A digital textile machine remote monitoring method and system
By screening and weighting the tension data of the textile machine and calculating its abnormality, the problem of difficulty in monitoring the operating status of the textile machine in traditional methods is solved, and the accurate monitoring of the operating status of the textile machine is achieved.
Patent Information
- Application Number
- CN202410993348.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-07-24
AI Technical Summary
Traditional methods are difficult to accurately monitor the operating status of the textile machine because the tension data of warp lines changes periodically, and it is difficult to determine whether the tension data is abnormal in fixed thresholds.
By obtaining the tension data of all warp lines in the textile machine, the core tension data and reference tension data are screened out, the weighted fit prediction data is used to calculate the amplitude and trend abnormality of the tension data, and the operating status of the textile machine is dynamically monitored.
It improves the accuracy of the operating status monitoring of the textile machine, avoids the impact of abnormal data on the monitoring results, and ensures that the predicted data is more in line with the tension data during normal operation of the textile machine, so as to accurately judge the operating status of the textile machine.
Smart Images

Figure CN118531551B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of textile machine operation monitoring, and in particular to a digital textile machine remote monitoring method and system. Background Art
[0002] The warp in a textile machine is the part of the textile that is responsible for bearing tension. It provides strength and stability to the textile. At the same time, the tension of the warp can also reflect the coordination between the various components of the textile machine. Therefore, the operating status of the textile machine can be remotely monitored by the tension of the warp in the textile machine. However, since the heald frames in the textile machine will pull the warp, the tension of the warp will change, that is, the tension data of the warp has a certain periodicity. Therefore, the traditional method of using a fixed threshold cannot accurately determine whether the tension data is abnormal, that is, it is impossible to accurately monitor the operating status of the textile machine. Summary of the invention
[0003] The present invention provides a digital textile machine remote monitoring method and system to solve the existing problem that it is difficult to accurately monitor the operating state of the textile machine according to the tension of the warp thread in the traditional way.
[0004] A digital textile machine remote monitoring method and system of the present invention adopts the following technical solutions:
[0005] An embodiment of the present invention provides a digital textile machine remote monitoring method, the method comprising the following steps:
[0006] Obtain the tension data of all warp threads in the textile machine at each moment;
[0007] From the tension data of all the warps at each moment, the core tension data and the benchmark tension data at each moment are screened out; according to the data distribution of the core tension data at each moment, the normality of the benchmark tension data at each moment is obtained; according to the benchmark tension data at all moments, combined with the normality of the benchmark tension data, the prediction data at all moments is obtained;
[0008] According to the difference in data amplitude between the tension data of all the warps at each moment and the predicted data, the degree of amplitude anomaly of the tension data of all the warps at each moment is obtained; according to the difference in data change between the tension data of all the warps at each moment and the predicted data, the degree of trend anomaly of the tension data of all the warps at each moment is obtained;
[0009] According to the abnormal degree of amplitude of tension data of all warp threads at each moment and the abnormal degree of trend, the abnormal degree of tension data of all warp threads at each moment is obtained; according to the abnormal degree of tension data of all warp threads at each moment, the operation status of the textile machine is monitored.
[0010] Preferably, the method of screening out the core tension data and the reference tension data at each moment from the tension data of all the warps at each moment includes the following specific methods:
[0011] For any moment, obtain the mean and standard deviation of the tension data of all the warp threads at that moment; preset a screening number, and record the tension data of all the warp threads at that moment, whose difference with the mean of the tension data is less than or equal to the screening number of standard deviations, as the core tension data at that moment; record the mean of all the core tension data at that moment as the baseline tension data at that moment.
[0012] Preferably, the method of obtaining the normality of the reference tension data at each moment according to the data distribution of the core tension data at each moment includes the following specific methods:
[0013] For any moment, the inverse of the variance of all core tension data at that moment is taken as the normality of the reference tension data at that moment.
[0014] Preferably, the method of obtaining the prediction data at all times according to the reference tension data at all times and combining the normality of the reference tension data includes the following specific methods:
[0015] According to the normality of the reference tension data at each moment, weighted fitting is performed on the reference tension data at all moments to obtain a normal data fitting curve;
[0016] A local range is preset; for any moment, the moment within the local range before the moment is taken as the local range of the moment; for a data point at any moment in the normal data fitting curve, the tension data at the moment is predicted according to the curve segment within the local range of the data point to obtain the predicted data at the moment.
[0017] Preferably, the method of obtaining the amplitude abnormality degree of the tension data of all the warp threads at each moment according to the difference in data amplitude between the tension data of all the warp threads at each moment and the predicted data includes the following specific methods:
[0018] A number of monitoring data is preset, and for the tension data of any warp thread at any time, the preceding tension data of the tension data is used as the monitoring data of the tension data;
[0019] Perform inverse proportional normalization on each monitoring data of the tension data, and use each normalization result as the calculation weight of each monitoring data of the tension data;
[0020] According to the calculation weight of each monitoring data of the tension data, the difference between each monitoring data of the tension data and the predicted data at the corresponding moment is weighted to obtain the amplitude abnormality degree of each monitoring data of the tension data; the amplitude abnormality degrees of all monitoring data of the tension data are fused to obtain the amplitude abnormality degree of the tension data.
[0021] Preferably, the method of obtaining the degree of abnormal trend of the tension data of all the warp threads at each moment according to the difference in data change between the tension data of all the warp threads at each moment and the predicted data includes the following specific methods:
[0022] For the tension data of any warp thread at any time, the difference between the tension data and the tension data at the previous time of the tension data is taken as the degree of change of the tension data;
[0023] For the predicted data at any moment, the difference between the predicted data and the predicted data at the previous moment of the predicted data is taken as the degree of change of the predicted data;
[0024] For the tension data of any warp at any time, the difference in the degree of change between each monitoring data of the tension data and the predicted data at the corresponding time is taken as the trend abnormality degree of each monitoring data;
[0025] The trend anomaly degree of all monitoring data of the tension data is fused to obtain the trend anomaly degree of the tension data.
[0026] Preferably, the abnormality degree of the tension data of all the warp threads at each moment is obtained according to the abnormality degree of the amplitude of the tension data of all the warp threads at each moment in combination with the abnormality degree of the trend, and the specific method includes:
[0027] For the tension data of any warp at any time, the product of the amplitude abnormality degree and the trend abnormality degree of the tension data is taken as the abnormality degree of the tension data.
[0028] Preferably, the monitoring of the operating state of the textile machine according to the abnormality of the tension data of all the warps at each moment includes the following specific methods:
[0029] An abnormality threshold is preset, and for the tension data of any warp thread at any time, when the abnormality of the tension data is greater than the abnormality threshold, an early warning is issued through the background display.
[0030] Preferably, after the abnormality level of the tension data is normalized, the abnormality level threshold is set to 0.3.
[0031] Another embodiment of the present invention provides a digital textile machine remote monitoring system, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the steps of the above-mentioned digital textile machine remote monitoring method when executing the computer program.
[0032] The beneficial effects of the technical solution of the present invention are as follows: the present invention screens out the core tension data and the reference tension data at each moment from the tension data of all warps at each moment, thereby avoiding the influence of the abnormal data on the subsequent calculation of the abnormal degree when the abnormal data appears, and further quantifies the normal degree of the data at each moment by the discrete degree of the core tension data at each moment, which is used as the weight when fitting the normal curve, so that the normal data fitting curve is more accurate, and then the normal data fitting curve is obtained by the normal data fitting curve, so that the predicted data is more consistent with the warp tension data when the textile machine is operating normally;
[0033] The abnormality of the tension data of all the warp threads at each moment is obtained by calculating the difference in data amplitude and trend between the tension data of all the warp threads at each moment and the predicted data. Since the predicted data is the warp tension data consistent with the normal operation of the textile machine, the abnormality of the tension data of all the warp threads at each moment can be accurately obtained by calculating the difference between the amplitude and trend between the tension data of all the warp threads at each moment and the predicted data, thereby improving the accuracy of monitoring the operating status of the textile machine. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0035] Figure 1 A flowchart of the steps of a digital textile machine remote monitoring method of the present invention;
[0036] Figure 2 Flowchart for monitoring the operating status of a textile machine. DETAILED DESCRIPTION
[0037] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a digital textile machine remote monitoring method and system proposed by the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0038] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0039] The specific scheme of a digital textile machine remote monitoring method and system provided by the present invention is described in detail below with reference to the accompanying drawings.
[0040] See also Figure 1 , which shows a flowchart of a digital textile machine remote monitoring method provided by an embodiment of the present invention, the method comprising the following steps:
[0041] Step S001: Obtain the tension data of all warp threads in the textile machine at each moment.
[0042] It should be noted that this embodiment is a digital remote monitoring method for textile machines, and its specific application scenario is to monitor the operating status of textile machines. The tension of the warp threads in the textile machine directly affects the quality of the textiles. Appropriate tension can ensure uniform density and strength of the textiles, and avoid problems such as textile distortion and pilling. At the same time, the tension of the warp threads can also reflect the coordination between the various components of the textile machine. Therefore, the operating status of the textile machine can be remotely monitored by the tension of the warp threads in the textile machine. To this end, it is first necessary to collect the tension of the warp threads in the textile machine.
[0043] Specifically, a tension sensor is installed on each warp path of the textile machine to collect the tension of all the warps at each moment.
[0044] Step S002: Filter out the core tension data and the benchmark tension data at each moment from the tension data of all warps at each moment; obtain the normality of the benchmark tension data at each moment based on the data distribution of the core tension data at each moment; obtain the predicted data at all moments based on the benchmark tension data at all moments in combination with the normality of the benchmark tension data.
[0045] It should be noted that, when the textile machine is working, the heald frames in the textile machine will move up and down periodically, and when the heald frames move up and down, they will pull the warp threads, causing the tension data of the warp threads to change periodically. Therefore, the traditional method of using a fixed threshold value cannot accurately determine whether the tension data is abnormal. Therefore, this embodiment predicts the tension data during normal operation of the textile machine, and dynamically quantifies the degree of abnormality of the tension data through the difference in amplitude and trend between the predicted and actual tension data at each moment, thereby accurately monitoring the operating status of the textile machine.
[0046] It should be further explained that the present embodiment realizes remote monitoring of the operating status of the textile machine through the tension data of all the warp threads in the textile machine at each moment. In order to avoid the influence of abnormal data on the subsequent calculation of the abnormality degree when abnormal data appears, it is first necessary to screen the tension data of all the warp threads at each moment, obtain the core tension data at each moment, avoid data contamination, and then predict the subsequent tension data based on the core tension data to provide data preparation for the subsequent calculation of the abnormality degree of the tension data.
[0047] Specifically, for any moment, obtain the mean and standard deviation of the tension data of all warps at that moment; preset a screening quantity , The specific value of can be set according to the actual situation. Describe the situation where the difference between the tension data of all warps at that moment and the mean value of the tension data is less than or equal to The tension data with standard deviations is recorded as the core tension data at that moment; the mean of all core tension data at that moment is recorded as the baseline tension data at that moment, and the inverse of the variance of all core tension data at that moment is taken as the normality of the baseline tension data at that moment.
[0048] It should be noted that, under normal circumstances, the warp tension data will not be abnormal at the same time. Therefore, in order to make the predicted tension data more consistent with the warp tension data during normal operation of the textile machine, this embodiment uses "3 "The criterion removes some excessive and insufficient values in the actual tension data to obtain the core tension data, which is more in line with the characteristics of the normal operation of the textile machine; the benchmark tension data is further obtained through the core tension data, so the benchmark tension data at each moment represents the tension data of all warps at each moment when the textile machine is in normal operation.
[0049] Furthermore, the least squares method is used to perform weighted fitting on the benchmark tension data at all moments according to the normality of the benchmark tension data at each moment to obtain a normal data fitting curve. Since the least squares method is a well-known prior art, it will not be described in detail in this embodiment.
[0050] It should be noted that, since the tension of all warp threads tends to be consistent during the operation of the textile machine, the more discrete the core tension data at any moment is, the more abnormal the data at that moment may be. Therefore, the weight when fitting the baseline data at that moment is smaller, so as to further improve the accuracy of the normal data fitting curve and make the data prediction results more consistent with the warp tension data during the normal operation of the textile machine.
[0051] Specifically, preset a local range , The specific value of can be set according to the actual situation. This embodiment does not make a hard requirement. For any moment, the previous moment, as the local range of that moment; for a data point at any moment in the normal data fitting curve, the ARIMA algorithm (time series prediction algorithm) is used to predict the tension data at that moment according to the curve segment within the local range of the data point, so as to obtain the predicted data at that moment. Since the ARIMA algorithm is a well-known prior art, it will not be described in detail in this embodiment.
[0052] It should be noted that the predicted data at the same time represents the predicted tension data of all warp threads at the same time.
[0053] At this point, the forecast data for all times is obtained.
[0054] Step S003: According to the difference in data amplitude between the tension data of all warp threads at each moment and the predicted data, obtain the degree of amplitude abnormality of the tension data of all warp threads at each moment; according to the difference in data change between the tension data of all warp threads at each moment and the predicted data, obtain the degree of trend abnormality of the tension data of all warp threads at each moment.
[0055] It should be noted that after obtaining the predicted data at all times through step S002, the amplitude abnormality and trend abnormality of the tension data of all warps at each moment can be obtained by comparing the differences in data amplitude and data changes between the predicted data at all times and the tension data of all warps at each moment, thereby providing data support for the subsequent acquisition of the abnormality of the tension data of all warps at each moment.
[0056] Specifically, preset a monitoring window , The specific value of can be determined according to the actual situation. This embodiment does not make any impact requirements. For the tension data of any warp at any time, the previous tension data as monitoring data of the tension data; and obtaining the abnormality degree of the amplitude of the tension data according to the difference between the monitoring data of the tension data and the predicted data at the corresponding moment.
[0057] It needs to be further explained that when the textile machine is working, the heald frame in the textile machine will move up and down periodically, and when the heald frame moves up and down, it will pull the warp threads, causing the tension data of the warp threads to change periodically. When the heald frame in the textile machine is displaced to the top, the heald frame will vibrate, causing the tension of the warp threads to suddenly increase. However, the change in tension of the warp threads at this time is caused by the normal operation of the heald frame, and is not caused by a malfunction of the textile machine. Therefore, when calculating the difference between the monitoring data of the tension data and the predicted data at the corresponding moment, a small calculation weight should be assigned to the monitoring data with large tension to avoid identifying the heald frame oscillation as a textile machine malfunction.
[0058] Specifically, for the tension data of any warp at any time, the monitoring data of the tension data is obtained, each monitoring data of the tension data is inversely normalized, and each normalization result is used as the calculation weight of each monitoring data of the tension data;
[0059] According to the calculation weight of each monitoring data of the tension data, the difference between each monitoring data of the tension data and the predicted data at the corresponding moment is weighted to obtain the amplitude abnormality degree of each monitoring data of the tension data; the amplitude abnormality degrees of all monitoring data of the tension data are fused to obtain the amplitude abnormality degree of the tension data;
[0060] In one embodiment of the present invention, the specific calculation formula is:
[0061]
[0062] In the formula, Indicates The meridian is The degree of abnormality of the amplitude of the tension data at each moment; Indicates The meridian is The number of monitoring data of tension data at each moment; Indicates The meridian is The tension data at the moment Monitoring data; Indicates The meridian is The tension data at the moment The predicted data corresponding to the monitoring data; Represents absolute value operation; Represents the normalization function, the normalization object is The meridian is All monitoring data of the tension data at the moment .
[0063] It should be noted that The larger the value of The meridian is The tension data at the moment The greater the difference in amplitude between the monitoring data and the warp tension data during normal operation of the textile machine, is to normalize the difference, It means the The meridian is The tension data at the moment The inverse normalization result of the monitoring data is used as the calculation weight of the difference, so The larger the value of The meridian is The tension data at a certain moment is more likely to be abnormal data; the abnormal degree of the amplitude of the tension data is obtained.
[0064] Further, for the tension data of any warp at any moment, the difference between the tension data and the tension data at the previous moment of the tension data is taken as the degree of change of the tension data;
[0065] For the predicted data at any moment, the difference between the predicted data and the predicted data at the previous moment of the predicted data is taken as the degree of change of the predicted data;
[0066] For the tension data of any warp at any time, the difference in the degree of change between each monitoring data of the tension data and the predicted data at the corresponding time is taken as the trend abnormality degree of each monitoring data;
[0067] The trend anomaly degree of all monitoring data of the tension data is integrated to obtain the trend anomaly degree of the tension data;
[0068] In one embodiment of the present invention, the specific calculation formula is:
[0069]
[0070] In the formula, Indicates The meridian is The degree of abnormal trend of tension data at a certain moment; Indicates The meridian is The number of monitoring data of tension data at each moment; Indicates The meridian is The tension data at the moment The degree of change of each monitoring data; No. The meridian is The tension data at the moment The degree of change of the predicted data corresponding to the monitoring data; Represents absolute value operation.
[0071] It should be noted that The larger the value, the The meridian is The tension data at the moment The greater the difference in the change trend between the warp tension data during normal operation of the textile machine and the monitoring data, is to normalize the difference, so The larger the value of The meridian is The tension data at a certain moment is more likely to be abnormal data; the degree of abnormal trend of the tension data is obtained.
[0072] So far, the amplitude anomaly degree and trend anomaly degree of all tension data are obtained through the above method.
[0073] Step S004: According to the abnormal degree of amplitude of the tension data of all warp threads at each moment and the abnormal degree of trend, the abnormal degree of tension data of all warp threads at each moment is obtained; according to the abnormal degree of tension data of all warp threads at each moment, the operating status of the textile machine is monitored.
[0074] It should be noted that after obtaining the amplitude abnormality and trend abnormality of all tension data in step S003, the abnormality of all tension data can be obtained according to the amplitude abnormality and trend abnormality of all tension data, so as to accurately monitor the operating status of the textile machine.
[0075] Specifically, for the tension data of any warp at any time, the product of the amplitude abnormality degree and the trend abnormality degree of the tension data is taken as the abnormality degree of the tension data, and the specific calculation formula is:
[0076]
[0077] In the formula, Indicates The meridian is The degree of abnormality of the tension data at each moment; Indicates The meridian is The degree of abnormality of the amplitude of the tension data at each moment; Indicates The meridian is The degree of abnormal trend of tension data at a certain moment.
[0078] Furthermore, a threshold of abnormality is preset. , The specific value of can be set according to the actual situation. This embodiment does not make a hard requirement. For the tension data of any warp at any time, the abnormality of the tension data is normalized. When the abnormality of the tension data is greater than When the textile machine fails, an early warning is given through the background display.
[0079] It should be noted that this embodiment screens the tension data of all warp threads at each moment, calculates the normality of the data at each moment, makes the predicted data more accurate, and further obtains the abnormality of the data through the difference in amplitude and trend between the actual collected data and the predicted data, so as to accurately monitor the operating status of the textile machine.
[0080] Figure 2 Flowchart for monitoring the operating status of a textile machine.
[0081] Another embodiment of the present invention provides a digital textile machine remote monitoring system, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a digital textile machine remote monitoring method in steps S001 to S004 when executing the computer program.
[0082] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A digital textile machine remote monitoring method, characterized in that: The method comprises the following steps: Obtain the tension data of all warp threads in the textile machine at each moment; From the tension data of all the warps at each moment, the core tension data and the benchmark tension data at each moment are screened out; The method of selecting the core tension data and the reference tension data at each moment from the tension data of all the warps at each moment includes: For any moment, the mean value and standard deviation of the tension data of all the warp threads at the moment are obtained; a screening number is preset, and the tension data of all the warp threads at the moment, whose difference from the mean value of the tension data is less than or equal to the screening number of standard deviations, is recorded as the core tension data at the moment; the mean value of all the core tension data at the moment is recorded as the reference tension data at the moment; According to the data distribution of the core tension data at each moment, the normality of the baseline tension data at each moment is obtained; The specific method of obtaining the normality of the reference tension data at each moment according to the data distribution of the core tension data at each moment is as follows: For any moment, the inverse of the variance of all core tension data at the moment is taken as the normality of the baseline tension data at the moment; According to the baseline tension data at all times and the normality of the baseline tension data, the prediction data at all times are obtained; The method of obtaining the prediction data at all times according to the reference tension data at all times and the normality of the reference tension data includes the following specific methods: According to the normality of the reference tension data at each moment, weighted fitting is performed on the reference tension data at all moments to obtain a normal data fitting curve; Preset a local range; for any moment, take the moment within the local range before the moment as the local range of the moment; for a data point at any moment in the normal data fitting curve, predict the tension data at the moment according to the curve segment within the local range of the data point, and obtain the predicted data at the moment; According to the difference in data amplitude between the tension data of all the warps at each moment and the predicted data, the degree of amplitude abnormality of the tension data of all the warps at each moment is obtained; The specific method of obtaining the amplitude abnormality degree of the tension data of all the warps at each moment according to the difference in data amplitude between the tension data of all the warps at each moment and the predicted data is as follows: A number of monitoring data is preset, and for the tension data of any warp thread at any time, the preceding tension data of the tension data is used as the monitoring data of the tension data; Perform inverse proportional normalization on each monitoring data of the tension data, and use each normalization result as the calculation weight of each monitoring data of the tension data; According to the calculation weight of each monitoring data of the tension data, the difference between each monitoring data of the tension data and the predicted data at the corresponding moment is weighted to obtain the amplitude abnormality degree of each monitoring data of the tension data; the amplitude abnormality degrees of all monitoring data of the tension data are fused to obtain the amplitude abnormality degree of the tension data; According to the difference in data change between the tension data of all the warps at each moment and the predicted data, the degree of trend anomaly of the tension data of all the warps at each moment is obtained; The specific method for obtaining the degree of abnormal trend of the tension data of all the warps at each moment according to the difference in data change between the tension data of all the warps at each moment and the predicted data is as follows: For the tension data of any warp thread at any time, the difference between the tension data and the tension data at the previous time of the tension data is taken as the degree of change of the tension data; For the predicted data at any moment, the difference between the predicted data and the predicted data at the previous moment of the predicted data is used as the degree of change of the predicted data; For the tension data of any warp at any time, the difference in the degree of change between each monitoring data of the tension data and the predicted data at the corresponding time is taken as the trend abnormality degree of each monitoring data; The trend anomaly degree of all monitoring data of the tension data is integrated to obtain the trend anomaly degree of the tension data; According to the abnormal degree of amplitude of tension data of all warp threads at each moment and the abnormal degree of trend, the abnormal degree of tension data of all warp threads at each moment is obtained; according to the abnormal degree of tension data of all warp threads at each moment, the operation status of the textile machine is monitored.
2. A digital textile machine remote monitoring method according to claim 1, characterized in that: The specific method of obtaining the abnormality degree of the tension data of all the warps at each moment according to the abnormality degree of the amplitude of the tension data of all the warps at each moment in combination with the abnormality degree of the trend is as follows: For the tension data of any warp at any time, the product of the amplitude abnormality degree and the trend abnormality degree of the tension data is taken as the abnormality degree of the tension data.
3. A digital textile machine remote monitoring method according to claim 1, characterized in that: The specific method of monitoring the operation state of the textile machine according to the abnormal degree of the tension data of all the warps at each moment is as follows: An abnormality threshold is preset, and for the tension data of any warp thread at any time, when the abnormality of the tension data is greater than the abnormality threshold, an early warning is issued through the background display.
4. A digital textile machine remote monitoring method according to claim 3, characterized in that: After the abnormality level of the tension data is normalized, the abnormality level threshold is set to 0.
3.
5. A digital textile machine remote monitoring system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of a digital textile machine remote monitoring method as described in any one of claims 1 to 4 are implemented.
