专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2021197782A1 DATA PROCESSING FOR INDUSTRIAL MACHINE LEARNING 审中-公开
公开(公告)号：WO2021197782A1
公开(公告)日：2021-10-07
申请号：PCT/EP2021/056093
申请日：2021-03-10
申请人： ABB SCHWEIZ AG
发明人： KLOEPPER, Benjamin , SCHMIDT, Benedikt , AMIHAI, Ido , CHIOUA, Moncef , SCHLAKE, Jan Christoph , KOTRIWALA, Arzam , HOLLENDER, Martin , JANKA, Dennis , LENDERS, Felix , ABUKWAIK, Hadil
IPC分类号： G06N20/00 , G06N7/00 , G06F17/40 , G06F16/215 , G05B23/00 , G05B23/024 , G05B23/0283 , G06N7/005
摘要： The invention relates to a computer-implemented method (100) for automating the development of industrial machine learning applications in particular for predictive maintenance, process monitoring, event prediction, or root-cause analysis. The method consists of one or more sub-methods that, depending on the industrial machine learning problem, may be executed iteratively. These sub-methods include at least one of a method to automate the data cleaning in training (S10) and later application (S15) of machine learning models, a method to label (S11) time series (in particular signal data) with help of other timestamp records, feature engineering (S12) with the help of process mining, and automated hyperparameter tuning (S14) for data segmentation and classification.

2. 发明申请

WO2022136108A1 AUTOMATIC IDENTIFICATION OF IMPORTANT BATCH EVENTS 审中-公开
公开(公告)号：WO2022136108A1
公开(公告)日：2022-06-30
申请号：PCT/EP2021/086189
申请日：2021-12-16
申请人： ABB SCHWEIZ AG
发明人： HOLLENDER, Martin , SCHMIDT, Benedikt
IPC分类号： G05B13/04 , G05B19/418 , G06F9/48
摘要： Method for automatic identification of important batch events for a batch execution alignment algorithm, comprising: receiving (S10) historical batch data of a batch process, wherein the historical batch data comprises a plurality of batch executions (10, 20), and wherein each of the plurality of batch executions (10, 20) comprises a plurality of batch events (E11, E12, E21, E22), indicating a specific event of the batch process, and at least one time series of a process variable (V1, V2, V3), indicating a development of the process variable during the batch process; determining (S20) a distance between the at least one time series (V1, V 2, V3) of the plurality of the batch executions (10, 20) for each of the plurality of batch events (E11, E12, E21, E22); and identifying (S30) at least one important batch event (Ml) for a batch execution alignment algorithm with a smallest distance using the determined distances.

3. 发明申请

WO2021198357A1 METHOD OF TRANSFER LEARNING FOR A SPECIFIC PRODUCTION PROCESS OF AN INDUSTRIAL PLANT 审中-公开
公开(公告)号：WO2021198357A1
公开(公告)日：2021-10-07
申请号：PCT/EP2021/058477
申请日：2021-03-31
申请人： ABB SCHWEIZ AG
发明人： SCHMIDT, Benedikt , AMIHAI, Ido , KOTRIWALA, Arzam , CHIOUA, Moncef , JANKA, Dennis , LENDERS, Felix , SCHLAKE, Jan Christoph , HOLLENDER, Martin , ABUKWAIK, Hadil , KLOEPPER, Benjamin
IPC分类号： G06N3/08 , G06N20/00 , G05B13/0265 , G05B17/02 , G05B19/41885 , G05B2219/32352 , G06N3/0454 , G06N3/082 , G06N3/088 , G06N5/022
摘要： The invention relates to a method of transfer learning for a specific production process of an industrial plant, comprises the steps: providing (S10) a plurality of data templates (T) defining expected data for a production process; providing (S20) plant data (P) of the industrial plant, comprising data points of the specific production process, wherein the data points (P) comprise information about input and output of the specific production process; wherein the data template (T) defines a grouping for the expected data according to their relation in the industrial plant; determining (S30) a process instance of the specific production process, defining a mapping between the plant data (P) to the expected data of the specific production process; determining (S40) historic process data, being historic sensor data relating to the specific production process using the determined process instance; determining (S50) training data using the determined process instance (I) and the determined historic process data (H); wherein the training data comprises a structured data matrix, wherein columns of the data matrix represent the sensor data that are grouped in accordance with the data template (T) and wherein rows of the data matrix represent timestamps of obtaining the sensor data; providing (S60) a pre-trained machine learning model using the determined process instance; and training (S70) a new machine learning model using the provided pre-trained model and the determined training data.

4. 发明申请

WO2020212254A1 COMPUTER-IMPLEMENTED DETERMINATION OF A QUALITY INDICATOR OF A PRODUCTION BATCH-RUN OF A PRODUCTION PROCESS 审中-公开
公开(公告)号：WO2020212254A1
公开(公告)日：2020-10-22
申请号：PCT/EP2020/060203
申请日：2020-04-09
申请人： ABB SCHWEIZ AG
发明人： BAUER, Reinhard , HOLLENDER, Martin , GAERTLER, Marco
IPC分类号： G05B19/418
摘要： To determine a quality indicator of production batch-run (220) of a production process (200), a computer (600) compares time-series with multi-source data from a reference batch-run (210) and time-series with multi-source data from the production batch-run (220). Before comparing, the computer converts multi-variate time-series to uni- variate time-series, by first multiplying data values of source-specific uni-variate time-series with source-specific factors from a conversion factor vector (610*) and second summing up the multiplied data values according to discrete time points. The source-specific factors of the conversion factor vector are obtained earlier by processing reference data, comprising the determination of characteristic portions of the time-series, converting, aligning by time-warping and evaluating displacement in time between characteristic portions before alignment and after alignment.

5. 发明申请

WO2019038283A1 METHOD FOR MONITORING AN INDUSTRIAL PLANT AND INDUSTRIAL CONTROL SYSTEM 审中-公开
公开(公告)号：WO2019038283A1
公开(公告)日：2019-02-28
申请号：PCT/EP2018/072559
申请日：2018-08-21
申请人： ABB SCHWEIZ AG
发明人： CHIOUA, Moncef , LUCKE, Matthieu , HOLLENDER, Martin , LI, Nuo , BAUER, Reinhard , HARJUNKOSKI, Iiro
IPC分类号： G05B23/02
CPC分类号： G05B23/0275
摘要： A method for monitoring an industrial plant is provided. The method includes: identifying an abnormal episode based on an alarm log (50); extracting abnormal events from the alarm log (50), the abnormal events being associated with the abnormal episode; computing from the extracted abnormal events an alarm correlation map describing correlations between the extracted abnormal events; and classifying the abnormal episode using the alarm correlation map.

6. 发明申请

WO2022161699A1 METHOD FOR ANALYSING PROCESS DATA RELATED TO A SEGMENT OF A PRODUCTION PROCESS 审中-公开
公开(公告)号：WO2022161699A1
公开(公告)日：2022-08-04
申请号：PCT/EP2021/086161
申请日：2021-12-16
申请人： ABB SCHWEIZ AG
发明人： HOLLENDER, Martin , SCHMIDT, Benedikt , TAN, Ruomu , XU, Chaojun , VOLKMANN, Lara-Marie
IPC分类号： G06F16/2455 , G06F16/2457
摘要： A method for analysing process data related to a segment of a production process as described including the following steps: providing a process data sequence of the segment of the production process exhibiting a data pattern of at least one process variable to be analysed; providing a set of metadata of the segment of the production process related to the provided process data sequence; determining process data sequences based on the provided set of metadata of the segment of the production process, which are stored in a first database; determining a start timestamp and end timestamp of each of the determined process data sequence, based on the first database; and calculating a similarity value for each of the determined process data sequences compared to the provided process data sequence, based on the data pattern of the at least one process variable, wherein the determined process data sequences for the calculation are provided, based on the related start timestamps and end timestamps, by accessing a second database comprising the process data sequences, for analysing the process data.

7. 发明申请

WO2021219429A1 METHOD FOR GENERATING A PROCESS MODEL 审中-公开
公开(公告)号：WO2021219429A1
公开(公告)日：2021-11-04
申请号：PCT/EP2021/060186
申请日：2021-04-20
申请人： ABB SCHWEIZ AG
发明人： SCHMIDT, Benedikt , DIX, Marcel , HOLLENDER, Martin , COHEN, Andrew , KOTRIWALA, Arzam , GAERTLER, Marco , MACZEY, Sylvia , KLOEPPER, Benjamin
IPC分类号： G05B19/042 , G05B17/02
摘要： A method (100) for generating a process model modeling a manual mode procedure instance of a plant process is proposed, the procedure instances comprising a related sequence of operational actions, i.e. mining of historical plant logs to generate a workflow model, including the steps of: Providing a plurality of log events (S1) of a plurality of operational actions (110) of the plant process; Selecting a plurality of related sequences of manual mode operational actions (S2) from the plurality of log events; Filtering the plurality of related sequences of manual mode operational actions according to an individual plant section (S3); Identifying a sequential order (S4) from the plurality of filtered related sequences of the manual mode operational actions; Determining statistical properties of values of related process variables and/or statistical properties of values of related set point changes (S5) to each sequential ordered manual mode operational action from the plurality of filtered related sequences of the manual mode operational actions; Generating the process model (S6) of the manual mode procedure instance by arranging related manual mode operational actions with the sequential order of each operational action assigned with the statistical properties of the values of related process variables and/or assigned with the statistical properties of the values of the related set point changes.

8. 发明申请

WO2021197796A1 METHOD AND APPARATUS FOR MONITORING MACHINE LEARNING MODELS 审中-公开
公开(公告)号：WO2021197796A1
公开(公告)日：2021-10-07
申请号：PCT/EP2021/056180
申请日：2021-03-11
申请人： ABB SCHWEIZ AG
发明人： SCHMIDT, Benedikt , AMIHAI, Ido , CHIOUA, Moncef , KOTRIWALA, Arzam , HOLLENDER, Martin , JANKA, Dennis , LENDERS, Felix , SCHLAKE, Jan Christoph , KLOEPPER, Benjamin , ABUKWAIK, Hadil
IPC分类号： G05B23/02 , G06N3/08 , G05B13/02 , G05B17/02 , G05B13/027 , G05B23/024 , G06N20/00
摘要： The invention relates to the field of monitoring or controlling an industrial process, particularly by means of an artificial neural net. The method comprises the steps of: training the first control model (10) by means of a first set of input data (31) as first input (11), resulting in a trained first control model (10T); copying the trained first control model (10T) to a second control model (20), wherein, after copying, the second input layer (22) and the plurality of second hidden layers (24) is identical to the plurality of first hidden layers (14), and the first output layer (18) is replaced by the second output layer (28); freezing the plurality of second hidden layers (24); training the second control model (20) by means of the first set of input data (31) as second input (21), resulting in a trained second control model (20T); and running the trained second control model (20T) by means of a second set of input data (32) as second input (21), wherein the second output (29) outputs the quality measure (qm) of the first control model (10).

9. 发明申请

WO2018162658A1 SCHEDULING SYSTEM AND METHOD FOR INDUSTRIAL PROCESS 审中-公开
公开(公告)号：WO2018162658A1
公开(公告)日：2018-09-13
申请号：PCT/EP2018/055805
申请日：2018-03-08
申请人： ABB SCHWEIZ AG
发明人： BAUER, Reinhard , GALLESTEY, Eduardo , HARJUNKOSKI, Iiro , HOLLENDER, Martin
IPC分类号： G06Q10/06 , G05B19/418 , G06Q50/04
CPC分类号： G06Q10/06 , G06Q50/04 , Y02P90/14 , Y02P90/20 , Y02P90/30
摘要： A scheduling system (20) for scheduling an industrial process is provided. The process comprises a plurality of tasks carried out by process equipment (10) of an industrial system. The scheduling system comprises a database (30) for storing process information including task status information regarding the tasks; a first interface (42) for receiving a task status message from the process equipment (10) relating to at least one of the tasks; an auto- correction module (44) configured for checking at least one of the received task status message and the stored process information for an inconsistent data entry, and for performing a correction using a correction rule; and an updater module (46) for updating the process information stored in the database based on the task status message. The auto- correction module (44) has an inconsistency-determining submodule for checking at least one of the received task status message and the stored process information for an inconsistent data entry; and a data-correcting submodule for correcting the correction data using the correction rule.

10. 发明申请

WO2018036714A1 COMPUTER SYSTEM AND METHOD TO PROCESS ALARM SIGNALS 审中-公开
标题翻译：计算机系统和处理报警信号的方法
公开(公告)号：WO2018036714A1
公开(公告)日：2018-03-01
申请号：PCT/EP2017/067537
申请日：2017-07-12
申请人： ABB SCHWEIZ AG
发明人： HOLLENDER, Martin , HARVAN, Matus
IPC分类号： G06Q10/00 , G05B23/02
CPC分类号： G05B23/027 , G05B23/0267 , G05B2223/06 , G06Q10/00
摘要： A computer system 100, computer-implemented method and computer program product is provided for processing alarm activations received from one or more technical systems (200). A particular alarm activation represents a deviation of the technical status of a particular technical system from its normal technical status. The computer system (100) includes a data storage interface (111) configured to record a plurality of received alarm activations in a data storage unit (110) wherein the recorded alarm activations correspond to one or more alarms (A1 to A6). Further, a data processing component (120) is configured to determine, from the recorded alarm activations, a plurality of time intervals (I1, I4, I5) for alarm analysis;and to compute similarity measures between the determined time intervals wherein the similarity measures depend on the occurrence of the recorded alarm activations in the determined time intervals. Thereby,the contribution of a particular alarm activation to the similarity of two time intervals is reduced with an increasing occurrence of the alarm in the determined time intervals. Further, a user interface component (130) is configured to provide one or more pairs (131, 132) of time intervals to an operator (10) of the one or more technical systems (200) wherein the one or more pairs (131, 132) of time intervals include time intervals with similarity measures indicating similar alarm floods in the respective time intervals.
摘要翻译：提供计算机系统100，计算机实现的方法和计算机程序产品，用于处理从一个或多个技术系统（200）接收的警报激活。特定的警报激活表示特定技术系统的技术状态与其正常技术状态的偏差。计算机系统（100）包括数据存储接口（111），该数据存储接口（111）被配置为在数据存储单元（110）中记录多个接收到的警报激活，其中所记录的警报激活对应于一个或多个警报（A1至A6）。此外，数据处理组件（120）被配置为从记录的警报激活中确定用于警报分析的多个时间间隔（I1，I4，I5）;并且计算所确定的时间间隔之间的相似性度量，其中相似性度量取决于在确定的时间间隔内记录的警报激活的发生。由此，特定警报激活对两个时间间隔的相似性的贡献随着在所确定的时间间隔内发生警报的增加而减小。此外，用户界面组件（130）被配置为向一个或多个技术系统（200）的操作员（10）提供一个或多个时间间隔对（131,132），其中所述一个或多个对（131,132） 132）的时间间隔包括具有指示相应时间间隔中的类似警报洪水的相似性度量的时间间隔。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式