Devices, methods, and systems for determining the cause of a fault in a heating, ventilation, and air conditioning (HVAC) system are described herein. One device includes a memory, and a processor configured to execute executable instructions stored in the memory to receive operational data associated with an HVAC system, receive control logic associated with a controller of the HVAC system, determine a cause of a fault occurring in the HVAC system based, at least in part, on the operational data associated with the HVAC system and the control logic of the controller of the HVAC system, and provide the cause of the fault occurring in the HVAC system to a user.

Method for monitoring and/or predicting machining processes and/or machining outcomes in mechanical workpiece machining carried out by a workpiece processing machine operable by specifiable operating parameters and having at least one machining tool. The monitoring and/or predicting occurs via a computer program product evaluation algorithm executed on a computer on the basis of training data sets. The training data sets include, as training data, adjustment data relating to adjustment of operating parameters of the workpiece processing machine for carrying out a machining process to be monitored and/or predicted. The training data sets further include outcome data of workpieces finished in a machining process to be monitored and/or predicted, and state data of the processing machine, determined by sensor, during a machining process to be monitored and/or predicted. In use, capture of outcome data by prediction made on the basis of machine-learned knowledge is avoided or reduced.

Disclosed is a method for monitoring and/or controlling a chemical plant (12) with multiple assets via a distributed computing system (10) with more than two deployment layers (14, 16, 30, 32, 34), wherein the deployment layers (14, 16, 30, 32, 34) comprise at least two of a first processing layer (14), a second processing layer (16, 32, 34) and an external processing layer (30), the method comprising the steps of: providing (60) a containerized application (48, 50) including an asset or plant template specifying input data, output data and an asset or plant model, deploying (62) the containerized application (48, 50) to execute on at least one of the deployment layers (14, 16, 30, 32, 34), wherein the deployment layer (14, 16, 30, 32, 34) is assigned based on the input data, a load indicator, or a system layer tag, and executing the containerized application (46, 52, 54) on the assigned deployment layer(s) (14, 16, 30, 32, 34) to generate output data for controlling and/or monitoring the chemical plant (12), providing (66) the generated output data for controlling and/or monitoring the chemical plant (12).

An overall efficiency of an actuator system can be monitored to determine the health of the actuator system. A ratio between the output power of the actuator system and the input power of the actuator system is monitored over time. Degradation of the efficiency of the actuator system may be observed and corrective action taken before failure of the actuator system.

A method executed by an arithmetic circuit of one or a plurality of computers includes periodically collecting log information from an electronic device, inputting the log information collected before a current clock time from the electronic device to a prediction model, causing the prediction model to predict an abnormal or normal operating state of a recording medium after the current clock time, and transmitting replacement notification information that is based on a prediction result to the electronic device. The prediction model is generated by performing machine learning using, as training data, training log information collected within a predetermined period up to a reference clock time from a plurality of training electronic devices each including a training recording medium, and state information indicating an operating state of the training recording medium determined after the reference clock time.

An automotive sensor integration module including a plurality of sensors which differ in at least one of a sensing period or an output data format, and a signal processing unit, which simultaneously outputs, as sensing data, pieces of detection data respectively output from the plurality of sensors on the basis of the sensing period of any one of the plurality of sensors, determines whether each region of an outer cover corresponding to a location of each of the plurality of sensors is contaminated on the basis of the pieces of detection data, and outputs a determination result as contamination data.

The present invention provides a data fusion and reconstruction method for fine chemical industry safety production based on a virtual knowledge graph. In view of the characteristics of fine chemical industry safety production data, such as a large amount of structured data, a multi-source heterogeneous database and a strong sequential logic, the present invention innovatively proposes a method of using a virtual knowledge graph to complete the fusion and reconstruction of a traditional database for fine chemical industry. The present invention fuses static structured knowledge in the field of fine chemical industry with a real-time dynamic database for chemical industry safety production in the concept of ontologies for the first time to organize time series data in the form of entities. In addition, the mapping rules of the existing OBDA system are improved based on a data set of the present invention.

When a general-purpose operation part (22, 23) is hidden by a window part (24), it becomes hard for an operator to visually check an association state between a field device (10A, 10B) and a hardware switch (3). If such a display state has occurred, an HMI server (5) stops a health check signal which is being output to a PLC (6). The PLC (6) detects the stop of the health check signal and forcibly cancels the association state between the field device (10A, 10B) and the hardware switch (3). Thus, a human error can be prevented.

An inference device, an inference method, and an inference program that can realize high precision inference regardless of an application target are provided. An inference device includes: an acquisition section configured to acquire a time series data group measured in accordance with processing of a target object in a predetermined processing unit of a manufacturing process; and an inference section configured to tune respective output data that is output by processing the acquired time series data group using a plurality of network sections that have been machine-learned in advance and to output an inference result by combining the respective tuned output data; wherein the inference section is configured to tune the respective output data using a correction parameter corresponding to an error included in the inference result.

A control method includes: monitoring a statistic obtained by performing a multivariate analysis on a plurality of parameters; extracting, from the plurality of parameters, a predetermined number of higher-order parameters in terms of an influence degree on fluctuation of the statistic; generating a plurality of experimental patterns according to an experimental design method; acquiring a measurement result of a specific parameter indicating quality of a product when at least one device is controlled according to each of the plurality of experimental patterns; setting a new target value of the predetermined number of higher-order parameters in order to stabilize a value of the specific parameter within a management range based on the measurement result; and controlling the at least one device such that the predetermined number of higher-order parameters approaches the new target value.