公开(公告)号：US11501132B2

公开(公告)日：2022-11-15

申请号：US16784566

申请日：2020-02-07

Applicant: Hitachi, Ltd.

Inventor： Qiyao Wang ,  Haiyan Wang ,  Chetan Gupta ,  Hamed Khorasgani ,  Huijuan Shao ,  Aniruddha Rajendra Rao

IPC: G06N3/04 ,  G06Q10/00 ,  G06N3/08

Abstract: In example implementations described herein, there are systems and methods for processing sensor data from an equipment over a period of time to generate sensor time series data; processing the sensor time series data in a kernel weight layer configured to generate weights to weigh the sensor time series data; providing the weighted sensor time series data to fully connected layers configured to conduct a correlation on the weighted sensor time series data with predictive maintenance labels to generate an intermediate predictive maintenance label; and providing the intermediate predictive maintenance label to an inversed kernel weight layer configured to inverse the weights generated by the kernel weight layer, to generate a predictive maintenance label for the equipment.

公开(公告)号：US11500370B2

公开(公告)日：2022-11-15

申请号：US16547374

申请日：2019-08-21

Applicant: Hitachi, Ltd.

Inventor： Shuai Zheng ,  Ahmed Khairy Farahat ,  Chetan Gupta

IPC: G05B23/02 ,  G06K9/62 ,  G06N3/08

Abstract: Example implementations involve a system for Predictive Maintenance using Generative Adversarial Networks for Failure Prediction. Through utilizing three processes concurrently and training them iteratively with data-label pairs, example implementations described herein can thereby generate a more accurate predictive maintenance model than that of the related art. Example implementations further involve shared networks so that the three processes can be trained concurrently while sharing parameters with each other.

公开(公告)号：US11031009B2

公开(公告)日：2021-06-08

申请号：US16380343

申请日：2019-04-10

Applicant: Hitachi, Ltd.

Inventor： Walid Shalaby ,  Chetan Gupta ,  Maria Teresa Gonzalez Diaz ,  Adriano Arantes

IPC: G10L15/22 ,  G10L15/18 ,  G10L15/197

Abstract: Example implementations involve a framework for knowledge base construction of components and problems in short texts. The framework extracts domain-specific components and problems from textual corpora such as service manuals, repair records, and public Q/A forums using: 1) domain-specific syntactic rules leveraging part of speech tagging (POS), and 2) a neural attention-based seq2seq model which tags raw sentences end-to-end identifying components and their associated problems. Once acquired, this knowledge can be leveraged to accelerate the development and deployment of intelligent conversational assistants for various industrial AI scenarios (e.g., repair recommendation, operations, and so on) through better understanding of user utterances. The example implementations give better tagging accuracy on various datasets outperforming well known off-the-shelf systems.

公开(公告)号：US20210056484A1

公开(公告)日：2021-02-25

申请号：US16547349

申请日：2019-08-21

Applicant: Hitachi, Ltd.

Inventor： Susumu SERITA ,  Chetan Gupta

IPC: G06Q10/06 ,  G06Q10/08 ,  G06F17/50 ,  G06N20/00

Abstract: Example implementations described herein involve methods and systems with one or more machines on a factory floor. Example implementations involve, in response to received orders, determining an initial scheduling policy for internal processes to meet the order and a due date policy for the order; a) executing a simulation involving scheduling decisions and due date quotations based on the initial scheduling policy and the due date policy; b) executing a machine learning process on the simulation results to update the scheduling policy and the due date policy by evaluating the scheduling decisions and the due date quotations according to a scoring function which is common for evaluating the scheduling decisions and evaluating the due date quotations; iteratively executing a) and b) until a finalized scheduling policy and the due date policy is determined; and output the finalized scheduling policy and the due date policy in response to the order.

公开(公告)号：US10901832B2

公开(公告)日：2021-01-26

申请号：US16324867

申请日：2017-07-26

Applicant: Hitachi, Ltd.

Inventor： Ahmed Khairy Farahat ,  Chetan Gupta ,  Kosta Ristovski

IPC: G06F11/00 ,  G06F11/07 ,  G06N5/02 ,  G06Q30/02

Abstract: Example implementations described herein involve a system for maintenance recommendation based on data-driven failure prediction. The example implementations can involve estimating the probability of having a failure event in the near future given sensor measurements and events from the equipment, and then alerts the system user or maintenance staff if the probability of failure exceeds a certain threshold. The example implementations utilize historical failure cases along with the associated sensor measurements and events to learn a group of classification models that differentiate between failure and non-failure cases. In example implementations, the system then chooses the optimal model for failure prediction such that the overall cost of the maintenance process is minimized.

公开(公告)号：US20230306084A1

公开(公告)日：2023-09-28

申请号：US17706382

申请日：2022-03-28

Applicant: Hitachi, Ltd.

Inventor： Hamed Khorasgani ,  Haiyan Wang ,  Hsiu-Khuern Tang ,  Chetan Gupta

IPC: G06K9/62 ,  G05B13/02

CPC classification number: G06K9/6263 ,  G06K9/6223 ,  G06K9/6256 ,  G05B13/0265

Abstract: K-nearest multi-agent reinforcement learning for collaborative tasks with variable numbers of agents. Centralized reinforcement learning is challenged by variable numbers of agents, whereas decentralized reinforcement learning is challenged by dependencies among agents' actions. An algorithm is disclosed that can address both of these challenges, among others, by grouping agents with their k-nearest agents during training and operation of a policy network. The observations of all k+1 agents in each group are used as the input to the policy network to determine the next action tor each of the k+1 agents in the group. When an agent belongs to more than one group, such that multiple actions are determined for the agent, an aggregation strategy can be used to determine the final action for that agent.

公开(公告)号：US11693392B2

公开(公告)日：2023-07-04

申请号：US16262778

申请日：2019-01-30

Applicant: Hitachi, Ltd.

Inventor： Shuai Zheng ,  Chetan Gupta ,  Susumu Serita

IPC: G06N3/04 ,  G06N3/08 ,  G05B19/418

CPC classification number: G05B19/41865 ,  G06N3/04 ,  G06N3/08 ,  G05B2219/32335 ,  G05B2219/34379 ,  G05B2219/40499

Abstract: Example implementations described herein are directed to a system for manufacturing dispatching using reinforcement learning and transfer learning. The systems and methods described herein can be deployed in factories for manufacturing dispatching for reducing job-due related costs. In particular, example implementations described herein can be used to reduce massive data collection and reduce model training time, which can eventually improve dispatching efficiency and reduce factory cost.

公开(公告)号：US11200137B1

公开(公告)日：2021-12-14

申请号：US16998926

申请日：2020-08-20

Applicant: Hitachi, Ltd.

Inventor： Susumu Serita ,  Chi Zhang ,  Chetan Gupta ,  Qiyao Wang ,  Huijuan Shao

IPC: G06F11/00 ,  G06F11/30 ,  G06F11/07 ,  G06F11/34

Abstract: Aspects of the present disclosure are directed to systems and methods for determining execution of failure prediction models and duration prediction models for a sensor system. Systems and methods can involve receiving streaming data from one or more sensors and for a failure prediction model processing the streaming data indicating a predicted failure with a probability higher than a threshold, obtaining a duration of the predicted failure from a duration prediction model configured to predict durations of detected failures based on the streaming data; deactivating the failure prediction model when the predicted failure occurs; and determining a time to reactivate the failure prediction model based on the obtained duration of the predicted failure.

公开(公告)号：US11099551B2

公开(公告)日：2021-08-24

申请号：US15884986

申请日：2018-01-31

Applicant: Hitachi, Ltd.

Inventor： Kosta Ristovski ,  Chetan Gupta ,  Ahmed Farahat ,  Onur Atan

IPC: G06N20/00 ,  G05B23/02 ,  G06N7/00 ,  G06N5/04 ,  G06F17/11

Abstract: Example implementations described herein involve a system for maintenance predictions generated using a single deep learning architecture. The example implementations can involve managing a single deep learning architecture for three modes including a failure prediction mode, a remaining useful life (RUL) mode, and a unified mode. Each mode is associated with an objective function and a transformation function. The single deep learning architecture is applied to learn parameters for an objective function through execution of a transformation function associated with a selected mode using historical data. The learned parameters of the single deep learning architecture can be applied with streaming data from with the equipment to generate a maintenance prediction for the equipment.

公开(公告)号：US11042145B2

公开(公告)日：2021-06-22

申请号：US16007892

申请日：2018-06-13

Applicant: Hitachi, Ltd.

Inventor： Chi Zhang ,  Chetan Gupta ,  Ahmed Khairy Farahat ,  Kosta Ristovski ,  Dipanjan Ghosh

IPC: G05B19/40 ,  G05B19/4065 ,  G05B19/042 ,  G06F11/34 ,  G06N20/00

Abstract: Example implementations described herein are directed to systems and methods for predictive maintenance with health indicators using reinforcement learning. An example implementation includes a method to receive sensor data, operational condition data, and failure event data and generate a model to determine health indicators that indicate equipment performance based on learned policies, state values, and rewards. The model is applied to external sensor readings and operating data for a piece of equipment to output a recommendation based on the model.