Некоторое содержание этого приложения в настоящий момент недоступно.
Если эта ситуация сохраняется, свяжитесь с нами по адресуОтзывы и контакты
1. (WO2019048437) PREDICTIVE DIAGNOSTICS METHOD FOR A CORRUGATED BOARD PRODUCTION PLANT
Примечание: Текст, основанный на автоматизированных процессах оптического распознавания знаков. Для юридических целей просьба использовать вариант в формате PDF

Claims

1. A method for monitoring the operation of a corrugated board production plant, comprising the following steps:

detecting at least one operational parameter of a functional unit of the plant and calculating a current value of at least a first statistical function of said parameter in a current temporal window;

calculating a maximum value and a minimum value of the first statistical function based on historicized data of the operational parameter; comparing the current value of the first statistical function with said maximum value and said minimum value of said first statistical function calculated on said historicized data;

based on the result of said comparison, generating a piece of information of predictive diagnostics regarding said functional unit.

2. The method of claim 1 , further comprising the following steps: calculating a current value of at least a second statistical function of said operational parameter in said current temporal window;

calculating a maximum value and a minimum value of the second statistical function based on said historicized data of the operational parameter; comparing the current value of the second statistical function with said maximum value and said minimum value of said second statistical function calculated on said historicized data;

generating a piece of information of predictive diagnostic based on the result of the comparison between the values of the first statistical function and the second statistical function with the respective maximum value and minimum value calculated on said historicized data of the operational parameter.

3. The method of claim 1 or 2, wherein the historicized data of the operational parameter are data contained in a movable learning temporal window, temporally preceding the current temporal window.

4. The method of claim 3, wherein the duration of the learning temporal window is longer than the duration of the current temporal window and preferably equal to a multiple of the duration of the current temporal window.

5. The method according to claim 3 or 4, wherein the maximum value and the minimum value of at least one of said first statistical function and second statistical function are determined as the maximum and the minimum of the same statistical function calculated on a plurality of windows for calculating a statistical function that are contained within the movable learning temporal window.

6. The method of claim 3 or 4 or 5, wherein the movable learning temporal window is distanced from the current temporal window by a time interval comprised between the movable learning temporal window and the current temporal window.

7. The method of claim 6, wherein the time interval comprised between the current temporal window and the movable learning temporal window has a fixed or variable duration.

8. The method according to one or more of claims 3 to 7, wherein the step of calculating the maximum value and the minimum value of the first statistical function or of the second statistical function on historicized data of the operational parameter comprises the following steps:

- calculating the value of at least one of said first statistical function and said second statistical function for each window of a sequence of windows for calculating the statistical function contained within the movable learning temporal window or into which the movable learning temporal window is subdivided;

- determining the maximum value and the minimum value of the first statistical function or of the second statistical function among the values of the statistical function calculated for said sequence of windows for calculating the statistical function contained within the movable learning temporal window.

9. The method of one or more of the previous claims, wherein the first statistical function is an average value of the parameter in the current temporal window, or a variance of the parameter in the current temporal window.

10. The method of one or more of the previous claims, wherein the second statistical function is a variance of the parameter in the current temporal window, or an average of the parameter in the current temporal window.

11. The method of one or more of the previous claims wherein the operational parameter is correlated with at least one further parameter of the functional unit.

12. The method of claim 11, wherein the historicized data of the operational parameter comprise a plurality of values of the operational parameter for each of different values of the further parameter of the functional unit.

13. The method of one or more of the previous claims, comprising the steps of: calculating respective maximum and minimum values of at least one statistical function of the operational parameter in a temporal sequence of learning intervals; detecting any drift over time of said maximum and minimum values calculated for the learning intervals of said sequence; in case a drift is detected, signaling an anomaly.

14. A method for monitoring the operation of a corrugated board production plant, comprising the following steps:

(a) calculating a maximum value and a minimum value of a statistical function of an operational parameter of a functional unit in a movable learning temporal window;

(b) calculating a current value of the statistical function of the operational parameter of the functional unit in a current temporal window, temporally following and distanced from the movable learning temporal window;

(c) comparing the current value of the statistical function with the maximum value and the minimum value of the statistical function calculated on the movable learning temporal window;

(d) based on the result of said comparison, generating a piece of information of predictive diagnostics regarding said functional unit;

(e) time-translating the movable learning temporal window and the current temporal window;

(f) repeating the steps from (a) to (e).

15. A plant for the production of corrugated board, comprising: one or more corrugators; at least one double facer section; a dry-end; a data processing and control system, configured to implement a method according to one or more of the previous claims.

16. A data support comprising one or more programs executable in a machine or IT system, configured to implement a method according to one or more of claims from 1 to 14.