Methods and systems for detecting and correcting anomalies includes generating historical binary codes from historical time series segments. The historical time series segments are each made up of measurements from respective sensors. A latest binary code is generated from a latest time series segment. It is determined that the latest time series segment represents anomalous behavior, based on a comparison of the latest binary code to the historical binary codes. The sensors are ranked, based on a comparison of time series data of the sensors in the latest time series segment to respective time series data of the historical time series, to generate a sensor ranking. A corrective action is performed responsive to the detected anomaly, prioritized according to the sensor ranking.

An exoskeleton comprising a plurality of support structures, and a plurality of joint mechanisms each joint mechanism rotatably coupling at least two of the plurality of support structures. A sensor suite discrepancy detection system can be operable to interrogate the suite of sensors within the exoskeleton, and can comprise a plurality of sensor groups, each associated with a respective joint mechanism, and each comprising a plurality of sensors from a suite of sensors. A controller can be configured to recruit at least one substitute sensor from a first sensor group of based on an identified discrepancy between the sensor output data of at least two sensors within the first sensor group and a target sensor within the first sensor group, and to execute a remedial measure associated with a safety mode of the exoskeleton for safe operation of the exoskeleton.

An exoskeleton operable in a safety mode comprises a plurality of support structures, and at least one joint mechanism rotatably coupling two of the plurality of support structures, and a plurality of sensors associated with the at least one joint mechanism. The exoskeleton comprises a controller configured to generate a plurality of command signals according to a plurality of respective control policies, and configured to generate each command signal based on sensor output data from at least one sensor of the plurality of sensors, and configured to control operation of the at least one joint mechanism according to a selected control policy, of the plurality of control policies, based on at least one of an identified discrepancy between at least some of the plurality of command signals or a determination whether each of the plurality of sensors satisfies at least one self-test defined criterion defined criterion or a comparison criterion between the output signal of two or more sensors of the plurality of sensors, or both of these.

An exoskeleton comprising a plurality of support structures, and a plurality of joint mechanisms each joint mechanism rotatably coupling at least two of the plurality of support structures. A sensor suite discrepancy detection system can be operable to interrogate the suite of sensors within the exoskeleton, and can comprise a plurality of sensor groups, each associated with a respective joint mechanism, and each comprising a plurality of sensors from a suite of sensors. A controller can be configured to recruit at least one substitute sensor from a first sensor group of based on an identified discrepancy between the sensor output data of at least two sensors within the first sensor group and a target sensor within the first sensor group, and to execute a remedial measure associated with a safety mode of the exoskeleton for safe operation of the exoskeleton.

Methods and systems for detecting and correcting anomalies includes generating historical binary codes from historical time series segments. The historical time series segments are each made up of measurements from respective sensors. A latest binary code is generated from a latest time series segment. It is determined that the latest time series segment represents anomalous behavior, based on a comparison of the latest binary code to the historical binary codes. The sensors are ranked, based on a comparison of time series data of the sensors in the latest time series segment to respective time series data of the historical time series, to generate a sensor ranking. A corrective action is performed responsive to the detected anomaly, prioritized according to the sensor ranking.

An exoskeleton comprising a plurality of support structures, and a plurality of joint mechanisms each joint mechanism rotatably coupling at least two of the plurality of support structures. A sensor discrepancy detection system can be operable to compare sensor output data from a user operated force moment sensor and at least one torque sensor of a joint mechanism. A controller can be configured to recruit at least one substitute sensor from a first sensor group of based on an identified discrepancy between the sensor output data and to execute a remedial measure associated with a safety mode of the exoskeleton for safe operation of the exoskeleton.

An online monitoring system for industrial processes, such as nuclear power processes, including a data acquisition unit configured to sample output signals simultaneously from a plurality of process sensors, and a computing unit configured to record sampled output signals from the data acquisition unit and to cross-correlate the output signals from two or more of the process sensors to diagnose operation of the industrial process, identify loose parts and/or degradation of industrial plant equipment, enable virtual sensing, calculate sensor response time using the noise analysis technique, and to verify sensor calibration using the cross calibration method and/or empirical and/or physical modeling.

A parameter setting device is configured to set a parameter relating to a speed of a table of a machine tool in accordance with the weight of an object placed on the table. The parameter setting device includes: an amount-of-strain obtaining unit configured to obtain the amount of strain of the table; a storage unit storing the parameter corresponding to the amount of strain; and a parameter setting unit configured to set, by using the storage unit, the parameter based on the amount of strain obtained by the amount-of-strain obtaining unit with the table standing still.

A method for detecting an anomaly in sensor data generated in a substrate processing apparatus is disclosed herein. A plurality of data sets is received. A first data set from a first sensor and second data set from a second sensor are selected. The first second sensors are defined as a sensor pair. A reference correlation is generated by selecting a subset of values in each data set for each of the first and second data sets. A difference of remaining data correlation outside the subset of values in each data set to the reference correlation is normalized. The normalized data set is filtered to smooth the normalized difference to avoid isolated outliers with high chance of false positive candidates. One or more anomalies are identified. Process parameters of the substrate processing apparatus are adjusted, based on the one or more identified anomalies from the filtered data set.

A method for detecting an anomaly in sensor data generated in a substrate processing apparatus is disclosed herein. A plurality of data sets is received. A first data set from a first sensor and second data set from a second sensor are selected. The first second sensors are defined as a sensor pair. A reference correlation is generated by selecting a subset of values in each data set for each of the first and second data sets. A difference of remaining data correlation outside the subset of values in each data set to the reference correlation is normalized. The normalized data set is filtered to smooth the normalized difference to avoid isolated outliers with high chance of false positive candidates. One or more anomalies are identified. Process parameters of the substrate processing apparatus are adjusted, based on the one or more identified anomalies from the filtered data set.