Abstract: A vehicle dynamics control system receives a feedback state signal including values of a roll rate and a roll angle of the motion of the vehicle and updates parameters of a model of roll dynamics of the vehicle by fitting the received values into the roll dynamics model. The roll dynamics model explains the evolution of the roll rate and the roll angle based on the parameters including a center of gravity (CoG) parameter modeling a location of a CoG of the vehicle, and a spring constant and a damping coefficient modeling suspension dynamics of the vehicle. The system determines a control command for controlling at least one actuator of the vehicle using a motion model including the updated CoG parameter and submits the control command to the vehicle controller to control the motion of the vehicle.

Abstract: A big data-based driving information provision system may include a sensor configured to measure and collect state monitoring data of an engine, vehicle monitoring data, and vibration data; an engine electronic control unit (ECU) configured to generate a combustion characteristic index (CCI) data of the engine; and a graphic controller configured to generate a primary deep learning model which classifies the big data including the state monitoring data, the vehicle monitoring data, the vibration data, and the CCI into at least two categories.

Abstract: A system and method for the use of machine learning for detecting faults for cylinder intake and/or exhaust valves that do not properly open or close as commanded and for generating a flag for such faults.

Abstract: An apparatus and method for controlling an autonomous vehicle are provided. The apparatus includes a user input unit that receives identification information of a driver within the vehicle during autonomous driving and an information collection unit that acquires a global route of the vehicle and surrounding environment information. A controller determines a learning section on the global route based on the surrounding environment information and outputs a driving pattern of the driver by performing repetitive learning based on operation information of the driver in the learning section. Autonomous driving of the vehicle is then executed based on the output driving pattern of the driver.

Abstract: A system control a vehicle using a friction function describing a friction between a type of surface of the road and a tire of the vehicle as a function of a slip of a wheel of the vehicle. The parameters of each friction function include an initial slope of the friction function defining a stiffness of the tire and one or combination of a peak friction, a shape factor and a curvature factor of the friction function. Upon estimating a slip and a stiffness of the tire, the system selects from the memory parameters of the friction function corresponding to the current stiffness of the tire, determines a control command using a value of the friction corresponding to the slip of the tire according to the friction function defined by the selected parameters, and submits the control command to an actuator of the vehicle.

Abstract: One embodiment is a system including a component for installation on a vehicle comprising a central maintenance computer (“CMC”); a configuration/maintenance module (“CMM”) associated with the component and including memory for storing component information, a sensor for detecting a condition and generating data indicative thereof; a microprocessor for processing the sensor data and updating the component information with the processing results; and a communications interface between the CMM and the CMC. The system further includes a remaining useful life (“RUL”) module associated with the component that periodically updates an RUL, the RUL module periodically updating an RUL value for the component and communicating the updated RUL value to the CMM for storage in the memory. The CMC communicates with the CMM to update the component information included in the memory based on information input to the CMC by a user or changes in a condition of the vehicle.

Abstract: A method and apparatus for analyzing an investigated complex system the complex system including a plurality of system components, the method includes the steps of providing a base virtual object oriented data model including abstract components corresponding to system components of the investigated complex system, wherein each abstract component of the base virtual object oriented data model includes parameters and attributes of the respective system component of the investigated complex system; mapping sensor tags of sensors deployed in the investigated complex system (2) and/or event names of events received from the investigated complex system to the parameters of the abstract components of the provided base virtual object oriented data model to generate a dedicated data model for the system type of the investigated complex system; and performing a failure mode and/or a root-cause analysis of the investigated complex system on the basis of the dedicated data model.

Abstract: A battery state estimation device for estimating a charged electric charge quantity of a rechargeable battery includes an impedance measurement unit configured to measure a plurality of complex impedances of the rechargeable battery by supplying measurement power to the rechargeable battery, a parameter calculation unit configured to calculate a parameter that includes a ratio of a difference between measurement angular velocities of two complex impedances in a diffusion region among the measured complex impedances to a difference between components of the two complex impedances, and an electric charge quantity estimation unit configured to estimate a charged electric charge quantity of the rechargeable battery based on the calculated parameter and preset correlated information between the charged electric charge quantity of the rechargeable battery and the parameter.

Abstract: Multiple data sources encrypt data using encryption key data received from a first system; a second system does not have access to the encryption key data. The second system receives the encrypted data from the multiple data sources. Because the encryption is additively homomorphic, the second system may create encrypted summation data using the encrypted data. The second system may send the encrypted summation data to the first system, which may then decrypt the encrypted summation data to create unencrypted summation data.

Abstract: A vehicle controller calculates a lateral slip amount indicating a degree to which a target wheel to be controlled which is a front wheel or a rear wheel of a vehicle is slipping in a rightward and leftward direction on a ground surface; performs a lateral slip suppressing control including at least one of a control for reducing an absolute value of a command value of a longitudinal force in a forward and rearward direction which is applied from the ground surface to the target wheel and a control for increasing a distributed load applied to the target wheel, in a case where it is determined that the lateral slip amount is greater than a lateral slip limit threshold; and decides the lateral slip limit threshold based on at least one of the longitudinal force and a normal force applied to the target wheel.

Abstract: A cooling device for a battery that is mounted in a vehicle includes: a cooling fan that is configured to suck air in a vehicle interior, and to blow the sucked air to the battery; an intake air temperature sensor that is configured to detect a temperature of the air sucked by the cooling fan; and an electronic control unit that is configured (i) to control the cooling fan, and (ii) to prohibit the cooling fan from being operated when a detected value of the intake air temperature sensor is lower than a first temperature.

Abstract: A method and apparatus for establishing a pathway for performing an automated validation of a condition of assembly. A sensor system coupled to an automated guided vehicle is moved into test positions relative to the structure. Image data is generated at each test position, using the sensor system, to build test images. Each test image is registered to a computer model of the structure to form registered images that are added to a collection of registered images. An optimal set of positions that will allow an entirety of an area of interest to be captured using a fewest number of registered images from the collection of registered images is determined. A pathway is generated for moving the automated guided vehicle to each optimal position in a least amount of time. A computer file identifying the pathway is generated for use in performing the automated validation of the condition of assembly.

Abstract: A resonance suppression control circuit provides operation stable for variations with a low order mode of vibration and suppressing spill-over due to high order mode of vibration. This circuit controls a physical system having two or more modes of vibration, and suppresses resonance in a lowest order mode of vibration from among the plurality of modes. The circuit has a controller designed by a ? design method, using a generalized plant with nominal model, and structured perturbation to the generalized plant. The nominal model is represented by the product of a low order vibration mode transfer function having the low order mode of vibration to be suppressed, and a high order vibration mode transfer function having a high order mode of vibration. The structured perturbation includes a first parameter perturbation term which imparts a multiplicative error to a spring constant included in the vibration mode transfer function being suppressed.

Abstract: Systems and methods are described for controlling vehicle steering. A target yaw rate and a target side-slip angle are determined for the vehicle and an initial steering angle setting is determined based on a position of a steering wheel operated by a driver of the vehicle. A nonlinear vehicle model is applied to calculate a compensated steering angle setting based on the initial steering angle setting, an actual yaw rate of the vehicle, and an actual side-slip angle of the vehicle. A steering system of the vehicle is then controls the angle of the front wheels of the vehicle based on the compensated steering angle and, by doing so, causes both the actual yaw rate and the actual side-slip angle to approach the target yaw rate and the target side-slip angle, respectively.

Abstract: A method of reconstructing a detected faulty signal. A roll sensor fault is detected by a processor. A signal of the detected faulty roll sensor is reconstructed using indirect sensor data. The reconstructed signal is output to a controller to maintain stability.

Abstract: Prognostic systems and methods for providing adaptive Time Between Overhaul (TBO) value for one or more Line Replaceable Units (LRUs) are provided. In one embodiment, the LRU prognostic system includes a first LRU, an aircraft position data source configured to monitor the position of an aircraft carrying the LRU prognostic system, and a controller coupled to the first LRU and to the aircraft position data source. The controller is configured to: (i) estimate the degradation of the first LRU based at least in part on the duration of time the aircraft position resides in any one of a plurality of different environmental zones while the aircraft is operational, and (ii) calculate an adaptive TBO value for the first LRU utilizing the estimated LRU degradation.

Abstract: Provided is an engine bench system capable of performing a racing test with good precision. A test body is separated into an engine main body and intermediate coupling body for connecting a crankshaft and an output shaft of the dynamometer. The engine bench system is provided with: a shaft torque sensor for detecting torsional torque; a shaft torque command generation apparatus for calculating a dynamo-side shaft torque command value by summing an engine-side shaft torque command value, and a torque value proportional to the moment of inertia of the intermediate coupling body; and a shaft torque controller for generating a torque control signal on the basis of the dynamo-side shaft torque command value and the output value of the shaft torque sensor.

Abstract: According to one embodiment, a resistance estimation apparatus includes a first detection unit, a second detection unit, a third detection unit and a first calculation unit. The first detection unit detects, as an output value, an output of a driving source of a vehicle. The second detection unit detects, as a braking value, a strength of a braking force. The third detection unit detects a speed of the vehicle. The first calculation unit calculates a traveling resistance resulting from a road surface that the vehicle has traveled during a traveling period, using a vehicle characteristic, the output value, the braking value and the speed, the traveling period including a period from a first time point when the vehicle starts and the speed changes from zero to a second time point when the vehicle stops and the speed changes to zero.

Abstract: The present disclosure describes roadway map updating using vehicle performance and location information from plural vehicles.

Abstract: Methods and electric vehicle diagnostic systems are provided for diagnosing performance of an active cooling system for cooling a rechargeable energy storage system (RESS) with a coolant. In one embodiment, a method includes determining, via a controller, whether the coolant temperature (TC) is less than the ambient temperature plus a first calibrated value (TA+V1). The method also includes determining, via a controller, whether the coolant temperature (TC) is less than the RESS temperature plus a second calibrated value (TR+V2). When the coolant temperature is less than the ambient temperature plus the first calibrated value and less than the RESS temperature plus the second calibrated value, the method provides for recording a diagnostic pass.

Abstract: A touch screen panel includes: a wave guide; a first transmitter at a first end of the wave guide to output an ultrasonic or light wave into the wave guide; a second transmitter at a second end of the wave guide to output the ultrasonic or light wave into the wave guide; a first receiver at the first end to receive the ultrasonic or light wave from the second transmitter and generate a first receipt signal; a second receiver at the second end to receive the ultrasonic or light wave and generate a second receipt signal; and a controller connected to the first receiver and the second receiver to detect a touch position on the wave guide using a time difference between a time point at which the first receipt signal is varied and a time point at which the second receipt signal is varied.

Abstract: This invention is related to an economic and practical method of using barcode systems for the management of railroad tracks. The systems consist of barcodes and device(s) which can optically read and decode the barcodes. The barcodes are permanently installed on one or both rails of a railroad track at predetermined locations along the track. The barcodes include coded contents such as track location coordinates and other railroad property information along the track. By using these novel track barcode systems, sections of problematic tracks could be accurately located either manually or automatically for repeatable monitoring, repairing or replacement purposes.

Abstract: A method of estimating a torque of a transmission clutch may include correcting an error by deducing an engine transient torque based on an engine angular velocity measured using a sensor, an engine static torque deduced using a data map, and a load torque depending on a driving load, deducing an engine angular velocity estimation value based on the engine static torque and the engine transient torque, and deducing a clutch torque estimation value depending on a slip in the transmission clutch from a difference between the engine angular velocity estimation value and the measured engine angular velocity.

Abstract: A method and a system for determining a running resistance Fres for a vehicle. A model-based running resistance Fres,mod is estimated. Thereafter an energy change difference ?Wdiff between a model-based estimated energy change ?Wpred and an actual energy change ?Wreal is determined for the vehicle from a starting point to an end point of a distance S which is traveled by the vehicle. A braking force Funknown which is unknown to the model and which acts upon the vehicle over the distance S is also determined on the basis of the energy change difference ?Wdiff. Thereafter the running resistance Fres is determined to an adjusted value of the model-based estimate of the running resistance Fres,mod, the adjustment being based on the braking force Funknown which is unknown to the model.

Abstract: A system and methods for real-time model based vehicle structural anomaly detection are disclosed. A real-time measurement corresponding to a location on a vehicle structure during an operation of the vehicle is received, and the real-time measurement is compared to expected operation data for the location to provide a modeling error signal. A statistical significance of the modeling error signal to provide an error significance is calculated, and a persistence of the error significance is determined. A structural anomaly is indicated, if the persistence exceeds a persistence threshold value.

Abstract: A system and method for supplying a corrective maintenance plan for a system includes supplying diagnostic data to a processor. The diagnostic data are representative of a set of two or more potential independent faults within the system, and each of the potential independent faults in the set has a unique corrective maintenance plan associated therewith. The diagnostic data are processed, in the processor, to select only one of the corrective maintenance plans. Maintenance plan data representative of the selected corrective maintenance plan are generated in the processor. For identical sets of two or more potential independent faults, the selected maintenance plan is not always the same.

Abstract: A method for recognizing unintended drive train responses of a motor vehicle includes at least one drive unit, in which at least one input variable of the motor vehicle and/or of the drive unit is input into the drive train, and at least one output variable is measured at the motor vehicle and/or the drive unit. In order to recognize an unintended drive train response early, the at least one input variable is supplied to a dynamic model which at least partially simulates the drive train of the motor vehicle, the dynamic model determining, based on the at least one input variable, at least one model output variable which is compared to the at least one measured output variable, and an unintended drive train response being deduced if there is a difference between the measured output variable and the model output variable.

Abstract: A method for predicting the temperature (Tin,p) of a wheel bearing of a vehicle wheel for a future moment (t+?tp) in relation to a present moment (t) or for a future time interval (t, t+?tp) in relation to a present moment (t), on the basis of a course of the temperature (Tin) of the wheel bearing in a past time interval (t??tb, t) in relation to the present moment (t), the predicted temperature (Tin,p) of the wheel bearing being determined from the sum of the temperature (Tin) of the wheel bearing at the present moment (t) and a corrective value (?TP) which is determined according to a change in at least one driving condition, such as the speed (?vtrain), and a change in the temperature (?Tb) of the wheel bearing within the past time interval (t??tb, t).

Abstract: A system method of estimating health of aircraft brake system friction material includes sensing a temperature of the friction material, and supplying the sensed temperature to a processor-implemented thermal model that is configured to estimate friction material temperatures at one or more locations on the friction material. The estimates of friction material temperatures are supplied to a processor-implemented thermal oxidation model that is configured, based on the estimates of friction material temperatures, to estimate friction material loss due to thermal oxidation. Data representative of runway fluid exposure are supplied to a processor-implemented catalytic oxidation model that is configured, based on the runway fluid exposure, to estimate friction material loss due to catalytic oxidation. The health of the friction material is estimated based on the estimates of friction material loss from the processor-implemented thermal oxidation model and the processor-implemented catalytic oxidation model.

Abstract: A method for inspecting assembly of components in a structure includes acquiring a visual representation of at least a portion of the structure, and saving an electronic file of the visual representation on a computer readable medium. A three-dimensional design of the structure, which contains information on a proper position of the components within the structure, is accessed. The visual representation is compared with the three-dimensional design using a computer, and a feedback indicating a result of the comparison is generated.

Abstract: A damping control unit sets a damping torque command value that corresponds to a steering angular velocity when a direction of a detected steering torque is a turning direction, a magnitude of the detected steering torque is larger than or equal to a first threshold, a direction of the steering angular velocity is a returning direction and a magnitude of the steering angular velocity is higher than or equal to a second threshold. An addition unit adds the damping torque command value generated by the damping control unit to a basic assist torque command value set by a basic assist torque command value setting unit.

Abstract: A method for detecting a wear condition of a tire utilizes tread pattern elements included on the tire. The elements are adapted to generate first and second acoustic footprint noises (BEA1, BEA2), with one of the first and second acoustic footprint noises being characteristic of the wear condition of the tire. According to the method, a parent frequency spectrum, which is capable of forming a frequency spectrum of one of the first and second acoustic footprint noises, and a child frequency spectrum, which is capable of forming a frequency spectrum of the other of the first and second acoustic footprint noises, are selected from a frequency spectrum of an acoustic signal acquired from the tire. Two detection confidence indices are determined. If each detection confidence index meets a predetermined condition, a warning is emitted indicating that tire wear has been detected.

Abstract: A system and method for actively controlling a structure is disclosed. At least one non-optimal event is identified in real-time based on at least one real-time elasticity measurement, if an event threshold exceeds a predetermined value. In response to an active control command, a control mechanism is then activated in real-time to compensate for the non-optimal event.

Abstract: A powertrain control module determines engine oil properties based on friction in an engine. The powertrain control module includes an engine combustion module that models engine torque based on engine speed and engine pumping losses due to intake and exhaust gasses. A transmission module models transmission torque applied to the engine based on transmission speed and gear. An accessory loads module models torque applied to the engine by accessory loads including at least one of a power steering pump, an air conditioning compressor, a water pump, and an alternator. An oil viscosity module determines engine oil viscosity based on a friction torque and predetermined engine data that coincides with reference oils. The friction torque is based on the engine torque, transmission torque, and accessory loads torque.

Abstract: A power steering device is mounted on a vehicle and includes a variable transmission ratio mechanism, a torque applying unit, and an applied friction torque changing unit. The torque applying unit sets an applied friction torque applied to the steering wheel and performs a control of applying the applied friction torque to the steering wheel. The applied friction torque changing unit changes the applied friction torque based on the transmission ratio of the variable transmission ratio mechanism.

Abstract: A method for identifying and analyzing data entities from (maintenance, repair, and overhaul (MRO)) data is provided. The method includes obtaining MRO data comprising unstructured text information. The method also includes performing named entity recognition on the MRO data to extract entities from the unstructured text information and label the entities with a tag. The method further includes analyzing the labeled entities via a heuristic to estimate an effectiveness of a fix for a specific issue or to estimate a reliability of a component.

Abstract: A method and a system for detecting the first signs of malfunction of an aircraft engine valve, including an acquisition device to acquire the output pressure measurements of the valve, and contextual and command data of the valve, a processor to define a set of indicators of the first signs of malfunction, according to the output pressure measurements and the contextual and command data. A set of estimators corresponding to the set of indicators of the first signs of a malfunction, is determined using a previously produced regression model. At least one distance between the set of indicators and the set of estimators is computed. The distance is compared to a threshold of the first signs of a malfunction, in order to detect the first signs of malfunction of the said valve.

Abstract: A plurality of control channels each include a power supply, an interface that receives a manipulation signal, an arithmetic processing portion that calculates and generates an operation command signal for actuators based on the manipulation signal, and a signal determination unit that determines a control signal for finally controlling the operation of the actuators and outputs the control signal. The arithmetic processing portions respectively provided in the plurality of control channels have designs different from one another. Each of the signal determination units determines the control signal by receiving a first operation command signal generated by the arithmetic processing portion of the control channel in which that signal determination unit is provided, and a second operation command signal generated in the arithmetic processing portion of another of the control channels, and comparing the first operation command signal and the second operation command signal, and outputs the control signal.

Abstract: An apparatus is provided for determining a tire operating condition including a tire-based pressure and temperature sensor and transmitter and a vehicle ignition system. A vehicle-based receiver/controller receives sensor signals and state of the ignition system. The controller provides an error signal when the sensed tire pressure is less than a set threshold value Pset and resets the error signal when the sensed tire pressure is greater than a reset threshold value Prst. The receiver/controller determines the set threshold value Pset and the reset threshold value Prst as a function of a calculated warm tire pressure value Pwarm, determines a mole value N of the tire pressure, and adjusts the determined set threshold value Pset and the reset threshold value Prst in response to the vehicle ignition state and a change in the determined mole value N. A display is provided for displaying the error signal.

Abstract: A method and a measurement system are specified for localizing at least one wheel on a motor vehicle. In this case the operating situation of the motor vehicle and the wheel load of the at least one wheel and/or a variable dependent on this is determined. Then the at least one measured value of the wheel load is compared with a value assigned to the operating situation. As an alternative or in addition, the comparison of at least one parameter dependent on at least two measured values can be undertaken with at least one of the parameters assigned to this operating situation. Finally the point on the motor vehicle at which the wheel is mounted is determined on the basis of the comparison results.

Abstract: The disclosed embodiments relate to methods and systems for requesting and retrieving aircraft data during flight of an aircraft. This aircraft data can be used to perform additional monitoring of aircraft sub-systems to detect an abnormal condition, and/or to identify one or more sources that are causing the abnormal condition. In one embodiment, aircraft data for one or more relevant parameters can be requested from the ground, measured on-board the aircraft, and stored in a data file that is then communicated back to personnel on the ground. The real-time aircraft data for one or more relevant parameters can then be analyzed to identify the one or more sources that are causing the abnormal condition.

Abstract: A computer-implemented method, a computer program product and a device for the condition monitoring of a component or system, such as for an aircraft or spacecraft. The method includes: providing an optimised decision tree, the nodes of which contain attributes of an input vector, the leaves of which each contain a classification function and the connections of which between the nodes are weighted; providing an input vector derived from a data signal; implementing a condition monitoring in which the condition of the component or system is determined using the weighted decision tree and on the basis of the input vector. In addition to an item of information concerning which of the classification functions of the decision tree best corresponds to the input vector, an additional item of information concerning the probability with which the other classes of the decision tree correspond to the examined input vector is calculated and output.

Abstract: A method and a system for determining a running resistance Fres for a vehicle. A model-based running resistance Fres,mod is estimated. Thereafter an energy change difference ?Wdiff between a model-based estimated energy change ?Wpred and an actual energy change ?Wreal is determined for the vehicle from a starting point to an end point of a distance S which is travelled by the vehicle. A braking force Funknown which is unknown to the model and which acts upon the vehicle over the distance S is also determined on the basis of the energy change difference ?Wdiff. Thereafter the running resistance Fres is determined to an adjusted value of the model-based estimate of the running resistance Fres,mod, the adjustment being based on the braking force Funknown which is unknown to the model.

Abstract: A system and method for real-time, self-learning characterization of fuel injector performance during engine operation. The system includes an algorithm for an engine controller which allows the controller to learn the correlation between the fuel mass and pulse width for each injector in the engine in real time while the engine is running. The controller progressively perceives those pulse widths that achieve the desired fuel mass, while it can continuously adapt what it has learned based on various input variations, such as temperature and fuel rail pressure. The controller then uses the learned actual performance of each injector to command the pulse width required to achieve the desired quantity of fuel for each cylinder on each cycle.

Abstract: A vehicle fault diagnosis and prognosis system includes a computing platform configured to receive a classifier from a remote server, the computing platform tangibly embodying computer-executable instructions for evaluating data sequences received from a vehicle control network and applying the classifier to the data sequences, wherein the classifier is configured to determine if the data sequences define a pattern that is associated with a particular fault.

Abstract: A monitoring method that includes calculating the autonomy of a lubrication system of an airplane engine and also providing for the diagnosis and prognosis of a plurality of problems and breakdowns of the engine and of its lubrication system by means of measurements taken by sensors arranged in the lubrication system. The method further comprises the step of calculating the status of the lubrication system at a given moment and calculating its evolution over time in order to determine the remaining lifetime before a breakdown.

Abstract: An output section of one detection coil of a first resolver and an output section of one detection coil of a second resolver are connected by a first inter-coil resistor element, and an output section of the other detection coil of the first resolver and an output section of the other detection coil of the second resolver are connected by a second inter-coil resistor element. A sin wave signal for excitation is supplied to one of first and second excitation coils, and a cos wave signal for excitation having the same frequency as that of the sin wave signal for excitation and having a phase delay of 90° in relation to the sin wave signal for excitation is supplied to the other of the first and second excitation coils. By virtue of this configuration, the rotational angles of the two resolvers can be calculated even when one of detection lines is broken.

Abstract: A system for automated control of a machine having a ground engaging work implement includes an implement load sensor system. A controller determines a change in terrain based at least in part upon a change in the load on the ground engaging work implement. If the change in terrain exceeds a threshold, the controller generates an alert command signal. A method is also provided.

Abstract: A method for determining a state of health (SOH) value for an electric power steering (EPS) system in a vehicle includes estimating a first Self-Aligning Torque (SAT) value using a tire dynamics model, which includes modeled dynamics in the linear region of a lateral force acting on the vehicle tires. The method also includes estimating a second SAT value using an extended state observer and nominal parameters for the EPS system, and calculating a variance between the first and second SAT values. The controller monitors a progression of the calculated variance over a calibrated interval using the controller to thereby determine the SOH value, and automatically executes a control action using the SOH value. An EPS system for a vehicle includes a steering wheel, torque and angle sensors, a rack and pinion assembly, a steering motor, and the controller. A vehicle is also disclosed having the same controller.

Abstract: An improved fault detection system and method is provided. The fault detection system and method combines the use of discrimination and representation based feature extraction to reliably detect symptoms of faults in turbine engines. Specifically, the fault detection system and method uses a kernel-based Maximum Representation Discrimination Features (MRDF) technique to detect symptoms of fault in turbine engines. The kernel-based MRDF system and method combines the use of discriminatory features and representation features in historical sensor data to facilitate feature extraction and classification of new sensor data as indicative fault in the turbine engine. Furthermore, the kernel-based MRDF technique facilitates the uncovering of nonlinear features in the sensor data, thus improving the reliability of the fault detection.