The modeling method of freehand sketch based on conceptual design is the focus research in CAD. Though projection and mapping algorithm, freehand 2D curved surface was identified and mapped to 3D space to conceive tar...
详细信息
The modeling method of freehand sketch based on conceptual design is the focus research in CAD. Though projection and mapping algorithm, freehand 2D curved surface was identified and mapped to 3D space to conceive target 3D curved surface. Man-machine interactive technology was used to realize on-line correction of a curved surface. At last, a software system for identifying space curve based on freehand sketch was designed. The experiment result indicated that the method could conceive ideal space curve and curved surface for user more freely and rapidly.
After analysis of the existing one-versus-one (OVO) decomposition methods for multi-class support vector machine (SVM), the improved weighted posterior probability (IWPP) reconstruction strategy is presented to combin...
详细信息
After analysis of the existing one-versus-one (OVO) decomposition methods for multi-class support vector machine (SVM), the improved weighted posterior probability (IWPP) reconstruction strategy is presented to combine binary SVM-based classifiers to multi-class one. The new strategy can resolve the unclassifiable region problems in the conventional max-win-voting (MWV) method and increase recognition accuracy. Firstly, the different prior probabilities of these binary SVM-based classifiers in OVO decomposition are considered. Then, the improved weight coefficients for combination of the probability output among these binary classifiers are re-derived based on conditional probability theory. To validate the proposed strategy, four examples on UCI database are used to illustrate the logical correctness of IWPP. Tests show that the IWPP strategy has less classification errors, better classification ability and more stable probability output than the original ones.
Analysing the cotton picker in current situation of China, this paper proposed a new design of Intelligent Cotton Picking Robot (ICPR) based on machine vision including the motion control subsystem and machine vision ...
详细信息
Analysing the cotton picker in current situation of China, this paper proposed a new design of Intelligent Cotton Picking Robot (ICPR) based on machine vision including the motion control subsystem and machine vision subsystem. The former adopts the YASKAWA MP2100 as the core, which can control the robot of 4-DOF and X-axis. The latter based on the interface module of SEED-VPM642 with 2-CCD cameras, can get an efficient and precise recognition. The identification of mature cotton is one of the critical tasks in this robotic application. According to the statistic experiments and analysis, an optimized segmentation algorithm based on chromatic aberration is studied. The results demonstrate that the method for cotton recognition is well done and the increased pace helps improve the speed of the processing.
To solve the problems of real-time on-line measurements of freezing point of diesel fuel, a novel method of soft sensor with near-infrared (NIR) spectrometry was proposed based on the integration of both principal com...
详细信息
To solve the problems of real-time on-line measurements of freezing point of diesel fuel, a novel method of soft sensor with near-infrared (NIR) spectrometry was proposed based on the integration of both principal component analysis (PCA) and least squares support vector machines (LS-SVM). In this method, the PCA was incorporated into the model, which not only solved the linear correlation of the input, but also simplified the LS-SVM structure and improved the training speed. Then, the soft sensor model for freezing point was established using LS-SVM regression algorithm. The model performance has been tested and the results show that the propose method is superior to the soft sensor model based on BP neural network or PCA+SVM. So it can satisfy the demand of the on-lines measurement of freezing point.
A new nonlinear compensation technique to capacitor pressure sensor (CPS) based on least square support vector regression (LSSVR) is proposed. In this technique, LSSVR is used as an inverse model of the CPS; therefore...
详细信息
A new nonlinear compensation technique to capacitor pressure sensor (CPS) based on least square support vector regression (LSSVR) is proposed. In this technique, LSSVR is used as an inverse model of the CPS; therefore, the proposed technique can automatically compensate the effect of the associated non-linearity to estimate the applied pressure. Furthermore, the flexibility of the proposed technique effectively compensates any variation of the CPS's output occurring due to change in environmental temperature. The results of actual CPS compensation experiment indicate that this LSSVR approach is a useful alternative to the existing ones. This technique would be useful for other types of sensors such as thermocouples, flow sensors, magnetometer etc., possessing similar nonlinear response characteristics. The presented method has a potential future in the field of instrumentation and measurement.
When tri-axial magnetometer is used to estimate a magnetic field's module, different results will be obtained in different attitudes. Focusing on the diversionary errors of tri-axial magnetometer, A new adaptive c...
详细信息
When tri-axial magnetometer is used to estimate a magnetic field's module, different results will be obtained in different attitudes. Focusing on the diversionary errors of tri-axial magnetometer, A new adaptive calibration method based on artificial neural networks (ANN) was proposed. The relationships between the diversionary errors and the tri-axial magnetometer's system parameters, such as nonorthogonality between axes, different sensitivity and zero-shift of each axes, were analyzed. Through the corresponding ANN structure, a mathematical adaptive calibration model was established, which could be used to estimate the magnetic field's module. The simulation and practical experiment's results show that the diversionary errors of tri-axial magnetometer can be rectified under 10nT from 500nT. Without expensive, complex and special equipments, the presented calibration method is more suitable for tri-axial magnetometer.
Based on analysis of cutting force, this paper studies the method for modeling and compensation of cutting force induced error. According to the relation between feed servo motor current and cutting force, online moni...
详细信息
Based on analysis of cutting force, this paper studies the method for modeling and compensation of cutting force induced error. According to the relation between feed servo motor current and cutting force, online monitoring of cutting force is realized by measuring the motor current. For the delay of current signal to cutting force, a reasoning method with artificial neural network is proposed to predict correctly and monitor the cutting force online. The cutting force induced error is obtained by subtracting the geometric error from the total error which is measured with a laser interferometer within the working volume. According to the multi-body system theory and the back-propagation neural network, cutting force induced error model is developed. In addition, a real-time compensation system for cutting force induced error is built up with the VC++ softwareplatform. The validity of the error model and reliability of the compensation method is examined by milling experiments. The results demonstrate that the developed approach reduces the cutting force error markedly, and the method for modeling and compensation is of great important to precision manufacturing.
暂无评论