Purpose Varian Ethos utilizes novel intelligent‐optimization‐engine (IOE) designed to automate the planning. However, this introduced a black box approach to plan optimization and challenge for planners to improve plan quality. This study aims to evaluate machine‐learning‐guided initial reference plan generation approaches for head & neck (H&N) adaptive radiotherapy (ART). Methods Twenty previously treated patients treated on C‐arm/Ring‐mounted were retroactively re‐planned in the Ethos planning system using a fixed 18‐beam intensity‐modulated radiotherapy (IMRT) template. Clinical goals for IOE input were generated using (1) in‐house deep‐learning 3D‐dose predictor (AI‐Guided) (2) commercial knowledge‐based planning (KBP) model with universal RTOG‐based population criteria (KBP‐RTOG) and (3) an RTOG‐based constraint template only (RTOG) for in‐depth analysis of IOE sensitivity. Similar training data was utilized for both models. Plans were optimized until their respective criteria were achieved or DVH‐estimation band was satisfied. Plans were normalized such that the highest PTV dose level received 95% coverage. Target coverage, high‐impact organs‐at‐risk (OAR) and plan deliverability was assessed in comparison to clinical (benchmark) plans. Statistical significance was evaluated using a paired two‐tailed student t‐test. Results AI‐guided plans were superior to both KBP‐RTOG and RTOG‐only plans with respect to clinical benchmark cases. Overall, OAR doses were comparable or improved with AI‐guided plans versus benchmark, while they increased with KBP‐RTOG and RTOG plans. However, all plans generally satisfied the RTOG criteria. Heterogeneity Index (HI) was on average <1.07 for all plans. Average modulation factor was 12.2 ± 1.9 (p = n.s), 13.1 ± 1.4 (p = <0.001), 11.5 ± 1.3 (p = n.s.) and 12.2 ± 1.9 for KBP‐RTOG, AI‐Guided, RTOG and benchmark plans, respectively. Conclusion AI‐guided plans were the highest quality. Both KBP‐enabled and RTOG‐only plans are feasible approaches as clinics adopt ART workflows. Similar to constrained optimization, the IOE is sensitive to clinical input goals and we recommend comparable input to an institution's planning directive dosimetric criteria.
Background: Friction stir welding technology is widely applied in the welding of dissimilar metal materials because of its characteristics of high welding efficiency, low welding process cost, high welding joint strength and reliability, and green environmental protection. The research on the processing methods and working principle of friction stir welding of dissimilar metals is beneficial to improve the mechanical properties of the joint and reduce weld defects. Therefore, the development of reliable friction stir welding technologies for dissimilar metals joining has been paid an increasing attention in recent years. Objective: To satisfy the processing of various dissimilar metals, improve the joint performance and weld defects, friction stir welding has developed bobbin tool friction stir welding and stationary shoulder friction stir welding. Methods: This paper retraces various current representative patents relative to friction stir welding, bobbin tool friction stir welding and stationary shoulder friction stir welding. Results: Through the investigation of a large number of patents on friction stir welding, the main current existing problems such as poor mechanical properties of the joints and defects in the welds are summarized and analyzed. In addition, the development trend of friction stir welding in dissimilar metal welding is also discussed. Conclusion: The research on friction stir welding methods and devices is beneficial to improve the mechanical properties of welded joints and reduce weld defects. More correlative patents will be invented in the future.
To explore the ignition performance of the ramjet combustion chamber, this paper combined the specific structure and working principle of the ramjet to model the ramjet combustion chamber, and carried out numerical simulation research on the flow field characteristics and combustion process of the stable operation of the combustion chamber. The results show that for the blunt-body of the flame stabilizer, the overall flame stability zone is relatively large at low inlet velocity, but the strength of the return zone at low inlet velocity is smaller than that at high speed. The flame stability zone formed at high inlet velocity is more stable and has stronger resistance to external disturbance. When the ratio of oil and gas mixtures is in the flammability limit range, the selection of ignition position has an important influence on the success of ignition. When the high-temperature zone formed by the initial ignition core can be diffused into the reflux zone and maintain sufficient temperature, the ignition can be successful.
Aiming at the problem of many aeroengine monitoring parameters, large amount of data, and timeliness of data, a novel aero-engine Remaining Useful Life (RUL) prediction method based on Temporal convolutional network (TCN) was proposed. Firstly, the data were redivided by setting different sliding window lengths, and then the optimal parameter selection of the model was studied. Finally, the remaining useful life prediction results of this method and traditional methods were compared and analyzed. The results showed that: The different parameters affected the conclusion of the calculation of the model. When the sliding window length was 30, the batch_size was 64, the dropout was 0.1, and the kenel_size was 8, the model had good prediction results. The best deterministic correlation coefficient between the predicted value and the actual value was 0.86, and the predicted trend of change was basically consistent with the actual value. The root mean square error of the model was 19.85, which was parallel to Long short-term memory (LSTM) and Convolutional neural networks (CNN), and the result verified the effectiveness of the method in predicting the remaining useful life of the engine. Through the above research, it provided a new model reference for solving the problem of engine remaining useful life prediction.
In the process of air combat intention identification, expert experience and traditional algorithm are relied on to analyze enemy aircraft combat intention in a single moment, but the identification time and accuracy are not excellent. In this paper, from the dynamic attributes of an airspace fighter air combat target and the dynamic and time series changing characteristics of the battlefield environment, we introduce the bidirectional long short-term memory neural network (BiLSTM + Attention) intention identification method based on the attention mechanism for air combat intention identification. In this method, five kinds of state parameters, including target maneuver type, distance, flight velocity, altitude and heading angle, were taken as datasets. The BiLSTM + Attention was used to extract enemy aircraft intention features. By introducing attention mechanism, the weight coefficients of characteristic states corresponding to air combat victories were corrected. Finally, it was input into the SoftMax function to obtain the category of the enemy’s intention. Experimental results showed that the proposed method can effectively identify enemy aircraft in the case of high complexity, multidimensional and large amount of data. Compared with bidirectional long short-term memory (BiLSTM), long short-term memory (LSTM), long short-term memory based on attention mechanisms (LSTM + Attention) and support vector machine (SVM) classification, the proposed method had higher accuracy and lower loss value.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.