The present disclosure describes a method of controlling a manufacturing system using multivariate time series, the method comprising: recording data from one or more devices in the manufacturing system; storing the recorded data in a data storage as a plurality of time series, wherein each time series has a first recorded value corresponding to a first time and a final recorded value corresponding to an end of the time series; interpolating, within a first time window, missing values in the plurality of time series using a Bayesian model, wherein the missing values fall between the first and end time of the respective time series; storing the interpolated values as prediction data in a prediction storage, wherein the interpolated values include the uncertainty of each interpolated value; loading the recorded data that fall within a second time window from the data storage; loading prediction data from the prediction storage that fall within the second time window and for which no recorded data are available; optimizing the parameters of the Bayesian model using the loaded recorded data and the prediction data; predicting, using the Bayesian model, values for each of the time series for which loaded recorded and prediction data are not available; storing the predicted values as prediction data in the prediction storage, wherein the prediction values include the uncertainty of each prediction value; and adjusting one or more of the devices that generate the recorded data based on the prediction data within the second time window.

The present invention provides a method for operating dual controller which monitors the state of a dual controller to determine whether the dual controller is faulty and enables operation thereof with a controller in a normal state. An operation method of a dual controller according to the present invention dq-converts control command output values of first and second controllers to calculate rates of change in dq conversion values and dq-converts feedback input values, fed back to the first and second controllers, to calculate average rates of change in dq conversion values. When the average rates of change in the dq conversion values for the control command output values and the average rates of change in the dq conversion values for the feedback input values for the respective first and second controllers are identical, the corresponding controller is determined to be in a normal state, and to be in a faulty state otherwise. According to the results of the determination, the controller in the faulty state is set to a standby state and the controller in the normal state is set to an active state.

The present disclosure describes a method of controlling a manufacturing system using multivariate time series, the method comprising: recording data from one or more devices in the manufacturing system; storing the recorded data in a data storage as a plurality of time series, wherein each time series has a first recorded value corresponding to a first time and a final recorded value corresponding to an end of the time series; interpolating, within a first time window, missing values in the plurality of time series using a Bayesian model, wherein the missing values fall between the first and end time of the respective time series; storing the interpolated values as prediction data in a prediction storage, wherein the interpolated values include the uncertainty of each interpolated value; loading the recorded data that fall within a second time window from the data storage; loading prediction data from the prediction storage that fall within the second time window and for which no recorded data are available; optimizing the parameters of the Bayesian model using the loaded recorded data and the prediction data; predicting, using the Bayesian model, values for each of the time series for which loaded recorded and prediction data are not available; storing the predicted values as prediction data in the prediction storage, wherein the prediction values include the uncertainty of each prediction value; and adjusting one or more of the devices that generate the recorded data based on the prediction data within the second time window.

There is described a system and method for active fault detection of an HVAC system and its associated mechanical equipment comprising building automation controllers and a remote device. A request for active fault detection of controllers of a building automation system (“BAS”) network is received. A passive test associated with each controller is executed by analyzing the controller via read-only access to operations of the controller. The passive test includes identifying a fault condition and a work item associated with the controller or a mechanical device connected to the controller. A full range full range active test based on the fault condition and the work item associated with each controller is executed by analyzing the controller via direct command access to the operations of the controller. A controller function associated with the request for active fault detection of the controllers is performed in response to executing the full range active test.

A manufacturing cell includes an allowable range setting unit configured to set an allowable range for physical quantity data or statistical processing data, and data output unit configured to output, in a case where the physical quantity data or the statistical processing data deviates from the allowable range, output information. The manufacturing cell further includes an abnormality information determination unit configured to compare the physical quantity data or the statistical processing data of a manufacturing cell as an abnormality source, with the retained physical quantity data or the retained statistical processing data of the manufacturing cell, to determine whether or not the abnormality is inherent to the manufacturing cell as the abnormality source, and a determination result notification unit for notifying a determination result.

The invention relates to a computer system, a computer-implemented method, a computer program product and a user interface for controlling, detecting, regulating, and/or analyzing biological, biochemical, chemical and/or physical processes, comprising at least two units which are designed to receive a substance or material in order to carry out at least one biological, biochemical, chemical, and/or physical process on said substance. Each unit has at least one sensor which is designed to detect measurement data relating to the process. Additionally, the computer system comprises at least one display unit via which the measurement data of the two units is displayed in respective temporal correlations which allows information to be obtained on a relationship inherent in the displayed measurement data.

A cloud-based analytics engine that analyzes data relating to an industrial automation system(s) to facilitate enhancing operation of the industrial automation system(s) is presented. The analytics engine can interface with the industrial automation system(s) via a cloud gateway(s) and can analyze industrial-related data obtained from the industrial automation system(s). The analytics engine can determine correlations between respective portions or aspects of the system(s), between a portion(s) or aspect(s) of the system(s) and extrinsic events or conditions, or between an employee(s) and the system(s). The analytics engine can determine and provide recommendations or instructions in connection with the industrial automation system(s) to enhance system performance based on the determined correlations. The analytics engine also can determine when there is a deviation or potential of deviation from desired system performance by an industrial asset or employee, and provide a notification, a recommendation, or an instruction to rectify or avoid the deviation.

A vacuum system includes at least one cryopump; sensors associated with the cryopump, each of the sensors being configured to sense an operating condition of the cryopump; and diagnostic circuitry configured to receive signals sampled from the sensors. The diagnostic circuitry includes a diagnostic model of the cryopump, the diagnostic model being derived from historical data of a plurality of cryopumps of a same type operating over a plurality of regeneration and servicing time periods and being configured to relate values of the sampled signals from the at least some sensors to a probability of the pump failing within a predetermined time. The diagnostic circuitry is configured to apply the sampled signals to the diagnostic model and to determine the probability of the at least one cryopump failing within a predetermined time from an output of the model.

Systems, methods, non-transitory computer readable media can be configured to access a plurality of sensor logs corresponding to a first machine, each sensor log spanning at least a first period; access first computer readable logs corresponding to the first machine, each computer readable log spanning at least the first period, the computer readable logs comprising a maintenance log comprising a plurality of maintenance task objects, each maintenance task object comprising a time and a maintenance task type; determine a set of statistical metrics derived from the sensor logs; determine a set of log metrics derived from the computer readable logs; and determine, using a risk model that receives the statistical metrics and log metrics as inputs, fault probabilities or risk scores indicative of one or more fault types occurring in the first machine within a second period.

A system and method for monitoring and diagnosis of engine health are provided. In one aspect, a system receives continuous operating data (COD) associated with an asset. The COD includes parameter values for one or more parameters over a collection time period. The system generates synthetic snapshot data based at least in part on the COD. The synthetic snapshot data includes one or more synthetic snapshots each containing the parameter values for the one or more parameters for a given timepoint within the collection time period. The system also receives snapshot data associated with the asset. The snapshot data includes one or more snapshots each containing parameter values for the one or more parameters for a given timepoint. The system generates an output indicating a health status of the asset or one or more components thereof based at least in part on the snapshot data and the synthetic snapshot data.