Summary
Decentralized waste water treatment facilities monitor many features that are complexly related. The ability to detect the onset of a fault and to identify variables accurately that have shifted because of the fault are vital to maintaining proper system operation and high quality produced water. Various multivariate methods have been proposed to perform fault detection and isolation, but the methods require data to be independent and identically distributed when the process is in control, and most require a distributional assumption. We propose a distribution-free retrospective change-point-detection method for auto-correlated and non-stationary multivariate processes. We detrend the data by using observations from an in-control time period to account for expected changes due to external or user-controlled factors. Next, we perform the fused lasso, which penalizes differences in consecutive observations, to detect faults and to identify shifted variables. To account for auto-correlation, the regularization parameter is chosen by using an estimated effective sample size in the extended Bayesian information criterion. We demonstrate the performance of our method compared with a competitor in simulation. Finally, we apply our method to waste water treatment facility data with a known fault, and the variables identified by our proposed method are consistent with the operators’ diagnosis of the fault's cause.
Unsupervised process monitoring for fault detection and data cleaning is underdeveloped for municipal wastewater treatment plants (WWTPs) due to the complexity and volume of data produced by sensors, equipment, and control systems. The goal of this work is to extensively test and tune an unsupervised process monitoring method that can promptly identify faults in a full-scale decentralized WWTP prior to significant system changes. Adaptive dynamic principal component analysis (AD-PCA) is a dimension reduction method modified to address autocorrelation and nonstationarity in multivariate processes and is evaluated in this work for its ability to continuously detect drift, shift, and spike faults. For spike faults, univariate drift faults, and multivariate shift faults, implementing AD-PCA on data that are subset by treatment processes and operating states with significant differences in covariates and whose model parameters use week-long training windows, moderate cumulative variance, and a high threshold for detection was found to detect faults prior to existing operational thresholds. To improve the consistency with which the AD-PCA method detects out-of-control conditions in real time, additional work is needed to remove outliers prior to model fitting and to detect multivariate drift faults in which the covariates change slowly.
Introduction: Coccidioidal meningitis (CM) is the most lethal form of disseminated coccidioidomycosis. Current guidelines recommend fluconazole as initial therapy but there has been a paucity of data regarding failure of fluconazole and optimal fluconazole dosage in the treatment of CM. We conducted this study to understand risk factors for fluconazole failure. Methods: We conducted a single-center retrospective chart review of patients diagnosed with coccidioidal meningitis between 1 January 1988 and 15 May 2021. Relevant demographic and clinical variables were collected, along with outcomes including treatment failure and death at any point. Univariate tests were conducted using the chi-squared goodness of fit test and analysis of variance. Results: Among 71 patients who began treatment for CM with fluconazole, 22 (31%) developed worsening meningitis at a median time of 206 days. Longer time from symptom onset to diagnosis of CM was a risk factor for fluconazole failure. Although the absolute failure rate of fluconazole starting dose of 400 mg daily was higher than that of 800 mg daily, the differences did not achieve statistical significance (p = 0.39). Conclusion: Fluconazole failure is not uncommon in the treatment of CM. A dose of 800 mg daily was not superior to a dose of 400 mg daily. All patients on fluconazole for CM require close monitoring.
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.