RESUMEN
State-of-charge (SOC) is a relative quantity that describes the ratio of the remaining capacity to the present maximum available capacity. Accurate SOC estimation is essential for a battery-management system. In addition to informing the user of the expected usage until the next recharge, it is crucial for improving the utilization efficiency and service life of the battery. This study focuses on applying deep-learning techniques, and specifically convolutional residual networks, to estimate the SOC of lithium-ion batteries. By stacking the values of multiple measurable variables taken at many time instants as the model inputs, the process information for the voltage or current generation, and their interrelations, can be effectively extracted using the proposed convolutional residual blocks, and can simultaneously be exploited to regress for accurate SOCs. The performance of the proposed network model was evaluated using the data obtained from a lithium-ion battery (Panasonic NCR18650PF) under nine different driving schedules at five ambient temperatures. The experimental results demonstrated an average mean absolute error of 1.260%, and an average root-mean-square error of 0.998%. The number of floating-point operations required to complete one SOC estimation was 2.24 × 106. These results indicate the efficacy and performance of the proposed approach.
Asunto(s)
Suministros de Energía Eléctrica , Litio , Iones , Redes Neurales de la ComputaciónRESUMEN
BACKGROUND: Primary sclerosing cholangitis (PSC) is a chronic cholestatic disorder characterized by progressive inflammation and fibrosis of the biliary tract, evolving to cirrhosis. It is commonly associated with inflammatory bowel disease (IBD). AIM: To communicate the clinical characteristics of patient with PSC seen in two reference centers. PATIENTS AND METHODS: Review of medical records of patients with PSC confirmed by liver biopsies. The clinical picture, laboratory abnormalities, imaging studies and treatment were recorded. RESULTS: Thirty three patients (aged 16 to 73 years, 64% female) were identified. They corresponded to 1.7% of liver biopsies done between 1991-2003. Clinical presentation was a cholestatic picture in 40%, right upper abdominal pain in 36%, a dysenteric syndrome in 9% and varied symptoms in 15%. Laboratory tests showed cholestasis in 94% and positive anti ANCA, SMA, ANA and AMA antibodies in 28, 18, 15 and 9% of cases, respectively. Endoscopic retrograde cholangiopancreatography and magnetic resonance cholangiography were diagnostic in 43 and 58% of patients, respectively. There was an association with ulcerative colitis in 12% of cases. Liver biopsies showed grade I PSC in 76% and grade II-III in 6% of patients. It also showed a concomitant chronic hepatitis and primary biliary cirrhosis in 12 and 6% of cases, respectively. Treatment consisted on ursodeoxycholic acid (UDCA) in 45%, UDCA plus 5-aminosalicylic acid derivatives in 12% and UDCA plus immunosuppresors in 12% of patients. Two patients had to be transplanted. CONCLUSIONS: PSC is an uncommon cause of chronic liver disease. It is suspected in cholestatic patients and confirmed with a liver biopsy. It can be associated with other autoimmune hepatic and extrahepatic diseases.