Characterization of unknown groundwater contaminant sources is an important but difficult step in effective groundwater management. The difficulties arise mainly due to the time of contaminant detection which usually ...Characterization of unknown groundwater contaminant sources is an important but difficult step in effective groundwater management. The difficulties arise mainly due to the time of contaminant detection which usually happens a long time after the start of contaminant source(s) activities. Usually, limited information is available which also can be erroneous. This study utilizes Self-Organizing Map (SOM) and Gaussian Process Regression (GPR) algorithms to develop surrogate models that can approximate the complex flow and transport processes in a contaminated aquifer. The important feature of these developed surrogate models is that unlike the previous methods, they can be applied independently of any linked optimization model solution for characterizing of unknown groundwater contaminant sources. The performance of the developed surrogate models is evaluated for source characterization in an experimental contaminated aquifer site within the heterogeneous sand aquifer, located at the Botany Basin, New South Wales, Australia. In this study, the measured contaminant concentrations and hydraulic conductivity values are assumed to contain random errors. Simulated responses of the aquifer to randomly specified contamination stresses as simulated by using a three-dimensional numerical simulation model are utilized for initial training of the surrogate models. The performance evaluation results obtained by using different surrogate models are also compared. The evaluation results demonstrate the different capabilities of the developed surrogate models. These capabilities lead to development of an efficient methodology for source characterization based on utilizing the trained and tested surrogate models in an inverse mode. The obtained results are satisfactory and show the potential applicability of the SOM and GPR-based surrogate models for unknown groundwater contaminant source characterization in an inverse mode.展开更多
Hydraulic piston pumps are commonly used in aircraft. In order to improve the viability of aircraft and energy efficiency, intelligent variable pressure pump systems have been used in aircraft hydraulic systems more a...Hydraulic piston pumps are commonly used in aircraft. In order to improve the viability of aircraft and energy efficiency, intelligent variable pressure pump systems have been used in aircraft hydraulic systems more and more widely. Efficient fault diagnosis plays an important role in improving the reliability and performance of hydraulic systems. In this paper, a fault diagnosis method of an intelligent hydraulic pump system（IHPS） based on a nonlinear unknown input observer（NUIO） is proposed. Different from factors of a full-order Luenberger-type unknown input observer, nonlinear factors of the IHPS are considered in the NUIO. Firstly, a new type of intelligent pump is presented, the mathematical model of which is established to describe the IHPS. Taking into account the real-time requirements of the IHPS and the special structure of the pump, the mechanism of the intelligent pump and failure modes are analyzed and two typical failure modes are obtained. Furthermore, a NUIO of the IHPS is performed based on the output pressure and swashplate angle signals. With the residual error signals produced by the NUIO, online intelligent pump failure occurring in real-time can be detected. Lastly, through analysis and simulation, it is confirmed that this diagnostic method could accurately diagnose and isolate those typical failure modes of the nonlinear IHPS. The method proposed in this paper is of great significance in improving the reliability of the IHPS.展开更多
Objective A diagnostic model was established to discriminate infectious diseases from non-infectious diseases. Methods The clinical data of patients with fever of unknown origin(FUO) hospitalized in Xiangya Hospital C...Objective A diagnostic model was established to discriminate infectious diseases from non-infectious diseases. Methods The clinical data of patients with fever of unknown origin(FUO) hospitalized in Xiangya Hospital Central South University, from January, 2006 to April, 2011 were retrospectively analyzed. Patients enrolled were divided into two groups. The first group was used to develop a diagnostic model: independent variables were recorded and considered in a logistic regression analysis to identify infectious and non-infectious diseases(αin = 0.05, αout = 0.10). The second group was used to evaluate the diagnostic model and make ROC analysis.Results The diagnostic rate of 143 patients in the first group was 87.4%, the diagnosis included infectious disease(52.4%), connective tissue diseases(16.8%), neoplastic disease(16.1%) and miscellaneous(2.1%). The diagnostic rate of 168 patients in the second group was 88.4%, and the diagnosis was similar to the first group. Logistic regression analysis showed that decreased white blood cell count(WBC < 4.0×109/L), higher lactate dehydrogenase level(LDH > 320 U/L) and lymphadenectasis were independent risk factors associated with non-infectious diseases. The odds ratios were 14.74, 5.84 and 5.11(P ≤ 0.01), respectively. In ROC analysis, the sensitivity and specificity of the positive predictive values was 62.1% and 89.1%, respectively, while that of negative predicting values were 75% and 81.7%, respectively(AUC = 0.76, P = 0.00).Conclusions The combination of WBC < 4.0×109/L, LDH > 320 U/L and lymphadenectasis may be useful in discriminating infectious diseases from non-infectious diseases in patients hospitalized as FUO.展开更多
文摘Characterization of unknown groundwater contaminant sources is an important but difficult step in effective groundwater management. The difficulties arise mainly due to the time of contaminant detection which usually happens a long time after the start of contaminant source(s) activities. Usually, limited information is available which also can be erroneous. This study utilizes Self-Organizing Map (SOM) and Gaussian Process Regression (GPR) algorithms to develop surrogate models that can approximate the complex flow and transport processes in a contaminated aquifer. The important feature of these developed surrogate models is that unlike the previous methods, they can be applied independently of any linked optimization model solution for characterizing of unknown groundwater contaminant sources. The performance of the developed surrogate models is evaluated for source characterization in an experimental contaminated aquifer site within the heterogeneous sand aquifer, located at the Botany Basin, New South Wales, Australia. In this study, the measured contaminant concentrations and hydraulic conductivity values are assumed to contain random errors. Simulated responses of the aquifer to randomly specified contamination stresses as simulated by using a three-dimensional numerical simulation model are utilized for initial training of the surrogate models. The performance evaluation results obtained by using different surrogate models are also compared. The evaluation results demonstrate the different capabilities of the developed surrogate models. These capabilities lead to development of an efficient methodology for source characterization based on utilizing the trained and tested surrogate models in an inverse mode. The obtained results are satisfactory and show the potential applicability of the SOM and GPR-based surrogate models for unknown groundwater contaminant source characterization in an inverse mode.
基金co-supported by the National Natural Science Foundation of China (Nos. 51620105010, 51575019 and 51675019)National Basic Research Program of China (No. 2014CB046400)111 Program of China
文摘Hydraulic piston pumps are commonly used in aircraft. In order to improve the viability of aircraft and energy efficiency, intelligent variable pressure pump systems have been used in aircraft hydraulic systems more and more widely. Efficient fault diagnosis plays an important role in improving the reliability and performance of hydraulic systems. In this paper, a fault diagnosis method of an intelligent hydraulic pump system（IHPS） based on a nonlinear unknown input observer（NUIO） is proposed. Different from factors of a full-order Luenberger-type unknown input observer, nonlinear factors of the IHPS are considered in the NUIO. Firstly, a new type of intelligent pump is presented, the mathematical model of which is established to describe the IHPS. Taking into account the real-time requirements of the IHPS and the special structure of the pump, the mechanism of the intelligent pump and failure modes are analyzed and two typical failure modes are obtained. Furthermore, a NUIO of the IHPS is performed based on the output pressure and swashplate angle signals. With the residual error signals produced by the NUIO, online intelligent pump failure occurring in real-time can be detected. Lastly, through analysis and simulation, it is confirmed that this diagnostic method could accurately diagnose and isolate those typical failure modes of the nonlinear IHPS. The method proposed in this paper is of great significance in improving the reliability of the IHPS.
文摘Objective A diagnostic model was established to discriminate infectious diseases from non-infectious diseases. Methods The clinical data of patients with fever of unknown origin(FUO) hospitalized in Xiangya Hospital Central South University, from January, 2006 to April, 2011 were retrospectively analyzed. Patients enrolled were divided into two groups. The first group was used to develop a diagnostic model: independent variables were recorded and considered in a logistic regression analysis to identify infectious and non-infectious diseases(αin = 0.05, αout = 0.10). The second group was used to evaluate the diagnostic model and make ROC analysis.Results The diagnostic rate of 143 patients in the first group was 87.4%, the diagnosis included infectious disease(52.4%), connective tissue diseases(16.8%), neoplastic disease(16.1%) and miscellaneous(2.1%). The diagnostic rate of 168 patients in the second group was 88.4%, and the diagnosis was similar to the first group. Logistic regression analysis showed that decreased white blood cell count(WBC < 4.0×109/L), higher lactate dehydrogenase level(LDH > 320 U/L) and lymphadenectasis were independent risk factors associated with non-infectious diseases. The odds ratios were 14.74, 5.84 and 5.11(P ≤ 0.01), respectively. In ROC analysis, the sensitivity and specificity of the positive predictive values was 62.1% and 89.1%, respectively, while that of negative predicting values were 75% and 81.7%, respectively(AUC = 0.76, P = 0.00).Conclusions The combination of WBC < 4.0×109/L, LDH > 320 U/L and lymphadenectasis may be useful in discriminating infectious diseases from non-infectious diseases in patients hospitalized as FUO.
