No abstract

At present, the research results for the stress response and deformation characteristics of composite support structures are mostly based on ideal or standard working conditions. External disturbances often exist in practical engineering, which makes the monitoring data deviate from the calculation results. In order to analyze the causes of deviation and correct them in practice, it is necessary to consider the time-varying effect and study the construction mechanics behaviors of composite support structures. Based on in situ test data, the effects of soil predisturbance, excessive excavation, unloading on the surface of edges, the tensioning and lagging of the anchor, and continuous rainfall on the stress-time curves of soil nails were analyzed. On the basis of verifying the effectiveness of the model, ABAQUS finite element software (v.2017) was used to simulate practical engineering based on ideal working conditions. Comparing the in situ test data and numerical simulation results, the development of mechanical response and deformation characteristics in the process of support structure installation and soil digging and filling were analyzed. Research shows that the time-varying effect has a significant impact on construction mechanics behaviors, especially on soil nailing combined with the use of prestressed anchors, due to layered excavation and support.

How to reduce the measurement error caused by linear regression is the key in measuring tea moisture content with microwave transmission techniques. In this paper, an improved BP algorithm, which combines the genetic algorithm, is given for training artificial neural network to get the range of weights and thresholds. The method makes BP algorithm avoid getting into infinitesimal locally and has the merits of high prediction precision and rapid convergence. The results show that the mean squared error is 0.0116, the mean absolute error is 0.0738, the mean relative error is 0.1182 and the certain coefficient is 0.9863 between the predicted value and the real one.

BP algorithm has been widely used in calibrating measurement results detected by microwave resonator for improvement of accuracy. Conventional BP algorithm tends to get into infinitesimal locally, which worsens the stability of the measurement accuracy. An evolutionary neural network model based on IA-BP optimal algorithm is proposed in this paper. In the model, IA algorithm is first used for global search and then BP algorithm for local search. Experiments indicated that the IA-BP optimal algorithm effectively avoid getting into infinitesimal locally and has the merits of high prediction precision, rapid convergence, global superiority and accuracy for optimization, which improves the measurement accuracy with the mean squared error 0.0125, the mean absolute error 0.0715, the mean relative error 0.1186 and the certain coefficient 0.9965 between the predicted moisture content and the real value.