Decision tree-based device feature data comparison and extraction method

Abstract

The invention discloses an equipment feature data comparison and extraction method based on a decision tree, and relates to the field of equipment feature data comparison and extraction, and the method comprises the steps: carrying out the hierarchical processing of equipment features, screening out main factors affecting the performance of equipment, and constructing a hierarchical decision tree structure; performing feature clustering analysis on the decision tree structure, combining similar features into a feature group, generating new synthetic features based on the feature group, and performing adaptive structure adjustment on the decision tree; setting importance initial weights of features in the nodes, and dynamically adjusting the importance weights of the features according to real-time data feedback by adopting an online learning algorithm; acquiring equipment real-time operation data of to-be-compared equipment, and selecting an optimal feature data comparison scheme based on the decision path node feature weight of each decision tree; and dynamically deleting redundant nodes of the decision tree based on the historical optimal feature data comparison scheme selection condition.

Description

Technical Field

[0001] The present invention relates to the field of equipment feature data comparison and extraction, and in particular to an equipment feature data comparison and extraction method based on a decision tree. Background Art

[0002] In modern manufacturing and industrial environments, equipment performance monitoring and fault detection have become particularly important. With the development of the Internet of Things and big data technologies, it has become possible for equipment to collect and analyze large amounts of real-time data. Traditional equipment monitoring methods usually rely on static feature selection and offline analysis, which is difficult to cope with the ever-changing conditions and characteristics of equipment operation.

[0003] How to establish a decision tree-based device feature data comparison and extraction method that can efficiently extract and compare device data through adaptive feature selection and real-time feedback mechanism, so as to quickly identify performance differences and potential faults, is an urgent problem that needs to be solved. Summary of the invention

[0004] In order to solve the above technical problems, a method for comparing and extracting device feature data based on a decision tree is provided. This technical solution solves the problems raised in the above background technology.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A device feature data comparison and extraction method based on a decision tree, comprising:

[0007] Perform hierarchical processing on equipment features, screen out the main factors affecting equipment performance, and build a hierarchical decision tree structure;

[0008] Perform feature clustering analysis on the decision tree structure, merge similar features into feature groups, generate new synthetic features based on the feature groups, and perform adaptive structural adjustments on the decision tree;

[0009] Set the initial importance weight of the features in the node, and use an online learning algorithm to dynamically adjust the importance weight of the features based on real-time data feedback;

[0010] Obtain the real-time operation data of the equipment to be compared, and select the optimal feature data comparison scheme based on the feature weights of the decision path nodes of each decision tree;

[0011] Based on the selection of the historical optimal feature data comparison scheme, redundant nodes of the decision tree are dynamically deleted.

[0012] Preferably, the hierarchical processing of the device characteristics, screening out the main factors affecting the device performance, and constructing a hierarchical decision tree structure specifically includes:

[0013] Get the comparison device set M;

[0014] Perform statistical analysis on the historical operation data of the equipment in the equipment set M, screen out the main factors affecting the equipment performance, and establish the corresponding relationship between the equipment and its main feature set;

[0015] Among them, the main feature uses the information gain algorithm to evaluate all the main factor features that affect the performance of the equipment, and selects the feature with the largest information gain as the main feature;

[0016] The identified features are divided into a systematic hierarchy, with the first level recording the main features of the device;

[0017] According to the specific operation data of the equipment, the subsequent layer structure is evaluated for in-depth information gain and feature classification is expanded, and the main features are further refined to identify specific performance indicators, and the specific performance indicators are filled into the subsequent layers as refined features;

[0018] Determine and construct the decision tree structure based on the feature hierarchy division, specifically:

[0019] The first-level features are used as the root nodes of the decision tree;

[0020] Based on each main feature root node, select secondary features for splitting in turn, and recursively construct the child nodes of each node. Each node represents a different performance indicator of the node on the previous layer, until all feature levels are expressed and the construction is completed;

[0021] Mark nodes without child nodes as leaf nodes, and leaf nodes store the performance status of devices;

[0022] A decision tree is established by comparing all devices in the device set M, which is marked as a decision tree set.

[0023] Preferably, the performing feature clustering analysis on the decision tree structure, merging similar features into feature groups, generating new synthetic features based on the feature groups, and performing adaptive structural adjustment on the decision tree specifically includes:

[0024] Obtain a decision tree set, and evaluate the complexity of the decision trees in the decision tree set based on the scale complexity measurement algorithm and leaf node distribution;

[0025] The above decision tree complexity evaluation calculation expression is:

[0026]

[0027] In the formula, C(T i ) is the complexity evaluation value of the ith decision tree, n is the total number of decision tree sets, m is the number of subtrees of the ith decision tree, L(Tc j ) is the number of leaf nodes in the jth subtree, Ltotal is the total number of child nodes, σ j 2 is the variance of the number of nodes at each level in the jth subtree, c is the number of feature categories, and p k is the proportion of the kth feature category in the leaf node;

[0028] Set a complexity adjustment threshold, filter out decision trees whose complexity calculation results exceed the complexity adjustment threshold, and establish a complex decision tree set V based on the screening results;

[0029] Perform feature similarity analysis on the decision trees in the complex decision tree set V, and identify the similarity between the features by calculating the Pearson correlation coefficient between the features;

[0030] The K-means clustering algorithm is used for iterative calculation to reduce the feature dimension of each complex decision tree and divide similar features into multiple cluster groups;

[0031] Taking feature similarity as weight, perform weighted aggregation on the clustering results in each feature clustering group to generate new synthetic features;

[0032] The information gain of the new synthetic features is re-evaluated, and the decision tree structure is adaptively adjusted according to the order of information gain.

[0033] Preferably, the initial weight of the importance of the feature in the node is set, and an online learning algorithm is used to dynamically adjust the importance weight of the feature according to real-time data feedback, specifically including:

[0034] The information gain calculation result corresponding to each node feature in the decision tree is used as the initial weight of the feature's importance;

[0035] Real-time monitoring and comparison of running devices in the device set M, obtaining real-time running data of the running devices, inputting the real-time running data of the devices into the decision tree, and obtaining the prediction results of the performance status of the devices;

[0036] By comparing the deviation between the current equipment performance state and the expected performance state, the contribution feedback of different features to the state deviation is quantified, and the contribution deviation feedback value of each feature is calculated. The specific expression is:

[0037]

[0038] In the formula, Δω z is the contribution bias feedback value of the z-th feature, η is the learning rate, is the difference between the actual equipment performance status y and the expected performance status Deviation quantization value, is the model prediction output For the zth feature Xz Sensitivity;

[0039] Among them, the feature sensitivity value is set based on the proportion of the initial weight of the feature's importance to the cumulative value of the initial weights of all feature importances;

[0040] Based on the feature contribution deviation results fed back in real time, the importance weights of the corresponding features are dynamically adjusted according to the contribution deviation ratio and scale.

[0041] Preferably, the step of acquiring the real-time operation data of the device to be compared and selecting the optimal feature data comparison scheme based on the feature weights of the decision path nodes of each decision tree specifically includes:

[0042] Obtain the real-time operation data of the device to be compared, input the real-time operation data into all decision trees in the decision tree set, and compare and analyze the real-time operation data with the nodes in the decision tree based on the node features and splitting rules in the decision tree;

[0043] For a given device D to be compared, after inputting the real-time operation data of the device, its decision path set is PD = {PD1…PD r …PD m}, where PD r The decision path determined for the rth decision tree;

[0044] Extract the importance weights of the features of the nodes passed by each decision path in the decision path set, calculate the cumulative value of the feature importance weights of each decision path, select and record the decision path with the largest cumulative weight value as the optimal decision path, and mark the feature expression set corresponding to the nodes passed by the optimal path as the optimal feature data comparison scheme of device D.

[0045] Preferably, the dynamically deleting redundant nodes of the decision tree based on the selection of the historical optimal feature data comparison scheme specifically includes:

[0046] Set the decision tree node adjustment time window size, and obtain the historical optimal decision path set of each decision tree record in the decision tree set in the previous time window of each adjustment time window;

[0047] The optimal decision path nodes of the decision tree are overlapped and reproduced, the number of times the historical optimal decision path passes through each node is marked as the number of times the node is active, and the minimum threshold for the number of times the node is active is set;

[0048] Nodes whose active times are less than the minimum active times threshold are pruned, and the feature information corresponding to the nodes is deleted.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] Perform feature clustering analysis on the decision tree structure, merge similar features into feature groups, generate new synthetic features based on feature groups, reduce redundant features, and thus reduce the complexity of the decision tree, while improving the generalization ability of the model when facing different device data. Set the initial weight of the importance of features in the node, use an online learning algorithm, and dynamically adjust the importance weight of features based on real-time data feedback to avoid the model from relying on outdated features, thereby reducing the risk of overfitting. Based on the feature weights of the decision path nodes of each decision tree, select the optimal feature data comparison scheme to ensure that the features compared each time are the most relevant features under the current device status, thereby improving the accuracy of the comparison. Based on the selection of the historical optimal feature data comparison scheme, dynamically delete redundant nodes of the decision tree to ensure that the model maintains the simplest structure and improve the computational efficiency of the model.

[0051] A decision tree-based device feature data comparison and extraction method is implemented to efficiently extract and compare device data through adaptive feature selection and real-time feedback mechanism, so as to quickly identify performance differences and potential faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A flow chart of a device feature data comparison and extraction method based on a decision tree of the present invention;

[0053] Figure 2 The invention performs hierarchical processing on device features, screens out the main factors affecting device performance, and constructs a hierarchical decision tree structure flow chart;

[0054] Figure 3 The present invention performs feature clustering analysis on the decision tree structure, merges similar features into feature groups, generates new synthetic features based on the feature groups, and performs adaptive structural adjustment on the decision tree.

[0055] Figure 4 The flow chart of setting the initial weight of the importance of features in a node of the present invention, using an online learning algorithm, and dynamically adjusting the importance weight of features according to real-time data feedback;

[0056] Figure 5 A flowchart of the present invention for obtaining the real-time operation data of the device to be compared and selecting the optimal feature data comparison scheme based on the feature weights of the decision path nodes of each decision tree;

[0057] Figure 6 The present invention is a flow chart for dynamically deleting redundant nodes of a decision tree based on the selection of the historical optimal feature data comparison scheme. DETAILED DESCRIPTION

[0058] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0059] Reference Figure 1 As shown, a device feature data comparison and extraction method based on a decision tree includes:

[0060] Perform hierarchical processing on equipment features, screen out the main factors affecting equipment performance, and build a hierarchical decision tree structure;

[0061] Perform feature clustering analysis on the decision tree structure, merge similar features into feature groups, generate new synthetic features based on the feature groups, and perform adaptive structural adjustments on the decision tree;

[0062] Set the initial importance weight of the features in the node, and use an online learning algorithm to dynamically adjust the importance weight of the features based on real-time data feedback;

[0063] Obtain the real-time operation data of the equipment to be compared, and select the optimal feature data comparison scheme based on the feature weights of the decision path nodes of each decision tree;

[0064] Based on the selection of the historical optimal feature data comparison scheme, redundant nodes of the decision tree are dynamically deleted.

[0065] Reference Figure 2 As shown in the figure, the device features are processed in layers, the main factors affecting the device performance are screened out, and the hierarchical decision tree structure is constructed, which specifically includes:

[0066] Get the comparison device set M;

[0067] Perform statistical analysis on the historical operation data of the equipment in the equipment set M, screen out the main factors affecting the equipment performance, and establish the corresponding relationship between the equipment and its main feature set;

[0068] Among them, the main feature uses the information gain algorithm to evaluate all the main factor features that affect the performance of the equipment, and selects the feature with the largest information gain as the main feature;

[0069] The information gain evaluation expression is:

[0070]

[0071] In the formula, IG(T,A) is the information gain evaluation value of feature A, H(T) is the entropy of data set T, and T q is the subset divided according to the feature A value q;

[0072] The identified features are divided into a systematic hierarchy, with the first level recording the main features of the device;

[0073] According to the specific operation data of the equipment, the subsequent layer structure is evaluated for in-depth information gain and feature classification is expanded, and the main features are further refined to identify specific performance indicators, and the specific performance indicators are filled into the subsequent layers as refined features;

[0074] This approach ensures that each step of the selection is made on the basis of maximizing information, thereby improving the effectiveness of the decision tree;

[0075] Determine and construct the decision tree structure based on the feature hierarchy division, specifically:

[0076] The first-level features are used as the root nodes of the decision tree;

[0077] Based on each main feature root node, select secondary features for splitting in turn, and recursively construct the child nodes of each node. Each node represents a different performance indicator of the node on the previous layer until all feature levels are expressed and the construction is completed. For example, if the root node is temperature (T), the child nodes can be further refined based on different temperature ranges (such as low temperature, medium temperature, and high temperature). These child nodes may include the performance of the equipment under different temperature conditions, such as load (L), energy consumption (P), and efficiency (E).

[0078] Nodes without child nodes are marked as leaf nodes. Leaf nodes store the performance status of the device. When recursively constructing child nodes, the data set is continuously split into multiple subsets until the preset stopping conditions are reached, such as reaching the maximum depth, insufficient number of samples, or information gain tending to zero.

[0079] Each node split is based on the value range of the current feature, and the priority of the split is determined according to the influence of each feature.

[0080] A decision tree is established by comparing all devices in the device set M, which is marked as a decision tree set.

[0081] Reference Figure 3 As shown in the figure, feature clustering analysis is performed on the decision tree structure, similar features are merged into feature groups, new synthetic features are generated based on the feature groups, and adaptive structural adjustments are made to the decision tree, specifically including:

[0082] Obtain a decision tree set, and evaluate the complexity of the decision trees in the decision tree set based on the scale complexity measurement algorithm and leaf node distribution;

[0083] The above decision tree complexity evaluation calculation expression is:

[0084]

[0085] In the formula, C(T i) is the complexity evaluation value of the ith decision tree, n is the total number of decision tree sets, m is the number of subtrees of the ith decision tree, L(Tc j ) is the number of leaf nodes in the jth subtree, L total is the total number of child nodes, σ j 2 is the variance of the number of nodes at each level in the jth subtree, c is the number of feature categories, and p k is the proportion of the kth feature category in the leaf node;

[0086] Set a complexity adjustment threshold, filter out decision trees whose complexity calculation results exceed the complexity adjustment threshold, and establish a complex decision tree set V based on the screening results;

[0087] Perform feature similarity analysis on the decision trees in the complex decision tree set V. By calculating the Pearson correlation coefficient between the features, the similarity between the features can be identified. By calculating the Pearson correlation coefficient, the similarity between the features can be quantified. A value close to 1 indicates a positive correlation, and a value close to -1 indicates a negative correlation.

[0088] The K-means clustering algorithm is used for iterative calculation to reduce the feature dimension of each complex decision tree and divide similar features into multiple clustering groups. The K-means clustering algorithm expression is:

[0089]

[0090] In the formula, e is the number of clusters, X l Indicates that it belongs to cluster C l The characteristics of μ i The optimal clustering scheme for the features is finally determined through continuous iterative calculations as the cluster center;

[0091] Taking feature similarity as weight, the clustering results in each feature clustering group are weighted and summarized to generate new synthetic features, which can comprehensively reflect the performance of the device;

[0092] The information gain of the new synthetic features is re-evaluated, and the decision tree structure is adaptively adjusted according to the order of information gain.

[0093] Through feature clustering analysis, the complexity of device features is effectively reduced and feature redundancy is reduced. Through similar feature analysis, clustering and synthesis of new features, the generated synthetic features show good discrimination ability in the decision tree model, enhancing the interpretability and computational efficiency of the model.

[0094] Reference Figure 4As shown in the figure, the initial weight of the importance of the features in the node is set, and the online learning algorithm is used to dynamically adjust the importance weight of the features according to real-time data feedback. Specifically, it includes:

[0095] The information gain calculation result corresponding to each node feature in the decision tree is used as the initial weight of the feature's importance;

[0096] Real-time monitoring and comparison of running devices in the device set M, obtaining real-time running data of the running devices, inputting the real-time running data of the devices into the decision tree, and obtaining the prediction results of the performance status of the devices;

[0097] By comparing the deviation between the current equipment performance state and the expected performance state, the contribution feedback of different features to the state deviation is quantified, and the contribution deviation feedback value of each feature is calculated. The specific expression is:

[0098]

[0099] In the formula, Δω z is the contribution bias feedback value of the z-th feature, η is the learning rate, is the difference between the actual equipment performance status y and the expected performance status Deviation quantization value, is the model prediction output For the zth feature X z Sensitivity;

[0100] Among them, the feature sensitivity value is set based on the proportion of the initial weight of the feature's importance to the cumulative value of the initial weights of all feature importances;

[0101] Based on the feature contribution deviation results fed back in real time, the importance weights of the corresponding features are dynamically adjusted at the same scale according to the contribution deviation ratio. The adjustment of the weights can be regarded as the model correcting its cognition of the device through learning, so as to better adapt to the new device status.

[0102] Real-time feedback processing is not a one-time process. As the device continues to run and data continues to come in, the model will continue to fine-tune the weights of each feature. This process is dynamic, ensuring that the model can still accurately predict device performance when device data is constantly changing.

[0103] Reference Figure 5 As shown, the real-time operation data of the device to be compared is obtained, and based on the feature weights of the decision path nodes of each decision tree, the optimal feature data comparison scheme is selected, which specifically includes:

[0104] The real-time operation data of the device to be compared is obtained, and the real-time operation data is input into all decision trees in the decision tree set. Based on the node characteristics and splitting rules in the decision tree, the real-time operation data is compared and analyzed with the nodes in the decision tree. During the analysis process, each node on the path will be split according to the characteristic value of the input data. By comparing the characteristic value and the splitting point, the decision path of the data flow is determined.

[0105] For a given device D to be compared, after inputting the real-time operation data of the device, its decision path set is PD = {PD1…PD r …PD m}, where PD r The decision path determined for the rth decision tree;

[0106] Extract the importance weights of the features of the nodes passed by each decision path in the decision path set, calculate the cumulative value of the feature importance weights of each decision path, select and record the decision path with the largest cumulative weight value as the optimal decision path, and mark the feature expression set corresponding to the nodes passed by the optimal path as the optimal feature data comparison scheme of device D.

[0107] This process achieves efficient analysis of equipment operation data and selects the most representative feature set in the comparison of each equipment feature data, improving the accuracy and real-time performance of the comparison analysis. Through dynamic feedback and optimization, the decision tree structure can be continuously adjusted and improved to ensure the accuracy and efficiency of the comparison process.

[0108] Reference Figure 6 As shown in the figure, based on the selection of the historical optimal feature data comparison scheme, the dynamic deletion of redundant nodes of the decision tree specifically includes:

[0109] Set the decision tree node to adjust the time window size. The time window can be set according to actual business needs, for example, every hour, every day, or every week. The size of the time window will affect the calculation frequency of the historical optimal decision path and the optimization frequency of the decision tree. The time window setting can be fixed or dynamically adjusted according to model performance. When the model performance (such as prediction accuracy or operating efficiency) fluctuates, the time window can be shortened or extended accordingly to adapt to the needs of business changes.

[0110] In each new time window, the historical optimal decision path in the previous time window is reproduced. By comparing the nodes of each historical optimal path, it is possible to determine which nodes appear repeatedly in multiple time windows or multiple decision trees.

[0111] The optimal decision path nodes of the decision tree are overlapped and reproduced, and the number of times the historical optimal decision path passes through each node is marked as the number of active times of the node. The more times a node appears, the greater its contribution to the overall prediction of the model. The minimum active times threshold of the node is set. Usually, the threshold can be dynamically adjusted according to the actual application scenario and model complexity. For example, if the model operation efficiency is prioritized, a higher threshold can be set to increase the pruning intensity; if the model prediction accuracy is prioritized, a lower threshold can be set to retain more nodes.

[0112] Nodes whose active times are less than the minimum active times threshold are pruned, and the feature information corresponding to the nodes is deleted. The purpose of node pruning is to reduce the complexity of the model and remove redundant or inefficient split nodes to improve the computational efficiency of the model. The pruning operation will directly remove nodes from the decision tree and adjust the structure of the tree. Deleting features can not only reduce the dimension of the model, but also avoid the interference of redundant features on the model prediction process. During the pruning process, important feature nodes are guaranteed not to be affected to ensure that the prediction performance of the model is not weakened.

[0113] Furthermore, the present solution also proposes a storage medium for a device feature data comparison and extraction method based on a decision tree, on which a computer-readable program is stored. When the computer-readable program is called, the above-mentioned device feature data comparison and extraction method based on a decision tree is executed.

[0114] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0115] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A device feature data comparison and extraction method based on a decision tree, characterized in that: include: Perform hierarchical processing on equipment features, screen out the main factors affecting equipment performance, and build a hierarchical decision tree structure; Perform feature clustering analysis on the decision tree structure, merge similar features into feature groups, generate new synthetic features based on the feature groups, and perform adaptive structural adjustments on the decision tree; Set the initial importance weight of the features in the node, and use an online learning algorithm to dynamically adjust the importance weight of the features based on real-time data feedback; Obtain the real-time operation data of the equipment to be compared, and select the optimal feature data comparison scheme based on the feature weights of the decision path nodes of each decision tree; Based on the selection of the historical optimal feature data comparison scheme, redundant nodes of the decision tree are dynamically deleted.

2. The device feature data comparison and extraction method based on decision tree according to claim 1 is characterized in that: The hierarchical processing of device features, screening out the main factors affecting device performance, and constructing a hierarchical decision tree structure specifically includes: Get the comparison device set M; Perform statistical analysis on the historical operation data of the equipment in the equipment set M, screen out the main factors affecting the equipment performance, and establish the corresponding relationship between the equipment and its main feature set; Among them, the main feature uses the information gain algorithm to evaluate all the main factor features that affect the performance of the equipment, and selects the feature with the largest information gain as the main feature; The identified features are divided into a systematic hierarchy, with the first level recording the main features of the device; According to the specific operation data of the equipment, the subsequent layer structure is evaluated for in-depth information gain and feature classification is expanded, and the main features are further refined to identify specific performance indicators, and the specific performance indicators are filled into the subsequent layers as refined features; Determine and construct the decision tree structure based on the feature hierarchy division, specifically: The first-level features are used as the root nodes of the decision tree; Based on each main feature root node, select secondary features for splitting in turn, and recursively construct the child nodes of each node. Each node represents a different performance indicator of the node on the previous layer, until all feature levels are expressed and the construction is completed; Mark nodes without child nodes as leaf nodes, and leaf nodes store the performance status of devices; A decision tree is established by comparing all devices in the device set M, which is marked as a decision tree set.

3. The device feature data comparison and extraction method based on decision tree according to claim 2 is characterized in that: The feature clustering analysis of the decision tree structure, merging similar features into feature groups, generating new synthetic features based on the feature groups, and adaptively adjusting the decision tree structure specifically include: Obtain a decision tree set, and evaluate the complexity of the decision trees in the decision tree set based on the scale complexity measurement algorithm and leaf node distribution; The above decision tree complexity evaluation calculation expression is: In the formula, C(T i ) is the complexity evaluation value of the ith decision tree, n is the total number of decision tree sets, m is the number of subtrees of the ith decision tree, L(Tc j ) is the number of leaf nodes in the jth subtree, L total is the total number of child nodes, σ j 2 is the variance of the number of nodes at each level in the jth subtree, c is the number of feature categories, and p k is the proportion of the kth feature category in the leaf node; Set a complexity adjustment threshold, filter out decision trees whose complexity calculation results exceed the complexity adjustment threshold, and establish a complex decision tree set V based on the screening results; Perform feature similarity analysis on the decision trees in the complex decision tree set V, and identify the similarity between the features by calculating the Pearson correlation coefficient between the features; The K-means clustering algorithm is used for iterative calculation to reduce the feature dimension of each complex decision tree and divide similar features into multiple cluster groups; Taking feature similarity as weight, perform weighted aggregation on the clustering results in each feature clustering group to generate new synthetic features; The information gain of the new synthetic features is re-evaluated, and the decision tree structure is adaptively adjusted according to the order of information gain.

4. The device feature data comparison and extraction method based on decision tree according to claim 3 is characterized in that: The initial weight of the importance of the feature in the node is set, and the online learning algorithm is used to dynamically adjust the importance weight of the feature according to real-time data feedback. Specifically, the following steps are performed: The information gain calculation result corresponding to each node feature in the decision tree is used as the initial weight of the feature's importance; Real-time monitoring and comparison of running devices in the device set M, obtaining real-time running data of the running devices, inputting the real-time running data of the devices into the decision tree, and obtaining the prediction results of the performance status of the devices; By comparing the deviation between the current equipment performance state and the expected performance state, the contribution feedback of different features to the state deviation is quantified, and the contribution deviation feedback value of each feature is calculated. The specific expression is: In the formula, Δω z is the contribution bias feedback value of the z-th feature, η is the learning rate, is the difference between the actual equipment performance status y and the expected performance status Deviation quantization value, is the model prediction output For the zth feature X z Sensitivity; Among them, the feature sensitivity value is set based on the proportion of the initial weight of the feature's importance to the cumulative value of the initial weights of all feature importances; Based on the feature contribution deviation results fed back in real time, the importance weights of the corresponding features are dynamically adjusted according to the contribution deviation ratio and scale.

5. The device feature data comparison and extraction method based on decision tree according to claim 4 is characterized in that: The step of obtaining the real-time operation data of the device to be compared and selecting the optimal feature data comparison scheme based on the feature weights of the decision path nodes of each decision tree specifically includes: Obtain the real-time operation data of the device to be compared, input the real-time operation data into all decision trees in the decision tree set, and compare and analyze the real-time operation data with the nodes in the decision tree based on the node features and splitting rules in the decision tree; For a given device D to be compared, after inputting the real-time operation data of the device, its decision path set is PD = {PD1…PD r …PD m }, where PD r The decision path determined for the rth decision tree; Extract the importance weights of the features of the nodes passed by each decision path in the decision path set, calculate the cumulative value of the feature importance weights of each decision path, select and record the decision path with the largest cumulative weight value as the optimal decision path, and mark the feature expression set corresponding to the nodes passed by the optimal path as the optimal feature data comparison scheme of device D.

6. The device feature data comparison and extraction method based on decision tree according to claim 5 is characterized in that: The dynamically deleting redundant nodes of the decision tree based on the selection of the historical optimal feature data comparison scheme specifically includes: Set the decision tree node adjustment time window size, and obtain the historical optimal decision path set of each decision tree record in the decision tree set in the previous time window of each adjustment time window; The optimal decision path nodes of the decision tree are overlapped and reproduced, the number of times the historical optimal decision path passes through each node is marked as the number of times the node is active, and the minimum threshold for the number of times the node is active is set; Nodes whose active times are less than the minimum active times threshold are pruned, and the feature information corresponding to the nodes is deleted.

Images