Search Results (5)

The application of Artificial Neuronal Networks (ANN) offers better statistical accuracy in erosion-corrosion (E-C) predictions compared to the conventional linear regression based on Multifactorial Analysis (MFA). However, the limitations of ANN to require large training datasets and a high number of inputs pose a practical challenge in the field of E-C due to the scarcity of data. To address this challenge, a novel ANN method is proposed, structured to a small training dataset and trained with the aid of synthetic data to produce an E-C neural network (E-C NN), applied for the first time in the study of E-C wear synergy. In the process, transfer learning is applied by pre-training and fine-tuning the model. The initial dataset is created from experimental data produced in a slurry pot setup, exposing API 5L X65 steel to a turbulent copper tailing slurry. To the previously known E-C scenario for selected values of flow velocity, particle concentration, temperature, pH, and the content of the dissolved $C{u}^{2+}$, new experimental data of stand-alone erosion and stand-alone corrosion is added. The prediction of wear loss by E-C NN considers individual parameters and their interactions. The main result is that E-C ANN provides better prediction than MFA as evaluated by a mean squared error (MSE) values of 2.5 and 3.7, respectively. The results are discussed in the context of the cross-effect between the proposed prediction model and the resulting estimation of relative contribution to E-C synergy, which is better predicted by the E-C NN. The E-C NN model is concluded to be a viable alternative to MFA, delivering similar prediction with better sensitivity to E-C synergy at shorter computation times when using the same experimental dataset. Full article

To handle the gangue well and control the settlement of the surface, as well as to reduce the risk of water bleeding, settlement and even blockage and pipe breaking of the gangue slurry in the process of conveying, the rheological characteristics of the slurry should be studied. The rheological properties of slurry with different concentrations prepared from gangue samples of the Ningtiaota coal mine were tested, and the correlation between the rheological characteristics of the coal gangue filling slurry and three factors, namely the gangue mass fraction, grain gradation and standing time, were studied by a single factor method and response surface methodology. The results show that the fitting curve of the Herschel–Bulkley model is mostly linear, that is, the shear stress of coal gangue paste increases as a function of the shear rate. Therefore, these two concentrations are too small to form a stable network structure to wrap large particles and can easily cause pipe blockage. The yield shear stress and plastic viscosity show an exponential increase with the increasing mass fraction. The shear stress and apparent viscosity of the pastes with mass fractions of 60% and 65%, respectively, increase significantly after 20, 40 and 60 min of standing. According to the comprehensive test results and the response surface, the optimization method is as follows: mass fraction of 72%; aggregate grading for 4.75~1.18 mm particle size is 30%, for 1.18~0.425 mm particle size is 40%, for 0.425~0.075 mm particle size is 10%, for less than 0.075 mm particle size is 20%; with different standing times, the yield shear stress of slurry ranges from 103.02 to 131.645 Pa; and the plastic viscosity ranges from 0.54 to 0.64 Pa.s. With the increase of the standing time, the slurry settlement is relatively small, and is a more ideal gangue slurry proportion. Full article

Water pollution from intensive livestock husbandry is a persistent social-ecological problem. Since remedies require attention to the slurry–water nexus among practitioners, the agricultural press is a strategic entry point for agenda setting. Systematic content analysis can provide insights into how farming practices and sustainability issues are communicated, which may influence farmers’ attention to the issue and to potential solutions. To address this question, we present a semantic network analysis of three specialized farming magazines in Germany and analyze their coverage of the slurry–water nexus, in particular relationships of actors and issues and co-occurrence with political events. We used text mining methods in order to analyze a text corpus consisting of 4227 online articles published between 2010 and 2020. Results show that one fifth of all slurry-themed articles contained water-related content. We found a shift over time from dominantly management-oriented content towards a politicized debate with more actors and stronger semantic relationships with water protection constructed as an insulated stand-alone issue. This is accompanied by a shift from thematic reporting to episodic reporting focused on environmental legislation and compliance management. This implies less attention to innovations for water-conserving slurry management. Despite its shortcomings, episodic coverage may open up windows of opportunity to improve communication by experts and policy makers. Full article

In pipe jacking, the continued growth of friction resistance around the pipe may cause problems, such as an insufficient jacking force, soil collapse, and even land subsidence, which seriously endangers the structural safety of the pipe and surrounding structures. Bentonite slurry is often used as a lubrication material, but the friction resistance increases due to the inappropriate slurry concentration, and this may cause construction safety problems. In addition, the slurry standing time increases the difficulty of re-jacking construction. To further study the above problems, the friction characteristics of a steel pipe-soil interface under different slurry concentrations and slurry standing times were studied using direct shear tests. The test results show that the peak shear stress and friction coefficient of the interface first decrease and then increase with the increase in the concentration, which is less than or equal to 20%. The peak shear stress and friction coefficient increase with the increase in the concentration, which is greater than 20%, and the position of shear failure changes from between the slurry soil mixture and pipe wall to between the slurry and pipe wall, and finally to the slurry interior. The influence of the slurry standing time on the friction characteristics of the interface is as follows: For the same slurry concentration, the peak shear stress and friction coefficient of the interface increase with the standing time, approximately increasing first and then stabilizing; for different slurry concentrations, the amplification of the peak shear stress and friction coefficient increase with the increase in the concentration. Full article

Stand-alone screens (SASs) are active sand control methods where compatible screens and slot sizes are selected through the sand retention test (SRT) to filter an unacceptable amount of sand produced from oil and gas wells. SRTs have been modelled in the laboratory using computer simulation to replicate experimental conditions and ensure that the selected screens are suitable for selected reservoirs. However, the SRT experimental setups and result analyses are not standardized. A few changes made to the experimental setup can cause a huge variation in results, leading to different plugging performance and sand retention analysis. Besides, conducting many laboratory experiments is expensive and time-consuming. Since the application of CNN in the petroleum industry attained promising results for both classification and regression problems, this method is proposed on SRT to reduce the time, cost, and effort to run the laboratory test by predicting the plugging performance and sand production. The application of deep learning has yet to be imposed in SRT. Therefore, in this study, a deep learning model using a one-dimensional convolutional neural network (1D-CNN) with adaptive moment estimation is developed to model the SRT with the aim of classifying plugging sign (screen plug, the screen does not plug) as well as to predict sand production and retained permeability using a varying sand distribution, SAS, screen slot size, and sand concentration as inputs. The performance of the proposed 1D-CNN model for the slurry test shows that the prediction of retained permeability and the classification of plugging sign achieved robust accuracy with more than a 90% value of R², while the prediction of sand production achieved 77% accuracy. In addition, the model for the sand pack test achieved 84% accuracy in predicting sand production. For comparative model performance, gradient boosting (GB), K-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) were also modelled on the same datasets. The results showed that the proposed 1D-CNN model outperforms the other four machine learning models for both SRT tests in terms of prediction accuracy. Full article