With the analysis of the complete process design for blade manufacturing of Hangzhou Steam Turbine Co.Ltd.,the design idea for the integrated CAPP system which is based on database and used for products are presented in the paper.The structure,functions and application of “Computer Aided Design System for Hangzhou Steam Turbine Blade Process(HTC?YPCAPP for abbrev.)are described in detail.
Based on the requirements of modern enterprises to CAPP system,the computer aided process planning system of blade in Hangzhou Steam Turbine Co.Ltd.(HTC YPCAPP)is developed. Through analyzing the whole course of design process,one design theory of hybrid CAPP system oriented product is put forward.
Combining genetic algorithm and probability statistics approach, a fast image threshold segmentation scheme is addressed in this article. The scheme is based on performance function of Ostu method. As this scheme speeds up the gauge image segmentation and pattern recognition hugely, the practical use of the new ship engine-room monitoring system is technically guaranteed. From the successful experimental results, it is shown that the proposed scheme is as effective as Ostu' method, also, speed of the presented pattern recognition approach is much higher than Ostu method considerably so that the practicability of new ship engine-room monitoring system is getting stronger and stronger
To evaluate consumers' willingness to pay (WTP) for Washington apples, the effects of firmness and sweetness as the representative sensory attributes are investigated in addition to those of consumer demographics and preferences. A tasting survey was conducted in Portland, Oregon on two varieties of apples, Gala and Red Delicious. Survey data is analyzed by employing a dichotomous-choice contingent valuation method, the double-bounded model, and maximum likelihood estimates are obtained. This study shows that firmer and sweeter apples induce more WTP. Age is also an important factor affecting WTP for apples. Education, eating frequency, and race affect WTP in the Gala model but not the Red Delicious. Other variables, such as gender, annual household income level, and whether they buy organic food, do not add significant explanatory power in estimating consumers' WTP.
We pursue an interpretable pitch tracking model and a jointly trained tone model for Mandarin tone classification. For pitch tracking, present deep learning based pitch model structure seldom considers the Viterbi decoding commonly implemented in prevalent manually designed pitch tracking algorithms. We propose RNN based Encoder-Decoder framework with gating mechanism which underlying models both the state cost estimation and Viterbi back-tracing pass implemented in the RAPT algorithm. Then we apply the pitch extractor to a down-stream Mandarin tone classification task. The basic motivation is to combine together the two conventional components in tone classification (i.e., the pitch extractor and tone classifier) and then the whole network are trained simultaneously in an end-to-end fashion. Various cascade methods are evaluated. We carry out pitch extraction and tone classification experiments on Mandarin continuous speech database to show the superiority of the proposed models. Experimental results on pitch extraction show proposed pitch tracking model outperforms the DNN-RNN and bi-directional variants. Tone classification experimental results show the composite model outperforms the traditional cascade tone classification framework which makes use of pitch related feature and a back-end classifier.
Recent advances in the time-domain speech separation methods, particularly those specialized in using attention mechanisms to model sequences, have significantly improved speech separation performance. In this paper, we address monaural (one microphone) speaker separation, mainly in the case of two concurrent speakers. We propose a dual-path hybrid attention network (DPHA-Net) for monaural speech separation based on time-domain. The critical component of DPHA-Net, the DPHA module, comprises multiple attentions and is designed to capture the short and long-term context information dependencies. DPHA module consists of the multi-head self-attention (MHSA), element-wise attention (EA), and adaptive feature fusion (AFF) units. We proposed an improved multi-stage aggregation training strategy during the training. That strategy has proven very effective for audio separation in this paper. The results of experiments on the benchmark WSJ0-2mix, WHAM! and Libri2Mix datasets show that our proposed DPHA-Net can achieves the competitive performance. For the task of two speaker separation on the WSJ0-2mix dataset, our proposed DPHA-Net is superior to the state of the art with a margin of 0.3 dB absolute improvement on the SI-SNRi and a margin of 0.4 dB absolute improvement on the SDRi in the same condition.
A novel 3D surface modeling method - 3D Surface Modeling based on Spatial Neighbor Points Coupling (SMSNPC) for scattered data points is addressed in this article. The main contribution contains two aspects: First, the 3D model of complex surface can be reconstructed through SMSNPC. Then, model parameters are recognized with Artificial Neural Network (ANN). To demonstrate the efficient applicability of the new algorithm, two groups of point data are presented. One collected by handheld laser scanner is used to validate the reconstruction result, and the other is used to be compared with non-coupling modeling. From the results, the new approach validates the expectation that SMSNPC can match the real complex surface satisfactorily which can't be finished by non-coupling modeling. By comparing the same sample data with non-coupling modeling, it is shown the reconstruction precision of SMSNPC is much higher.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)