Physical meaning and prediction efficiency of the load/unload response ratio of rocks in strain-weakening phase before failure

Rock experiment results indicate that the load/unload response ratio (LURR) of rocks expressed via strain energy may have singular or negative value after the stress in the rock reaches its maximum before rock failure or when the rock goes into the strain-weakening phase. The universality of this phenomenon is discussed. Expressed via strain or strain energy and the travel time of P wave, the variation form of the reciprocal of LURR during the process of rock failure preparation is derived. The results show that after a sharp decrease the reciprocal of LURR reaches its minimum when the main fracture of the rock is about to appear. This feature can be taken as an indication that the rock main fracture is impending.

Control method on serial type pump-valve coordinated electro-hydraulic servo system

In order to compromise the conflicts between control accuracy and system efficiency of conventional electro-hydraulic servo systems,a novel pump-valve coordinated electro-hydraulic servo system was designed and a corresponding control strategy was proposed.The system was constituted of a pumpcontrolled part and a valve-controlled part,the pump controlled part is used to adjust the flow rate of oil source and the valve controlled part is used to complete the position tracking control of the hydraulic cylinder.Based on the system characteristics,a load flow grey prediction method was adopted in the pump controlled part to reduce the system overflow losses,and an adaptive robust control method was adopted in the valve controlled part to eliminate the effect of system nonlinearity and parametric uncertainties due to variable hydraulic parameters and system loads on the control precision.The experimental results validated that the adopted control strategy increased the system efficiency obviously with guaranteed high control accuracy.

Explainable deep transfer learning for energy efficiency prediction based on uncertainty detection and identification

Energy efficiency is an important aspect of increasing production capacity, minimizing environmental impact, and reducing energy usage in the petrochemical industries. However, in practice, data quality can be degraded by measurement malfunction throughout the operation, leading to unreliable and inaccurate prediction results. Therefore, this paper presents a transfer learning fault detection and identification-energy efficiency predictor (TFDI-EEP) model formulated using long short-term memory. The model aims to predict the energy efficiency of the petrochemical process under uncertainty by using the knowledge gained from the uncertainty detection task to improve prediction performance. The transfer procedure resolves weight initialization by applying partial layer freezing before fine-tuning the additional part of the model. The performance of the proposed model is verified on a wide range of fault variations to thoroughly examine the maximum contribution of faults that the model can tolerate. The results indicate that the TFDI-EEP achieved the highest r-squared and lowest error in the testing step for both the 10% and 20% fault variation datasets compared to other conventional methods. Furthermore, the revelation of interconnection between domains shows that the proposed model can also identify strong fault-correlated features, enhancing monitoring ability and strengthening the robustness and reliability of the model observed by the number of outliers. The transfer parameter improves the prediction performance by 9.86% based on detection accuracy and achieves an r-squared greater than 0.95 on the 40% testing fault variation.

Energy efficiency and savings analysis with multirate sampling for petrochemical process using convolutional neural network-based transfer learning

Energy efficiency in the petrochemical industry is crucial in reducing energy consumption and environmental impact.An accurate energy efficiency model will provide valuable insight for supporting operational adjustment decisions.In practice,due to inconsistent sampling intervals in the petrochemical industry,the traditional approach for obtaining energy efficiency may be unreliable and difficult to handle these multirate data char-acteristics.Therefore,in this paper,a multi-channel convolutional neural network model integrating a model parameter-based transfer learning approach is proposed to improve the prediction of energy efficiency under inconsistent sampling intervals.The multi-channel structure aims to recognize a different pattern from the dataset by convolving the information along the time dimension.Concurrently,transfer learning allows the model to learn a new pattern of input after the model is fully trained.Finally,the performance for energy ef-ficiency prediction and saving analysis is validated by applying it to the vinyl chloride monomer production case study.The result shows that the proposed model outperformed traditional models and typical convolutional neural network structures in terms of accuracy and reproducibility,with an r-square of 0.97.The utilization of transfer learning prevents a significant drop in performance and enhances adaptability in model learning on real-time energy tracking.Moreover,the energy gap analysis of the prediction result identified a significant energysaving potential,which would decrease annual energy consumption by 7.25%on average and a 5,709-ton reduction in carbon dioxide emissions.

Efficiency test of modeled empirical equations in predicting soil loss from ephemeral gully erosion around Mubi,Northeast Nigeria

A field study was carried out to assess soil loss from ephemeral gully(EG)erosion at 6 different locations(Digil,Vimtim,Muvur,Gella,Lamorde and Madanya)around the Mubi area between April,2008 and October,2009.Each location consisted of 3 watershed sites from where data was collected.EG shape,land use,and conservation practices were noted,while EG length,width,and depth were measured.Physico-chemical properties of the soils were studied in the field and laboratory.Soil loss was both measured and predicted using modeled empirical equations.Results showed that the soils are heterogeneous and lying on flat to hilly topographies with few grasses,shrubs and tree vegetations.The soils comprised of sand fractions that predominated the texture,with considerable silt and clay contents.The empirical soil loss was generally related with the measured soil loss and the predictions were widely reliable at all sites,regardless of season.The measured and empirical aggregate soil loss were more related in terms of volume of soil loss(VSL)(r^(2)=0.93)and mass of soil loss(MSL)(r^(2)=0.92),than area of soil loss(ASL)(r^(2)=0.27).The empirical estimates of VSL and MSL were consistently higher at Muvur(less vegetation)and lower at Madanya and Gella(denser vegetations)in both years.The maximum efficiency(M_(se))of the empirical equation in predicting ASL was between 1.41(Digil)and 89.07(Lamorde),while the M_(se) was higher at Madanya(2.56)and lowest at Vimtim(15.66)in terms of VSL prediction efficiencies.The M_(se) also ranged from 1.84(Madanya)to 15.74(Vimtim)in respect of MSL predictions.These results led to the recommendation that soil conservationists,farmers,private and/or government agencies should implement the empirical model in erosion studies around Mubi area.