Knowledge aided model-based approach to failure diagnosis of adaptively controlled systems

Author(s):  
K. Kumamaru ◽  
K. Inoue ◽  
S. Nonaka ◽  
T. Nakashima
Author(s):  
Matti Linjama

Energy-efficient motion control of hydraulic actuators is a challenging task. Throttle-free solutions have the potential for high efficiency. The main throttle-free approaches are pump-controlled systems, transformer-based solutions, and digital hydraulic solutions, such as switching transformers, multi-chamber cylinder and multi-pressure systems. This paper presents a novel solution based on a so-called digital hydraulic power management system (DHPMS). The DHPMS is freely rotating and a hydraulic accumulator is used for energy storage. In contrast to existing approaches, each actuator has its own DHPMS and a small accumulator to locally handle the power peaks. Only an average amount of power is needed from the hydraulic grid, radically reducing the size of the supply pump and the hydraulic piping and hosing. Pump flow is only 12.5% of the peak flow of the actuator in the case studied. Control of this type of system is challenging, and the model-based approach is used. The controller uses a simplified model and functionality is verified by using a detailed simulation model of the system. The results show that the approach is feasible but is demanding on the control valves. The system delay is also relatively long, which reduces the control performance in high-end systems. Nevertheless, this approach has potential in mobile machines, for example.


2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
C Coorey ◽  
O Tang ◽  
J.Y.H Yang ◽  
G Figtree

Abstract Background There is emerging evidence that the pathophysiological mechanisms of heart failure are associated with alterations in serum metabolites. Such metabolomic signatures may be useful for heart failure diagnosis, stratification and prognosis. Purpose To evaluate the utility of including metabolomic biomarkers in addition to traditional cardiac biomarkers in a machine learning prediction model of heart failure diagnosis in the well-characterised Canagliflozin Cardiovascular Assessment Study (CANVAS) cohort. Methods A subgroup of the CANVAS/CANVAS-R study cohort was analysed. 101 metabolites in plasma were measured by HPLC (HILIC)-mass spectrometry. A 10-times 5-fold cross-validated support vector machine model with radial basis kernel function was constructed to predict heart failure diagnosis using traditional biomarkers alone and using the combination of traditional biomarkers and metabolomic biomarkers. Model performance and variable importance were both evaluated by area under the curve (AUC) of the receiver operating characteristics (ROC) curve. Results are shown as mean ± standard deviation. Results 967 patients (of which 402 patients had heart failure) were included in the analysis with 341 females, mean age 63±8 years and mean body mass index (BMI) 33±5 kg/m2. All patients had diabetes mellitus with mean HbA1c 8.2±0.9%. The prediction model based on only traditional biomarkers had mean AUC 72±3% and the prediction model based on both traditional biomarkers and metabolomic biomarkers had mean AUC 80±3%. The top metabolomic biomarkers for predicting heart failure were threonine, L-homoserine, creatine and deoxyadenosine. Conclusion Metabolomic biomarkers improved diagnostic performance of a heart failure prediction model and captured variation not encompassed by traditional cardiac biomarkers. FUNDunding Acknowledgement Type of funding sources: Private company. Main funding source(s): Janssen Research and Development


Author(s):  
Pentti Lautala ◽  
Tuula Ruokonen ◽  
Martti Välisuo ◽  
Juhani Hyvärinen

1991 ◽  
Vol 24 (3) ◽  
pp. 657-662 ◽  
Author(s):  
K. Kumamaru ◽  
S. Sagara ◽  
A. Nakai ◽  
T. Söderström

Sign in / Sign up

Export Citation Format

Share Document