An error diagnosis method includes: the parameter value obtaining step of obtaining multiple parameter values; the error detection step of calculating a Mahalanobis distance from a unit space based on the obtained parameter values and diagnosing whether or not error is caused at the real machine based on the calculated Mahalanobis distance; the error portion estimation step of estimating a error portion of the real machine based on the Mahalanobis distance calculated at the error detection step; and the matching determination step of structuring an error analyzing model for analyzing the real machine based on the error portion of the real machine estimated at the error portion estimation step and determining whether or not an output analytical signal of the real machine obtained by analysis of the error analyzing model and the output signal output from the real machine match with each other.

A method of detecting an operational anomaly of an industrial system can include receiving operational values for a plurality of process parameters from an industrial system at a localized anomaly detection system, wherein the plurality of process parameters, accessing a machine learning model stored in a non-volatile memory system operating within the localized anomaly detection system, to determine predicted values for the process parameters based on the operational values of the process parameters received from the industrial system, and determining residual values for the process parameters, each representing a difference between a respective one of the predicted values and a respective one of the operational values.

Disclosed is a fault signal recovery system including a data processor configured to generate a signal subset U* by removing, from a signal set U for a plurality of tags, some tags including a fault signal, and a first learning signal subset X* by removing tags disposed at positions corresponding to the some tags from a learning signal set X containing only tags of normal signals, a modeling unit configured to generate feature information F extractable from the first learning signal subset X* and recovery information P on a plurality of recovery models usable for restoring the fault signal, and a recovery unit configured to estimate and recover normal signals for the some tags based on the signal subset U*, the first learning signal subset X*, the feature information F, the recovery information P on the plurality of recovery models, and similarity Z.

A system includes an industrial automation component configured to receive a first voltage from a voltage source to enable the industrial automation component to perform one or more operations, a mechanical device configured to generate a second voltage, and a display configured to present image data. The display is configured to maintain presentation of the image data in absence of the first voltage received from the voltage source or the second voltage received from the mechanical device. The system also includes processing circuitry configured to use the second voltage generated by the mechanical device to adjust the image data presented by the display when the first voltage is unavailable.

A method for diagnosing and predicting operation conditions of large-scale equipment based on feature fusion and conversion, including: collecting a vibration signal of each operating condition of the equipment, and establishing an original vibration acceleration data set of the vibration signal; performing noise reduction on the original vibration acceleration data set, and calculating a time domain parameter; performing EMD on a de-noised vibration acceleration and calculating a frequency domain parameter; constructing a training sample data set through the time domain parameter and the frequency domain parameter; establishing a GBDT model, and inputting the training sample data set into the GBDT model; extracting a leaf node number set from a trained GBDT model; performing one-hot encoding on the leaf node number set to obtain a sparse matrix; and inputting the sparse matrix into a factorization machine to obtain a prediction result.

A fault database includes a fault identifier, a signature or pattern that indicates the presence of the fault, and a set of mitigation control steps. The fault database is intermittently updated and downloaded to an agricultural machine. A fault identification system on the agricultural machine scans data logs that are generated by a log generation system on the agricultural machine and compares information in the data logs to the signature or pattern in the fault database to determine whether any of the faults in the fault database are present on the agricultural machine. If a fault in the fault database is present, a mitigation control step is identified to mitigate the fault, and a control signal is generated on the agricultural machine to implement the mitigation control step.

An arc fault detection method for a photovoltaic system based on an adaptive kernel function and instantaneous frequency estimation includes steps of: sampling signal x.sub.t in a time window length of T.sub.NCT and obtaining an iterative time-frequency diagram of x.sub.t 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 x.sub.t 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.

Anomaly detection and filtering of time-series data, including: identifying, for a multivariate time-series signal, one or more previously observed multivariate time-series signals that are similar within a predetermined threshold to the multivariate time-series signal; and labelling the multivariate time-series signal based on the labels associated with the one or more previously observed multivariate time-series signals.

Example control methods and apparatus are described. One example control method includes obtaining, by a first controller, a first operating status of the first controller before a control function of the first controller and/or a control function of a second controller are/is activated. The first controller receives first indication information sent by the second controller, where the first indication information indicates a controller status of the second controller. The first controller sets a first controller mode of the first controller based on the first operating status and the first indication information. Second indication information is sent by the first controller to the second controller, so that a first controller mode of the second controller that is set by the second controller does not conflict with the first controller mode of the first controller.

A monitoring method, to be performed by a monitoring device that performs analysis of time-series data, includes calculating statistical information corresponding to a comparison result between time-series data of a search object and past time-series data, and outputting the calculated statistical information.