Diagnosing injection-production system faults in the same well using the rough set-LVQ neural network.

This study proposed a reverse calculation model of the unique rod pump injection and production system structures in the same well to diagnose and resolve defects, after which dynamometer diagrams of the system production and injection pumps were drawn. The invariant moment feature method was applied to identify seven such characteristics in the injection pump power graph, establishing a downhole system for fault diagnosis in rod pump injection and production systems in the same well using Rough Set(RS)-Learning Vector Quantization(LVQ). On the premise of keeping the classification ability unchanged, the Self-Organizing Map(SOM) neural network was used to discretize the original feature data, while RS theory was employed for attribute reduction.

Study on the Powder-Spreading Process of Walnut Shell/Co-PES Biomass Composite Powder in Additive Manufacturing.

Powder laying is a necessary procedure during powder bed additive manufacturing (PBAM), and the quality of powder bed has an important effect on the performance of products. Because the powder particle motion state during the powder laying process of biomass composites is difficult to observe, and the influence of the powder laying process parameters on the quality of the powder bed is still unclear, a simulation study of the biomass composite powder laying process during powder bed additive manufacturing was conducted using the discrete element method. A discrete element model of walnut shell/Co-PES composite powder was established using the multi-sphere unit method, and the powder-spreading process was numerically simulated using two different powder spreading methods (rollers/scrapers).

Study of Forming Performance and Characterization of DLP 3D Printed Parts.

In order to explore the effect of printing parameter configurations on the forming performance of Digital Light Processing (DLP) 3D printed samples, printing experiments were carried out on the enhanced adhesion and efficient demolding of DLP 3D printing devices. The molding accuracy and mechanical properties of the printed samples with different thickness configurations were tested. The test results show that when the layer thickness increases from 0.

Main control factors affecting mechanical oil recovery efficiency in complex blocks identified using the improved k-means algorithm.

The system efficiency of pumping units in the middle and late stages of oil recovery is characterized by several factors, complex data and poor regulation. Further, the main control factors that affect system efficiency in different blocks vary greatly; therefore, it is necessary to obtain the block characteristics to effectively improve system efficiency. The k-means algorithm is simple and efficient, but it assumes that all factors have the same amount of influence on the output value.

Impact of Particle Size on Performance of Selective Laser Sintering Walnut Shell/Co-PES Powder.

The agricultural and forestry waste walnut shell and copolyester hot-melt adhesives (Co-PES) powder were selected as feedstock. A kind of low-cost, low-power consumption, and environmentally friendly walnut shell/Co-PES powder composites (WSPC) was used for selective laser sintering (SLS). Though analyzing the size and morphology of walnut shell particle (≤550 μm) as well as performing an analysis of surface roughness, density, and mechanical test of WSPC parts with different particle sizes, results showed that the optimal mechanical performance (tensile strength of 2.

Fault diagnosis method of submersible screw pump based on random forest.

The difficulty in directly determining the failure mode of the submersible screw pump will shorten the life of the system and the normal production of the oil well. This thesis aims to identify the fault forms of submersible screw pump accurately and efficiently, and proposes a fault diagnosis method of the submersible screw pump based on random forest. HDFS storage system and MapReduce processing system are established based on Hadoop big data processing platform; Furthermore, the Bagging algorithm is used to collect the training set data.