Combined soft measurement on key indicator parameters of new competitive advantages for China’s export

The estimation of the difference between the new competitive advantages of China’s export and the world’s trading powers have been the key measurement problems in China-related studies.In this work,a comprehensive evaluation index system for new export competitive advantages is developed,a soft-sensing model for China’s new export competitive advantages based on the fuzzy entropy weight analytic hierarchy process is established,and the soft-sensing values of key indexes are derived.The obtained evaluation values of the main measurement index are used as the input variable of the fuzzy least squares support vector machine,and a soft-sensing model of the key index parameters of the new export competitive advantages of China based on the combined soft-sensing model of the fuzzy least squares support vector machine is established.The soft-sensing results of the new export competitive advantage index of China show that the soft measurement model developed herein is of high precision compared with other models,and the technical and brand competitiveness indicators of export products have more significant contributions to the new competitive advantages of China’s export,while the service competitiveness indicator of export products has the least contribution to new competitive advantages of China’s export.

Online soft measurement for wastewater treatment system based on hybrid deep learning

The existing automated wastewater treatment control systems encounter challenges such as the utilization of specialized testing instruments, equipment repair complications, high operational costs, substantial operational errors, and low detection accuracy. An effective soft measure model offers a viable approach for real-time monitoring and the development of automated control in the wastewater treatment process. Consequently, a novel hybrid deep learning CNN-BNLSTM-Attention (CBNLSMA) model, which incorporates convolutional neural networks (CNN), bidirectional nested long and short-term memory neural networks (BNLSTM), attention mechanisms (AM), and Tree-structure Parzen Estimators (TPE), has been developed for monitoring effluent water quality during the wastewater treatment process. The CBNLSMA model is divided into four stages: the CNN module for feature extraction and data filtering to expedite operations;the BNLSTM module for temporal data’s temporal information extraction;the AM module for model weight reassignment;and the TPE optimization algorithm for the CBNLSMA model’s hyperparameter search optimization. In comparison with other models (TPE-CNN-BNLSTM, TPE-BNLSTM-AM, TPE-CNN-AM, PSO-CBNLSTMA), the CBNLSMA model reduced the RMSE for effluent COD prediction by 25.4%, decreased the MAPE by 32.9%, and enhanced the R2 by 14.9%. For the effluent SS prediction, the CBNLSMA model reduced the RMSE by 26.4%, the MAPE by 21.0%, and improved the R2 by 35.7% compared to other models. The simulation results demonstrate that the proposed CBNLSMA model holds significant potential for real-time effluent quality monitoring, indicating its high potential for automated control in wastewater treatment processes.

Measurement of the Elasticity of Biological Soft Tissue of Finite Thickness

Elasticity is of profound significance to evaluating the function of a biological soft tissue. When the elasticity of a tissue is macroscopically changed, it means that the biological function of the tissue is abnormal and some disease or injury may occur. In the present work, an elastometer is developed to measure the elasticity of biological soft tissues. The measurement is based on the indentation method and the force is measured by the bending of the cantilever. The force-indentation data of the soft tissue is experimentally measured by this elastometer and Young＇s modulus of the tissue is calculated using the Hertz-Sneddon model. For comparison, a numerical model for the indentation method is established using the finite element method. The difference between the actual modulus and the measured modulus is discussed. The effect of the thickness of the specimen on the measurement is investigated. Young＇s moduli of beef, porcine liver and porcine kidney are experimentally measured. The results indicate that our elastometer is effective in measuring Young＇s modulus of a soft tissue quantitatively.

State Estimation of the Electric Drive Articulated Dump Truck Based on UKF

The requirements of vehicle dynamic stability control are higher than ever as the significant increase of electric drive articulated vehicle speed. According to the construction features of articulated dumping truck and nonlinear characteristics of moving vehicles,nonlinear observer of vehicle status is designed to strength robustness of dynamic control system in this paper. A 4-degree-of-freedom nonlinear dynamic model of articulated electric drive vehicle is built as reference model to estimate the state of the articulated vehicle. And by adopting Unscented Kalman Filter( UKF) algorithm,a series of state parameters such as longitudinal velocities of front and rear frames,yaw rate and side-slip angle are estimated. During the test of 60 t articulated electric drive vehicle,2 inertial navigation modules are installed in the front frame and rear frame respectively and the speed of each electric drive wheel is obtained simultaneously. As the test results suggest,in various working conditions,the algorithm based on UKF is able to accurately estimate the state parameters of articulated vehicle with the estimated error less than 5%. The proposed method is justified to be the theoretical basis and application guidance for articulated vehicle stability control.

RADIOGRAPHIC MEASUREMENT OF THE PREVERTEBRAL SOFT TISSUE OF CERVICAL VERTEBRAE

The radiographic measurement of the prevertebral soft tissue of cervical vertebrae was performed in 87 normal adults. According to the results of the measurement, 10 mm and 20 mm were used as the upper limit normal values of the retropharyngeal and retrotracheal space respectively. We conclude that although the widened soft tissue space is of diagnostic significance, diagnosis should be made on the basis of analysis of the injury history, clinical manifestation and imaging examination.

A novel deep learning framework with variational auto-encoder for indoor air quality prediction

Exposure to poor indoor air conditions poses significant risks to human health, increasing morbidity and mortality rates. Soft measurement modeling is suitable for stable and accurate monitoring of air pollutants and improving air quality. Based on partial least squares (PLS), we propose an indoor air quality prediction model that utilizes variational auto-encoder regression (VAER) algorithm. To reduce the negative effects of noise, latent variables in the original data are extracted by PLS in the first step. Then, the extracted variables are used as inputs to VAER, which improve the accuracy and robustness of the model. Through comparative analysis with traditional methods, we demonstrate the superior performance of our PLS-VAER model, which exhibits improved prediction performance and stability. The root mean square error (RMSE) of PLS-VAER is reduced by 14.71%, 26.47%, and 12.50% compared to single VAER, PLS-SVR, and PLS-ANN, respectively. Additionally, the coefficient of determination (R2) of PLS-VAER improves by 13.70%, 30.09%, and 11.25% compared to single VAER, PLS-SVR, and PLS-ANN, respectively. This research offers an innovative and environmentally-friendly approach to monitor and improve indoor air quality.

Friction Estimation and Roll Force Prediction during Hot Strip Rolling

A mathematical model of friction coefficient was proposed for the roll force calculation of hot-rolled strips. The online numerical solving method of the roll force calculation formula based on the proposed friction model was developed and illustrated by the practical calculation case. Then, the friction coefficient during hot strip rolling was estimated from the measured roll force by force model inversion. And then, the expression of friction model was pro posed by analyzing the calculation process of stress state coefficient, and the model parameters were determined by the shared parameter multi-model nonlinear optimization method. Finally, the industrial experiments demonstrated the feasibility and effectiveness of the related models. The accuracy of the new roll force model based on the built friction model was much higher than that of the traditional Sims model, and it could be applied in the online hot rolling process control.

Long-and Short-Term Self-Learning Models of Rolling Force in Rolling Process Without Gaugemeter of Plate

Owing to a lack of gaugemeter and the variety of steel grades and standards in some plate mills, the longand short-term self-learning models of rolling force based on gauge soft-measuring with high precision were brought up. The soft-measuring method and target value locked method were used in these models to confirm the actual exit gauge of passes, and thick layer division and exponential smoothing method were used to dispose the deformation resistance parameter, which could be calculated from the actual data of the rolling process. The correlative mathematical methods can also be adapted to self-learning with gaugemeter. The models were applied to the process control system of AGC （automatic gauge control） reconstruction on 2800 mm finishing mill of Anyang steel and favorable effect was obtained.