Abstract: The technology described herein is directed to a DC input power supply unit with an auxiliary boost control circuit (or controller) that facilitates continuous supply of power to a standby output load of the power supply unit in a bootloader mode. More specifically, the auxiliary boost circuit (or controller) is configured to assume control of a primary power boost stage from a primary controller in a bootloader mode so that the power supply unit can continue to supply power to the standby output with a protection function regardless of the state of the power supply unit or primary controller.

Abstract: A time-admittance fault detection and isolation system includes a series of time-admittance switches spaced apart along the power line, each including a respective time-admittance function. Together, the time-admittance functions define a cascade trip sequence in a downstream-to-upstream direction, which autonomously causes a closest upstream time-admittance switch to a fault to trip to isolate the fault on an upstream side of the fault without communication with the time-admittance switches. The fault detection and isolation system may also include a radio communicating a trip signal from the closest upstream time-admittance switch to the fault to a closest downstream time-admittance switch to the fault. The trip signal causes the closest downstream time-admittance switch to the fault to trip to isolate the fault on a downstream side of the fault. A tie switch closes to back-feed a portion of the electric power line downstream from the closest downstream time-admittance switch to the fault.

Abstract: A digital data rate enhancement filter is described. The digital data rate enhancement filter-includes an enhancement filter input, a first interpolation filter, a second interpolation filter, and a multiplexer circuit. The first interpolation filter is connected to the enhancement filter input downstream of the enhancement filter input. The second interpolation filter is connected to the first interpolation filter downstream of the first interpolation filter. The enhancement filter input is configured to receive a digital input signal set. The first interpolation filter is configured to receive the digital input signal set and to interpolate the digital input signal set, thereby obtaining a first interpolated signal set. The second interpolation filter is configured to receive the first interpolated signal set and to interpolate the first interpolated signal set, thereby obtaining a second interpolated signal set.

Abstract: A method, computer program, and computer system is provided for fault detection in an electrical network. An inductance between a reference point and a fault is determined at a first time based on measuring a fault current. A resistance between the reference point and the fault may be determined at a second time based on measuring a differential of the fault current as zero. A location of the fault may be identified based on the inductance and the resistance.

Abstract: A transformer area identification method includes: performing data acquisition on all sub-meters and a master meter in an identification domain to obtain a steady-state load, and generating a steady-state load jump curve; and performing load jump feature matching between steady-state load jump curves of all the sub-meters and a steady-state load jump curve of the master meter, and obtaining attribution of the sub-meters with a load jump according to matching results. A method for constructing transformer area line topology is further provided. A load jump identification technique is utilized to acquire a load value of each node in a transformer area power supply network, so as to form a load jump curve for each node. By performing load jump feature matching between load jump curves of all sub-meters and a load jump curve of a master meter, a mounting relationship of a corresponding electric meter is determined.

Abstract: Disclosed is a multi-core cable fault classification system which includes a reference signal measurement unit configured to measure a core-specific reference signal generated by applying an electromagnetic signal to a multi-core cable having at least two cores, a reflected-signal measurement unit configured to measure a core-specific reflected signal generated by reflecting the generated core-specific reference signal at a point of the multi-core cable, a data processing unit configured to extract, from time-series data for the measured core-specific reflected signal, core-specific partial time-series data based on whether baseline data of the multi-core cable is present, configured to transform the core-specific partial time-series data into a time-frequency distribution, and configured to extract faulty-core determination data, and a faulty core classification unit configured to classify a fault core from the multi-core cable by inputting the extracted faulty-core determination data to a neural network.

Abstract: Provided is a determination method of differential protection suitable for an electricity transmission line with multi-terminal T-connection.

Abstract: Apparatus and associated methods relate to predicting failure and/or estimating remaining useful life of an air-data-probe heater. Failure is predicted or useful life is estimated based on an electrical metric of the electrical operating power provided to a resistive heating element of the air-data-probe heater. The electrical metric of the air data probe heater is one or more of: i) phase relation between voltage across the resistive heating element and leakage current, which is conducted from the resistive heating element to a conductive sheath surrounding the resistive heating element; ii) a time-domain profile of leakage current through the heating element insulation during a full power cycle; and/or iii) high-frequency components of the electrical current conducted by the resistive heating element and/or the voltage across the resistive heating element.

Abstract: A computer implemented method, a fault detection and management system and a computer program product for managing an open circuit fault on an overhead line in a power network, are provided, that include obtaining overhead line data from a sensor mounted on the overhead line, determining fault detection parameters associated with one or more nodes of the overhead line on occurrence of a predefined node condition, that is, a low voltage and a negative rate of change of line current at the one or more nodes, and generating an output based on the fault detection parameters, wherein the output indicates potential presence of an open circuit at one or more nodes.

Abstract: Among network devices for use within a wireless communication network, a transmitting network device is configured to transmit to a receiving network device via a control channel one or more control signals for configuring the receiving network device for a characterization of at least one of the transmitting network device and the receiving network device and/or for a characterization of one or more communication channels between the transmitting network device and the receiving network device.

Abstract: A system includes a transformer rectifier unit (TRU) having three inputs, a first AC bus configured to supply power to a first of the three inputs, a second AC bus configured to supply power to a second of the three inputs, and a third AC bus configured to supply power to a third of the three inputs. The system includes a power quality sense device electrically connected to each of the first, second and third AC busses. The system includes an electrically held contactor electrically connected between the TRU and the power quality sense device. The electrically held contactor is configured and adapted to be switched ON or OFF depending on whether the power quality sense device is energized or de-energized.

Abstract: Detecting an imminent failure of a power supply. An internal computerized component periodically reads a set of measurements from one or more sensors affixed to a power supply. The internal computerized component and power supply may reside in a variety of different technical contexts. The internal computerized component analyzes the set of measurements using, at least in part, a weighted set of factors, to detect the imminent failure in the power supply. The weighted set of factors may be updated or revised over time and may be specifically tailored for use with specific types of power supplies.

Abstract: A method for fail-safe resolver excitation includes generating a resolver excitation signal and providing the resolver excitation signal to an input of a first resolver control circuit and to an input of a second resolver control circuit. The method also includes, in response to the first resolver control circuit detecting a fault in the resolver excitation signal provided to the first resolver control circuit: biasing, using the first resolver control circuit, a first resolver amplifier; and communicating, via a communication bus between the first resolver control circuit and the second resolver control circuit, an indication to the second resolver control circuit that the first resolver control circuit detected the fault in the resolver excitation signal provided to the first resolver control circuit.

Abstract: Provided is a noise remover of a PWM motor without a frequency control filter in a PWM control motor, and more particularly, includes a micom formed in the vehicle terminal and converting to and transmitting the frequency avoiding the radio frequency; a frequency filter for suppressing the noise converted by the micom; a motor part for transmitting the frequency that the frequency filter outputs to a vehicle motor, and operating the motor; and a pulse modulation/demodulation control part for controlling the rotation amount of the vehicle motor inside the motor part, which are divided roughly as four, and rotate a rotor of the motor part without noise by selectively applying the frequency which is not overlapped with radio frequency to a first FET, a second FET, a third FET, and a fourth FET.

Abstract: Techniques for monitoring the health of a three-phase induction motor are provided. An expected threshold value is calculated as a function of an expected ratio of current unbalance to voltage unbalance for the three-phase motor. Embodiments determine whether a measured current unbalance exceeds the expected threshold value. Responsive to the measured current unbalance exceeding the expected threshold value, a remedial action may be taken, such as generating diagnostic information or activating one or more protection operations for the three-phase induction motor.

Abstract: A method of controlling a renewable energy power plant is provided. The method includes retrieving output power measurement values for each inverter of a total number of inverters from a plurality of sensors provided at a location proximal to each inverter and retrieving a point of interconnection (POI) output measurement value for the renewable energy power plant based on a plurality of ON inverters of the total number of inverters. The method also includes calculating a POI measured setpoint for the renewable energy power plant based on a difference between a power reference value for the renewable energy power plant and the retrieved POI output measurement value for the renewable energy power plant, assigning a setpoint to each of the ON inverters and classifying each ON inverter as either a TRACKING ON inverter or a NON-TRACKING ON inverter based on whether each ON inverter is tracking at the setpoint.

Abstract: The condition monitoring system includes an acquisition unit and a generation unit. The acquisition unit acquires waveform data from a measuring device to measure an electrical signal that is either output or input of a converter. The waveform data represents a waveform of the electrical signal. The generation unit generates, based on the waveform data, analysis data to monitor the condition concerning the converter. The generation unit obtains, by frequency analysis, a plurality of combinations, each including a value of a frequency and a value of a feature quantity that is either intensity or phase, based on the waveform data when a value of the drive frequency varies and thereby generate the analysis data having at least three variables including the frequency, the feature quantity, and the drive frequency.

Abstract: A method for detecting fault in a power transmission line of a power transmission system and protection system using the same. The method includes: obtaining a system parameter of the power transmission system, adjusting protection reachability of a fault detecting element based on the obtained system parameter such that the adjusted protection reachability of the fault detecting element is applicable to a predetermined protection range, identifying whether there is an internal fault occurring on the transmission line using the adjusted fault detecting element, and generating a fault detection decision signal indicating the identified fault. If the predetermined protection range is desirable for the fault detecting element, its protection reachability may be adjusted in consideration of the influence imposed by the SIR such that the reach point of the adjusted fault detecting element can be extended to approach the end of the predetermined protection range.

Abstract: A display device can include a display panel having a plurality of sub pixels, each of the sub pixels including a switching transistor, a driving transistor, a sensing transistor, a storage capacitor, and a light emitting element; and a detector configured to sense a voltage difference between a first electrode of the sensing transistor and a second electrode of the sensing transistor for determining that an anode and a cathode of the light emitting element are shorted, in which a gate electrode of the switching transistor and a gate electrode of the sensing transistor are connected to a same gate line.

Abstract: A battery system includes at least one battery including a plurality of cells and a hybrid control module configured to monitor a differential capacity of the at least one battery, determine when the monitored differential capacity of the at least one battery corresponds to a predetermined differential capacity of the at least one battery, and determine a state of charge of the battery in response to the determination that the monitored differential capacity corresponds to the predetermined differential capacity.

Abstract: A set of input conditions is obtained. A plurality of potential decisions is obtained based at least in part on the set of input conditions. A rule-based system is used to process the plurality of potential decisions and obtain a set of one or more updated potential decisions, wherein: the rule-based system specifies a plurality of rules; a rule specifies a rule condition and a corresponding action, wherein when the rule condition is met, the corresponding action is to be performed; and using the rule-based system to process the plurality of potential decisions includes: for a selected potential decision in the plurality of potential decisions, determining whether the rule condition is met for a selected rule among the plurality of rules, wherein the selected rule condition is dependent on, at least in part, the selected potential decision; and in response to the selected rule condition being met, performing the corresponding action. The set of one or more updated potential decisions to be executed is output.

Abstract: A method, a device, and a non-transitory storage medium to receive from customer devices, sensor messages indicating a power state of on or off, a location, and a timestamp; select an element of a utility system based on the sensor messages; determine a power state of on or off for the element based on the sensor messages and a location and time pertaining to the element; store a temporal and spatial model that includes an outage event; receive weather data pertaining to the element; generate an outage model based on the temporal and spatial model and the weather data; receive forecasted weather data; calculate a predicted outage pertaining to one or more elements of the utility system based on the outage model and the forecasted weather data; and transmit a message that includes the predicted outage.

Abstract: The present disclosure provides a method and system for performing fault diagnosis by bearing noise detection. The method provides: collecting noise in bearing detection, the noise comprising bearing noise and operating condition noise; subjecting the collected noise to pre-processing, to obtain a first time domain signal and a second frequency domain signal; and inputting the first time domain signal and second frequency domain signal to a bearing fault diagnosis model. The bearing fault diagnosis model includes a characteristic extraction model and a fault discrimination model, the characteristic extraction model subjects the first time domain signal and second frequency domain signal to characteristic extraction separately to obtain a first characteristic associated with a time domain shock peak and a second characteristic associated with a fault frequency peak.

Abstract: An instruction duty computation unit computes an instruction duty ratio representing a ratio between an energization time and a non-energization time of a motor based on an actual rotation angle detected by a rotation angle sensor and a target rotation angle of a valve member. The rotation angle sensor detects an actual rotation angle of a valve member of a fluid control valve. A stress computation unit computes a valve member load torque of the valve member based on the actual rotation angle and an actual duty ratio of the motor. An actual duty computation unit computes a new value of the actual duty ratio based on an instruction duty ratio computed by using an instruction duty computation unit and a valve member load torque computed by using a stress computation unit.

Abstract: In a meter for performing a measurement of an electrical parameter, an output from a sensor is sampled to produce at least one sample, and an iterative method is performed comprising: producing further samples; holding in memory a stored array of samples comprising the at least one sample and each of the further samples from each iteration; determining a measure of statistical variability of a mean for the respective iteration from a measure of statistical variability and from the number of samples used to generate the measure of statistical variability; comparing the measure of statistical variability of the mean with a pre-determined threshold; and generating an electrical signal indicating a state of the measurement if the measure of statistical variability of the mean of the samples taken during the measurement is less than or equal to the pre-determined threshold.

Abstract: Systems and methods for detecting and identifying arcing are disclosed. A method of detecting arcing includes obtaining data indicative of voltage and data indicative of current, determining a waveform of a cycle of a primary load current according to the data indicative of current, determining at least one noise signal according to the determined waveform of a cycle of the primary load current and the data indicative of current, determining a probability density of the noise signal according to a time window, and comparing the probability density of the noise signal with at least one model probability density.

Abstract: A method and a system for power equipment diagnosis based on windowed feature and Hilbert visualization are provided, which belong to the field of power equipment fault diagnosis. The method includes: obtaining an original data set of monitoring data containing power equipment fault features; introducing windowed feature calculation considering logarithmic constraints to process data to obtain a feature sequence; using Hilbert visualization method for further processing to obtain a Hilbert image data set used to train and verify a convolutional neural network; and finally directly inputting newly obtained test sample data after windowed feature calculation and Hilbert visualization processing into the trained network for fault diagnosis and location.

Abstract: A method for operating a power consumption metering system and a power consumption metering system are disclosed. In an embodiment a method include measuring, by a sensor deployed at a monitored site, high speed power consumption values over time to obtain a high speed value pattern of power consumption with a resolution of more than 1000 values per second, determining one or more harmonics of the high speed value pattern, measuring, by the sensor, low speed power consumption values over time to obtain a low speed value pattern of the power consumption with a resolution of less than 100 values per second, providing the harmonics and the low speed value pattern to a cloud based data processing system and identifying a status of a power consumer of the monitored site dependent on the measured harmonics and the low speed value pattern.

Abstract: A power supply unit for an aerosol generation device includes an internal power supply configured to hold power supplied to a heater configured to heat an aerosol source, a first connector connectable to an external device and including a first communication terminal, a controller configured to control power supply from the internal power supply to the heater and including a second communication terminal, a first communication path between the first communication terminal of the first connector and the second communication terminal of the controller, and a switch unit positioned on the first communication path and configured to set the first communication path to a conductive state or a disconnected state.

Abstract: This application discloses a drone control method and device and a drone and pertains to the technical field of drone control. The method includes: monitoring a running status of each power motor in a drone; determining according to the running status of each power motor whether the drone is in a crashed state; and controlling the drone to alarm when determining that the drone is in the crashed state. The drone control method and device and the drone can rapidly locate a crashed drone, greatly increasing the probability of finding back the crashed drone.

Abstract: An arc fault detection method for a photovoltaic system based on an adaptive kernel function and instantaneous frequency estimation includes steps of: sampling signal xt in a time window length of TNCT and obtaining an iterative time-frequency diagram of xt by nonlinear chirplet transform; extracting detection variables based on frequency component in the selected iterative time-frequency diagram to determine a moment when spectrum energy increases; when the moment is found, obtaining a matrix distribution form of the xt in time-frequency domain obtained by the adaptive optimum kernel time-frequency representation, and processing the matrix with sum of squares in a time dimension to obtain a column vector; processing each selected frequency bands with integration operation in a frequency dimension to obtain multiple detection variable values as inputs of a well-trained Naive Bayes model.

Abstract: A method for calculating a maximum output current of multiple thyristor converters connected in parallel, step 1: setting an operating time t; step 2: assuming a trigger angle; step 3: calculating a maximum output current of a single converter according to an output current model for the single converter; step 4: equally dividing a total output DC current into a plurality of parts according to a working duration of six converter bridge arms, thereby obtaining a pulse operating current of a single bridge arm; step 5: checking whether a present junction temperature of a thyristor is below a limiting temperature based on a thermal resistance model for the thyristor, if no, correcting the trigger angle, and repeating step 2 to step 5 until the condition is met; step 6: giving a present trigger angle; and step 7: giving a maximum output current of multiple converters connected in parallel.

Abstract: One illustrative method comprises retrieving a set of drive information associated with an operation of an electric drive in a time period from a drive control unit and one or more sensor units. The method further includes obtaining reliability information associated with the electric drive from a server. The reliability information is computed in the server, with the set of drive information and a model corresponding to a drive type of the electric drive. The reliability information includes a probability of occurrence of the abnormal condition in a specified future time period. The method further includes, providing at least one condition indication regarding the abnormal condition to one of a human machine interface and a drive controller based on the probability of occurrence of the abnormal condition.

Abstract: A photovoltaic (“PV”) sensor for the early detection of potential induced degradation (“PID”) comprising a housing; a power source located within the housing; an electrical connection presented by the housing for electrically communicating the power source with a PV module; and wherein current supplied by the power source to the PV module is less than 10 mA.

Abstract: A method for monitoring a measurement variable and performing predictive monitoring of a compliancy of a characteristic of a field device to a requirement is described. The method includes a step of determining a deviation between a measured value of a monitored variable and a reference value of the monitored variable. The deviation is indicative of a degree of compliancy to the requirement. The method also includes a step of applying a filter to the deviations based on the deviations and the filtered deviations. The method further includes a step of determining a noise superimposed on the filtered deviations. At the end of a monitoring interval, a time remaining until the deviations will exceed the deviation range is determined using a Monte Carlo simulation.

Abstract: A bypass mechanism for a photovoltaic module which switches out the electronics and switches in a bypass mechanism.

Abstract: A transformer assembly includes an electric transformer a temperature sensor system, and a computation unit for determining a thermal state of the electric transformer. The electric transformer includes a cooling device having at least one liquid coolant channel to absorb exhaust heat from the electric transformer a heat spreader for transferring heat from the liquid coolant to a heat dissipation surface of the heat spreader, and an air blower configured to effect an airstream along the heat dissipation surface. The temperature sensor system includes an entering coolant sensor for providing an entering coolant temperature signal, a leaving coolant sensor for providing a leaving coolant temperature signal, an entering airstream sensor for providing an entering airstream temperature signal, and a leaving airstream sensor for providing a leaving airstream temperature signal. The computation unit is configured to determine a thermal state of the transformer.

Abstract: The technology described herein is directed to a DC input power supply unit with an auxiliary boost control circuit (or controller) that facilitates continuous supply of power to a standby output load of the power supply unit in a bootloader mode. More specifically, the auxiliary boost circuit (or controller) is configured to assume control of a primary power boost stage from a primary controller in a bootloader mode so that the power supply unit can continue to supply power to the standby output with a protection function regardless of the state of the power supply unit or primary controller.

Abstract: Systems and methods to detect that a protective device is operating outside of a time inverse overcurrent tolerance region are described. For example, a central monitoring station may obtain a time inverse overcurrent tolerance region of a protective device on a power line. The central monitoring station may obtain a fault magnitude measurement and a fault duration measurement of a wireless line sensor on the power line. The central monitoring station may determine that the protective device is operating outside of the tolerance region based at least in part on the fault magnitude measurement and the fault duration measurement. The central monitoring station may provide a signal indicating that there is a potential issue with the protective device.

Abstract: Determining direct current (DC) leakage current flowing through an insulating structure in a high voltage DC power system wherein the DC leakage current is a composite DC current having one or more high magnitude momentary spikes, and having a DC component and an alternating current (AC) component, wherein the AC component has a first rate of change, and wherein the DC component has a second rate of change less than the first, having (a) providing a waveform separator which is configured to receive the composite DC current flowing through the insulating structure and to separate the composite DC current into the corresponding DC component and AC component, and (i) receive at least one corresponding digital signal and the DC component, ii) analyze the at least one corresponding digital signal and the DC component, (iii) determine a resultant leakage current flowing through the insulating structure, (b) electrically connecting the waveform separator to the insulating structure, (c) separating, in the waveform s

Abstract: A method and an apparatus for detecting capacitance of a filter capacitor of an inverter are provided, wherein each output terminal of the inverter is connected to one terminal of a first filter capacitor through an inductor, and the other terminals of all first filter capacitors are interconnected. The method includes: outputting a first voltage {dot over (U)}1i through an ith output terminal of the inverter, i=1, 2 . . . N, i?j, 1?j?N, i and j are positive integers, and N is a total quantity of output terminals of the inverter; obtaining ?ik and determining a ratio of |?ij| to |?ik|, where ?ik is a current of an inductor connected to a kth output terminal when the ith output terminal outputs the first voltage {dot over (U)}1i, k=1, 2 . . . N, and k is a positive integer; and determining capacitance of a first filter capacitor connected to the jth output terminal based on ?ij, {dot over (U)}1i, and the ratio of |?ij| to |?ik|.

Abstract: A current sensor diagnosing apparatus for diagnosing an error of a plurality of current sensors connected to a secondary battery cell. The current sensor diagnosing apparatus may diagnose an error of a current sensor in the same way regardless of the type of a system using the current sensor, the type of a current source, a voltage characteristic, or the like by diagnosing an error of current sensors using offset deviations and current values of two current sensors and may be particularly applied to various systems including a plurality of current sensors.

Abstract: Method and system allowing more accurate detection and identification of unwanted arcing include novel processing of signal voltage representing recovered power-line current. In one implementation, arc-faults are detected based on numerical analysis where individual cycles of line voltage and current are observed and data collected during each cycle is processed to estimate likelihood of presence of arc-event within each individual cycle based on pre-defined number of arc-events occurring within pre-defined number of contiguous cycles.

Abstract: An electric power substation includes one or more primary relay panels located at a substation site and susceptible to damage caused by radiated or coupled electromagnetic energy, and an electromagnetic pulse mitigation module located at the substation site and comprising a continuous conductive enclosure that is impervious to the radiated or coupled electromagnetic energy. One or more backup relay panels are housed within the electromagnetic pulse mitigation module and capable of assuming operation of the one or more primary relay panels.

Abstract: A system includes a transformer rectifier unit (TRU) having three inputs, a first AC bus configured to supply power to a first of the three inputs, a second AC bus configured to supply power to a second of the three inputs, and a third AC bus configured to supply power to a third of the three inputs. The system includes a power quality sense device electrically connected to each of the first, second and third AC busses. The system includes an electrically held contactor electrically connected between the TRU and the power quality sense device. The electrically held contactor is configured and adapted to be switched ON or OFF depending on whether the power quality sense device is energized or de-energized.

Abstract: Provided is a data driving circuit, including: a pixel current generation circuit including an input terminal and an output terminal and configured to generate a pixel current based on a data voltage inputted via the input terminal, wherein the output terminal of the pixel current generation circuit is configured to be connected to a pixel circuit; and a first operational amplifier including a first input terminal connected to the output terminal of the pixel current generation circuit, a second input terminal, and an output terminal. A first voltage is inputted via the second input terminal of the first operational amplifier and is positively related to the data voltage, and the output terminal of the first operational amplifier is configured to be connected to the pixel circuit; and wherein the first operational amplifier is configured to generate a bias current based on the first voltage.

Abstract: A method for characterizing a fault in a transmission line network, the method includes the steps of: obtaining a first measured time reflectogram Rm from a signal previously injected into the network, obtaining a second time reflectogram Rs corresponding to the network in the absence of faults, determining the time difference Rref between the first measured time reflectogram Rm and the second time reflectogram Rs, identifying, in the time difference Rref, an amplitude peak characterizing the presence of a fault and its time abscissa indicating the position of the fault, simulating a plurality of time reflectogram hypotheses each corresponding to the network comprising a fault at the identified position, each hypothesis being associated with a different value of at least one parameter characteristic of the fault, selecting the time reflectogram hypothesis closest to the time difference Rref.

Abstract: In an embodiment, a method includes receiving in parallel first data and second data; and delivering in series the first and second data, where the first data comprises electric power delivery configuration data. In some embodiments, delivering in series the first and second data includes delivering the first and second data wirelessly.

Abstract: State estimation in an electric power system includes acquiring electrical measurements from the electric power system at a reporting rate of the electrical measurements, processing the electrical measurements into sequence data including positive sequence data, processing positive sequence data by an observable state estimator to generate a plurality of estimated states including a plurality of estimated observable states, parameters of the observable state estimator being updated by a first training module in a first time thread, processing the plurality of estimated states by an unobservable state estimator to generate a plurality of estimated unobservable states, parameters of the unobservable state estimator being updated by a second training module in a second time thread independent of the first time thread, and outputting a plurality of final estimated states generated by concatenating the plurality of estimated observable states and the plurality of estimated unobservable states.

Abstract: A circuit fault detection apparatus includes an AD conversion circuit, a corrector, first and second determination devices, and a fault detector. The AD conversion circuit detects a voltage corresponding to a current or a voltage applied to the circuit fault detection element, and converts the voltage to a digital value. The corrector corrects a measurement value to a corrected measurement value. The first determination device determines whether or not the electric circuit has the fault, based on a comparison between an uncorrected measurement value and an uncorrected threshold value. The second determination device determines whether the electric circuit has the fault, based on a comparison between the corrected measurement value and a corrected threshold value. The fault detector detects the fault in the electric circuit, based on a condition that at least one of the first or second determination devices determines that the electric circuit has the fault.