阅读说明：本技术 用于监控行进纱线的纱线张力的方法和装置 (Method and device for monitoring the yarn tension of a running yarn ) 是由 J·胡特马赫尔 于 2018-06-01 设计创作，主要内容包括：本发明涉及一种用于监控纱线处置过程中行进纱线的纱线张力的方法和装置。为此,连续测量纱线的纱线张力,并将纱线张力的测量信号相比于允许纱线张力的阈值。在测量信号有不允许的容差偏差的情形下,纱线张力的短期信号路径被检测而作为故障图形。为了能够进行故障诊断,使用机器学习程序分析纱线张力的故障图形。然后将故障图形分配至一个已知故障类别或者新故障类别。根据本发明的装置包括针对该目的的诊断单元(18),其与纱线张力评估单元(19)相应地协作。(The invention relates to a method and a device for monitoring the yarn tension of a running yarn during a yarn treatment process. For this purpose, the yarn tension of the yarn is continuously measured and the measurement signal of the yarn tension is compared to a threshold value that allows the yarn tension. In the case of an inadmissible tolerance deviation of the measuring signal, a short-term signal path of the yarn tension is detected as a fault pattern. In order to be able to carry out fault diagnosis, a machine learning program is used to analyze the fault pattern of the yarn tension. The failure pattern is then assigned to a known failure category or a new failure category. The device according to the invention comprises a diagnostic unit (18) for this purpose, which cooperates correspondingly with a yarn tension evaluation unit (19).)

1. Method for monitoring the yarn tension of a running yarn in a yarn treatment process, wherein the yarn tension of the yarn is measured continuously, a measurement signal of the yarn tension is compared with at least one limit value for an allowable yarn tension, and in case of an impermissible tolerance deviation of the measurement signal a short-term signal profile of the yarn tension is acquired as a fault pattern, characterized in that the fault pattern of the yarn tension is analyzed using a machine learning program and assigned to a known fault pattern class or a new fault pattern class.

2. A method according to claim 1, wherein each said fault pattern category is embodied by a fault pattern of one of said fault patterns and/or of a group of fault patterns.

3. Method according to claim 1 or 2, characterized in that to each of said fault pattern categories a specific process disturbance and/or a specific operational fault and/or a specific disturbance parameter and/or a specific product fault is assigned.

4. A method according to claim 3, characterized in that after assigning one of the failure patterns to one of the failure pattern classes, a control command regarding the failure pattern class is triggered to make a process change.

5. The method according to any one of claims 1 to 4, characterized in that the analysis of the fault pattern is performed by at least one machine learning algorithm of the machine learning program.

6. The method of claim 5, wherein at least one of the fault pattern classes is defined solely by the machine learning algorithm from the analyzed fault patterns.

7. Device for monitoring the yarn tension of a running yarn during yarn processing, in particular for carrying out a method according to any one of claims 1 to 6, comprising: a yarn tension measuring unit (17) having a yarn tension sensor (17.1) and a measuring signal pickup (17.2); and a yarn tension analysis unit (19) with a fault pattern generator (19.1), characterized in that the yarn tension analysis unit (19) interacts with a diagnostic unit (18) such that a fault pattern can be analyzed using a machine learning program and a known fault pattern class or a new fault pattern class is assigned to the fault pattern.

8. The apparatus of claim 7, wherein the diagnostic unit (18) comprises a memory unit (21) and a programmable learning processor (20) for executing the machine learning program.

9. The device according to claim 8, characterized in that the learning processor (20) is coupled to an input unit (22), by means of which input unit (22) one or more determined failure patterns can be input.

10. The device according to claim 8 or 9, characterized in that the learning processor (20) is coupled to an output unit (23), by means of which output unit (23) the assignment of the analyzed fault pattern to one of the fault pattern categories can be visualized.

11. The apparatus of any of claims 8 to 10, wherein the learning processor (20) comprises a neural network for executing the machine learning procedure.

12. The device according to any one of claims 7 to 11, characterized in that the diagnostic unit (18) is connected to a machine control unit (16), by means of which machine control unit (16) control commands for process changes can be executed.