Abnormality monitoring method and system for aluminum plate cutting equipment

Abstract

The invention relates to the technical field of data processing, and particularly discloses an abnormity monitoring method and system for aluminum plate cutting equipment, and the method comprises the following steps: obtaining a training set which comprises a plurality of cutting pressure values; training the isolated forest model by using the training set to obtain a trained isolated forest model; the improved threshold value of the isolated forest model is inversely correlated with the mean value of the pollution proportions of all isolated trees in the isolated forest model; the pollution proportion is inversely correlated with the discrete degree of each cutting pressure value in each isolated tree and the correlation degree of the diversity of the aluminum plates; the diversity is a variance of a weighted average value of normalized values of all parameters of all the aluminum plates; and inputting a to-be-measured cutting pressure value into the trained isolated forest model, when an output anomaly score is greater than an improved threshold value, judging that an anomaly exists, and performing early warning and stopping operation of the aluminum plate cutting equipment. According to the scheme of the invention, the accuracy of anomaly detection is improved, and misinformation and missing report conditions are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an abnormality monitoring method and system for aluminum plate cutting equipment. Background Art

[0002] Aluminum plate cutting equipment plays a vital role in modern industrial production. Its performance stability and cutting accuracy directly affect product quality and production efficiency. However, in the actual production process, the performance of aluminum plate cutting equipment is often affected by many factors, such as material properties, cutting parameters, equipment aging, improper operation, etc. These factors may cause equipment abnormalities. Traditional equipment monitoring methods mainly rely on manual regular inspections or judgments based on experience. This method is not only time-consuming and labor-intensive, but also often difficult to detect abnormal conditions of equipment in a timely and accurate manner.

[0003] With the rapid development of computer technology and anomaly detection algorithms, it is becoming more and more common to apply anomaly detection algorithms to equipment anomaly detection. It not only saves time and effort, but also has high detection accuracy and can detect equipment anomalies in a timely manner. One of the important parameters of aluminum plate cutting equipment is the cutting pressure value, that is, the pressure value of the cutting head. The pressure value of normal data indicates that the aluminum plate cutting equipment is in a normal state, while the pressure value that is different from the normal data indicates that the aluminum plate cutting equipment has an abnormal risk. As a simple and efficient anomaly detection algorithm, the isolation forest algorithm can monitor the operation of aluminum plate cutting equipment by detecting the pressure value of aluminum plate cutting equipment.

[0004] The Isolation Forest Algorithm is based on the following theoretical foundation: abnormal data accounts for a small proportion of the total sample data, normal data is densely distributed, and abnormal data is often isolated, and abnormal data is usually quite different from normal data, so abnormal data is easier to separate and identify. The Isolation Forest Algorithm builds multiple isolated trees based on multiple sample data, calculates the average path length of each sample data in all isolated trees, obtains the abnormal score of the sample data, and takes the sample data with an abnormal score greater than the threshold as abnormal data.

[0005] The threshold is set according to the contamination ratio, which is the ratio of the estimated abnormal data samples to the total data samples. It is an empirical value set manually. The higher the contamination ratio is set, the more abnormal data is estimated, and the smaller the threshold is, so that more sample data is judged as abnormal data. The lower the contamination ratio is set, the less abnormal data is estimated, and the larger the threshold is, so that less sample data is judged as abnormal data. However, since the contamination ratio is set manually, there are unreasonable settings. If the contamination ratio is set too high, normal sample data will be considered abnormal data, resulting in false alarms of the device. If the contamination ratio is set too low, the real abnormal data will be ignored and potential abnormal conditions of the device will be missed. Summary of the invention

[0006] The present invention provides an abnormality monitoring method and system for aluminum plate cutting equipment, aiming to solve the technical problem in the prior art that the accuracy of the isolation forest model is low and false alarms or missed alarms occur due to unreasonable setting of the pollution ratio.

[0007] The method for monitoring abnormality of aluminum plate cutting equipment of the present invention comprises the following steps: Acquire a training set, wherein the training set includes a plurality of cutting pressure values; The isolation forest model is trained using the training set to obtain a trained isolation forest model; wherein the threshold of the isolation forest model is an improved threshold; the improved threshold is inversely correlated with the mean of the pollution ratio of all isolated trees in the isolation forest model; the pollution ratio is inversely correlated with the discreteness of each cutting pressure value in each isolated tree and the correlation degree of the diversity of aluminum plates; the correlation degree is the arithmetic square root of the absolute value of the square difference between the discreteness and the diversity; the diversity is the variance of the weighted average of the normalized values ​​of each parameter corresponding to all aluminum plates in each isolated tree; Wherein, when obtaining the weighted average value, the weight of the normalized value of each parameter is the normalized value of the correlation between the corresponding parameter and the cutting pressure value; the parameters include the hardness of the aluminum plate, the thickness of the aluminum plate and the surface friction of the aluminum plate; The cutting pressure value to be measured is input into the trained isolation forest model, and the corresponding anomaly score is output; when the anomaly score is greater than the improved threshold, it is determined that the aluminum plate cutting equipment is abnormal, and an early warning and stop of the aluminum plate cutting equipment are issued.

[0008] In the above scheme, by calculating the discrete degree of each cutting pressure value in each isolated tree and the diversity of aluminum plates, the actual pollution proportion in each isolated tree is obtained, and then the improved threshold is obtained. The isolation forest model with the improved threshold is used for anomaly detection, which can improve the accuracy of anomaly detection and prevent false alarms or omissions.

[0009] Preferably, the improved threshold for:

[0010] In the formula, For the The pollution ratio of an isolated tree, is the total number of isolated trees, is the total number of cutting pressure values ​​in the training set, is the standard normalization function.

[0011] Preferably, Pollution ratio of an isolated tree for: ; In the formula, For the The correlation between the discreteness of each cutting pressure value in an isolated tree and the diversity of aluminum plates, The natural constant The exponential function of base .

[0012] In the above scheme, the pollution ratio of the isolated tree is represented by the correlation degree of the isolated tree, which can truly reflect the pollution situation of the isolated tree and make the calculation result more accurate.

[0013] Preferably, The discrete degree of each cutting pressure value in an isolated tree for: ; In the formula, For the The total number of cutting pressure values ​​in an isolated tree, For the Isolated tree Cutting pressure value, For the The mean of all cutting pressure values ​​in an isolated tree.

[0014] In the above scheme, by calculating the discrete degree of the cutting pressure value in each isolated tree, the deviation degree of any cutting pressure value from the average cutting pressure value is reflected, which is convenient for the subsequent calculation of the pollution ratio.

[0015] Preferably, The discrete degree of each cutting pressure value in an isolated tree for: ; In the formula, For the The total number of cutting pressure values ​​in an isolated tree, For the Isolated tree Cutting pressure value, For the The mean of all cutting pressure values ​​in an isolated tree.

[0016] Preferably, the aluminum plate The weight of the parameters for: ; In the formula, For aluminum plate The correlation between the parameters and the corresponding cutting pressure value, is the total number of parameters of the aluminum plate.

[0017] Preferably, the cutting pressure value to be measured is Anomaly score for:

[0018] In the formula, is the cutting pressure value to be measured The average path length among all isolated trees, is the normalization factor for the expected path length, is the total number of cutting pressure values ​​in the training set.

[0019] Preferably, the correlation between the parameters of the aluminum plate and the cutting pressure value is represented by a DTW correlation function or a Pearson correlation coefficient.

[0020] In the above scheme, the DTW correlation function has the advantages of robustness and accurate calculation results, while the Pearson correlation coefficient has the advantages of intuitiveness and simple calculation.

[0021] The present invention also provides an aluminum plate cutting equipment abnormality monitoring system, comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to implement any of the aluminum plate cutting equipment abnormality monitoring methods described above.

[0022] The beneficial effects are: The solution of the present invention first calculates the correlation between the discrete degree of the cutting pressure value and the diversity of the aluminum plate, then obtains the pollution ratio of each isolated tree, and then obtains the improved threshold value according to the mean of the pollution ratio of all isolated trees, and finally performs abnormal detection on the data with the isolation forest model of the improved threshold value. Compared with the artificially set pollution ratio in the prior art, the present invention calculates the real pollution ratio in the data to obtain the appropriate improved threshold value in the isolation forest model, so that the isolation forest model can more accurately distinguish normal data from abnormal data, improve the accuracy of abnormal detection, and reduce false positives and false negatives in the abnormal monitoring process of aluminum plate cutting equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flowchart of the steps of the abnormality monitoring method for aluminum plate cutting equipment according to an embodiment of the present invention; Figure 2 It is a structural block diagram of the abnormality monitoring system for aluminum plate cutting equipment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0025] like Figure 1As shown, according to a first aspect of the present invention, a method for monitoring abnormality of aluminum plate cutting equipment is provided, comprising the following steps: S1. Obtain a training set, where the training set includes multiple cutting pressure values.

[0026] In this step, the cutting pressure value is the pressure value of the cutting head. In the process of cutting the aluminum plate, the cutting head is in direct contact with the aluminum plate, and the cutting head needs to withstand greater pressure. The cutting head is also the most vulnerable part of the aluminum plate cutting equipment. The pressure value of the cutting head can reflect the operating status of the aluminum plate cutting equipment. Normal cutting pressure values ​​account for the majority and are concentratedly distributed, reflecting that the aluminum plate cutting equipment is in a normal operating state. Abnormal cutting pressure values ​​are less and different from normal data, reflecting that the aluminum plate cutting equipment is in an abnormal operating state, and the aluminum plate cutting equipment needs to be checked and processed in time. The cutting pressure value can be collected through a pressure sensor installed on the aluminum plate cutting equipment.

[0027] S2. Use the training set to train the isolation forest model to obtain a trained isolation forest model.

[0028] It should be noted that the isolation forest algorithm itself belongs to the existing technology. Its core idea is to "isolate" data points by constructing a series of random isolation trees. The isolation forest gradually divides the data set by randomly selecting features and split values ​​to form a tree structure. Abnormal data points are more likely to be isolated due to their rarity and characteristics different from normal data points, so they show a shorter path length in the isolation tree. The isolation forest algorithm consists of two stages. The first stage is to train the isolation forest model, and the second stage is to use the trained isolation forest model to detect data anomalies.

[0029] Among them, training the isolation forest model includes the following steps: S21. Select model parameters of the isolation forest model.

[0030] The model parameters of the isolation forest model include the number of isolated trees, maximum tree depth, subsample size, random seed, and contamination ratio. The more isolated trees there are, the higher the stability and accuracy of the isolation forest model is generally, but the computational cost will also increase. The larger the maximum tree depth, the better it can capture the details of the data, but it may lead to overfitting. The subsample size is the number of samples used in each isolated tree. Smaller subsamples can improve the efficiency of the model but may reduce accuracy. The random seed is used to control the random process to ensure the repeatability of the results. The contamination ratio is the ratio of the estimated number of abnormal data to the total number of data, which is used to adjust the threshold of the anomaly score.

[0031] S22, constructing an isolated tree according to the model parameters of the isolation forest model. Specifically, it includes the following steps: S221, randomly selecting a preset number of cutting pressure value data from the training set as subsamples, and putting them into the root node of the isolated tree; S222, randomly select any dimension of the data, and randomly select a segmentation value within the range of the dimension. Since the present invention has only one dimension of the cutting pressure value, the segmentation value is a cutting pressure value randomly selected within the range of the cutting pressure value.

[0032] S223, compare all data in the sub-sample with the split value respectively, and distribute them to the left subtree and the right subtree; S224, recursively divide the data in the subtree into the next layer of subtrees until the maximum tree depth is reached; for example, the maximum tree depth is 10.

[0033] S225, repeating steps S221 to S224 until a specified number of isolated trees are constructed. For example, the number of isolated trees is 100.

[0034] In step S21, since the pollution ratio is set manually, it often cannot truly reflect the proportion of abnormal data to the total data. The threshold value obtained by the artificially set pollution ratio may cause false alarms or missed alarms in the aluminum plate cutting equipment. The specific situation is as follows: When the contamination ratio is set too high, the Isolation Forest Model will consider the proportion of abnormal data to be large, so the conditions for determining abnormal data will be loose, that is, the threshold will be small, so that the abnormal scores of more data are greater than the threshold, thereby increasing the number of abnormal data. This will cause some normal data to be mistakenly considered as abnormal data by the Isolation Forest Model, resulting in false alarms of aluminum plate cutting equipment.

[0035] When the contamination ratio is set too low, the Isolation Forest Model will think that the proportion of abnormal data is small, so the conditions for judging abnormal data will be strict, that is, the threshold will be large, so that the abnormal scores of fewer data are greater than the threshold to reduce the number of abnormal data. This will cause some abnormal data to be mistakenly regarded as normal data by the Isolation Forest Model, resulting in underreporting of aluminum plate cutting equipment.

[0036] Through the above analysis, it can be seen that when the isolation forest model in the prior art performs abnormal monitoring on aluminum plate cutting equipment, false alarms or missed alarms may occur. The main reason is that the artificially set pollution ratio is inappropriate and cannot truly reflect the proportion of abnormal data, making the threshold setting inappropriate, and then making the isolation forest model unable to accurately distinguish normal data from abnormal data, resulting in false alarms or missed alarms of aluminum plate cutting equipment.

[0037] Therefore, the present invention improves the pollution ratio artificially set in the prior art and obtains a suitable threshold value, so that the isolation forest model can accurately distinguish normal data from abnormal data, thereby avoiding the situation where the aluminum plate cutting equipment is falsely reported or missed. Specifically, the present invention includes the following steps: S23. Obtain the pollution ratio of each isolated tree.

[0038] Since the data of the subsamples in each isolated tree are randomly selected from the training set when constructing an isolated tree, the contamination ratio of each isolated tree is different, and the contamination ratio of each isolated tree needs to be calculated. The contamination ratio is inversely correlated with the discrete degree of each cutting pressure value in each isolated tree and the correlation degree of the diversity of aluminum plates. Among them, the diversity of aluminum plates is reflected in the fact that aluminum plates are composed of different parameters, including aluminum plate hardness, aluminum plate thickness and aluminum plate surface friction, all of which affect the cutting pressure value. For example, the greater the hardness and thickness of the aluminum plate, the greater the surface friction, and the greater the cutting pressure value. The smaller the hardness and thickness of the aluminum plate, the smaller the surface friction, and the smaller the cutting pressure value. The diversity of aluminum plates will directly affect the discrete degree of the cutting pressure value. The greater the diversity of aluminum plates, the greater the discrete degree of the cutting pressure value. These seemingly abnormal but actually normal cutting pressure values ​​are caused by the diversity of aluminum plates, not by the abnormality of aluminum plate cutting equipment. And the higher the correlation between the diversity of aluminum plates and the discrete degree of cutting pressure values, the more likely it is that these data are normal data, that is, the smaller the actual contamination ratio. Therefore, by calculating the discrete degree of the cutting pressure value in each isolated tree and the correlation degree of the diversity of the aluminum plate, it can be used to represent the pollution ratio of the isolated tree. Specifically, obtaining the pollution ratio of each isolated tree includes the following steps: S231, obtaining the discrete degree of the cutting pressure value.

[0039] No. The discrete degree of cutting pressure value in an isolated tree for: ; In the formula, For the The total number of cutting pressure values ​​in an isolated tree, For the Isolated tree Cutting pressure value, For the The mean of all cutting pressure values ​​in an isolated tree.

[0040] In some alternative embodiments, the dispersion can also be expressed by standard deviation. The discrete degree of cutting pressure value in an isolated tree for: ; In the formula, For the The total number of cutting pressure values ​​in an isolated tree, For the Isolated tree Cutting pressure value, For the The mean of all cutting pressure values ​​in an isolated tree.

[0041] In this step, the degree of dispersion of the cutting pressure value in each isolated tree is calculated to reflect the degree of deviation of any cutting pressure value from the average cutting pressure value, which is convenient for the subsequent calculation of the pollution ratio.

[0042] S232. Obtain the diversity of aluminum plates.

[0043] The diversity of aluminum sheets is the variance of the weighted average of each parameter of all aluminum sheets in each isolated tree. Obtaining the diversity of aluminum sheets includes the following steps: S2321. Normalize various parameters of the aluminum plate.

[0044] The parameters of aluminum plates include aluminum plate hardness, aluminum plate thickness and aluminum plate surface friction. In order to eliminate the dimensional differences between different parameters and facilitate numerical calculation and analysis, it is necessary to first normalize the collected parameters of aluminum plates so that each parameter falls within the range of 0 to 1.

[0045] S2322. Calculate the weight of the normalized value of each parameter.

[0046] The weight of the normalized value of each parameter is the normalized value of the correlation between the corresponding parameter and the cutting pressure value. The weight of the parameters for: ; In the formula, For aluminum plate The correlation between the parameters and the corresponding cutting pressure value, is the total number of parameters of the aluminum plate.

[0047] Specifically, the three parameters of aluminum plate hardness, aluminum plate thickness and aluminum plate surface friction are used for explanation. The weight of aluminum plate hardness is set as , the weight of the aluminum plate thickness is set to , the weight of the friction force on the aluminum plate surface is set to .

[0048] Weight of aluminum plate hardness for: ; Weight of aluminum plate thickness for: ; Weight of friction force on aluminum plate surface for: ; In the formula, is the correlation between the hardness of the aluminum plate and the corresponding cutting pressure value, is the correlation between the thickness of the aluminum plate and the corresponding cutting pressure value, is the correlation between the surface friction of the aluminum plate and the corresponding cutting pressure value.

[0049] The correlation between the parameters of the aluminum plate and the cutting pressure value is expressed by the DTW correlation function or the Pearson correlation coefficient.

[0050] S2323. Obtain the diversity of aluminum plates in each isolated tree.

[0051] Diversity is the variance of the weighted average of the normalized values ​​of each parameter for all aluminum plates in each isolated tree. Diversity of aluminum plates in an isolated tree for: ; In the formula, is the weight of the aluminum plate hardness, is the weight of the aluminum plate thickness, is the weight of the friction force on the aluminum plate surface, is the normalized value of the aluminum plate hardness, is the normalized value of the aluminum plate thickness, is the normalized value of the friction force on the aluminum plate surface, is the variance function.

[0052] In some alternative embodiments, the diversity of the aluminum plates may also be the coefficient of variation of the weighted average of the normalized values ​​of each parameter of all the aluminum plates in each isolated tree.

[0053] S233. Calculate the correlation between the discreteness of each cutting pressure value in each isolated tree and the diversity of the aluminum plates.

[0054] The correlation is the square root of the absolute value of the square difference between the dispersion and the diversity. Correlation between the discreteness of each cutting pressure value in an isolated tree and the diversity of aluminum plates for: ; In the formula, For the Diversity of aluminum plates in an isolated tree, For the The degree of dispersion of the cutting pressure values ​​in an isolated tree.

[0055] S234. Obtain the pollution ratio of each isolated tree.

[0056] The pollution ratio is inversely correlated with the relevance of each isolated tree. Pollution ratio of an isolated tree for: ; In the formula, For the The correlation between the discreteness of each cutting pressure value in an isolated tree and the diversity of aluminum plates, The natural constant The exponential function of base .

[0057] S24. Calculate an improved threshold value according to the pollution ratio.

[0058] The improved threshold is inversely correlated with the mean of the contamination ratios of all isolated trees. Specifically, the improved threshold for:

[0059] In the formula, For the The pollution ratio of an isolated tree, is the total number of isolated trees, is the total number of cutting pressure values ​​in the training set, is the standard normalization function.

[0060] The present invention obtains the pollution ratio of each isolated tree by calculating the discrete degree of cutting pressure values ​​and the correlation degree of the diversity of aluminum plates, and then obtains the improved threshold value by the average value of the pollution ratio of all isolated trees. Compared with the threshold value obtained by artificially setting the pollution ratio in the prior art, the setting of the improved threshold value is more reasonable, so that the isolation forest model can accurately distinguish normal data and abnormal data, and avoid false alarms or omissions in aluminum plate cutting equipment.

[0061] S3. Input the cutting pressure value to be measured into the trained isolation forest model, and output the corresponding anomaly score; when the anomaly score is greater than the improved threshold, it is determined that the aluminum plate cutting equipment is abnormal, and an early warning and stop of the aluminum plate cutting equipment are issued.

[0062] After the training of the isolation forest model is completed, the cutting method of these isolated trees is fixed, that is, the segmentation value of each node in the isolated tree is determined. The cutting pressure value to be tested is transmitted to the trained isolation forest model, so that the cutting pressure value to be tested traverses each isolated tree, and the path length of the cutting pressure value to be tested in all isolated trees is obtained. According to the abnormal score calculation formula, the abnormal score of the cutting pressure value to be tested can be obtained.

[0063] Cutting pressure value to be measured Anomaly score for:

[0064] In the formula, is the cutting pressure value to be measured The average path length among all isolated trees, is the normalization factor for the expected path length, is the total number of cutting pressure values ​​in the training set.

[0065] In some embodiments, The calculation formula is as follows:

[0066] In the formula, , is the total number of cutting pressure values ​​in the training set.

[0067] In some embodiments, when the abnormality score is greater than the improvement threshold, but the difference between the abnormality score and the improvement threshold is less than the preset value, only a warning signal is issued to remind the operator to check whether the equipment has abnormal risks. When the difference between the abnormality score and the improvement threshold is greater than or equal to the preset value, the aluminum plate cutting equipment is stopped. These measures can timely detect abnormal conditions of aluminum plate cutting equipment to avoid equipment damage and property losses.

[0068] In some embodiments, the detected abnormal data is further analyzed to determine the cause and impact of the abnormality. For example, a visualization tool may be used to display the distribution and characteristics of the abnormal data to better analyze and understand the abnormal data.

[0069] In the abnormality monitoring method for aluminum plate cutting equipment of the present invention, the pollution ratio of each isolated tree is adaptively adjusted by calculating the discrete degree of the cutting pressure value and the correlation degree of the diversity of the aluminum plate, and then the improved threshold is obtained according to the mean value of the pollution ratio of all isolated trees. The isolation forest model with the improved threshold is used for abnormality detection, which can more accurately distinguish normal data from abnormal data, improve the accuracy of abnormality detection, reduce false alarms and missed alarms, and make the abnormality monitoring method for aluminum plate cutting equipment of the present invention more reliable.

[0070] like Figure 2 As shown, according to the second aspect of the present invention, there is also provided an abnormality monitoring system for aluminum plate cutting equipment, the system comprising a memory and a processor, the processor executing a computer program stored in the memory to implement the abnormality monitoring method for aluminum plate cutting equipment described in the first aspect of the present invention.

[0071] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0072] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented by computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.

[0073] 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 abnormality of aluminum plate cutting equipment, characterized in that: The steps include: Acquire a training set, wherein the training set includes a plurality of cutting pressure values; The isolation forest model is trained using the training set to obtain a trained isolation forest model; wherein the threshold of the isolation forest model is an improved threshold; the improved threshold is inversely correlated with the mean of the pollution ratio of all isolated trees in the isolation forest model; the pollution ratio is inversely correlated with the discreteness of each cutting pressure value in each isolated tree and the correlation degree of the diversity of aluminum plates; the correlation degree is the arithmetic square root of the absolute value of the square difference between the discreteness and the diversity; the diversity is the variance of the weighted average of the normalized values ​​of each parameter corresponding to all aluminum plates in each isolated tree; Wherein, when obtaining the weighted average value, the weight of the normalized value of each parameter is the normalized value of the correlation between the corresponding parameter and the cutting pressure value; the parameters include the hardness of the aluminum plate, the thickness of the aluminum plate and the surface friction of the aluminum plate; The cutting pressure value to be measured is input into the trained isolation forest model, and the corresponding anomaly score is output; when the anomaly score is greater than the improved threshold, it is determined that the aluminum plate cutting equipment is abnormal, and an early warning and stop of the aluminum plate cutting equipment are issued.

2. The method for monitoring abnormality of aluminum plate cutting equipment according to claim 1, characterized in that: The improvement threshold for: In the formula, For the The pollution ratio of an isolated tree, is the total number of isolated trees, is the total number of cutting pressure values ​​in the training set, is the standard normalization function.

3. The method for monitoring abnormality of aluminum plate cutting equipment according to claim 2, characterized in that: No. Pollution ratio of an isolated tree for: ； In the formula, For the The correlation between the discrete degree of each cutting pressure value in an isolated tree and the diversity of aluminum plates, The natural constant The exponential function of base .

4. The method for monitoring abnormality of aluminum plate cutting equipment according to claim 1, characterized in that: No. The discrete degree of each cutting pressure value in an isolated tree for: ； In the formula, For the The total number of cutting pressure values ​​in an isolated tree, For the Isolated tree Cutting pressure value, For the The mean of all cutting pressure values ​​in an isolated tree.

5. The method for monitoring abnormality of aluminum plate cutting equipment according to claim 1, characterized in that: No. The discrete degree of each cutting pressure value in an isolated tree for: ； In the formula, For the The total number of cutting pressure values ​​in an isolated tree, For the Isolated tree Cutting pressure value, For the The mean of all cutting pressure values ​​in an isolated tree.

6. The method for monitoring abnormality of aluminum plate cutting equipment according to claim 1, characterized in that: Aluminum Plate The weight of the parameters for: ； In the formula, For aluminum plate The correlation between the parameters and the corresponding cutting pressure value, is the total number of parameters of the aluminum plate.

7. The method for monitoring abnormality of aluminum plate cutting equipment according to claim 1, characterized in that: Cutting pressure value to be measured Anomaly score for: In the formula, is the cutting pressure value to be measured The average path length among all isolated trees, is the normalization factor for the expected path length, is the total number of cutting pressure values ​​in the training set.

8. The method for monitoring abnormality of aluminum plate cutting equipment according to claim 1, characterized in that: The correlation between the parameters of the aluminum plate and the cutting pressure value is expressed by the DTW correlation function or the Pearson correlation coefficient.

9. An abnormality monitoring system for aluminum plate cutting equipment, comprising a memory and a processor, characterized in that: The processor executes the computer program stored in the memory to implement the abnormality monitoring method for aluminum plate cutting equipment according to any one of claims 1 to 8.

Images