Novel accurate and efficient equivalent circuit trained artificial neural-network （EC-ANN） models,which inherit and improve upon EC model and EM-ANN models＇ advantages,are developed for coplanar waveguide （CPW） d...Novel accurate and efficient equivalent circuit trained artificial neural-network （EC-ANN） models,which inherit and improve upon EC model and EM-ANN models＇ advantages,are developed for coplanar waveguide （CPW） discontinuities. Modeled discontinuities include ： CPW step, interdigital capacitor, symmetric cross junction, and spiral inductor, for which validation tests are performed. These models allow for circuit design, simulation, and optimization within a CAD simulator. Design and realization of a coplanar lumped element band pass filter on GaAs using the developed CPW EC-ANN models are demonstrated.展开更多
A kind of feed forward neural network with three layers was applied to detect conveyor belt fire faster. And backward propagation (BP) algorithm was used to train the network parameters. The appropriate parameters and...A kind of feed forward neural network with three layers was applied to detect conveyor belt fire faster. And backward propagation (BP) algorithm was used to train the network parameters. The appropriate parameters and architecture of network were ob- tained after training with 81 pair of data. Matlab was used to simulate and the experi- ment result shows training time is least and error reduces most rapidly when ten neu- rons were in hidden layer and momentum coefficient is equal to 0.95. Temperature, rate of temperature change, dense of carbon monoxide and rate of carbon monoxide dense change were considered as four parameters to detect the PVC belt fire in this paper. It is indicated that the network can give alarm as fire takes place about 350 s. The network can effectively detect the fire at the early stage of conveyor belt fire. At the same time, the reliability of alarm can be increased and the anti-interference capability can be en- hanced when using this network.展开更多
In this paper, a novel method of licence plate recognition (LPR) using the vertical traverse density (VTD) and horizontal traverse density (HTD) is presented. The neutral network algorithm using VTD and HTD features i...In this paper, a novel method of licence plate recognition (LPR) using the vertical traverse density (VTD) and horizontal traverse density (HTD) is presented. The neutral network algorithm using VTD and HTD features is also an innovation. In addition, a so called secondary recognition method which splits characters into different parts is developed. Experimental results show that it is a simple and fast algorithm, which meets the request of real time and nicety performances of LPR and thus has applied value in intelligence transportation system (ITS).展开更多
Conventionally, direct tensile tests are employed to measure mechanical properties of industrially pro- duced products. In mass production, the cost of sampling and labor is high, which leads to an increase of total p...Conventionally, direct tensile tests are employed to measure mechanical properties of industrially pro- duced products. In mass production, the cost of sampling and labor is high, which leads to an increase of total pro- duction cost and a decrease of production efficiency. The main purpose of this paper is to develop an intelligent pro- gram based on artificial neural network （ANN） to predict the mechanical properties of a commercial grade hot rolled low carbon steel strip, SPHC. A neural network model was developed by using 7 x 5 x 1 back-propagation （BP） neural network structure to determine the multiple relationships among chemical composition, product pro- cess and mechanical properties. Industrial on-line application of the model indicated that prediction results were in good agreement with measured values. It showed that 99.2 % of the products＇ tensile strength was accurately pre- dicted within an error margin of ~ 10 %, compared to measured values. Based on the model, the effects of chemical composition and hot rolling process on mechanical properties were derived and the relative importance of each in- put parameter was evaluated by sensitivity analysis. All the results demonstrate that the developed ANN models are capable of accurate predictions under real-time industrial conditions. The developed model can be used to sub- stitute mechanical property measurement and therefore reduce cost of production. It can also be used to control and optimize mechanical properties of the investigated steel.展开更多
The authors discussed the method of wavelet neural network （WNN） for correlation of base-level cycle. A new vectored method of well log data was proposed. Through the training with the known data set, the WNN can re...The authors discussed the method of wavelet neural network （WNN） for correlation of base-level cycle. A new vectored method of well log data was proposed. Through the training with the known data set, the WNN can remenber the cycle pattern characteristic of the well log curves. By the trained WNN to identify the cycle pattern in the vectored log data, the ocrrdation process among the well cycles was completed. The application indicates that it is highly efficient and reliable in base-level cycle correlation.展开更多
文摘Novel accurate and efficient equivalent circuit trained artificial neural-network （EC-ANN） models,which inherit and improve upon EC model and EM-ANN models＇ advantages,are developed for coplanar waveguide （CPW） discontinuities. Modeled discontinuities include ： CPW step, interdigital capacitor, symmetric cross junction, and spiral inductor, for which validation tests are performed. These models allow for circuit design, simulation, and optimization within a CAD simulator. Design and realization of a coplanar lumped element band pass filter on GaAs using the developed CPW EC-ANN models are demonstrated.
文摘A kind of feed forward neural network with three layers was applied to detect conveyor belt fire faster. And backward propagation (BP) algorithm was used to train the network parameters. The appropriate parameters and architecture of network were ob- tained after training with 81 pair of data. Matlab was used to simulate and the experi- ment result shows training time is least and error reduces most rapidly when ten neu- rons were in hidden layer and momentum coefficient is equal to 0.95. Temperature, rate of temperature change, dense of carbon monoxide and rate of carbon monoxide dense change were considered as four parameters to detect the PVC belt fire in this paper. It is indicated that the network can give alarm as fire takes place about 350 s. The network can effectively detect the fire at the early stage of conveyor belt fire. At the same time, the reliability of alarm can be increased and the anti-interference capability can be en- hanced when using this network.
基金funded by the NSFC program with grant 60672117supported in part by Xian Desheng Scientific Tech. Inc., Xian, P. R. China
文摘In this paper, a novel method of licence plate recognition (LPR) using the vertical traverse density (VTD) and horizontal traverse density (HTD) is presented. The neutral network algorithm using VTD and HTD features is also an innovation. In addition, a so called secondary recognition method which splits characters into different parts is developed. Experimental results show that it is a simple and fast algorithm, which meets the request of real time and nicety performances of LPR and thus has applied value in intelligence transportation system (ITS).
文摘Conventionally, direct tensile tests are employed to measure mechanical properties of industrially pro- duced products. In mass production, the cost of sampling and labor is high, which leads to an increase of total pro- duction cost and a decrease of production efficiency. The main purpose of this paper is to develop an intelligent pro- gram based on artificial neural network （ANN） to predict the mechanical properties of a commercial grade hot rolled low carbon steel strip, SPHC. A neural network model was developed by using 7 x 5 x 1 back-propagation （BP） neural network structure to determine the multiple relationships among chemical composition, product pro- cess and mechanical properties. Industrial on-line application of the model indicated that prediction results were in good agreement with measured values. It showed that 99.2 % of the products＇ tensile strength was accurately pre- dicted within an error margin of ~ 10 %, compared to measured values. Based on the model, the effects of chemical composition and hot rolling process on mechanical properties were derived and the relative importance of each in- put parameter was evaluated by sensitivity analysis. All the results demonstrate that the developed ANN models are capable of accurate predictions under real-time industrial conditions. The developed model can be used to sub- stitute mechanical property measurement and therefore reduce cost of production. It can also be used to control and optimize mechanical properties of the investigated steel.
基金Supported by Project of Dagang Branch of Petroleum Group Company Ltd,CNPC No TJDG-JZHT-2005-JSDW-0000-00339
文摘The authors discussed the method of wavelet neural network （WNN） for correlation of base-level cycle. A new vectored method of well log data was proposed. Through the training with the known data set, the WNN can remenber the cycle pattern characteristic of the well log curves. By the trained WNN to identify the cycle pattern in the vectored log data, the ocrrdation process among the well cycles was completed. The application indicates that it is highly efficient and reliable in base-level cycle correlation.
