Multi-mode process monitoring based on a novel weighted local standardization strategy and support vector data description

There are multiple operating modes in the real industrial process, and the collected data follow the complex multimodal distribution, so most traditional process monitoring methods are no longer applicable because their presumptions are that sampled-data should obey the single Gaussian distribution or non-Gaussian distribution. In order to solve these problems, a novel weighted local standardization(WLS) strategy is proposed to standardize the multimodal data, which can eliminate the multi-mode characteristics of the collected data, and normalize them into unimodal data distribution. After detailed analysis of the raised data preprocessing strategy, a new algorithm using WLS strategy with support vector data description(SVDD) is put forward to apply for multi-mode monitoring process. Unlike the strategy of building multiple local models, the developed method only contains a model without the prior knowledge of multi-mode process. To demonstrate the proposed method's validity, it is applied to a numerical example and a Tennessee Eastman(TE) process. Finally, the simulation results show that the WLS strategy is very effective to standardize multimodal data, and the WLS-SVDD monitoring method has great advantages over the traditional SVDD and PCA combined with a local standardization strategy(LNS-PCA) in multi-mode process monitoring.

Standard liver weight model in adult deceased donors with fatty liver: A prospective cohort study

BACKGROUND Standard liver weight(SLW)is frequently used in deceased donor liver transplantation to avoid size mismatches with the recipient.However,some deceased donors(DDs)have fatty liver(FL).A few studies have reported that FL could impact liver size.To the best of our knowledge,there are no relevant SLW models for predicting liver size.AIM To demonstrate the relationship between FL and total liver weight(TLW)in detail and present a related SLW formula.METHODS We prospectively enrolled 212 adult DDs from West China Hospital of Sichuan University from June 2019 to February 2021,recorded their basic information,such as sex,age,body height(BH)and body weight(BW),and performed abdominal ultrasound(US)and pathological biopsy(PB).The chi-square test and kappa consistency score were used to assess the consistency in terms of FL diagnosed by US relative to PB.Simple linear regression analysis was used to explore the variables related to TLW.Multiple linear regression analysis was used to formulate SLW models,and the root mean standard error and interclass correlation coefficient were used to test the fitting efficiency and accuracy of the model,respectively.Furthermore,the optimal formula was compared with previous formulas.RESULTS Approximately 28.8%of DDs had FL.US had a high diagnostic ability(sensitivity and specificity were 86.2%and 92.9%,respectively;kappa value was 0.70,P<0.001)for livers with more than a 5%fatty change.Simple linear regression analysis showed that sex(R2,0.226;P<0.001),BH(R2,0.241;P<0.001),BW(R2,0.441;P<0.001),BMI(R2,0.224;P<0.001),BSA(R2,0.454;P<0.001)and FL(R2,0.130;P<0.001)significantly impacted TLW.In addition,multiple linear regression analysis showed that there was no significant difference in liver weight between the DDs with no steatosis and those with steatosis within 5%.Furthermore,in the context of hepatic steatosis,TLW increased positively(nonlinear);compared with the TLW of the non-FL group,the TLW of the groups with hepatic steatosis within 5%,between 5%and 20%and more than 20%increased by 0 g,90 g,and 340 g,respectively.A novel formula,namely,-348.6+(110.7 x Sex[0=Female,1=Male])+958.0 x BSA+(179.8 x FLUS[0=No,1=Yes]),where FL was diagnosed by US,was more convenient and accurate than any other formula for predicting SLW.CONCLUSION FL is positively correlated with TLW.The novel formula deduced using sex,BSA and FLUS is the optimal formula for predicting SLW in adult DDs.