Supervised Learning Predictive Models for Automated Fracturing Treatment Design: A Workflow Based on Algorithm Comparison and Multiphysics Model Validation

Diagnostic pumping techniques are used routinely in proppant fracturing design. The pumping process can be time consuming; however, it yields technical confidence in treatment and productivity optimization. Recent developments in data analytics and machine learning can aid in shortening operational workflows and enhance project economics. Supervised learning was applied to an existing database to streamline the process and affect the design framework. Five classification algorithms were used for this study. The database was constructed through heterogeneous reservoir plays from the injection/falloff outputs. The algorithms used were support vector machine, decision tree, random forest, multinomial, and XGBoost. The number of classes was sensitized to establish a balance between model accuracy and prediction granularity. Fifteen cases were developed for a comprehensive comparison. A complete machine learning framework was constructed to work through each case set along with hyperparameter tuning to maximize accuracy. After the model was finalized, an extensive field validation workflow was deployed. The target outputs selected for the model were crosslinked fluid efficiency, total proppant mass, and maximum proppant concentration. The unsupervised clustering technique with t-SNE algorithm that was used first lacked accuracy. Supervised classification models showed better predictions. Cross-validation techniques showed an increasing trend of prediction accuracy. Feature selection was done using one-variable-at-a-time (OVAT) and a simple feature correlation study. Because the number of features and the dataset size were small, no features were eliminated from the final model building. Accuracy and F1 score calculations were used from the confusion matrix for evaluation, XGBoost showed excellent results with an accuracy of 74 to 95% for the output parameters. Fluid efficiency was categorized into three classes and yielded an accuracy of 96%. Proppant concentration and proppant mass predictions showed 77% and 86% accuracy, respectively, for the six-class case. The combination of high accuracy and fine granularity confirmed the potential application of machine learning models. The ratio of training to testing (holdout) across all cases ranged from 80:20 to 70:30. Model validations were done through an inverse problem of predicting and matching the fracture geometry and treatment pressures from the machine learning model design and the actual net pressure match. The simulations were conducted using advanced multiphysics simulations. The advantages of this innovative design approach showed four areas of improvement: reduction in polymer consumption by 30%, reduction of the flowback time by 25%, reduction of water usage by 30%, and enhanced operational efficiency by 60 to 65%.

Dynamic Point Cloud Compression Based on Projections, Surface Reconstruction and Video Compression

In this paper we will present a new dynamic point cloud compression based on different projection types and bit depth, combined with the surface reconstruction algorithm and video compression for obtained geometry and texture maps. Texture maps have been compressed after creating Voronoi diagrams. Used video compression is specific for geometry (FFV1) and texture (H.265/HEVC). Decompressed point clouds are reconstructed using a Poisson surface reconstruction algorithm. Comparison with the original point clouds was performed using point-to-point and point-to-plane measures. Comprehensive experiments show better performance for some projection maps: cylindrical, Miller and Mercator projections.

TDCA: Improved Optimization Algorithm with Degree Distribution and Communication Traffic for the Deployment of Software Components Base on AUTOSAR Architecture

AUTOSAR (Automotive Open System Architecture), as an open, standardized framework for automotive electronic software development, has gradually become the standard followed by major automotive manufacturers and automotive electronic device suppliers. The electronic software system problem improves the development efficiency and portability of the system by reducing the development cost of automotive electronic software while ensuring the quality of products and services, which is beneficial for subsequent upgrades and updates of the system. In order to improve the reliability of the software component deployment algorithm based on AUTOSAR architecture, we proposed the TDCA algorithm. During the execution of the algorithm, communication volume and communication degree are introduced to improve the accuracy of the deployment plan by optimizing the bus load and ECU balancing. Algorithm comparison experiments show that comparing heuristic and linear optimization algorithms, the TDCA algorithm proposed in this paper has significant advantages in reducing bus load and balancing ECU utilization. The algorithm can reduce the communication between cores and balance ECU load according to the constraints of AUTOSAR architecture.

Adaptive robust precision control of an active spray boom suspension with disturbance estimation

When the boom sprayer works in the field, the boom must be parallel to the undulating ground or crop canopy. Aiming at the problem of low control accuracy and poor stability caused by parameter uncertainties and time-varying disturbances in the electro-hydraulic active boom suspension system, this paper proposes an adaptive robust precision control algorithm based on disturbance estimation. Firstly, the dynamic analysis modeling method is adopted to establish the nonlinear dynamic model and mechanism geometric equation of the pendulum active and passive suspension. Then, the controller was designed based on the nonlinear model of the suspension system. The proposed controller uses the backstepping design method to integrate the disturbance observer into the adaptive robust controller, which can effectively deal with the parameter uncertainties and time-varying disturbances in the suspension system model. Finally, a large number of experiments were carried out by taking a 28 m large boom active suspension driven by a single-rod hydraulic pressure as an example. Using an established rapid control prototype of a large boom suspension, a variety of control algorithm comparison experiments were carried out, and a 6-DOF motion platform was used to simulate the motion coupling interference of the sprayer chassis. The experiment results illustrate the high-performance characteristics of the proposed controller and improve the tracking performance of the active pendulum suspension system under various parameter uncertainties and time-varying disturbances.

Object detection for automotive radar point clouds – a comparison

Automotive radar perception is an integral part of automated driving systems. Radar sensors benefit from their excellent robustness against adverse weather conditions such as snow, fog, or heavy rain. Despite the fact that machine-learning-based object detection is traditionally a camera-based domain, vast progress has been made for lidar sensors, and radar is also catching up. Recently, several new techniques for using machine learning algorithms towards the correct detection and classification of moving road users in automotive radar data have been introduced. However, most of them have not been compared to other methods or require next generation radar sensors which are far more advanced than current conventional automotive sensors. This article makes a thorough comparison of existing and novel radar object detection algorithms with some of the most successful candidates from the image and lidar domain. All experiments are conducted using a conventional automotive radar system. In addition to introducing all architectures, special attention is paid to the necessary point cloud preprocessing for all methods. By assessing all methods on a large and open real world data set, this evaluation provides the first representative algorithm comparison in this domain and outlines future research directions.

A novel machine learning-based approach for the detection and analysis of spontaneous synaptic currents

Spontaneous synaptic activity is a hallmark of neural networks. A thorough description of these synaptic signals is essential for understanding neurotransmitter release and the generation of a postsynaptic response. However, the complexity of synaptic current trajectories has either precluded an in-depth analysis or it has forced human observers to resort to manual or semi-automated approaches based on subjective amplitude and area threshold settings. Both procedures are time-consuming, error-prone and likely affected by human bias. Here, we present three complimentary methods for a fully automated analysis of spontaneous excitatory postsynaptic currents measured in major cell types of the mouse retina and in a primary culture of mouse auditory cortex. Two approaches rely on classical threshold methods, while the third represents a novel machine learning-based algorithm. Comparison with frequently used existing methods demonstrates the suitability of our algorithms for an unbiased and efficient analysis of synaptic signals in the central nervous system.

A Construction Method of Intelligent Manufacturing System under Industry 4.0 Model

Starting from the current problems facing Industry 4.0, this article analyzes the changes in the macro and industrial environment that Industry 4.0 faces and explains the problems, opportunities, and strategies for the manufacturing industry in the external environment. First, the reference system of the intelligent manufacturing system, the current status, and the existing problems of industrial production management are analyzed through the investigation of the status quo of industrial production and management. This puts forward the detailed requirements of the industrial intelligent manufacturing system in the data acquisition layer, data storage layer, and analysis and decision support layer and then designs the hierarchical structure of the industrial intelligent manufacturing system. Subsequently, it adopts design methods and lists product manufacturing costs, pointing out that Industry 4.0 requires industrial transformation, and finally proposes the strategic direction of smart manufacturing in combination with the Industry 4.0 network strategy. At the same time, in view of the problems of long parameter measurement time and untimely system feedback in the existing koji-making process, an online parameter measurement method based on network optimization is proposed. On the basis of the neural network, an industrial neural network with double hidden layers and self-feedback of the output layer is proposed. Through algorithm comparison experiments, the proposed parameter prediction model based on industrial neural network has better prediction results and higher accuracy. Finally, a comparison of cost, quality, delivery time, etc., before and after the implementation of Industry 4.0 intelligent manufacturing is carried out. An intelligent solution is proposed, the implementation goal is formulated, and the implementation is gradually implemented in stages, and finally an intelligent upgrade and transformation are realized. It is shown in many aspects that intelligent manufacturing provides a powerful means for enterprises to achieve agility, virtualization, lean, integration, and collaboration, and it can bring efficiency, reliability, and safety to the manufacturing process of enterprises.

A Non-dominated Genetic Algorithm Based on Decoding Rule of Heat Treatment Equipment Volume and Job Delivery Date

This paper investigated the flexible job-shop scheduling problem with the heat treatment process. To solve this problem, we built an unified mathematical model of the heat treatment process and machining process. Up to now, this problem has not been investigated much. Based on the features of this problem, we are intended to minimize Cmax, maximize the space utilization rate of heat treatment equipment, and minimize the total delay penalty to optimize the scheduling. By taking the dynamic process arrival under consideration, this paper proposed a set of decoding rules based on the heat treatment equipment volume and job delivery date to achieve a hybrid dynamic scheduling solution during one scheduling procedure. When the utilization rate of heat treatment equipment volume is maximized, and the job delivery date is taken under consideration, it is preferred to minimize the number of workpiece batches in the same job, and reduce the waiting time of the pending job. In combination with the improved adaptive non-dominated genetic algorithm, we worked out the solution. Furthermore, we verified the effectiveness of the proposed decoding rules and improved algorithm through algorithm comparison and calculation results. Finally, a software system for algorithm verification and algorithm comparison was developed to verify the validity of our proposed algorithm.