Abstract: A prediction method implemented by a computer, the method includes: receiving a classification model from a server, the classification model being a model for classifying logs of an electronic device into two or more classes, the server being a computer configured to distribute the classification model; calculating, with respect to different time points, a prediction error by using a predicted value outputted by the classification model and an actual measured value observed at each of the different time points; performing sequential machine learning for the classification model to have the prediction error satisfy a certain condition; and when a cumulative sum with respect to the prediction error of the sequential machine learning is equal to or greater than a threshold, requesting the server apparatus to relearn the classification model.

Abstract: A method may include obtaining, at a server or analysis device, sensor data comprising at least one of vibration data and impulse data from one or more sensor devices coupled to a first utility infrastructure; obtaining training sensor data associated with at least one of the first utility infrastructure from a previous time period and one or more second utility infrastructures; comparing the sensor data with the training sensor data associated with the at least one of the first utility infrastructure from the previous time period and the one or more second utility infrastructures; and identifying or predicting a fault occurrence associated with the first utility infrastructure based on the comparing the sensor data associated with the first utility infrastructure to the training sensor data associated with the at least one of the first utility infrastructure from the previous time period and the one or more second utility infrastructures.

Abstract: A method includes estimating a replacement time of a consumable part of a processing device, specifying a timing after substrate processing of the processing device is completed in a period before the replacement time as a replaceable timing of the consumable part, estimating a movement time period required for the part transporting device to move to a position of the processing device requiring the replacement, and estimating a preparation time period required for preparation until the part transporting device moved to the position of the processing device requiring the replacement becomes a state in which the consumable part is replaceable. The method further includes transmitting a replacement instruction to the part transporting device at a timing before a timing that is earlier than the replaceable timing by a total time of the movement time period and the preparation time period, and instructing the replacement of the consumable part.

Abstract: An operation assistance method for presenting a recommended operational action in response to an alert issued in a facility includes: detecting issuance of the alert; extracting, from an alert history storage unit, an issuance history of a same type of alert as the alert of which the issuance or the sign of issuance has been detected; extracting, from an operation history storage unit storing an operation history of the facility, an operational action after issuance of the same type of alert; extracting, from an operational data storage unit storing information indicating an operational state of the facility, information indicating the operational state after the operational action, and verifying an influence of the operational action on the operational state; and presenting the recommended operational action in response to the alert of which the issuance has been detected, based on the extracted operational action and the verified influence.

Abstract: Disclosed herein is a method of repairing a component. The method includes scanning a damaged area of the component, and preparing a repair plan in response to the scanning. The method may also include providing the repair plan to a guided tool having a position correcting controller, and removing damaged material from the component in preparation for a repair operation. An apparatus is also disclosed that includes a computing device configured for performing actions. The computing device includes a processor and a local memory. The actions include detecting damage to the component, recording position information of the detected damage, and incorporating the position information in the repair plan.

Abstract: A non-transitory, computer-readable recording medium stores a program of reinforcement learning by a state-value function. The program causes a computer to execute a process including calculating a temporal difference (TD) error based on an estimated state-value function, the TD error being calculated by giving a perturbation to each component of a feedback coefficient matrix that provides a policy; calculating based on the TD error and the perturbation, an estimated gradient function matrix acquired by estimating a gradient function matrix of the state-value function with respect to the feedback coefficient matrix for a state of a controlled object, when state variation of the controlled object in the reinforcement learning is described by a linear difference equation and an immediate cost or an immediate reward of the controlled object is described in a quadratic form of the state and an input; and updating the feedback coefficient matrix using the estimated gradient function matrix.

Abstract: There is described a system and method of a building management system for preventive maintenance of an HVAC unit. Runtime data of the HVAC unit is received at a control system remote from the HVAC unit. A service message is initiated, by the control system, to a service device associated with the HVAC unit in response to determining that a preventive maintenance visit is warranted based on the runtime data. A hot-cold test for the HVAC unit is activated by the control system in response to receiving the registration message of the preventive maintenance visit from the service device. A validation message is reported in response to validating the preventive maintenance visit based on a result of the hot-cold test for the HVAC unit.

Abstract: A state display device 100 includes a display device 30 for displaying a temporal change of a first parameter representing an operation state of a thermal power generation facility 10, and a correlation between the first parameter and a second parameter representing an operation state of the thermal power generation facility 10, an input device 70 for respectively selecting and inputting a first period t1 and a second period t2 different from the first period t2 in the temporal change of the first parameter, and a processing device 50. The processing device 50 is configured to display the temporal change of the first parameter on the display device 30, and to display, on the display device 30, the correlation between the first parameter and the second parameter in each of the first period t1 and the second period t2 input via the input device 70.

Abstract: A method for monitoring and assessing correct position Pi of a work slide of a wedge drive tool in a press, without a position sensor. The slide of the wedge drive tool is actuated from an end position (XE) back to the starting position (XA) of the slide by a spring. The spring is arranged in the wedge drive tool. The press is opened from a lower press position to an upper press position while a slide bed of the wedge drive tool is relieved. The position of the slide is indirectly detected in that at least the restoring force of the spring is detected and evaluated.

Abstract: The invention is a method to optimize solar photovoltaic power plant repowering by making use of the smart predictive and preventive maintenance which detects failures in modules or in cells within modules, i.e., aerial inspections by infrared thermography and/or electroluminescence. In the method object of the invention, the detected failed modules are separated in different types of failures: A—irreversible; B—reversible and C—partly reusable. Repowering consists on substituting modules of type A for new, more powerful ones, and re-group them series-connected within the same strings (1). Modules with type B failures are repaired and installed back in their original place, and modules C are either re-grouped in series-strings, or substituted by new, more powerful modules, also series connected in strings (1).

Abstract: A system and method for optimizing an additive manufacturing process in which a reinforcement material is randomly introduced to a fabrication bed. An image of the fabrication bed is captured. The image is analyzed by code in a computer to identify the actual arrangement of the randomly deposited reinforcement material relative to the object being manufactured. Based on the image data showing the reinforcement material, a toolpath is dynamically determined that incorporates the random reinforcement material. Accordingly, the toolpath incorporates the reinforcement material into the structure of the object, which can result in a reduction of the total amount of raw material is fused to create the object being manufactured.

Abstract: Complexity of a geometry of a desired (i.e., target) three-dimensional (3D) object being produced by an additive manufacturing system, as well as atypical behavior of the processes employed by such a system, pose challenges for producing a final version of the desired 3D object with fidelity relative to the desired object. An example embodiment enables such challenges to be overcome as a function of feedback to enable the final version to be produced with fidelity. The feedback may be at least one value that is associated with at least one characteristic of a printed object following processing of the printed object. Such feedback may be obtained as part of a calibration process of the 3D printing system or as part of an operational process of the 3D printing system.

Abstract: According to certain embodiments, a system comprises a primary unit and a plurality of secondary units each having a unique unit number. The primary unit is configured to communicate a command to each secondary unit with instructions to reply during a time window. The primary unit is also configured to receive a reply communication indicating the secondary unit's unique unit number from at least one of the secondary units, and determine an address to assign to the replying secondary unit based at least in part on the received unique unit number.

Abstract: A sensor management system includes a historical data repository, a building management system (BMS) controller, and a sensor diagnostics system. The historical data repository may store historical data by a plurality of sensors. The BMS controller may control one or more components of a building subsystem based on data provided by one or more sensors. The sensor diagnostic system may receive, from a sensor, sensor data. The sensor diagnostic system may determine at least one fault in the sensor data. The sensor diagnostic system may select, from the historical data repository, substitute sensor data for the sensor based on a comparison of one or more attributes of the sensor data and one or more attributes of the historical data in the data repository. The sensor diagnostic system may provide, in replacement of the sensor data from the sensor, the supplemental sensor data to the BMS controller.

Abstract: An artificial intelligence server for controlling a plurality of robots using artificial intelligence includes a communication unit configured to receive a captured image of each of a plurality of zones and a processor configured to acquire situation information of each zone based on the received image, acquire degrees of guidance urgency respectively corresponding to the plurality of zones based on the acquired situation information of each zone, determine whether there is a degree of guidance urgency greater than a predetermined value in the acquired degrees of guidance urgency, and, when there is a degree of guidance urgency greater than the predetermined value, transmit a first control command for moving one or more robots to a zone corresponding to the degree of guidance urgency.

Abstract: A setting method according to the present invention determines a desired time response in an optimum servo control structure corresponding to a servo control structure of a control target, calculates a predetermined gain corresponding to the desired time response, and calculates a first weighting coefficient Qf, a second weighting coefficient Q, and a third weighting coefficient R of a predetermined Riccati equation according to the Riccati equation on the basis of the predetermined gain. The first weighting coefficient Qf, the second weighting coefficient Q, and the third weighting coefficient R are set as a weighting coefficient corresponding to a terminal cost, a weighting coefficient corresponding to a state quantity cost, and a weighting coefficient corresponding to a control input cost, respectively, in a predetermined evaluation function for model prediction control.

Abstract: A ceiling fan comprising an image capture device. The image capture device operable to capture one or more images depicting at least a portion of a room or area in which the ceiling fan is located.

Abstract: A climate control unit configured to control a heating unit and a cooling unit. The climate control unit includes a temperature sensor configured to measure a current dry bulb temperature, a humidity sensor configured to measure a current relative humidity, a processor, and a storage medium operably coupled to the processor. The storage medium has software instructions stored therein, which, when executed by the processor, cause the processor to determine a current apparent temperature based on the current dry bulb temperature and the current relative humidity, receive a user-selected desired apparent temperature, activate a heating mode when the current apparent temperature is below a lower apparent temperature threshold, and activate a cooling mode when the current apparent temperature is above an upper apparent temperature threshold. The software instructions, when executed by the processor, cause the processor to automatically switch between the heating mode and the cooling mode.

Abstract: An equipment management system includes an information processing apparatus obtains equipment information about equipment, and a management apparatus. The management apparatus communicates the equipment information with the information processing apparatus under a predetermined communication condition, and manages the equipment. Either or both of the management apparatus and the information processing apparatus include a candidate communication condition generating unit that generates one or more candidate communication conditions in accordance with one or both of a state of the equipment and a state of an installation space in which the equipment is installed.

Abstract: Disclosed is a method for controlling a smart air purifier, the method including: obtaining first air cleanliness of a first area in which a first air purifier is placed, and obtaining second air cleanliness of a second area in which a second air purifier is placed; when at least one of the first air cleanliness or the second air cleanliness is equal to or smaller than a preset threshold value, driving both the first air purifier and the second air purifier; monitoring a variation of the first air cleanliness and the second air cleanliness; calculating a weight that is proportional to the variation of the first air cleanliness and the second air cleanliness; and setting a driving mode for the first air purifier and the second air purifier based on the weight.