkable characteristic of lighting system based on digital addressable lighting interface is panorama supervised which results from feedback control. This paper proposes the three-state feedback mechanism and the relative system consists of master units, slave units and a graphical user interface (GUI) for inputting parameters and supervising the detail of system. Slave units include standard slave units and feedback slave units which have AT90PWM2 controller. Built upon this system, the three-state feedback mechanism takes the feedback comprising the states of controller unit, implementation unit and controlled object unit according to the requirement of lighting protocol. Experimental results will be provided to verify the effectiveness of the proposed system.
暂无评论