Unknown fault detection for EGT multi-temperature signals based on self-supervised feature learning and unary classification

Intelligent tpower systems scanimprove operational efficiency by installing a large number of sensors.Data-based methods of supervised learning have gained popularity because of available Big Data and computing resources.However,the common paradigm of the loss function in supervised learning requires large amounts of labeled data and cannot process unlabeled data.The scarcity of fault data and a large amount of normal data in practical use pose great challenges to fault detection algorithms.Moreover,sensor data faults in power systems are dynamically changing and pose another challenge.Therefore,a fault detection method based on self-supervised feature learning was proposed to address the above two challenges.First,self-supervised learning was employed to extract features under various working conditions only using large amounts of normal data.The self-supervised representation learning uses a sequence-based Triplet Loss.The extracted features of large amounts of normal data are then fed into a unary classifier.The proposed method is validated on exhaust gas temperatures(EGTs)of a real-world 9F gas turbine with sudden,progressive,and hybrid faults.A comprehensive comparison study was also conducted with various feature extractors and unary classifiers.The results show that the proposed method can achieve a relatively high recall for all kinds of typical faults.The model can detect progressive faults very quickly and achieve improved results for comparison without feature extractors in terms ofF1 score.

Insights into the Functionalization of the Methylsalicyclic Moiety during the Biosynthesis of Chlorothricin by Comparative Kinetic Assays of the Activities of Two KAS Ⅲ-like Acyltransferases

Summary of main observation and conclusion Chlorothricin (CHL),an archetypal member of the family of spirotetronate antibiotics,possesses a tetronate-containing pentacyclic aglycone that is conjugated with a modified methylsalicyclic acid (MSA) moiety through a disaccharide linkage.MSA is a polyketide product assembled by the iterative type Ⅰ polyketide synthase ChlB1.incorporation of this pharmaceutically important moiety into CHL relies on the activities of two distinct β-Ketoacyl-ACP synthase Ⅲ(KAS Ⅲ)-Iike acyltransferases,ChlB3 and ChlB6,which function together to coordinate the transfer of MSA through ChlB2,a discrete acyl carrier protein (ACP).During the maturation of CHL,MSA needs to be further functionalized by C2-O-methylation and C5-chlorination;however,timing of this functionalization process remains poorly understood.In this study,we report comparative kinetic assays of the activities of the two KAS Ⅲ-like acyltransferases ChlB3 and ChlB6 using substrates that vary in substitution extent and ACP carrier.ChlB3 prefers to transfer the immediately assembled 6-methyI-MSA moiety from ChlB1-ACP to the discrete ACP ChlB2,from which this moiety is preferred to be transferred directly onto the molecule desmethylsalicyl-CHL prior to C2-O-methylation and C5-chlorination.Consequently,MSA functionalization appears to occur at the molecule level rather than at the covalently tethered protein level,i.e.,ChlB1-ACP or ChlB2.Both ChlB3 and ChlB6 are flexible in substrate tolerance,holding promise for CHL engineering-based structural diversity by using variable MSA moiety.