Search

Objective.Cone-Beam CT (CBCT) often results in severe image artifacts and inaccurate HU values, meaning poor quality CBCT images cannot be directly applied to dose calculation in radiotherapy. To overcome this, we propose a cycle-residual connection with a dilated convolution-consistent generative adversarial network (Cycle-RCDC-GAN). Approach. The cycle-consistent generative adversarial network (Cycle-GAN) was modified using a dilated convolution with different expansion rates to extract richer semantic features from input images. Thirty pelvic patients were used to investigate the effect of synthetic CT (sCT) from CBCT, and 55 head and neck patients were used to explore the generalizability of the model. Three generalizability experiments were performed and compared: the pelvis trained model was applied to the head and neck; the head and neck trained model was applied to the pelvis, and the two datasets were trained together. Main results. The mean absolute error (MAE), the root mean square error (RMSE), peak signal to noise ratio (PSNR), the structural similarity index (SSIM), and spatial nonuniformity (SNU) assessed the quality of the sCT generated from CBCT. Compared with CBCT images, the MAE improved from 28.81 to 18.48, RMSE from 85.66 to 69.50, SNU from 0.34 to 0.30, and PSNR from 31.61 to 33.07, while SSIM improved from 0.981 to 0.989. The sCT objective indicators of Cycle-RCDC-GAN were better than Cycle-GAN’s. The objective metrics for generalizability were also better than Cycle-GAN’s. Significance. Cycle-RCDC-GAN enhances CBCT image quality and has better generalizability than Cycle-GAN, which further promotes the application of CBCT in radiotherapy.

Electric propulsion systems, such as ion thrusters and Hall thrusters, are widely utilized in aerospace. The target indirect measurement method (TIMM) is a simple and robust way to measure its thrust. In general, one can obtain the thrust by scaling up the force exerted on the target surface immersed in the plume flow. However, the charge exchange (CEX) allows ions to become neutral particles, increasing the scaling coefficient. Meanwhile, the sputtered atoms and reflected incident particles exert force on the target surface and enlarge the measured thrust. In this study, the effects of the CEX, the sputtering, and the reflection on the TIMM are mathematically quantified, and then a modified model of the TIMM is proposed. Besides, the thrusts of the LIPS-200 and LIPS-300 ion thrusters were separately measured using the TIMM with the modified model, and the measured thrusts are in good agreement with the rated thrusts. Under the test conditions, the results of the LIPS-300 ion thruster show that the fast neutral atoms produced by the CEX account for more than 20% of all fast particles impacting on the target, and the force caused by the sputtered atoms is about 3.4% of the total force exerted on the target. We discuss how test conditions affect the CEX, sputtering, and reflection, thereby influencing the TIMM. The modified model was also validated through the simulation results, by showing that the measured thrust cannot be influenced by the test conditions.

When m value is above 21, If the horizontal load has not reached the design value of the theoretical ultimate bearing capacity, the foundation pile will first appear bending failure. That is to say, when m value is greater than 21, the horizontal bearing capacity of pile group bearing platform foundation begins to depend on the bending strength of pile itself. The ultimate horizontal bearing capacity of pile group bearing platform foundation in actual engineering has been difficult to reach the ideal design value。 When the value of M is less than 21, the actual horizontal ultimate bearing capacity is consistent with the theoretical calculation, when the m value is greater than 21, the actual horizontal ultimate bearing capacity can be calculated according to the simplified formula proposed in this paper.

At present, HAZOP analysis and LOPA analysis are widely used to analyze and control the risk of process flow, but few people manage HAZOP and LOPA for risk during operation. Through the research of HAZOP and LOPA analysis methods, combined with long-term work experience in the field, the author proposes to combine HAZOP and LOPA analysis methods into operational process safety risk analysis, and use the same subject expert team to identify the risks in the operation process. Control and control results also help to re-revise the operating procedures, conduct risk management and control from the operational level, and improve the completeness of safety evaluation. This paper introduces the basic method of HAZOP_LOPA joint analysis operation process, clarifies the analysis points, and lists the commonly used 8 types of guidance words. Finally, the risk of maintenance and maintenance operation of quick-open blind filter is analyzed by examples. The results show that Based on HAZOP_LOPA, operational risk analysis can quantitatively evaluate the reliability of existing protection measures, eliminate or reduce safety risks, and achieve safety risk review of operational procedures. This method improves the reliability of operating procedures and enhances the safe operation level of employees. It is of great significance.

Electricity tariff recovery has always been an important part of power companies. However, there are often some users who are in arrears in electricity charges. Therefore, how to make effective risk assessment for electricity customers is the key work at present. In this paper, an ensemble learning method named gradient boosting decision tree-random forest-adaboost-logical regression (GRAL) is proposed to construct a risk prediction model of electricity tariff recovery. Firstly, the data provided by the power company was preprocessed with feature engineering. Secondly, the GRAL ensemble learning method and the traditional logistic regression algorithm are used separately to construct the risk prediction model of electricity tariff recovery to predict the probability that the user will default next month. Finally, we make a risk assessment for users according the probability and predict whether the user in different risk levels will be in arrears. Experimental analysis shows that the proposed GRAL ensemble learning method has better experimental results compared with the traditional logistic regression algorithm, this method can effectively evaluate the payment behavior of power customers and make a more accurate prediction about whether users will be in arrears.