A method and system for monitoring operating status parameters of ultrasonic therapeutic apparatus

Abstract

The present invention relates to the field of data processing technology, and more specifically, to a method and system for monitoring the operating state parameters of an ultrasonic therapeutic apparatus, the method comprising: constructing a random segmentation forest of an acquired temperature data sequence, determining the possibility that the temperature data corresponding to any node in the random segmentation forest is the real temperature data, calculating the importance of any node in the random segmentation forest, using the node with the smallest corresponding importance as the node to be replaced when inserting new temperature data in the random segmentation forest, so as to improve the replacement mechanism of the random segmentation forest, and monitoring the abnormality of the temperature data of the ultrasonic therapeutic apparatus based on the random segmentation forest after the improved replacement mechanism. The present invention can reduce the influence of the replaced node on the abnormality detection result of the random segmentation forest, and thus can improve the accuracy of abnormality detection of the temperature data inserted into the random segmentation forest.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically, to a method and system for monitoring operating status parameters of an ultrasonic therapeutic apparatus. Background Art

[0002] In the field of medical equipment, anomaly detection of temperature data during the operation of ultrasonic therapeutic devices can timely identify problems in the operation of the equipment, and promptly handle abnormal conditions of the equipment to ensure the safety of the equipment operation process. The Robust Random Cut Forest (RRCF) algorithm is an anomaly detection algorithm for dynamic data volumes. It can dynamically maintain the distribution of random segmentation trees on the data stream, judge the abnormality of new samples based on the impact of the insertion or deletion of new sample points on the complexity of the segmentation tree, and realize anomaly detection.

[0003] Mingzhi Zhang, Xinyu Wang, Wenyi Zhao, Real-time Detection Method for Gross Errors of GNSS Displacement Series Based on Robust Random Partition Forest, Geodesy and Geodynamics, 2024. In this paper, according to the RRCF outlier detection model of the real-time GNSS displacement monitoring data stream, the oldest point in the tree is replaced by each sample point to be tested in the real-time input data stream, and the collusion anomaly score of the sample point to be tested is calculated using the RRCF outlier detection model, so as to perform anomaly detection based on the collusion anomaly score.

[0004] However, when the scheme in the above article performs anomaly detection on the sample point to be tested, the sample point to be tested is replaced by the oldest node in the random segmentation tree, that is, the node farthest from the current moment, and the oldest node may contain important feature information. When the node containing important feature information is replaced, it may affect the random segmentation tree's anomaly detection of the sample to be tested, thereby possibly reducing the accuracy of the anomaly detection result obtained when the random segmentation tree performs anomaly detection on the sample point to be tested. Summary of the invention

[0005] In order to solve the problem of low accuracy in detecting anomalies in data using a random partition tree due to the influence of replaced nodes, the present invention proposes a method and system for monitoring operating status parameters of an ultrasonic therapeutic apparatus.

[0006] According to a first aspect of an embodiment of the present invention, there is provided a method for monitoring operating status parameters of an ultrasonic therapeutic apparatus, comprising:

[0007] Obtain a temperature data sequence when the ultrasonic therapeutic apparatus is running, and construct a random segmentation forest of the temperature data sequence, wherein the nodes in the random segmentation forest correspond one-to-one to the temperature data in the temperature data sequence;

[0008] Determine the possibility that the temperature data corresponding to any node in the random segmentation forest is the real temperature data, and calculate the importance of any node in the random segmentation forest , For the The possibility that the temperature data corresponding to each node is the real temperature data, For the The temperature data corresponding to the node is within the preset local range. The fitted value of the temperature data, is the first Temperature data, is the number of temperature data in this local range, is the absolute value symbol, For the summation symbol, The natural constant An exponential function with base ;

[0009] The node with the least importance is used as the node to be replaced when inserting new temperature data in the random segmentation forest, so as to improve the replacement mechanism of the random segmentation forest, and the abnormal situation of the temperature data of the ultrasonic therapeutic device is monitored based on the random segmentation forest with the improved replacement mechanism.

[0010] The present invention combines the possibility that the temperature data corresponding to each node in the random segmentation forest is the real temperature data, calculates the importance of each node in the random segmentation forest, and can ensure the accuracy of the determined importance. The corresponding node with the smallest importance is used as the node to be replaced when inserting new temperature data in the random segmentation forest. The replacement mechanism in the random segmentation forest is improved, and it can be ensured that the replaced node has a very small possibility of being a node containing important features, so that the replaced node can be guaranteed to have the least impact on the corresponding random segmentation tree, and further ensure the accuracy of abnormal detection of the inserted new temperature data using the random segmentation tree, so as to accurately monitor the abnormal situation of the temperature data of the ultrasonic therapeutic device during operation.

[0011] In an exemplary embodiment of the present invention, determining the possibility that the temperature data corresponding to any node in the random segmentation forest is the true temperature data includes:

[0012] Determine the number of extreme value points within a preset local range of temperature data corresponding to any node;

[0013] When the number is greater than the preset value, the possibility that the temperature data corresponding to any node is the true temperature data is positively correlated with the variance of the time interval between adjacent extreme points in the local range and the variance of the difference between adjacent extreme points;

[0014] When the number is less than or equal to the preset value, the possibility that the temperature data corresponding to any node is the real temperature data is 2.

[0015] The present invention counts the number of extreme points in a local range, and can evaluate the fluctuation of data in the local range of each temperature data. When the number of extreme points is large, the multiple characteristics of adjacent extreme points are combined to ensure the accuracy of the possibility of determining the real temperature data.

[0016] In an exemplary embodiment of the present invention, when the number is greater than a preset value, the possibility that the temperature data corresponding to any node is the real temperature data satisfies the following relationship:

[0017] ;

[0018] In the formula, For the The possibility that the temperature data corresponding to each node is the real temperature data; For the The variance of the time intervals between adjacent extreme points in the local range of the temperature data corresponding to each node; For the The variance of the difference between adjacent extreme points in the local range of the temperature data corresponding to each node; is a hyperparameter; is the normalization function.

[0019] The normalization function in the calculation formula provided by the present invention can unify the dimensions of different data for analysis, thereby making it possible to calculate the true temperature data by integrating a variety of data, thereby ensuring the accuracy of the calculation results.

[0020] In an exemplary embodiment of the present invention, a method for obtaining the number of extreme value points in a local range includes:

[0021] The difference method is used to identify the extreme points in the local range of the temperature data corresponding to any node, and the number of the identified extreme points is counted to obtain the number of the extreme points in the local range of the temperature data corresponding to any node.

[0022] In an exemplary embodiment of the present invention, a method for obtaining a fitting value includes:

[0023] The least square method is used to perform least square fitting on the data within the local range of the temperature data corresponding to any node to obtain the fitting value of the data within the local range.

[0024] The method of determining the fitting value of the present invention is relatively simple and more accurate, thereby improving the accuracy of the importance of calculation to a certain extent.

[0025] In an exemplary embodiment of the present invention, monitoring abnormal conditions of temperature data of an ultrasonic therapeutic apparatus based on a random segmentation forest after an improved replacement mechanism includes:

[0026] An anomaly detection model is constructed and trained based on the random segmentation forest after the improved replacement mechanism to obtain a trained anomaly detection model;

[0027] The current temperature data is input into the trained anomaly detection model to calculate the collusion anomaly score of the current temperature data. When the collusion anomaly score is greater than the preset threshold, the current temperature data is regarded as anomaly data.

[0028] The anomaly detection model constructed based on the random segmentation forest after the improved replacement mechanism in the present invention can accurately detect anomalies in temperature data, thereby accurately monitoring the abnormal conditions of temperature data during the operation of the ultrasonic therapeutic apparatus.

[0029] In an exemplary embodiment of the present invention, a method for obtaining a local range of temperature data corresponding to any node includes:

[0030] The temperature data corresponding to any node in the temperature data sequence is taken as the target data, and a temperature data segment of a preset length is intercepted with the target data as the center to obtain the local range of the temperature data corresponding to any node.

[0031] According to a second aspect of an embodiment of the present invention, a system for monitoring operating status parameters of an ultrasonic therapeutic device is provided. The system for monitoring operating status parameters of an ultrasonic therapeutic device includes a memory and a processor. A computer program is stored in the memory. The processor executes the computer program to implement the steps of the first aspect of the embodiment of the present invention.

[0032] The present invention has the following effects:

[0033] The present invention improves the replacement mechanism of the random segmentation forest so that when new temperature data is inserted into the random segmentation forest, the replaced node is always the node with the smallest importance in the random segmentation forest, thereby ensuring that the replaced node has the smallest impact on the random segmentation forest, and further ensuring accurate detection of abnormal conditions of temperature data, so as to accurately monitor abnormal conditions of temperature data during operation of an ultrasonic therapeutic apparatus; and when determining the importance of each node in the random segmentation forest, a variety of data are integrated to ensure the accuracy of the determined importance. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0035] Figure 1 The present invention is a schematic diagram of the steps of a method for monitoring operating status parameters of an ultrasonic therapeutic apparatus according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0037] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0038] Reference Figure 1 , a method for monitoring operating status parameters of an ultrasonic therapeutic apparatus, comprising steps S1 to S3, specifically as follows:

[0039] S1: Obtain the temperature data sequence when the ultrasonic therapeutic device is running, and construct a random segmentation forest of the temperature data sequence. The nodes in the random segmentation forest correspond one-to-one to the temperature data in the temperature data sequence.

[0040] In an exemplary embodiment of the present invention, the temperature data sequence may be a sequence obtained by collecting readings of a temperature sensor electrically connected to the ultrasonic therapeutic apparatus at a certain collection frequency, such as 1 Hz, during the operation of the ultrasonic therapeutic apparatus. This embodiment does not specifically limit the collection frequency of the temperature data.

[0041] The random segmentation forest can be a collection of multiple random segmentation trees constructed based on the temperature data sequence using the Robust Random Cut Forest (RRCF) algorithm. It should be noted that the position of each node in the random segmentation forest is independent of the order of the temperature data in the temperature data sequence, but is related to the value of the temperature data. Among them, the process of constructing a random segmentation forest based on the algorithm is a prior art, and this embodiment will not be described in detail here.

[0042] S2: Determine the possibility that the temperature data corresponding to any node in the random segmentation forest is the true temperature data, and calculate the importance of any node in the random segmentation forest.

[0043] In an example embodiment of the present invention, any node in the random segmentation forest can be the parent node of any random segmentation tree in the random segmentation forest, or the leaf node of any random segmentation tree in the random segmentation forest. Of course, it can also be a non-leaf node of any random segmentation tree in the random segmentation forest. This embodiment does not specifically limit the type of any node in the random segmentation forest.

[0044] Importance refers to the data obtained after correcting the possibility that the temperature data corresponding to any node is the real temperature data, which is used as the basis for selecting the node to be replaced when inserting new temperature data in the random segmentation forest. For example, when the importance of any node in the random segmentation forest is high, it means that the importance of the node in the random segmentation forest is higher, and when inserting new temperature data in the random segmentation forest, the possibility of the node being replaced is relatively small.

[0045] In an exemplary embodiment of the present invention, the possibility of determining whether the temperature data corresponding to any node is the real temperature data can be achieved by the following steps:

[0046] (1) Determine the number of extreme value points within a preset local range of temperature data corresponding to any node;

[0047] It should be noted that during the operation of the ultrasonic therapeutic device, the temperature data collected by the temperature sensor may fluctuate irregularly due to interference from the surrounding environment, thereby generating noise data. Therefore, the possibility that the corresponding temperature data is noise data can be determined through the fluctuations in the local range of each temperature data, thereby determining the possibility that each temperature data is real temperature data.

[0048] In an exemplary embodiment of the present invention, the local range of temperature data corresponding to any node can be determined by the following steps:

[0049] The temperature data corresponding to any node in the temperature data sequence is taken as the target data, and a temperature data segment of a preset length is intercepted with the target data as the center to obtain the local range of the temperature data corresponding to any node.

[0050] Optional, if the random partition forest The node and the temperature data sequence If the temperature data corresponds to the first The temperature data is taken as the target data, and then the preset length is intercepted with the target data as the center. The data segment is taken as the first segment in the random segmentation forest. The local range of temperature data corresponding to the nodes, where the preset length The length of the data segment consisting of 21 temperature data collected continuously. This embodiment does not specifically limit the length of the local range.

[0051] Optionally, when the number of temperature data on either side of the target data is less than , then discard the temperature data on that side and compare it with the temperature data on the other side A data segment consisting of temperature data is used as the local range of the target data.

[0052] In an exemplary embodiment of the present invention, the number of extreme value points in a local range of temperature data corresponding to any node can be determined by the following steps:

[0053] The difference method is used to identify the extreme points in the local range of the temperature data corresponding to any node, and the number of the identified extreme points is counted to obtain the number of the extreme points in the local range of the temperature data corresponding to any node.

[0054] Optionally, a curve fitting may be performed on a local range of temperature data corresponding to any node to determine the extreme points in the fitting curve, and then the number of extreme points in the local range may be determined. This embodiment does not specifically limit the number of extreme points in the local range. It should be noted that the step of identifying extreme points in data using the differential method is a prior art and is not described in detail in this embodiment.

[0055] (2) When the number is greater than the preset value, the possibility that the temperature data corresponding to any node is the true temperature data is positively correlated with the variance of the time interval between adjacent extreme points in the local range and the variance of the difference between adjacent extreme points;

[0056] Specifically, if the number of extreme value points in the local range of the temperature data corresponding to any node is greater than a preset value, such as 3, then the possibility that the temperature data corresponding to the node is the true temperature data satisfies the following relationship:

[0057] ;

[0058] In the formula, For the The possibility that the temperature data corresponding to each node is the real temperature data; For the The variance of the time intervals between adjacent extreme points in the local range of the temperature data corresponding to each node; For the The variance of the difference between adjacent extreme points in the local range of the temperature data corresponding to each node; is a hyperparameter used to prevent the denominator from being zero; is the normalization function.

[0059] Optionally, you can All extreme points in the local range of the temperature data corresponding to the node are recorded as , then the variance of the time intervals between adjacent extreme points in the local range is for The variance of The smaller it is, the more consistent the time intervals between adjacent extreme points in the local range are, and the corresponding fluctuation frequency of the temperature data in the local range is relatively consistent, which can indicate that the fluctuation in the local range is relatively stable. The possibility that the temperature data corresponding to the node is noise data is low, that is, the temperature data is more likely to be true temperature data.

[0060] Among them, The variance of the difference between adjacent extreme points in the local range of the temperature data corresponding to the nodes ,for The variance of The smaller the value, the more consistent the differences between the adjacent extreme points in the local range, and the more consistent the fluctuation of the corresponding extreme points in the local range, which can indicate that the fluctuation intensity of the temperature data in the local range is more consistent. The possibility that the temperature data corresponding to the node is noise data is low, that is, the temperature data is more likely to be true temperature data.

[0061] In another embodiment, the possibility that the temperature data corresponding to any node is real data may also be determined by other calculation formulas, such as by a product calculation formula instead of a summation calculation formula.

[0062] (3) When the number is less than or equal to the preset value, the probability that the temperature data corresponding to any node is the true temperature data is 2.

[0063] Optionally, when the number of extreme points in the local range of the temperature data corresponding to any node is less than or equal to a preset value, such as 3, it means that the fluctuation of the local range of the temperature data corresponding to the node is small, and the possibility that the temperature data corresponding to the node is noise data is extremely low, which can indicate that the temperature data corresponding to the node is more likely to be true temperature data.

[0064] It should be noted that when the number of extreme points in the local range of temperature data corresponding to any node is greater than a preset value, the maximum value of the possibility that the temperature data corresponding to the node is the true temperature data is 2. Therefore, this maximum value can be used as the possibility that the temperature data whose number of extreme points in the corresponding local range is less than or equal to the preset value is the true temperature data, thereby ensuring the consistency of the upper limit value of each temperature data as the true temperature data.

[0065] It should be further explained that, since there may be some isolated noise data in the temperature data sequence, it may not be possible to determine the isolated noise data by calculating the possibility that each temperature data is the true temperature data. Isolated noise data often appears as outliers, and when fitting the data within the local range of the outliers, the existence of the outliers will cause the corresponding fitting error to be large. Therefore, this feature can be used to correct the possibility that each temperature data is the true temperature data, and obtain the importance of the node corresponding to each temperature data in the random segmentation forest.

[0066] Furthermore, after determining the possibility that the temperature data corresponding to any node is the real temperature data, the importance of the node can be calculated. Specifically, the importance of any node satisfies the following relationship:

[0067] ;

[0068] In the formula, For the The importance of each node; For the The possibility that the temperature data corresponding to each node is the real temperature data; For the The temperature data corresponding to the node is within the preset local range. The fitted value of the temperature data; is the first Temperature data; is the number of temperature data within the local range; is the absolute value symbol; for the summation symbol; The natural constant An exponential function with base .

[0069] in, It reflects the overall fitting error in the local range. The larger the value is, the larger the overall fitting error of the data in the local range is, indicating that when fitting the data in the local range, it is more likely to be affected by noise data. In this case, it is necessary to correct the possibility that the temperature data is the real temperature data, thereby reducing the importance of the node corresponding to the temperature data in the random segmentation forest. The corresponding node has a relatively small importance in the random segmentation forest.

[0070] In an exemplary embodiment of the present invention, the fitting value of the temperature data in the local range corresponding to any node can be determined by the following steps:

[0071] The least square method is used to perform least square fitting on the data within the local range of the temperature data corresponding to any node to obtain the fitting value of the data within the local range.

[0072] Optionally, a polynomial fitting algorithm may be used to fit data within a local range of any temperature data. Of course, a suitable custom function may be selected according to specific circumstances to fit data within a local range of any temperature data. This embodiment does not specifically limit the method for determining the fitting value of data within a local range. It should be noted that least squares fitting of data is a prior art, and this embodiment will not be described in detail.

[0073] S3: The node with the least importance is used as the node to be replaced when inserting new temperature data in the random segmentation forest to improve the replacement mechanism of the random segmentation forest, and the abnormal situation of the temperature data of the ultrasonic therapy device is monitored based on the random segmentation forest after the improved replacement mechanism.

[0074] It should be noted that the present invention only improves the selection method of the replaced nodes in the random segmentation forest when inserting new temperature data in the random segmentation forest. The process of inserting new data in the random segmentation forest is a prior art and will not be described in detail in this embodiment.

[0075] Optionally, the node with the smallest corresponding importance is used as the node to be replaced when inserting new temperature data in the random segmentation forest, so that the replaced node has a greater possibility of being noise data, thereby reducing the impact of the replaced node on the anomaly detection result of the random segmentation forest, and further improving the accuracy of anomaly detection for temperature data inserted into the random segmentation forest.

[0076] In an exemplary embodiment of the present invention, the abnormality of the temperature data of the ultrasonic therapeutic apparatus can be monitored by the following steps:

[0077] (1) Build and train an anomaly detection model based on the random segmentation forest after the improved replacement mechanism to obtain a trained anomaly detection model;

[0078] Among them, the anomaly detection model refers to a neural network model deployed with a random segmentation forest, which is used to detect anomalies in the input temperature data, thereby detecting abnormalities in the temperature data of the ultrasonic therapeutic device during operation. The anomaly detection model can be constructed by hot start modeling or cold start modeling. This embodiment does not specifically limit the modeling method used when constructing the anomaly detection model. It should be noted that the process of constructing an anomaly detection model based on the random segmentation forest using cold start modeling or hot start modeling is a prior art and is not specifically described in this embodiment.

[0079] Optionally, in the process of constructing anomaly detection model, the number of random segmentation trees contained in the random segmentation forest can be set to 150 according to empirical values, and the number of nodes of the random segmentation tree can be set to 70. In the process of training the model, the abnormal data in the temperature data sequence collected in any time period can be marked as 0, and the normal data can be marked as 1. Then, the temperature data sequence and the corresponding marks are used as training sample sets to train the constructed random segmentation tree. It should be noted that the process of training the constructed random segmentation data using the training sample set is a prior art and is not described in detail in this embodiment.

[0080] (2) Input the current temperature data into the trained anomaly detection model and calculate the collusion anomaly score of the current temperature data. When the collusion anomaly score is greater than the preset threshold, the current temperature data is regarded as anomaly data.

[0081] Among them, the collusion anomaly score refers to data used to measure the possibility that the current temperature data is abnormal data. If the collusion anomaly score of the current temperature data is greater than a preset threshold, such as 0.81, the current temperature data can be determined to be abnormal data, indicating that the temperature data of the ultrasonic therapeutic device at the current moment is abnormal, and an alarm is issued to promptly remind relevant personnel to handle it, thereby ensuring the safety of the ultrasonic therapeutic device during operation, and then accurately monitoring the abnormality of the temperature data of the ultrasonic therapeutic device during operation.

[0082] The present invention also provides an ultrasonic therapeutic apparatus operating status parameter monitoring system, the system includes a memory and a processor, and a computer program is stored in the memory, the computer program integrates the function of an ultrasonic therapeutic apparatus operating status parameter monitoring method, when the computer program is executed, an ultrasonic therapeutic apparatus operating status parameter monitoring method can be used to reduce the influence of the replaced node on the abnormal detection result of the random segmentation forest, thereby improving the accuracy of abnormal detection of temperature data inserted into the random segmentation forest.

[0083] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0084] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for monitoring operating status parameters of an ultrasonic therapeutic apparatus, characterized in that: include: Acquire a temperature data sequence when the ultrasonic therapeutic apparatus is running, and construct a random segmentation forest of the temperature data sequence, wherein the nodes in the random segmentation forest correspond one-to-one to the temperature data in the temperature data sequence; Calculate the importance of any node in the random segmentation forest , For the The possibility that the temperature data corresponding to each node is the real temperature data, For the The temperature data corresponding to the node is within the preset local range. The fitted value of the temperature data, is the first Temperature data, is the number of temperature data within the local range, is the absolute value symbol, For the summation symbol, The natural constant An exponential function with base ; The node with the least importance is used as the node to be replaced when inserting new temperature data into the random segmentation forest, so as to improve the replacement mechanism of the random segmentation forest, and the abnormality of the temperature data of the ultrasonic therapeutic apparatus is monitored based on the random segmentation forest after the improved replacement mechanism; The method for obtaining the possibility is as follows: when the number of extreme value points in a preset local range of temperature data corresponding to any node is greater than a preset value, the possibility , For the The variance of the time intervals between adjacent extreme points in the local range of the temperature data corresponding to the node, For the The variance of the difference between adjacent extreme points in the local range of the temperature data corresponding to the node, is a hyperparameter, is a normalized function; when the number is less than or equal to a preset value, the possibility is 2.

2. The method for monitoring operating status parameters of an ultrasonic therapeutic apparatus according to claim 1, characterized in that: The method for obtaining the number of extreme value points in the local range includes: The extreme value points in the local range of the temperature data corresponding to any node are identified by using the difference method, and the number of the identified extreme value points is counted to obtain the number of the extreme value points in the local range of the temperature data corresponding to any node.

3. The method for monitoring operating status parameters of an ultrasonic therapeutic apparatus according to claim 1, characterized in that: The method for obtaining the fitting value includes: The least square method is used to perform least square fitting on the data within a local range of the temperature data corresponding to any node to obtain a fitting value of the data within the local range.

4. The method for monitoring operating status parameters of an ultrasonic therapeutic apparatus according to claim 1, characterized in that: The random segmentation forest based on the improved replacement mechanism monitors the abnormality of the temperature data of the ultrasonic therapeutic apparatus, including: An anomaly detection model is constructed and trained based on the random segmentation forest after the improved replacement mechanism to obtain a trained anomaly detection model; The current temperature data is input into the trained anomaly detection model, and the collusion anomaly score of the current temperature data is calculated. When the collusion anomaly score is greater than a preset threshold, the current temperature data is regarded as anomaly data.

5. The method for monitoring operating status parameters of an ultrasonic therapeutic apparatus according to claim 2, characterized in that: The method for obtaining the local range of temperature data corresponding to any node includes: The temperature data corresponding to any one of the nodes in the temperature data sequence is taken as the target data, and a temperature data segment of a preset length is intercepted with the target data as the center to obtain a local range of the temperature data corresponding to any one of the nodes.

6. An ultrasonic therapeutic apparatus operating status parameter monitoring system, characterized in that: The ultrasonic therapeutic device operating status parameter monitoring system includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the method as described in any one of claims 1-5.

Images