A deep Koopman operator-based modelling approach for long-term prediction of dynamics with pixel-level measurements

Although previous studies have made some clear leap in learning latent dynamics from high-dimensional representations,the performances in terms of accuracy and inference time of long-term model prediction still need to be improved.In this study,a deep convolutional network based on the Koopman operator(CKNet)is proposed to model non-linear systems with pixel-level measurements for long-term prediction.CKNet adopts an autoencoder network architecture,consisting of an encoder to generate latent states and a linear dynamical model(i.e.,the Koopman operator)which evolves in the latent state space spanned by the encoder.The decoder is used to recover images from latent states.According to a multi-step ahead prediction loss function,the system matrices for approximating the Koopman operator are trained synchronously with the autoencoder in a mini-batch manner.In this manner,gradients can be synchronously transmitted to both the system matrices and the autoencoder to help the encoder self-adaptively tune the latent state space in the training process,and the resulting model is time-invariant in the latent space.Therefore,the proposed CKNet has the advantages of less inference time and high accuracy for long-term prediction.Experiments are per-formed on OpenAI Gym and Mujoco environments,including two and four non-linear forced dynamical systems with continuous action spaces.The experimental results show that CKNet has strong long-term prediction capabilities with sufficient precision.

Polo-like kinase 1 suppresses lung adenocarcinoma immunity throughnecroptosis

Polo-like kinase 1(PLK1)plays a crucial role in cell mitosis and has been associated with necroptosis.However,the role of PLK1 and necroptosis in lung adenocarcinoma(LA)remains unclear.In this study,we analyzed The Cancer Genome Atlas(TCGA)and Genotype-Tissue Expression databases to evaluate the prognostic value and mechanistic role of PLK1 in LA.PLK1 was found to be highly expressed in LA and was positively associated with advanced disease staging and poor survival outcomes.Functional enrichment analysis showed that PLK1 was involved in cell mitosis,neurotransmitter transmission,and drug metabolism.Further analysis using single-sample gene set enrichment analysis and ESTIMATE algorithm revealed a correlation between PLK1 expression and immune infiltration in LA.Silencing of PLK1 using miRNA transfection in LA cells reduced cell proliferation and increased apoptosis,as well as upregulating the expression of necroptosis-related proteins,such as RIPK1,RIPK3,and MLKL.Additionally,nude mouse transplantation tumor experiments demonstrated that silencing PLK1 reduced the growth capacity of LA cells.These findings suggest that PLK1 plays a critical role in LA progression by regulating necroptosis and immune infiltration,and may serve as a potential therapeutic target for immunotherapy.Furthermore,PLK1 expression can be used as a prognostic biomarker for LA patients.

CDC20,TOP2A and NEK2 Expression in Esophageal Squamous Cell Carcinoma and Its Clinical Significance

Objective:to study the expression and clinical significance CDC20,TOP2A,NEK2 esophageal squamous cell carcinoma.Methods:To select 70 patients with esophageal squamous cell carcinoma,Between August 2018-August 2020,All intraoperative pathological specimens,A group-35 cases),Cancer tissue,B group,adjacent tissues),two groups of CDC20,TOP2A,NEK 2 expression were detected and analyzed by immunohistochemistry and semi-quantitative reverse transcription polymerase chain reaction-RT-PcR)assay.Results:the values of CDC20,TOP2A,NEK2 expression level in A group were significantly higher than those in B group-P<0.05).The expression level CDC20,TOP2A,NEK2 esophageal squamous cell carcinoma was positively correlated with TNM stage and lymphatic metastasis,and negatively correlated with tumor differentiation.Conclusion:CDC20,TOP2A,NEK2 high expression level directly affects the metastasis,recurrence and prognosis of esophageal squamous cell carcinoma.The combination of three indexes can accurately evaluate the pathological status of patients with esophageal squamous cell carcinoma and help to judge the prognosis of patients accurately.

Rapid identification of volatile organic compounds and their isomers in the atmosphere

Isomers are widely present in volatile organic compounds(VOCs),and it is a tremendous challenge to rapidly distinguish the isomers of VOCs in the atmosphere.In this work,laserinduced breakdown spectroscopy(LIBS)technology was developed to online distinguish VOCs and their isomers in the air.First,LIBS was used to directly detect halogenated hydrocarbons(a typical class of VOCs)and the characteristic peaks of the related halogens were observed in the LIBS spectra.Then,comparing the LIBS spectra of various samples,it was found that for VOCs with different molecular formulas,although the spectra are completely the same in elemental composition,there are still significant differences in the relative intensity of the spectral lines and other information.Finally,in light of the shortcomings of traditional LIBS technology in identifying isomers,machine learning algorithms were introduced to develop the LIBS technique to identify the isomers of atmospheric VOCs,and the recognition results were very good.It is proved that LIBS combined with machine learning algorithms is promising for online traceability of VOCs in the atmospheric environment.

Expression of CDC20, TOP2A in Esophageal Phosphorus Carcinoma and Its Relationship with Survival of Esophageal Carcinoma

Objective:To study the expression of CDC20,TOP2A in esophageal squamous cell carcinoma and its relationship with survival of esophageal carcinoma.Methods:65 patients with esophageal squamous cell carcinoma from January 2016 to June 2018 were selected by computer random selection.All patients were treated with radical operation.The CDC20,TOP2A expression of the patients was examined.At the same time,the relationship between 3-year survival rate and CDC20,TOP2A was analyzed by follow-up investigation.Results:the CDC20,TOP2A expression level of cancer tissue group was higher than that of adjacent tissue group and normal tissue group(P<0.05),and the CDC20,TOP2A expression level of adjacent tissue group was higher than that of normal tissue group(P<0.05).There was no significant difference in sex,age,tumor size,tumor location and CDC20,TOP2A expression level in patients with esophageal squamous cell carcinoma,P>0.05;there were differences between groups(P P>0.05)and positive proportion in TNM stage,lymphatic metastasis,invasion factor and CDC20,TOP2A expression level;there were differences in tumor differentiation,5-year survival rate and CDC20,TOP2A expression level(P P>0.05),and showed inverse proportion relationship.Conclusion:metastasis,recurrence and prognosis of esophageal squamous cell carcinoma are related to the level of CDC20,TOP2A expression.These two indexes can effectively evaluate the pathological situation of esophageal cancer and provide an important reference for the prognosis of esophageal squamous cell carcinoma patients.

压缩机泄压放空天然气部分回收工艺设计研究

通过分析研究长输管道典型压气站工艺,提出基于天然气支线管道的压缩机泄压放空天然气部分回收工艺设计方案,并进行了经济性和可行性分析,流程简单,投入小,为其他压气站工艺改造和新建压气站提供工艺设计参考。

Deep reinforcement learning based active surge control for aeroengine compressors

This study proposes an active surge control method based on deep reinforcement learning to ensure the stability of compressors when adhering to the pressure rise command across the wide operating range of an aeroengine.Initially,the study establishes the compressor dynamic model with uncertainties,disturbances,and Close-Coupled Valve(CCV)actuator delay.Building upon this foundation,a Partially Observable Markov Decision Process(POMDP)is defined to facilitate active surge control.To address the issue of unobservability,a nonlinear state observer is designed using a finite-time high-order sliding mode.Furthermore,an Improved Soft Actor-Critic(ISAC)algorithm is developed,incorporating prioritized experience replay and adaptive temperature parameter techniques,to strike a balance between exploration and convergence during training.In addition,reasonable observation variables,error-segmented reward functions,and random initialization of model parameters are employed to enhance the robustness and generalization capability.Finally,to assess the effectiveness of the proposed method,numerical simulations are conducted,and it is compared with the fuzzy adaptive backstepping method and Second-Order Sliding Mode Control(SOSMC)method.The simulation results demonstrate that the deep reinforcement learning based controller outperforms other methods in both tracking accuracy and robustness.Consequently,the proposed active surge controller can effectively ensure stable operation of compressors in the high-pressure-ratio and high-efficiency region.

Pneumatic pressure control based on improved NMPC and its application to aeroengine surge simulation

In the semi-physical simulation of aeroengines,using the pneumatic pressure servo control technology to provide realistic pneumatic excitation to the sensors and electronic controller can improve the confidence of the simulation and reduce the test cost and risk.However,the existing methods could not satisfy the precise simulation of large-amplitude and high-frequency pulsating pressure during aeroengine surge.In this paper,a pneumatic pressure control system with asymmetric groups of the High-Speed on–off Valve(HSV)is designed,and an Improved Nonlinear Model Predictive Control(INMPC)method is proposed.First,the volumetric flow characteristics of HSV are tested and analyzed with Pulse Width Modulation(PWM)signal input.Then,a simplified HSV model with the volume flow characteristic correction is developed.Based on these,an integrated model for the whole system is further established and used as the prediction model in INMPC.To improve the computational speed of the rolling optimization process,the mapping scheme from control signal to PWM duty cycle of HSVs and the objective function with exterior penalty function are designed.Finally,the random step,sinusoidal and real engine surge data are set as the reference pressure in multiple comparative experiments to verify the effectiveness of the pressure tracking system.

Spatial compartmentalization of metal nanoparticles within metal-organic frameworks for tandem reaction

Fabrication of multifunctional catalysts has always been the pursuit of synthetic chemists due to their efficiency,cost-effectiveness,and environmental friendliness.However,it is difficult to control multi-step reactions in one-pot,especially the spatial compartmentalization of incompatible active sites.Herein,we constructed metal-organic framework(MOF)composites which regulate the location distribution of metal nanoparticles according to the reaction path and coupled with the diffusion of substrates to achieve tandem reaction.The designed UiO-66-Pt-Au catalyst showed good activity and selectivity in hydrosilylation-hydrogenation tandem reaction,because the uniform microporous structures can control the diffusion path of reactants and intermediates,and Pt and Au nanoparticles were arranged in core-shell spatial distribution in UiO-66.By contrast,the low selectivity of catalysts with random deposition and physical mixture demonstrated the significance of artificial control to the spatial compartmentalization of active sites in tandem catalytic reactions,which provides a powerful approach for designing high-performance and multifunctional heterogeneous catalysts.