Few-shot working condition recognition of a sucker-rod pumping system based on a 4-dimensional time-frequency signature and meta-learning convolutional shrinkage neural network

The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.

Comparative study of the clinical efficacy of all-inside and traditional techniques in anterior cruciate ligament reconstruction

BACKGROUND Many studies have focused on the femoral tunnel technique and fixation method,but few studies have involved the tibial tunnel technique and fixation method.The all-inside technique is one of the new techniques that has been described in recent years.All-inside anterior cruciate ligament(ACL)reconstruction is based on a tibial socket instead of a full tunnel.This method has many potential advantages.AIM To compare clinical outcomes of knee ACL autograft reconstruction using allinside quadrupled semitendinosus(AIST)and traditional hamstring tendon(TBT)techniques.METHODS From January 2017 to October 2019,the clinical data of 80 patients with ACL reconstruction were retrospectively analyzed,including 67 males and 13 females.The patients had an average age of 24.3±3.1 years(age range:18-33 years).The AIST technique was used in 42 patients and the TBT technique was used in 38 patients.The time between operation and injury,operative duration,postoperative visual analogue scale(VAS)score and knee functional recovery were recorded and compared between the two groups.The International Knee Documentation Committee(IKDC)and Lysholm scoring system were used to comprehensively evaluate clinical efficacy.RESULTS Eighty patients were followed for 24-36 mo,with an average follow-up duration of 27.5±1.8 mo.There were no significant differences in the time between surgery and injury,operative duration,IKDC and Lysholm scores of the affected knee at the last follow-up evaluation between the two groups.There were significant differences in VAS scores 1 d,3 d,7 d,2 wk and 1 mo after surgery(P<0.05).There was no significant difference in VAS score at 3 mo,6 mo and 1 year after operation.CONCLUSION The efficacy of the AIST ACL reconstruction technique was comparable to the TBT technique,but the postoperative pain was less with the AIST technique.Thus,the AIST technique is an ideal treatment choice for ACL reconstruction.

Arthroscopy with subscapularis upper one-third tenodesis for treatment of recurrent anterior shoulder instability independent of glenoid bone loss

BACKGROUND Recurrent anterior shoulder instability is a common traumatic injury,the main clinical manifestation of which is recurrent anteroinferior dislocation of the humeral head.The current follow-up study showed that the effect of arthroscopic Bankart repair is unreliable.AIM To evaluate the clinical efficacy of arthroscopy with subscapularis upper one-third tenodesis for treatment of anterior shoulder instability,and to develop a method to further improve anterior stability and reduce the recurrence rate.METHODS Between January 2015 and December 2018,male patients with recurrent anterior shoulder instability were selected.One hundred and twenty patients had a glenoid defect<20%and 80 patients had a glenoid defect>20%.The average age was 25 years(range,18–45 years).Patients with a glenoid defect<20%underwent arthroscopic Bankart repair with a subscapularis upper one-third tenodesis.The patients with a glenoid defect>20%underwent an arthroscopic iliac crest bone autograft with a subscapularis upper one-third tenodesis.All patients were assessed with Rowe and Constant scores.RESULTS The average shoulder forward flexion angle was 163.6°±8.3°and 171.8°±3.6°preoperatively and at the last follow-up evaluation,respectively.The average external rotation angle when abduction was 90°was 68.4°±13.6°and 88.5°±6.2°preoperatively and at the last follow-up evaluation,respectively.The mean Rowe scores preoperatively and at the last follow-up evaluation were 32.6±3.2 and 95.2±2.2,respectively(P<0.05).The mean Constant scores preoperatively and at the last follow-up evaluation were 75.4±3.5 and 95.8±3.3,respectively(P<0.05).No postoperative dislocations were recorded by the end of the follow-up period.CONCLUSION Arthroscopy with subscapularis upper one-third tenodesis was effective for treatment of recurrent anterior shoulder instability independent of the size of the glenoid bone defect,enhanced anterior stability of the shoulder,and did not affect postoperative range of motion of the affected limb.

An online BOF terminal temperature control model based on big data learning

The development of basic oxygen furnace(BOF)intelligent steelmaking model based on artificial intelligence and big data is the focus of international research and development.In the view of the current situation that the BOF cannot continuously detect the composition and molten steel temperature,combined with the monitoring results of the high-definition and high-brightness camera at the converter mouth,an online BOF terminal temperature control model is established based on big data learning case-based reasoning model and expert system model.The on-site online operation shows that the model can effectively improve the"flying lance"phenomenon and the splashing condition,the stability and safety of smelting process are better than that of artificial smelting,the"flying lance"rate decreases from 39.2% to 0,the early splashing rate decreases from 21.4% to 13.3% and the late splashing rate decreases from 81.25% to 56.7%.When the temperature fluctuation is controlled at±15 oC,the hit rate of the terminal temperature under the automatic control of the model is 90.91%.

Properties of positive solutions to a nonlinear parabolic problem

This paper deals with the properties of positive solutions to a quasilinear parabolic equation with the nonlinear absorption and the boundary flux. The necessary and sufficient conditions on the global existence of solutions are described in terms of different parameters appearing in this problem. Moreover, by a result of Chasseign and Vázquez and the comparison principle, we deduce that the blow-up occurs only on the boundary ?Ω. In addition, for a bounded Lipschitz domain Ω, we establish the blow-up rate estimates for the positive solution to this problem with a = 0.

On pattern formation in the Gray-Scott model

In the paper, we investigate an elliptic system well-known as the Gray-Scott model and present some further results for positive solutions of this model. More precisely, we give the refined a priori estimates of positive solutions, and improve some previous results for the non-existence and existence of positive non-constant solutions as the parameters are varied, which imply some certain conditions where the pattern formation occurs or not.