Protection net anomaly detection system and method

Abstract

The invention relates to the technical field of protection net anomaly detection, in particular to a protection net anomaly detection system and method, which comprises a three-dimensional display unit, a first early warning unit, a second early warning unit, a real-time alarm unit, an image acquisition unit and a defect classification unit, and further comprises a model construction unit, a detection unit and a processing unit, the model building unit is used for performing three-dimensional modeling on a target protective net through a three-dimensional modeling technology to obtain a three-dimensional model of the target protective net, and transmitting the three-dimensional model of the target protective net to the region matching unit and the three-dimensional display unit. The state monitoring unit and the early warning unit are used for obtaining the state data of the multiple positions of the target protective net in real time, early warning is carried out according to the preset state threshold table, and the real-time performance can help to find abnormal conditions possibly existing in the protective net in time.

Description

Technical Field

[0001] The present invention relates to the technical field of protection net anomaly detection, and in particular to a protection net anomaly detection system and method. Background Art

[0002] Protective nets usually refer to mesh structures or barriers used for safety purposes. Protective nets are often used in industrial facilities, construction sites, stadiums and other places to prevent people or objects from accidentally falling or entering dangerous areas, and to protect the safety of workers and the public.

[0003] Traditional systems usually rely on manual inspections and monitoring. Operators need to regularly check the status of the protective net. The monitoring of traditional systems often relies on the subjective judgment and experience of operators, which may lead to misjudgment or omission of minor abnormalities or hidden defects. Traditional systems usually provide status updates in the form of regular inspections or reports. Therefore, it may take a long time to be discovered and reported after a problem occurs. Summary of the invention

[0004] The purpose of the present invention is to propose a protection net abnormality detection system and method in view of the problems existing in the background technology.

[0005] The technical solution of the present invention is a protection net abnormality detection system, comprising a three-dimensional display unit, a first early warning unit, a second early warning unit, a real-time alarm unit, an image acquisition unit and a defect classification unit, and also comprising:

[0006] A model building unit, the model building unit is used to perform three-dimensional modeling on the target protection net by using a three-dimensional modeling technology to obtain a three-dimensional model of the target protection net, and transmit the three-dimensional model of the target protection net to the area matching unit and the three-dimensional display unit;

[0007] A region matching unit, wherein the region matching unit receives the three-dimensional model of the target protection net transmitted by the model building unit, obtains a geographical map of the location of the target protection net, matches the geographical map with the three-dimensional model of the target protection net to obtain a region mapping table, and transmits the region mapping table to a three-dimensional display unit;

[0008] A status monitoring unit, wherein the status monitoring unit is used to set fixed monitoring points at multiple positions of the target protection net, and set sensor groups at the fixed monitoring points, and monitor the status of multiple positions of the target protection net through the sensor groups to obtain real-time status data of the multiple positions of the target protection net, the real-time status data including temperature data, humidity data and vibration data, and transmit the real-time status data of the multiple positions of the target protection net to the first early warning unit and the second early warning unit.

[0009] Preferably, the first early warning unit receives the real-time status data of multiple positions of the target protection net transmitted by the status monitoring unit, and matches the real-time status data of multiple positions of the target protection net with the status threshold table pre-stored in the database to obtain real-time early warning information of multiple positions of the target protection net, and transmits the real-time early warning information of multiple positions of the target protection net to the three-dimensional display unit and the real-time alarm unit.

[0010] Preferably, the second early warning unit receives the real-time status data of multiple positions of the target protection net transmitted by the status monitoring unit, and predicts the real-time risks of multiple positions of the target protection net through a trained risk prediction model to obtain multiple risk positions of the target protection net, and transmits the multiple risk positions of the target protection net to the three-dimensional display unit, the real-time alarm unit and the image acquisition unit.

[0011] Preferably, the image acquisition unit receives the multiple risk positions of the target protection net transmitted by the second early warning unit, and performs image acquisition on the multiple risk positions of the target protection net to obtain the target protection net image, and transmits the target protection net image to the defect classification unit.

[0012] Preferably, the defect classification unit receives the target protection net image transmitted by the image acquisition unit, and performs defect classification on the target protection net image through a trained defect classification model to obtain the defect type corresponding to the target protection net image, thereby obtaining the defect types corresponding to multiple risk positions of the target protection net, and transmitting the defect types corresponding to the multiple risk positions of the target protection net to the three-dimensional display unit and the real-time alarm unit.

[0013] Preferably, the three-dimensional display unit receives the three-dimensional model of the target protection net transmitted by the model building unit, the area mapping table transmitted by the area matching unit, the real-time warning information of multiple positions of the target protection net transmitted by the first warning unit, the multiple risk positions of the target protection net transmitted by the second warning unit, and the defect types corresponding to the multiple risk positions of the target protection net transmitted by the defect classification unit, and maps the real-time warning information of the multiple positions of the target protection net to the corresponding areas in the three-dimensional model of the target protection net according to the area mapping table, and displays the real-time warning information in the corresponding areas in the three-dimensional model of the target protection net, matches the multiple risk positions of the target protection net with the area mapping table to obtain the corresponding areas of the multiple risk positions of the target protection net in the three-dimensional model of the target protection net, and highlights the corresponding areas, and displays the defect types corresponding to the risk positions in the corresponding areas.

[0014] Preferably, the real-time alarm unit receives the real-time warning information of multiple positions of the target protection net transmitted by the first warning unit, the multiple risk positions of the target protection net transmitted by the second warning unit, and the defect types corresponding to the multiple risk positions of the target protection net transmitted by the defect classification unit, and issues abnormal alarms for the real-time warning information of multiple positions of the target protection net, the multiple risk positions of the target protection net and the corresponding defect types through the alarm device.

[0015] Preferably, the risk prediction model includes an encoding module, a state evolution perception module and a risk prediction module, the encoding module is used to encode the location information, temperature data, humidity data and vibration data of the target protection network to obtain a low-dimensional feature set, and embed and fuse the low-dimensional feature set to obtain a low-dimensional fusion feature, the state evolution perception module adopts a global recurrent memory network, and the global recurrent memory network is used to process the low-dimensional fusion features of the location information, temperature data, humidity data and vibration data of the target protection network to obtain a monitoring state representation of the target protection network, the risk prediction module is used to jointly calculate the weight of the current node based on the hidden layer states of all nodes before the current time step, and fuse the monitoring state representation of the target protection network based on the weight of the current node, and classify the fused monitoring state representation through a Sigmoid classifier to obtain multiple risk positions of the target protection network.

[0016] Preferably, the low-dimensional feature set expression is as follows:

[0017]

[0018] in, and Represent the low-dimensional features of location information, temperature data, humidity data, and vibration data, respectively. loc 、M tem 、M hum and M vib Respectively represent the embedding matrices of the location information, temperature data, humidity data, and vibration data to be learned, and Represents one-hot encoding of location information, temperature data, humidity data, and vibration data respectively;

[0019] The low-dimensional fusion feature expression is as follows:

[0020]

[0021] Among them, x i represents low-dimensional fusion features, ReLU represents activation function, W irepresents the potential impact parameter for measuring the effects of dependency and timing variation, b i represents the bias vector;

[0022] The expression of the monitoring state is as follows:

[0023]

[0024] in, represents the hidden state at the i-th time step, and Represent the cell states of the i-th and i-1-th time steps respectively, LSTM i Represents a global recurrent memory network.

[0025] Preferably, the defect classification model includes a feature extraction module and a feature measurement module, the feature extraction module includes 4 residual blocks, the residual blocks include a convolution layer, a BN layer and an activation function layer, after the target protection net image passes through the 4 residual blocks, a tensor feature map is obtained, and the tensor feature map is flattened to obtain a local descriptor set, the feature measurement module calculates the similarity between the local descriptor set and the feature aggregation pool, and compares the similarity between the two with a preset similarity threshold, if it is greater than the preset similarity threshold, the target protection net image is classified as the type of the corresponding template image in the feature aggregation pool.

[0026] Preferably, the local descriptor expression is as follows:

[0027] Ψ(Y)=(y1,...,y i ,...,y m );

[0028] Among them, Ψ(Y) represents the local descriptor set, y i Represents the i-th local descriptor of the tensor feature map.

[0029] The technical solution of the present invention is a protection net abnormality early warning method, which is applicable to the protection net abnormality detection system described above, comprising the following steps:

[0030] S1. Use 3D modeling technology to perform 3D modeling on the target protection network, obtain a 3D model of the target protection network, obtain a geographical map of the location of the target protection network, match the geographical map with the 3D model, and generate a regional mapping table;

[0031] S2. Set fixed monitoring points at multiple locations of the target protection network, set a sensor group at each monitoring point to monitor data such as temperature, humidity and vibration, obtain real-time status data of multiple locations of the target protection network, and match the real-time status data with a preset status threshold table to generate real-time warning information;

[0032] S3. Use the trained risk prediction model to predict the risk position of the target protection net, collect images of the risk position, obtain image data of the target protection net, and use the trained defect classification model to classify the images to obtain the defect type corresponding to each risk position;

[0033] S4. Map the real-time warning information to the corresponding three-dimensional model area for display, highlight the risk location, and issue an abnormal alarm through the alarm device.

[0034] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects:

[0035] 1. The present invention obtains the status data of multiple positions of the target protection net in real time through the status monitoring unit and the early warning unit, and issues early warnings according to the preset status threshold table. This real-time performance can help to timely discover possible abnormal conditions of the protection net, such as temperature, humidity or vibration abnormalities, as well as possible risk positions. The second early warning unit uses the trained risk prediction model to predict the positions where risks may exist, and transmits these positions to the three-dimensional display unit and the real-time alarm unit. The defect classification unit collects images and classifies defects at the risk positions, thereby further confirming the risk type.

[0036] 2. The present invention uses a three-dimensional display unit to utilize the three-dimensional model of the target protection net provided by the model building unit and the area mapping table provided by the area matching unit to accurately map the real-time warning information and risk locations to the corresponding three-dimensional model areas and highlight them. This display method helps the operator to intuitively understand the abnormal conditions and defect types of various parts of the protection net. The real-time alarm unit uses the alarm device to issue an abnormal alarm based on the received real-time warning information, risk location and defect type. This mechanism ensures that the operator can respond quickly and take necessary measures to prevent the problems of the protection net that may be caused by defects or risk locations from further deteriorating. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of the overall system flow in an embodiment of the present invention;

[0038] Figure 2 The figure is a flow chart of an overall method in one embodiment of the present invention.

[0039] Figure numerals: 1. Model building unit; 2. Region matching unit; 3. Three-dimensional display unit; 4. Status monitoring unit; 5. First warning unit; 6. Second warning unit; 7. Real-time alarm unit; 8. Image acquisition unit; 9. Defect classification unit. DETAILED DESCRIPTION

[0040] Embodiment 1, as Figure 1 As shown, a protective net abnormality detection system proposed by the present invention includes a three-dimensional display unit 3, a first warning unit 5, a second warning unit 6, a real-time alarm unit 7, an image acquisition unit 8 and a defect classification unit 9, and also includes:

[0041] The model building unit 1 is used to perform three-dimensional modeling on the target protection net by using a three-dimensional modeling technology to obtain a three-dimensional model of the target protection net, and transmit the three-dimensional model of the target protection net to the area matching unit 2 and the three-dimensional display unit 3;

[0042] The area matching unit 2 receives the three-dimensional model of the target protection net transmitted by the model building unit 1, obtains a geographical map of the location of the target protection net, matches the geographical map with the three-dimensional model of the target protection net to obtain an area mapping table, and transmits the area mapping table to the three-dimensional display unit 3;

[0043] The status monitoring unit 4 is used to set fixed monitoring points at multiple positions of the target protection net, set sensor groups at the fixed monitoring points, and monitor the status of multiple positions of the target protection net through the sensor groups to obtain real-time status data of multiple positions of the target protection net, the real-time status data includes temperature data, humidity data and vibration data, and transmit the real-time status data of multiple positions of the target protection net to the first early warning unit 5 and the second early warning unit 6.

[0044] In the present invention, three-dimensional modeling technology is the process of creating a three-dimensional model of an object or scene using computer software or tools. It is usually used in fields such as engineering, design, animation production and scientific research. The three-dimensional modeling technology is used to generate a three-dimensional model of a target protection network for subsequent analysis, design or display; a geographic map is a map that describes the geographical features, terrain and location of the earth's surface, and is used to display and analyze the geographical information of a specific area on the earth, such as roads, buildings, terrain, etc., so as to determine the specific geographical coordinates and environmental characteristics of the location of the target protection network; the area mapping table is a table or data structure that maps the three-dimensional data in the model to the actual geographic space. It contains the matching relationship between the three-dimensional model of the target protection network generated by the model building unit and the geographic map information. This mapping is to ensure that the three-dimensional model can accurately reflect the position and layout in the actual geographical environment; the sensor group refers to a collection of sensor devices installed at multiple locations of the target protection network. These sensors are used to monitor the status information of the target protection network, such as temperature, humidity and vibration.

[0045] In an optional embodiment, the first early warning unit 5 receives the real-time status data of multiple positions of the target protection net transmitted by the status monitoring unit 4, and matches the real-time status data of multiple positions of the target protection net with the status threshold table pre-stored in the database to obtain real-time early warning information of multiple positions of the target protection net, and transmits the real-time early warning information of multiple positions of the target protection net to the three-dimensional display unit 3 and the real-time alarm unit 7.

[0046] It should be noted that the status threshold table is a predefined database, which contains preset thresholds for different status parameters at various locations of the target protection network. These status parameters may include temperature, humidity, vibration intensity, etc., depending on the specific characteristics and environmental conditions that need to be monitored by the target protection network.

[0047] In an optional embodiment, the second early warning unit 6 receives the real-time status data of multiple positions of the target protection net transmitted by the status monitoring unit 4, and predicts the real-time risks of multiple positions of the target protection net through a trained risk prediction model to obtain multiple risk positions of the target protection net, and transmits the multiple risk positions of the target protection net to the three-dimensional display unit 3, the real-time alarm unit 7 and the image acquisition unit 8.

[0048] In an optional embodiment, the image acquisition unit 8 receives the multiple risk positions of the target protection net transmitted by the second early warning unit 6, and performs image acquisition on the multiple risk positions of the target protection net to obtain the target protection net image, and transmits the target protection net image to the defect classification unit 9.

[0049] In an optional embodiment, the defect classification unit 9 receives the target protection net image transmitted by the image acquisition unit 8, and performs defect classification on the target protection net image through a trained defect classification model to obtain the defect type corresponding to the target protection net image, thereby obtaining the defect types corresponding to multiple risk positions of the target protection net, and transmitting the defect types corresponding to multiple risk positions of the target protection net to the three-dimensional display unit 3 and the real-time alarm unit 7.

[0050] In an optional embodiment, the three-dimensional display unit 3 receives the three-dimensional model of the target protection net transmitted by the model building unit 1, the area mapping table transmitted by the area matching unit 2, the real-time warning information of multiple positions of the target protection net transmitted by the first warning unit 5, the multiple risk positions of the target protection net transmitted by the second warning unit 6, and the defect types corresponding to the multiple risk positions of the target protection net transmitted by the defect classification unit 9, and maps the real-time warning information of the multiple positions of the target protection net to the corresponding areas in the three-dimensional model of the target protection net according to the area mapping table, and displays the real-time warning information in the corresponding areas in the three-dimensional model of the target protection net, matches the multiple risk positions of the target protection net with the area mapping table to obtain the multiple risk positions of the target protection net in the corresponding areas in the three-dimensional model of the target protection net, and highlights them in the corresponding areas, and displays the defect types corresponding to the risk positions in the corresponding areas.

[0051] In an optional embodiment, the real-time alarm unit 7 receives the real-time warning information of multiple positions of the target protection net transmitted by the first warning unit 5, the multiple risk positions of the target protection net transmitted by the second warning unit 6, and the defect types corresponding to the multiple risk positions of the target protection net transmitted by the defect classification unit 9, and issues an abnormal alarm for the real-time warning information of multiple positions of the target protection net, the multiple risk positions of the target protection net and the corresponding defect types through the alarm device.

[0052] It should be noted that alarm equipment generally refers to equipment used to emit sound or visual signals. Its purpose is to alert operators or relevant personnel when the monitoring system detects abnormal or warning conditions so that necessary actions can be taken in time.

[0053] Embodiment 2: A protection net abnormality detection system proposed in the present invention, compared with embodiment 1, this embodiment also includes: a risk prediction model includes a coding module, a state evolution perception module and a risk prediction module, the coding module is used to encode the location information, temperature data, humidity data and vibration data of the target protection net to obtain a low-dimensional feature set, and embed and fuse the low-dimensional feature set to obtain a low-dimensional fusion feature, the state evolution perception module adopts a global recurrent memory network, and the global recurrent memory network is used to process the low-dimensional fusion features of the location information, temperature data, humidity data and vibration data of the target protection net to obtain a monitoring state representation of the target protection net, the risk prediction module is used to jointly calculate the weight of the current node based on the hidden layer states of all nodes before the current time step, and fuse the monitoring state representation of the target protection net based on the weight of the current node, and classify the fused monitoring state representation through the Sigmoid classifier to obtain multiple risk positions of the target protection net.

[0054] In this embodiment, the low-dimensional feature set is used to obtain the feature set after dimensionality reduction processing on the original data, which usually has higher information content and less redundancy; the global recurrent memory network is a neural network structure specially used to process sequence data, which can remember and utilize information of all past time steps, and helps to capture long-term dependencies and dynamic changes in the data; the Sigmoid classifier is a commonly used classifier, which is used to map input data to probability values ​​between 0 and 1, and is usually used for binary classification problems.

[0055] In an optional embodiment, the low-dimensional feature set expression is as follows:

[0056]

[0057] in, and Represent the low-dimensional features of location information, temperature data, humidity data, and vibration data, respectively. loc 、M tem 、M hum and M vib Respectively represent the embedding matrices of the location information, temperature data, humidity data, and vibration data to be learned, and Represents one-hot encoding of location information, temperature data, humidity data, and vibration data respectively;

[0058] The low-dimensional fusion feature expression is as follows:

[0059]

[0060] Among them, x i represents low-dimensional fusion features, ReLU represents activation function, W i represents the potential impact parameter for measuring the effects of dependency and timing variation, b i represents the bias vector;

[0061] The expression of monitoring status is as follows:

[0062]

[0063] in, represents the hidden state at the i-th time step, and Represent the cell states of the i-th and i-1-th time steps respectively, LSTM i Represents a global recurrent memory network.

[0064] In an optional embodiment, the defect classification model includes a feature extraction module and a feature measurement module. The feature extraction module includes 4 residual blocks. The residual blocks include a convolution layer, a BN layer and an activation function layer. After the target protection net image passes through the 4 residual blocks, a tensor feature map is obtained, and the tensor feature map is flattened to obtain a local descriptor set. The feature measurement module calculates the similarity between the local descriptor set and the feature aggregation pool, and compares the similarity between the two with a preset similarity threshold. If it is greater than the preset similarity threshold, the target protection net image is classified as the type of the template image in the corresponding feature aggregation pool.

[0065] It should be noted that the residual block is a commonly used building block in deep learning, which is used to solve the gradient disappearance and gradient explosion problems in deep neural network training; the convolution layer is one of the core layers in deep learning, which is used to extract spatial features in the input image or feature map; the BN layer is used to normalize the input of each layer during the deep neural network training process, which helps to speed up the training and enhance the generalization ability of the model; the flattening operation converts the multi-dimensional tensor feature map into a one-dimensional vector so that it can be input into the subsequent fully connected layer or other classifiers; the feature pool refers to a feature template library used to aggregate and store known defect types, which is used to calculate the similarity with the local descriptor of the image to be classified; in the feature measurement module, the local descriptor set is calculated for similarity with the template in the feature pool, and commonly used methods include Euclidean distance, cosine similarity, etc.; the preset similarity threshold is a pre-defined boundary used to determine whether the similarity between the local descriptor of the image to be classified and the template in the feature pool is high enough, so as to determine the classification type of the image.

[0066] In an optional embodiment, the local descriptor expression is as follows:

[0067] Ψ(Y)=(y1,...,y i ,...,y m );

[0068] Among them, Ψ(Y) represents the local descriptor set, y i Represents the i-th local descriptor of the tensor feature map.

[0069] Embodiment three, as Figure 2 As shown, a protection net abnormality early warning method proposed by the present invention is applicable to the protection net abnormality detection system described above, and comprises the following steps:

[0070] S1. Use 3D modeling technology to perform 3D modeling on the target protection network, obtain a 3D model of the target protection network, obtain a geographical map of the location of the target protection network, match the geographical map with the 3D model, and generate a regional mapping table;

[0071] S2. Set fixed monitoring points at multiple locations of the target protection network, set a sensor group at each monitoring point to monitor data such as temperature, humidity and vibration, obtain real-time status data of multiple locations of the target protection network, and match the real-time status data with a preset status threshold table to generate real-time warning information;

[0072] S3. Use the trained risk prediction model to predict the risk position of the target protection net, collect images of the risk position, obtain image data of the target protection net, and use the trained defect classification model to classify the images to obtain the defect type corresponding to each risk position;

[0073] S4. Map the real-time warning information to the corresponding three-dimensional model area for display, highlight the risk location, and issue an abnormal alarm through the alarm device.

[0074] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto, and various changes can be made within the knowledge scope of technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A protection net abnormality detection system, comprising a three-dimensional display unit (3), a first early warning unit (5), a second early warning unit (6), a real-time alarm unit (7), an image acquisition unit (8) and a defect classification unit (9), Features: A model building unit (1), the model building unit (1) is used to perform three-dimensional modeling on the target protection net by using a three-dimensional modeling technology to obtain a three-dimensional model of the target protection net, and transmit the three-dimensional model of the target protection net to a region matching unit (2) and a three-dimensional display unit (3); A region matching unit (2), wherein the region matching unit (2) receives the three-dimensional model of the target protection net transmitted by the model building unit (1), obtains a geographical map of the location of the target protection net, matches the geographical map with the three-dimensional model of the target protection net to obtain a region mapping table, and transmits the region mapping table to a three-dimensional display unit (3); A status monitoring unit (4), the status monitoring unit (4) is used to set fixed monitoring points at multiple positions of the target protection net, set sensor groups at the fixed monitoring points, and monitor the status of multiple positions of the target protection net through the sensor groups to obtain real-time status data of the multiple positions of the target protection net, the real-time status data including temperature data, humidity data and vibration data, and transmit the real-time status data of the multiple positions of the target protection net to a first early warning unit (5) and a second early warning unit (6).

2. A protective net abnormality detection system according to claim 1, It is characterized in that The first warning unit (5) receives the real-time status data of the multiple positions of the target protection net transmitted by the status monitoring unit (4), matches the real-time status data of the multiple positions of the target protection net with the status threshold table pre-stored in the database to obtain real-time warning information of the multiple positions of the target protection net, and transmits the real-time warning information of the multiple positions of the target protection net to the three-dimensional display unit (3) and the real-time alarm unit (7); The second early warning unit (6) receives the real-time status data of the multiple positions of the target protection net transmitted by the status monitoring unit (4), and predicts the real-time risks of the multiple positions of the target protection net through the trained risk prediction model to obtain the multiple risk positions of the target protection net, and transmits the multiple risk positions of the target protection net to the three-dimensional display unit (3), the real-time alarm unit (7) and the image acquisition unit (8).

3. A protection net abnormality detection system according to claim 2, It is characterized in that The image acquisition unit (8) receives the multiple risk positions of the target protection net transmitted by the second early warning unit (6), and performs image acquisition on the multiple risk positions of the target protection net to obtain an image of the target protection net, and transmits the image of the target protection net to the defect classification unit (9); The defect classification unit (9) receives the target protection net image transmitted by the image acquisition unit (8), and classifies the target protection net image by using a trained defect classification model to obtain the defect type corresponding to the target protection net image, thereby obtaining the defect types corresponding to multiple risk positions of the target protection net, and transmitting the defect types corresponding to the multiple risk positions of the target protection net to the three-dimensional display unit (3) and the real-time alarm unit (7).

4. A protection net abnormality detection system according to claim 3, It is characterized in that The three-dimensional display unit (3) receives the three-dimensional model of the target protection net transmitted by the model building unit (1), the area mapping table transmitted by the area matching unit (2), the real-time warning information of multiple positions of the target protection net transmitted by the first warning unit (5), the multiple risk positions of the target protection net transmitted by the second warning unit (6), and the defect types corresponding to the multiple risk positions of the target protection net transmitted by the defect classification unit (9), and maps the real-time warning information of the multiple positions of the target protection net to the corresponding areas in the three-dimensional model of the target protection net according to the area mapping table, and displays the real-time warning information in the corresponding areas in the three-dimensional model of the target protection net, matches the multiple risk positions of the target protection net with the area mapping table to obtain the corresponding areas of the multiple risk positions of the target protection net in the three-dimensional model of the target protection net, and highlights the corresponding areas, and displays the defect types corresponding to the risk positions in the corresponding areas; The real-time alarm unit (7) receives the real-time warning information of multiple positions of the target protection net transmitted by the first warning unit (5), the multiple risk positions of the target protection net transmitted by the second warning unit (6), and the defect types corresponding to the multiple risk positions of the target protection net transmitted by the defect classification unit (9), and issues an abnormal alarm for the real-time warning information of multiple positions of the target protection net, the multiple risk positions of the target protection net and the corresponding defect types through the alarm device.

5. A protection net abnormality detection system according to claim 2, It is characterized in that The risk prediction model includes an encoding module, a state evolution perception module and a risk prediction module. The encoding module is used to encode the location information, temperature data, humidity data and vibration data of the target protection network to obtain a low-dimensional feature set, and embed and fuse the low-dimensional feature set to obtain a low-dimensional fusion feature. The state evolution perception module adopts a global recurrent memory network, and the global recurrent memory network is used to process the low-dimensional fusion features of the location information, temperature data, humidity data and vibration data of the target protection network to obtain the monitoring state representation of the target protection network. The risk prediction module is used to jointly calculate the weight of the current node based on the hidden layer states of all nodes before the current time step, and fuse the monitoring state representation of the target protection network based on the weight of the current node, and classify the fused monitoring state representation through a Sigmoid classifier to obtain multiple risk positions of the target protection network.

6. A protection net abnormality detection system according to claim 5, It is characterized in that The low-dimensional feature set expression is as follows: in, and Represent the low-dimensional features of location information, temperature data, humidity data, and vibration data, respectively. loc 、M tem 、M hum and M vib Respectively represent the embedding matrices of the location information, temperature data, humidity data, and vibration data to be learned, and Represents one-hot encoding of location information, temperature data, humidity data, and vibration data respectively; The low-dimensional fusion feature expression is as follows: Among them, x i represents low-dimensional fusion features, ReLU represents activation function, W i represents the potential impact parameter for measuring the effects of dependency and timing variation, b i represents the bias vector; The expression of the monitoring state is as follows: Among them, H i v represents the hidden state at the i-th time step, and Represent the cell states of the i-th and i-1-th time steps respectively, LSTM i Represents a global recurrent memory network.

7. A protection net abnormality detection system according to claim 3, It is characterized in that The defect classification model includes a feature extraction module and a feature measurement module. The feature extraction module includes 4 residual blocks. The residual blocks include a convolution layer, a BN layer and an activation function layer. After the target protection net image passes through the 4 residual blocks, a tensor feature map is obtained, and the tensor feature map is flattened to obtain a local descriptor set. The feature measurement module calculates the similarity between the local descriptor set and the feature aggregation pool, and compares the similarity between the two with a preset similarity threshold. If it is greater than the preset similarity threshold, the target protection net image is classified as the type of the corresponding template image in the feature aggregation pool.

8. A protection net abnormality detection system according to claim 7, It is characterized in that The local descriptor expression is as follows: Ψ(Y)=(y 1 ,...,and i ,...,and m ); Among them, Ψ(Y) represents the local descriptor set, y i Represents the i-th local descriptor of the tensor feature map.

9. A protection net abnormality early warning method, which is applicable to a protection net abnormality detection system according to any one of claims 1 to 8, It is characterized in that The following steps are involved: S1. Use 3D modeling technology to perform 3D modeling on the target protection network, obtain a 3D model of the target protection network, obtain a geographical map of the location of the target protection network, match the geographical map with the 3D model, and generate a regional mapping table; S2. Set fixed monitoring points at multiple locations of the target protection network, set a sensor group at each monitoring point to monitor data such as temperature, humidity and vibration, obtain real-time status data of multiple locations of the target protection network, and match the real-time status data with a preset status threshold table to generate real-time warning information; S3. Use the trained risk prediction model to predict the risk position of the target protection net, collect images of the risk position, obtain image data of the target protection net, and use the trained defect classification model to classify the images to obtain the defect type corresponding to each risk position; S4. Map the real-time warning information to the corresponding three-dimensional model area for display, highlight the risk location, and issue an abnormal alarm through the alarm device.

Images