Mitsubishi Electric Research Laboratories, Inc.

Mitsubishi Electric Corporation

Emil Laftchiev

Daniel Nikolaev Nikovski

Diego Romeres

Devesh Jha

Saleh Nabi

Piyush Grover

Annamalai Natarajan

Qing Yan

Wenyu Zhang

A control system for controlling a heating ventilation and air conditioning (HVAC) system, uses a thermal comfort model (TCM), an airflow dynamics model (ADM) and an HVAC model connecting thermal states at air vents with states of actuators of the HVAC system, for determining a target thermal state at the air vents connecting the HVAC system to an environment, such that the target thermal state at the air vents results in a thermal state at the location of an occupant according to the ADM connecting uneven distribution of thermal states at different locations in the environment. Further, the control system determines and submits control commands to one or multiple actuators of the HVAC system producing the target thermal state at the air vents.

System and method for personalized thermal comfort control

A computer-implemented method of training an autoencoder to recover missing data is provided. The autoencoder includes an encoder for encoding its inputs into a latent space and a decoder for decoding the encodings from the latent space. The method comprises creating a first training set including a valid data set of multiple dimensions, and training the encoder and the decoder in a first training stage using the first training set to reduce a difference between the valid data set provided to the encoder and a data set decoded by the decoder. The method further comprises creating a second training set comprising an invalid data set, and training the encoder in a second training stage using the second training set to reduce a difference between encodings of valid data instances and encodings of their corresponding invalid data instances.

System and a method for training a neural network having autoencoder architecture to recover missing data

A system for detecting an anomaly in an execution of a task in mixed human-robot processes. Receiving human worker (HW) signals and robot signals. A processor to extract from the HW signals, task information, measurements relating to a state of the HW, and input into a Human Performance (HP) model, to obtain a state of the HW based on previously learned boundaries of the state of the HW, the state of the HW is then inputted into a Human-Robot Interaction (HRI) model, to determine a classification of an anomaly or no anomaly. Update HRI model with robot operation signals, HW signals and classified anomaly, determine a control action of a robot interacting with the HW or a type of an anomaly alarm using the updated HRI model and classified anomaly. Output the control action of the robot to change a robot action or output the type of the anomaly alarm.

Systems and methods automatic anomaly detection in mixed human-robot manufacturing processes

A system for detection of an anomaly in a discrete manufacturing process (DMP) with human-robot teams executing a task. Receive signals including robot, worker and DMP signals. Predict a sequence of events (SOEs) from DMP signals. Determine whether the predicted SOEs in the DMP signals is inconsistent with a behavior of operation of the DMP described in a DMP model, and if the predicted SOEs from DMP signals is inconsistent with the behavior, then an alarm is to be signaled. Input worker data into a Human Performance (HP) model, to obtain a state of the worker based on previously learned boundaries of human state. The state of the HW is then input into the HRI model and the DMP model to determine a classification of anomaly or no anomaly. Update a Human-Robot Interaction (HRI) model to obtain a control action of a robot or a type of an anomaly alarm.

Systems and methods for advance anomaly detection in a discrete manufacturing process with a task performed by a human-robot team

A controller for controlling a heating, ventilating, and air-conditioning (HVAC) system arranged to condition an environment according to HVAC setpoints is provided. The controller is configured to accept target values of thermal states at predetermined locations in the conditioned environment, current values of the thermal states at the predetermined locations in the conditioned environment, and current values of the HVAC setpoints. The controller is further configured to determine, using a neural network, target HVAC setpoints such that a difference in an operation of the HVAC system according to the target HVAC points with respect to the operation of the HVAC system according to the current HVAC setpoints changes thermal states in the predetermined locations in the conditioned environment from the current values of the thermal state to the target values of the thermal state.

System and method for thermal control based on invertible causation relationship

A system evaluates a plurality of faults in an operation of a machine at a set of future instances of time. The system uses a neural network including a first subnetwork sequentially connected with a sequence of second subnetworks for each of the future instance of time such that an output of one subnetwork is an input to a subsequent subnetwork. The first subnetwork accepts the current time-series data and the current setpoints of operation of the machine. Each of the second subnetworks accepts the output of a preceding subnetwork, an internal state of the preceding subnetwork, and a future setpoint for a corresponding future instance of time. Each of the second subnetworks outputs an individual prediction of each fault of a plurality of faults at the corresponding future instance of time.

Predictive classification of future operations

Systems and methods for controlling an operation of devices for an occupant. A processor to iteratively train a personalized thermal comfort model (PTCM) during an initialization period. Receive a sequence of unlabeled real-time data. A transmitter requests the occupant to label an instance of unlabeled data, when there is a disagreement between the labels of stored historical labeled data (LD) similar to received unlabeled data and a predicted label on the new unlabeled data that exceeds a threshold. The processor, in response to receiving the labeled data, trains the PTCM using different weights of the personalized LD than to the historical LD. Retrains PTCM using the historical database and the updated personalized database. A controller controls the set of devices based on the retrained PTCM.

Growing community of inventors

Cambridge, MA, United States of America

Emil Laftchiev