Running abnormity monitoring method and system for rubber tube coiling machine

Abstract

The invention relates to the technical field of industrial equipment monitoring, in particular to an abnormal operation monitoring method and system for a rubber tube coiling machine. The method comprises the steps of obtaining multi-dimensional operation data in the operation process of the coiling machine, wherein the operation data comprises motor rotating speed data, current data and rubber tube temperature data; constructing a detection correction factor; and detecting the running state of the equipment by using an LOF anomaly detection algorithm based on the running data, and correcting the detection result of the LOF by using the detection correction factor to determine the running state of the equipment. The method has the effect of improving the accuracy of operation monitoring of the coiling machine.

Description

Technical Field

[0001] The present application relates to the technical field of industrial equipment monitoring, and particularly to an abnormal operation monitoring method and system for a hose coiling machine. Background Art

[0002] A hose is a rubber product and can be used for conveying gases or liquids, etc. The hose is extruded and formed by an extruder, and then is coiled and packaged by a hose coiling machine. During the coiling process of the hose, the running stability of the coiling machine is directly related to the final packaging effect of the hose. For example, insufficient tension of the hose during the coiling process of the coiling machine will cause the finally coiled hose to be too loose, too large tension of the hose will cause the motor to heat up, and unsmooth movement of the hose will cause uneven tightness of the coiled hose. Therefore, during the operation of the coiling machine, it is usually necessary to detect the running state of the coiling machine in order to timely detect the abnormality of the hose coiling machine and adjust the coiling machine. The LOF (Local Outlier Factor) algorithm is a common anomaly detection algorithm, which is applied to medical diagnosis, network security, and industrial equipment monitoring. Its main principle is: by calculating the density of a data point and its neighboring data points, to determine whether this data point is an outlier. If a data point is located in a low-density area while its neighboring data points are located in a high-density area, then this data point may be an outlier. If the density of a data point is similar to the density of its neighboring data points, it indicates that this data point may be a normal data point.

[0003] However, a hose coiling machine is a complex process equipment, involving the coordinated movement of multiple mechanical components, such as motor drive, reel rotation, and reciprocating movement of the wire leader. The complexity of these mechanical movements may lead to non-linear relationships and coupling effects in the sensor data, thereby making it difficult for the traditional LOF anomaly detection algorithm to accurately distinguish normal fluctuations and true anomaly signals. Therefore, when the traditional LOF anomaly detection algorithm is applied to a complex hose coiling machine, the accuracy is insufficient. Summary of the Invention

[0004] In order to solve the problem of insufficient accuracy of the traditional LOF detection algorithm for monitoring the operation of a hose coiling machine, the present application provides an abnormal operation monitoring method and system for a hose coiling machine.

[0005] In a first aspect, the present application provides an abnormal operation monitoring method for a hose coiling machine, adopting the following technical solution: A method for monitoring abnormal operation of a hose coiling machine, comprising the steps of: obtaining multi-dimensional operation data during the operation of the coiling machine, where the operation data includes motor speed data, current data, and hose temperature data; constructing a detection correction factor; detecting the operation state of the equipment using the LOF anomaly detection algorithm based on the operation data, and using the detection correction factor to correct the detection result of the LOF to determine the operation state of the equipment; Calculating the abnormal winding degree of the hose coiling at each moment based on the motor speed and current at each moment; constructing an observation sequence for each moment in the hose temperature data, and obtaining the temperature anomaly index at the corresponding moment according to the ratio of the hose temperature data in the observation sequence to the limit temperature of the hose deformation; for any moment, constructing a neighboring winding sequence at that moment based on the abnormal winding degree, and constructing a neighboring temperature sequence based on the abnormal temperature index; determining the period abnormal amplitude based on the magnitudes of the data in the neighboring winding sequence and the neighboring temperature sequence, and determining the period abnormal fluctuation based on the fluctuations of the data in the neighboring winding sequence and the neighboring temperature sequence, and taking the product of the period abnormal amplitude and the period abnormal fluctuation as the detection correction factor.

[0006] The beneficial effects are as follows: Analyzing the speed data and current data during the operation of the coiling machine to construct the abnormal winding degree. Constructing a neighboring winding sequence at a certain moment according to the abnormal winding degree. Constructing the temperature anomaly index for each temperature acquisition moment according to the temperature of the hose and the limit temperature that the hose can withstand, and constructing a neighboring temperature sequence at a certain moment according to the temperature anomaly index. The abnormal winding degree can reflect whether there is a jamming phenomenon during the hose coiling process, and the jamming phenomenon is mainly reflected in the changes of the motor speed and current. The temperature anomaly index reflects the temperature of the hose during the coiling process, and the generation of the hose temperature mainly includes the tension it receives and the contact friction with its lead wire device. Therefore, the change in temperature can reflect the abnormal tension of the hose itself or whether the lead wire device is abnormal. Combining the magnitudes of the data in the neighboring temperature sequence and the neighboring winding sequence, the jamming situation and the temperature situation of the hose in the neighboring time period at a certain moment, and constructing the detection correction factor based on this. Using this detection correction factor to correct the detection result of the traditional LOF detection algorithm, thereby improving the accuracy of the final equipment detection. Compared with the traditional LOF detection algorithm, the detection result in this application more comprehensively considers the change relationship between the motor current, motor speed, and hose temperature on the basis of combining the current data, and is more sensitive to large and drastic data mutations, facilitating the distinction between normal fluctuations and abnormal fluctuations in the operation data, so it has higher accuracy.

[0007] Optionally, the calculation steps for the abnormal winding degree at any moment include: obtaining the current data and speed data at that moment, and taking the ratio of the current data and speed data at that moment as the abnormal winding degree at that moment.

[0008] The beneficial effects are as follows: During the coiling process of the hose, when the coiling of the hose gets stuck, the load on the motor increases, the current rises, and at the same time, the rotational speed of the motor decreases. Therefore, by combining the motor current and the motor rotational speed, it is possible to determine whether the equipment gets stuck during operation, and further determine the operating state of the equipment based on this.

[0009] Optionally, the calculation steps for the abnormal winding degree at any moment include: obtaining the current data and rotational speed data at this moment and before this moment ; obtaining the average current of the current data and the average rotational speed of the rotational speed data, and taking the ratio of the average current to the average rotational speed as the abnormal winding degree at this moment.

[0010] The beneficial effects are as follows: During the calculation of the abnormal winding degree, the calculation is based on the averages of multiple data, which improves the accuracy and robustness of the abnormal winding degree calculation and reduces the influence of noise signals on the abnormal winding degree calculation.

[0011] Optionally, the acquisition frequency of the hose temperature data is lower than the acquisition frequencies of the rotational speed data and the current data, and the acquisition frequencies of the rotational speed data and the current data are equal; is the difference between the acquisition frequency of the current data and the acquisition frequency of the hose temperature data.

[0012] The beneficial effects are as follows: During the operation of the equipment, the temperature data changes relatively slowly, so the acquisition frequency of the temperature is reduced.

[0013] Optionally, the steps for constructing the observation sequence at each moment in the hose temperature data include: determining the length of the observation sequence , and for any moment, taking the hose temperature data at this moment and before this moment as the observation sequence at this moment.

[0014] The beneficial effects are as follows: Taking the data at a certain moment and before this moment as the observation sequence at this moment is convenient for analyzing the temperature change in the recent time period and accurately reflecting the current temperature situation.

[0015] Optionally, the steps for obtaining the temperature anomaly index at the corresponding moment according to the ratio of the hose temperature data in the observation sequence to the limit temperature of the hose deformation include: taking the sum of the ratios of multiple hose temperature data in the observation sequence to the limit temperature as the temperature anomaly index.

[0016] The beneficial effects are as follows: The limit temperature of the hose deformation represents the maximum temperature that the hose can withstand. During the operation of the coiling machine, the closer the temperature of the hose is to the limit temperature, the more dangerous the current operating state is, and the more likely the hose is to deform. Therefore, taking the ratio of the hose temperature to the limit temperature as the temperature anomaly index, the larger the temperature anomaly index, the worse the current temperature situation and the more likely the hose is to deform.

[0017] Optionally, the steps of constructing the adjacent winding sequence and the adjacent temperature sequence include: for any moment, the abnormal winding degrees at this moment and before this moment constitute the adjacent winding sequence, and the temperature anomaly indexes at this moment and before this moment constitute the adjacent temperature sequence.

[0018] Optionally, the steps of obtaining the period anomaly amplitude include: obtaining the mean value of the data in the adjacent winding sequence and the mean value of the data in the adjacent temperature sequence, and taking the sum of the two mean values as the period anomaly amplitude; Obtaining the standard deviation of the data in the adjacent winding sequence and the standard deviation of the data in the adjacent temperature sequence, and taking the sum of the two mean values as the period anomaly fluctuation.

[0019] The beneficial effect is that: the mean values in the adjacent winding sequence and the adjacent temperature sequence indicate the overall amplitude of the jamming anomaly degree and the temperature anomaly index of the coiler, and can reflect the overall anomaly degree within this time period. Therefore, the sum of the two mean values is taken as the period anomaly amplitude. And the standard deviation of the data in the two sequences reflects the fluctuation amplitude of the data in the two sequences and can reflect the situation of data mutation in the sequences. Therefore, the sum of the two standard deviations is taken as the period anomaly, which further improves the accuracy of anomaly detection.

[0020] Optionally, the steps of determining the operating state of the device by correcting the detection result of LOF based on the detection correction factor include: constructing a monitoring vector corresponding to each temperature acquisition moment based on the anomaly score and the detection correction factor at each temperature acquisition moment, clustering the monitoring vectors using a clustering method, and judging the operating state at each moment based on the clustering result.

[0021] The beneficial effect is that: the detection correction factor and the anomaly score obtained by the traditional LOF detection algorithm constitute the monitoring vector. The monitoring vectors at each moment are clustered through clustering, and the operating state at each moment is judged according to the clustering result, so as to realize the detection of the operating state of the device.

[0022] In a second aspect, the present application provides an operating anomaly monitoring system for a hose coiler, adopting the following technical solution: An operating anomaly monitoring system for a hose coiler includes a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, an operating anomaly monitoring method for a hose coiler according to the above is implemented.

[0023] The beneficial effect is that: generating a computer program for the above-mentioned operating anomaly monitoring method for a hose coiler and storing it in the memory to be loaded and executed by the processor. Thus, a system is made according to the memory and the processor, which is convenient to use.

[0024] The present application has the following technical effects: In the present application, an abnormal winding degree is extracted based on the current data and rotational speed data during the operation of the coiler, a temperature anomaly index is constructed based on the temperature data of the hose, and then a detection correction factor is constructed by combining the two to correct the traditional LOF detection result, thereby improving the accuracy of the final detection of the equipment operation status. Description of the Drawings

[0025] Figure 1 is a flowchart of a method for monitoring abnormal operation of a hose coiler according to an embodiment of the present application.

[0026] Figure 2 is a flowchart of step S2 in the method for monitoring abnormal operation of a hose coiler according to an embodiment of the present application. Detailed Embodiment

[0027] An embodiment of the present application discloses a method and system for monitoring abnormal operation of a hose coiler, which obtains multi-dimensional operation data during the operation of the coiler, extracts the coupling relationship between the data of each dimension, constructs a detection correction factor, and optimizes the detection result of the traditional LOF detection algorithm through the detection correction factor. Compared with the method in the traditional LOF algorithm that relies on adjacent data to judge the state of the current data point, the method in the present application takes into account the relationship between multi-dimensional data, reduces the dependence of the traditional detection algorithm on adjacent data, and thus improves the accuracy of the final detection of the coiler operation.

[0028] Refer to Figure 1 , a method for monitoring abnormal operation of a hose coiler includes steps S1 - S3.

[0029] S1: Obtain multi-dimensional operation data during the operation of the coiler, and the operation data includes motor rotational speed data, current data, and hose temperature data.

[0030] The coiler mainly includes structures such as a frame, a winding disk, a motor, and a lead-in device. During its operation, the lead-in device is used to drive the operation of the hose, the motor is used to drive the winding disk to rotate, and the rotation of the winding disk can wind the hose onto the winding disk to realize the coiling of the hose. The coiler is a conventional device in the art, so the specific structure will not be described in detail here.

[0031] During the operation of the coiler, collect the rotational speed data of the motor, the current data of the motor, and the hose temperature data of the hose on the winding disk. In this embodiment, the collection frequencies of the rotational speed data and the current data are both 100 Hz, that is, the amount of data collected within 1 second is 100. Since the change of temperature is relatively slow, the collection frequency of the hose temperature data is set to 1 Hz in this embodiment.

[0032] During the process of collecting the above data, the collected data may have anomalies such as noise and missing values due to factors such as environmental interference and sensor errors. To improve the data quality, this application denoises the collected data through a median filtering algorithm and fills the missing values using a regression filling method. At the same time, to avoid the influence of different dimensions on the final calculation results, this application normalizes the collected current data and rotational speed data using the maximum normalization method. Among them, the median filtering algorithm, the regression filling method, and the maximum normalization method are well-known technologies, and the specific processes will not be elaborated here.

[0033] S2: Construct a detection correction factor.

[0034] The steps of constructing the detection correction factor include: Step S21 - Step S23.

[0035] S21: Calculate the abnormal winding degree of abnormal hose winding at each moment based on the motor speed and current at each moment; During the operation of the hose coiling machine, if the hose is not wound smoothly or the hose is stuck somewhere, then the motor needs to overcome greater resistance to drive the coiling disk. In this case, the load of the motor suddenly increases, which in turn affects the sudden increase in current. At the same time, as the resistance increases, the rotational speed of the motor cannot be maintained at the normal level and will decrease to a certain extent. The change in the rotational speed of the motor and the sudden change in the winding resistance will affect the normal winding of the hose, and the long-term high-frequency jamming of the motor will also cause the motor to overheat, causing major damage to the equipment.

[0036] Therefore, in this application, the abnormal winding degree during the hose winding process is extracted by analyzing the current and motor speed data.

[0037] In one embodiment, the steps of calculating the abnormal winding degree include: for the abnormal winding degree at any moment, taking the ratio of the current data and the motor speed data at that moment as the abnormal winding degree at that moment.

[0038] When the current of the motor increases, it indicates that the load of the motor increases, and there may be jamming during the hose winding process. At the same time, when the rotational speed of the motor decreases, it also indicates that there may be jamming during the winding process. Combining the current data and the motor speed data can jointly reflect the abnormal winding degree of the abnormal situation during the hose winding process by the winding equipment.

[0039] In another embodiment, the abnormal winding degree can also be obtained through the following steps: First, obtain any moment and the previous moment of that moment Collect current data and rotational speed data, obtain the average current and average rotational speed, and use the ratio of the average current to the average rotational speed as the abnormal winding degree. After jamming occurs during the hose winding process, the resistance will disappear, but it takes a certain amount of time for the rotational speed and current to recover. That is to say, within a certain period of time, its current is greater than the normal current level, and the motor rotational speed is less than the normal rotational speed level; by calculating the average of multiple data, reduce the influence of individual extreme data on the finally calculated abnormal winding degree, and improve the accuracy and robustness of the abnormal winding degree calculation.

[0040] In this embodiment is the difference between the current data acquisition frequency and the hose temperature data acquisition frequency. Taking the hose temperature data acquisition frequency in this embodiment as an example. Taking the sampling frequency of the temperature data in this application as 1 Hz, then the average current is the average of the current within one second, and this average can reflect the overall magnitude of the current during this period.

[0041] S22: Construct the observation sequence for each moment in the hose temperature data, and obtain the temperature anomaly index corresponding to each moment according to the ratio of the hose temperature data in the observation sequence to the limit temperature of hose deformation; During the hose coiling process, friction between the lead-in device and the hose will generate a certain amount of heat. At the same time, the hose itself will also generate some heat after being subjected to tension. During the normal operation of the coiling machine, the tension on the hose is relatively stable (it can also be understood that there is no jamming phenomenon during the coiling process). At the same time, the friction between the lead-in device and the hose is rolling friction. When the coiling equipment jams or the lead-in device is abnormal, it will cause the temperature of the hose to rise. And if the temperature of the hose is too high, then the hose may crack or deform. Therefore, the temperature of the hose is analyzed here to further identify the operating state of the coiling machine.

[0042] Determine the length of the observation sequence , for any moment, use the hose temperature data at this moment and the previous hose temperature data as the observation sequence at this moment.

[0043] Since the change in temperature is relatively slow and accumulates continuously, an observation sequence is set for each moment here, and multiple hose temperature data in the observation sequence are analyzed to improve the accuracy of the finally calculated temperature anomaly indication.

[0044] Calculate the ratio of each hose temperature data in the observation sequence to the limit temperature of hose deformation, and use the cumulative result of multiple ratios as the temperature anomaly index. The limit temperature of hose deformation refers to the temperature at which the hose begins to deform under a certain tension state. This temperature is a preset value, usually obtained through multiple tests, and is specifically set according to the actual production situation and hose material.

[0045] In this embodiment, the length of the observation sequence is 30. Considering that the acquisition frequency of the hose temperature data in this application is 1 Hz, it can also be understood that the observation sequence contains the hose temperature data for the most recent thirty seconds at a certain moment.

[0046] The closer the hose temperature data in the observation sequence is to the limit temperature of hose deformation, the more dangerous the current state of the hose is, and it is more likely that the abnormal temperature rise of the hose is caused by the abnormality of the coiling machine.

[0047] S23: For any moment, construct the neighboring winding sequence at this moment based on the abnormal winding degree, and construct the neighboring temperature sequence based on the abnormal temperature index; determine the period abnormal amplitude based on the data sizes in the neighboring winding sequence and the neighboring temperature sequence, determine the period abnormal fluctuation based on the data fluctuations in the neighboring winding sequence and the neighboring temperature sequence, and take the product of the period abnormal amplitude and the period abnormal fluctuation as the detection correction factor.

[0048] For any moment, calculate the mixed abnormality at this moment through the temperature abnormality index and the abnormal winding degree at this moment. In order to improve the accuracy and robustness of the calculation of the temperature mixing degree at this moment, in this embodiment, obtain the temperature abnormality indexes at this moment and before this moment, and the corresponding multiple abnormal winding degrees. Among them, the multiple temperature abnormality indexes form the neighboring winding sequence, and the multiple temperature abnormality indexes form the neighboring temperature sequence.

[0049] Obtain the period abnormal amplitude and the period abnormal fluctuation based on the neighboring winding sequence and the neighboring temperature sequence; take the product of the period abnormal amplitude and the period abnormal fluctuation as the mixed abnormality; take the mixed abnormality as the detection correction factor.

[0050] Specifically, obtain the mean value of the abnormal winding degree data in the neighboring winding sequence and the mean value of the temperature abnormality indexes in the neighboring temperature sequence, and take the sum of the two mean values as the period abnormal amplitude. Obtain the standard deviation of the data in the neighboring winding sequence and the standard deviation of the data in the neighboring temperature sequence, and take the sum of the two mean values as the period abnormal fluctuation.

[0051] The mean value of the abnormal winding degree in the neighboring winding sequence illustrates the overall level of the data in the neighboring winding sequence. The standard deviation of the data in the neighboring winding sequence illustrates the degree of data fluctuation in the neighboring winding sequence, corresponding to the stuck abnormality during the operation of the winding equipment. Calculate the mixed abnormality by combining the period abnormal amplitude and the period abnormal fluctuation, so as to improve the accuracy of the final detection of the equipment operation state.

[0052] S3: Detect the equipment operation state using the LOF anomaly detection algorithm based on the operation data, and use the detection correction factor to correct the detection result of LOF to determine the equipment operation state.

[0053] The detection correction factors corresponding to each temperature acquisition moment are obtained through the above steps, and the detection results of the traditional LOF algorithm are corrected by the detection correction factors. Therefore, first, the current mean value and the rotational speed mean value corresponding to the temperature acquisition moment are used as the inputs of the LOF algorithm, and the LOF anomaly scores at the corresponding moments are output. At this time, each temperature acquisition moment corresponds to a detection correction factor and an anomaly score, and the detection correction factor and the anomaly score at the same temperature acquisition moment form the monitoring vector at this temperature acquisition moment. The clustering method is used to cluster the monitoring vectors at multiple moments, so that multiple clustering clusters can be obtained.

[0054] In this embodiment, the K-means clustering algorithm is used for clustering, and the number of clusters is set to 4. The mean value of the norms of the monitoring vectors included in each clustering cluster is calculated respectively, and the clustering clusters are sorted in ascending order from small to large. The sorted clustering clusters are sequentially denoted as normal, slightly abnormal, moderately abnormal, and severely abnormal. According to the labels of the severe clusters corresponding to each temperature acquisition moment, the operating state of the device at this moment is judged, and different signals are sent according to different operating states to realize the hierarchical early warning of the device operating state.

[0055] The embodiment of the present application also discloses an operating anomaly monitoring system for a hose coiling machine, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, an operating anomaly monitoring method for a hose coiling machine according to the present application is realized.

[0056] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be elaborated here.

[0057] The above are all the preferred embodiments of the present application. The protection scope of the present application is not limited by this. Therefore, all equivalent changes made according to the structure, shape, and principle of the present application should be covered within the protection scope of the present application.

Claims

1. A method for monitoring abnormal operation of a hose coiling machine, characterized in that, Including the steps of: obtaining multi-dimensional operation data during the operation of the coiling machine, where the operation data includes the rotational speed data, current data, and hose temperature data of the motor; constructing a detection correction factor; Detecting the operation state of the equipment using the LOF anomaly detection algorithm based on the operation data, and correcting the detection result of the LOF using the detection correction factor to determine the operation state of the equipment; Calculating the abnormal winding degree of the hose winding at each moment based on the motor rotational speed and current at each moment; Constructing an observation sequence for each moment in the hose temperature data, and obtaining the temperature anomaly index corresponding to each moment according to the ratio of the hose temperature data in the observation sequence to the limit temperature of the hose deformation; for any moment, constructing an adjacent winding sequence for this moment based on the abnormal winding degree, and constructing an adjacent temperature sequence based on the abnormal temperature index; determining the period abnormal amplitude based on the magnitudes of the data in the adjacent winding sequence and the adjacent temperature sequence, and determining the period abnormal fluctuation based on the fluctuations of the data in the adjacent winding sequence and the adjacent temperature sequence, and taking the product of the period abnormal amplitude and the period abnormal fluctuation as the detection correction factor.

2. The abnormal operation monitoring method for a hose coiling machine according to claim 1, characterized in that, The calculation steps for the abnormal winding degree at any moment include: obtaining the current data and rotational speed data at this moment, and taking the ratio of the current data and rotational speed data at this moment as the abnormal winding degree at this moment.

3. A method for monitoring abnormal operation of a hose coiling machine according to claim 1, characterized in that, The calculation steps for the abnormal winding degree at any moment include: obtaining the current data and rotation speed data at this moment and before this moment; obtaining the average current of the current data and the average rotation speed of the rotation speed data, and taking the ratio of the average current to the average rotation speed as the abnormal winding degree at this moment.

4. A method for monitoring abnormal operation of a hose coiling machine according to claim 3, characterized in that, The acquisition frequency of the hose temperature data is lower than that of the rotational speed data and the current data, and the acquisition frequencies of the rotational speed data and the current data are equal; It is the difference between the acquisition frequency of the current data and the acquisition frequency of the hose temperature data.

5. A method for monitoring abnormal operation of a hose coiling machine according to claim 1, characterized in that, The steps for constructing the observation sequence of the hose temperature data at each moment include: determining the length of the observation sequence , for any moment, the hose temperature data at this moment and the previous moments are used as the observation sequence at this moment.

6. The operating anomaly monitoring method for a hose coiling machine according to claim 5, characterized in that, The steps of obtaining the temperature anomaly index according to the ratio of the hose temperature data in the observation sequence to the limit temperature of the hose deformation include: taking the sum of the ratios of multiple hose temperature data in the observation sequence to the limit temperature as the temperature anomaly index.

7. A method for monitoring abnormal operation of a hose coiling machine according to claim 1, characterized in that, The steps of constructing the adjacent winding sequence and the adjacent temperature sequence include: for any moment, the winding degrees of abnormality at this moment and the moments before this moment constitute the adjacent winding sequence, and the temperature abnormality indices at this moment and the moments before this moment constitute the adjacent temperature sequence.

8. A method for monitoring abnormal operation of a hose coiling machine according to claim 7, characterized in that, The steps of obtaining the period abnormal amplitude include: obtaining the mean value of the data in the adjacent winding sequence and the mean value of the data in the adjacent temperature sequence, and taking the sum of the two mean values as the period abnormal amplitude; Obtaining the standard deviation of the data in the adjacent winding sequence and the standard deviation of the data in the adjacent temperature sequence, and taking the sum of the two mean values as the period abnormal fluctuation.

9. The operation abnormal monitoring method for a hose coiling machine according to claim 1, characterized in that, The steps of correcting the detection result of the LOF using the detection correction factor to determine the operation state of the equipment include: constructing a monitoring vector corresponding to each temperature acquisition moment based on the anomaly score and the detection correction factor at each temperature acquisition moment, clustering each monitoring vector using a clustering method, and judging the operation state of each moment based on the clustering result.

10. An abnormal operation monitoring system for a hose coiling machine, characterized in that, Including: A processor and a memory, where the memory stores computer program instructions, and when the computer program instructions are executed by the processor, it realizes a method for monitoring the abnormal operation of a hose coiling machine according to any one of claims 1-9.

Images