Silo structure deformation monitoring and health assessment system

Abstract

The embodiment of the invention relates to the field of silo structure deformation monitoring, in particular to a silo structure deformation monitoring and health assessment system. A specific implementation mode of the system comprises a strain sensor assembly, a temperature and humidity sensor assembly, an inclination sensor assembly, a data acquisition unit and a data processing unit, the temperature and humidity sensor assemblies are arranged at the top and the bottom of the silo; the inclination sensor assemblies are arranged on the top and the bottom of the silo; the data acquisition unit is in communication connection with each strain sensor in the strain sensor assembly, each temperature and humidity sensor in the temperature and humidity sensor assembly and each inclination sensor in the inclination sensor assembly. The data processing unit is in communication connection with the data acquisition unit. According to the implementation mode, the safety of the silo can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of silo structure deformation monitoring, and specifically to a silo structure deformation monitoring and health assessment system. Background Art

[0002] Silo structures are widely used in grain storage, chemical raw material storage and other fields. Due to the long-term influence of the external environment, such as temperature changes, corrosion, load, etc., silo structures are prone to deformation, corrosion, local buckling and other problems, which may lead to structural failure in severe cases. Relying on traditional sensors, there are problems such as low accuracy, susceptibility to environmental interference, and large signal transmission loss, which makes it difficult to meet the long-term and high-precision monitoring needs of silo structures. Therefore, the development of an efficient and stable structural health monitoring system has become a current research hotspot. At present, when monitoring the deformation of silo structures, the commonly used method is to use fiber grating sensors. Fiber grating sensors have gradually become a research hotspot in the field of structural health monitoring due to their small size, anti-electromagnetic interference, corrosion resistance, and easy distributed measurement.

[0003] However, it is found in practice that when the above method is used to monitor the deformation of silo structure, the following technical problems often occur:

[0004] Fiber Bragg grating sensors have the problem of wavelength cross-sensitivity, making it difficult to accurately distinguish displacement from strain. In addition, how to achieve simultaneous monitoring of multiple parameters (strain, displacement, tilt) and how to extract effective features for damage identification are still technical problems that need to be solved. Summary of the invention

[0005] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present application propose a silo structure deformation monitoring and health assessment system to solve one or more of the technical problems mentioned in the above background technology section.

[0007] Some embodiments of the present application provide a silo structure deformation monitoring and health assessment system, which includes: a strain sensor assembly, a temperature and humidity sensor assembly, an inclination sensor assembly, a data acquisition unit, and a data processing unit. Among them, the above-mentioned strain sensor assembly is arranged on the silo wall, silo bottom, and support structure. Among them, there is a certain distance between each strain sensor in the above-mentioned strain sensor assembly, and the strain sensors in the above-mentioned strain sensor assembly are fiber Bragg grating sensors; the above-mentioned temperature and humidity sensor assembly is arranged on the top and bottom of the silo. Among them, there is a certain distance between each temperature and humidity sensor in the above-mentioned temperature and humidity sensor assembly, and the temperature and humidity sensors in the above-mentioned temperature and humidity sensor assembly are fiber Bragg grating sensors; the above-mentioned inclination sensor assembly is arranged on the top and bottom of the silo. Among them, there is a certain distance between each inclination sensor in the above-mentioned inclination sensor assembly, and the inclination sensors in the above-mentioned inclination sensor assembly are fiber Bragg grating sensors; the above-mentioned data acquisition unit is respectively communicatively connected to each strain sensor in the above-mentioned strain sensor assembly, each temperature and humidity sensor in the above-mentioned temperature and humidity sensor assembly, and each inclination sensor in the above-mentioned inclination sensor assembly; the above-mentioned data processing unit is communicatively connected to the above-mentioned data acquisition unit.

[0008] Optionally, the above-mentioned silo structure deformation monitoring and health assessment system further includes: an optical cable; the above-mentioned data acquisition unit includes: a communication interface assembly; at least one communication interface in the communication interface assembly included in the above-mentioned data acquisition unit is communicatively connected to each strain sensor in the above-mentioned strain sensor assembly through the optical cable; at least one communication interface in the communication interface assembly included in the above-mentioned data acquisition unit is communicatively connected to each inclination sensor in the above-mentioned inclination sensor assembly through the optical cable; at least one communication interface in the communication interface assembly included in the above-mentioned data acquisition unit is communicatively connected to each temperature and humidity sensor in the above-mentioned temperature and humidity sensor assembly through the optical cable; the above-mentioned data processing unit is communicatively connected to the above-mentioned data acquisition unit through the optical cable.

[0009] Optionally, the above strain sensor assembly is configured to: collect silo strain information and send the silo strain information to the above data acquisition unit; the above temperature and humidity sensor assembly is configured to: collect silo temperature and humidity information and send the silo temperature and humidity information to the above data acquisition unit; the above tilt sensor assembly is configured to: collect silo tilt angle information and send the silo tilt angle information to the above data acquisition unit; the above data acquisition unit is configured to: in response to receiving the silo strain information, the silo temperature and humidity information, and the silo tilt angle information, send the silo strain information, the silo temperature and humidity information, and the silo tilt angle information to the data processing unit; the above data processing unit is configured to: preprocess the silo strain information, the silo temperature and humidity information, and the silo tilt angle information respectively to obtain silo strain filtered information, silo temperature and humidity filtered information, and silo tilt filtered information; perform feature extraction processing on the silo strain filtered information, the silo temperature and humidity filtered information, and the silo tilt filtered information respectively to obtain silo strain feature information, silo corrosion feature information, and silo tilt feature information; input the silo strain feature information, silo corrosion feature information, and silo tilt feature information into a pre-trained silo anomaly recognition model to obtain silo anomaly recognition information.

[0010] Optionally, the above data processing unit is further configured to: perform filtering processing on the silo strain information to obtain silo strain filtered information; perform interpolation processing on the silo strain filtered information to obtain silo strain filtered information; perform filtering processing on the silo temperature and humidity information to obtain silo temperature and humidity filtered information; perform interpolation processing on the silo temperature and humidity filtered information to obtain silo temperature and humidity filtered information; perform filtering processing on the silo tilt angle information to obtain silo tilt filtered information; perform interpolation processing on the silo tilt filtered information to obtain silo tilt filtered information.

[0011] Optionally, the above data processing unit is further configured to: collect an initial strain sensor information set; generate initial strain sensor installation position information; optimize the initial strain sensor installation position information based on the initial strain sensor information set to obtain optimized strain sensor installation position information; send the optimized strain sensor installation position information to the strain sensor installation control terminal to adjust the installation positions of the respective strain sensors in the strain sensor assembly.

[0012] Optionally, the above data processing unit is further configured to: obtain a sample silo information set, where the sample silo information in the sample silo information set includes: sample silo strain characteristic information, sample silo corrosion characteristic information, sample silo inclination characteristic information, and sample silo anomaly information; select target sample silo information from the sample silo information set and perform the following training steps: input the sample silo strain characteristic information, sample silo corrosion characteristic information, and sample silo inclination characteristic information included in the target sample silo information into the spatial feature extraction sub-model included in the initial silo anomaly recognition model to obtain initial silo spatial feature information, where the initial semantic feature extraction model further includes: a time feature extraction sub-model; input the initial silo spatial feature information into the time feature extraction sub-model included in the initial silo anomaly recognition model to obtain initial silo time feature information; based on a preset loss function, determine the anomaly recognition accuracy value of the sample silo anomaly information and the initial silo time feature information included in the target sample silo information; in response to determining that the anomaly recognition accuracy value is less than the target threshold, determine the initial silo anomaly recognition model as the silo anomaly recognition model.

[0013] Optionally, the above data processing unit is further configured to: in response to determining that the anomaly recognition accuracy value is greater than or equal to the target threshold, adjust the relevant parameters in the initial silo anomaly recognition model, determine the adjusted initial silo anomaly recognition model as the initial silo anomaly recognition model, and select target sample silo information from each unselected sample silo information in the sample silo information set for re-executing the above training steps.

[0014] The above-mentioned various embodiments of the present application have the following beneficial effects: Through the silo structure deformation monitoring and health assessment system of some embodiments of the present application, the safety of the silo can be improved. Specifically, the reasons for the reduction of the safety of the silo are as follows: The fiber Bragg grating sensor has a problem of wavelength cross-sensitivity, making it difficult to accurately distinguish displacement and strain. In addition, how to achieve simultaneous monitoring of multiple parameters (strain, displacement, tilt) and how to extract effective features for damage identification are still technical problems to be solved urgently. Based on this, the silo structure deformation monitoring and health assessment system of some embodiments of the present application includes: a strain sensor assembly, a temperature and humidity sensor assembly, a tilt sensor assembly, a data acquisition unit, and a data processing unit. Among them, the above-mentioned strain sensor assembly is arranged on the silo wall, silo bottom, and support structure. Among them, the various strain sensors in the above-mentioned strain sensor assembly are spaced apart by a certain distance, and the strain sensors in the above-mentioned strain sensor assembly are fiber Bragg grating sensors. The above-mentioned temperature and humidity sensor assembly is arranged on the top and bottom of the silo. Among them, the various temperature and humidity sensors in the above-mentioned temperature and humidity sensor assembly are spaced apart by a certain distance, and the temperature and humidity sensors in the above-mentioned temperature and humidity sensor assembly are fiber Bragg grating sensors. The above-mentioned tilt sensor assembly is arranged on the top and bottom of the silo. Among them, the various tilt sensors in the above-mentioned tilt sensor assembly are spaced apart by a certain distance, and the tilt sensors in the above-mentioned tilt sensor assembly are fiber Bragg grating sensors. The above-mentioned data acquisition unit is respectively communicatively connected to each strain sensor in the above-mentioned strain sensor assembly, each temperature and humidity sensor in the above-mentioned temperature and humidity sensor assembly, and each tilt sensor in the above-mentioned tilt sensor assembly. The above-mentioned data processing unit is communicatively connected to the above-mentioned data acquisition unit. Therefore, some silo structure deformation monitoring and health assessment systems of the present application can monitor with high precision: By optimizing the design of fiber Bragg grating sensors and signal processing algorithms, high-precision monitoring of silo structure deformation is achieved. Multi-parameter monitoring: It can simultaneously monitor multiple parameters such as strain, displacement, and tilt to ensure the comprehensiveness and accuracy of data. Intelligent evaluation: Through a deep learning model, dynamic prediction and real-time monitoring of the structural health status are achieved, improving the intelligent level of the monitoring system. Durability and stability: Durable and corrosion-resistant packaging materials and packaging technologies are adopted to ensure the long-term stable operation of the sensors in harsh environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the various embodiments of the present application will become more obvious. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0016] Figure 1 is a schematic structural diagram of some embodiments of the silo structure deformation monitoring and health assessment system according to the present application;

[0017] Figure 2 It is a schematic diagram of the sensor arrangement according to some embodiments of the silo structure deformation monitoring and health assessment system of the present application;

[0018] Figure 3 It is a schematic diagram of the overall framework of the silo structure deformation monitoring system according to some embodiments of the silo structure deformation monitoring and health assessment system of the present application;

[0019] Figure 4 It is a schematic diagram of the generation process of the silo anomaly identification model according to some embodiments of the silo structure deformation monitoring and health assessment system of the present application. Detailed implementation manners

[0020] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not used to limit the protection scope of the present application.

[0021] In addition, it should be noted that only parts related to the relevant invention are shown in the drawings for the sake of convenience of description. Without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0022] It should be noted that the concepts such as "first" and "second" mentioned in the present application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence relationship of the functions performed by these devices, modules or units.

[0023] It should be noted that the modifications of "one" and "multiple" mentioned in the present application are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0024] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0025] The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0026] Figure 1FIG. 100 is a schematic structural diagram showing some embodiments of a silo structure deformation monitoring and health assessment system according to the present application. In some embodiments, the silo structure deformation monitoring and health assessment system includes: a strain sensor assembly 101, a temperature and humidity sensor assembly 102, an inclination sensor assembly 103, a data acquisition unit 104, and a data processing unit 105. Among them, the above-mentioned strain sensor assembly 101 is arranged on the silo wall, the silo bottom, and the support structure. Among them, each strain sensor in the above-mentioned strain sensor assembly 101 is separated by a certain distance, and the strain sensors in the above-mentioned strain sensor assembly 101 can be fiber Bragg grating sensors. Specifically, each strain sensor in the above-mentioned strain sensor assembly 101 arranged on the silo wall can be arranged along the height direction of the silo wall. The strain sensors in the above-mentioned strain sensor assembly 101 can be strain sensors for measuring the strain change of the silo.

[0027] As an example, the above-mentioned certain distance can be 0.5 meters or 1 meter.

[0028] The above-mentioned temperature and humidity sensor assembly 102 is arranged on the top and bottom of the silo. Among them, each temperature and humidity sensor in the above-mentioned temperature and humidity sensor assembly 102 is separated by a certain distance, and the temperature and humidity sensors in the above-mentioned temperature and humidity sensor assembly 102 can be fiber Bragg grating sensors. Specifically, the temperature and humidity sensors in the above-mentioned temperature and humidity sensor assembly 102 can be sensors for measuring the temperature and humidity inside the silo.

[0029] The above-mentioned inclination sensor assembly 103 is arranged on the top and bottom of the silo. Among them, each inclination sensor in the above-mentioned inclination sensor assembly 103 is separated by a certain distance, and the inclination sensors in the above-mentioned inclination sensor assembly 103 can be fiber Bragg grating sensors. Among them, the inclination sensors in the above-mentioned inclination sensor assembly 103 can be inclination sensors for measuring the inclination angle of the silo.

[0030] The above-mentioned data acquisition unit 104 is respectively communicatively connected to each strain sensor in the above-mentioned strain sensor assembly 101, each temperature and humidity sensor in the above-mentioned temperature and humidity sensor assembly 102, and each inclination sensor in the above-mentioned inclination sensor assembly 103. Among them, the above-mentioned data acquisition unit can be a data collector for collecting sensor data.

[0031] The above-mentioned data processing unit 105 is communicatively connected to the above-mentioned data acquisition unit 104. Among them, the above-mentioned data processing unit 105 can be a device for processing the sensor data collected by the above-mentioned data acquisition unit.

[0032] As an example, the above-mentioned data processing unit 105 can be a CPU (Central Processing Unit).

[0033] Specifically, the installation positions of the above-mentioned strain sensor assembly 101, temperature and humidity sensor assembly 102, and tilt sensor assembly 103 in the silo can refer to Figure 2 the schematic diagram of sensor arrangement shown in some embodiments of the silo structure deformation monitoring and health assessment system according to the present application. As Figure 2 shown, each sensor can be installed at the top, bottom, and nodes of the silo wall in the silo.

[0034] Optionally, the above-mentioned silo structure deformation monitoring and health assessment system further includes: an optical cable 106. Among them, the above-mentioned optical cable 106 can be an optical cable for signal transmission. The above-mentioned data acquisition unit 104 includes: a communication interface component 1041. The communication interface in the above-mentioned communication interface component 1041 can be an interface for data transmission. At least one communication interface in the communication interface component 1041 included in the above-mentioned data acquisition unit 104 is communicatively connected to each strain sensor in the above-mentioned strain sensor assembly 101 through the optical cable 106. At least one communication interface in the communication interface component 1041 included in the above-mentioned data acquisition unit 104 is communicatively connected to each tilt sensor in the above-mentioned tilt sensor assembly 102 through the optical cable 106. At least one communication interface in the communication interface component 1041 included in the above-mentioned data acquisition unit 104 is communicatively connected to each temperature and humidity sensor in the above-mentioned temperature and humidity sensor assembly 103 through the optical cable 106. The above-mentioned data processing unit 104 is communicatively connected to the above-mentioned data acquisition unit 105 through the optical cable 106.

[0035] As an example, the communication interface in the above-mentioned communication interface component 1041 can be, but is not limited to, at least one of the following: RS485 communication interface, Ethernet communication interface, or fiber optic interface.

[0036] Thus, by flexibly selecting the transmission method according to the actual wiring scheme, a stable data transmission method can be realized to transmit data to the data center.

[0037] As an example, the operation process of the above-mentioned silo structure deformation monitoring and health assessment system can refer to Figure 3 the schematic diagram of the overall framework of the silo structure deformation monitoring system shown in some embodiments of the silo structure deformation monitoring and health assessment system according to the present application. As Figure 3As shown, the above-mentioned silo structure deformation monitoring and health assessment system can, firstly, prepare for monitoring, including selecting monitoring parameters and designing a sensor wiring scheme. Secondly, conduct sensor optimization, including selecting sensors, grating spectrum reconstruction, packaging technology, and fiber optic wiring protection. Then, build a silo structure monitoring system, including sensor installation, data acquisition device installation, data transmission, and data preprocessing. Next, conduct data analysis, including corrosion assessment, local buckling deformation assessment, and overall tilt change assessment. Finally, establish a health assessment model, including model selection, model training, threshold setting, and anomaly alarm.

[0038] Optionally, the above-mentioned strain sensor assembly 101 can be configured to: collect silo strain information and send the above-mentioned silo strain information to the above-mentioned data acquisition unit. Wherein, the above-mentioned silo strain information can characterize the strain forces at various positions in the silo where the strain sensor assembly 101 is arranged.

[0039] The above-mentioned temperature and humidity sensor assembly 102 can be configured to: collect silo temperature and humidity information and send the above-mentioned silo temperature and humidity information to the above-mentioned data acquisition unit. Wherein, the above-mentioned silo temperature and humidity information can characterize the temperature and humidity at various positions in the silo where the temperature and humidity sensor assembly 102 is arranged.

[0040] The above-mentioned tilt sensor assembly 103 can be configured to: collect silo tilt angle information and send the above-mentioned silo tilt angle information to the above-mentioned data acquisition unit. Wherein, the above-mentioned silo tilt angle information can characterize the tilt angles at various positions in the silo where the tilt sensor assembly 103 is arranged.

[0041] The above-mentioned data acquisition unit 104 can be configured to: in response to receiving the above-mentioned silo strain information, the above-mentioned silo temperature and humidity information, and the above-mentioned silo tilt angle information, send the above-mentioned silo strain information, the above-mentioned silo temperature and humidity information, and the above-mentioned silo tilt angle information to the data processing unit.

[0042] The above data processing unit 105 can be configured as follows: First, preprocess the above silo strain information, the above silo temperature and humidity information, and the above silo tilt angle information respectively to obtain silo strain filtering information, silo temperature and humidity filtering information, and silo tilt filtering information. Second, perform feature extraction processing on the above silo strain filtering information, the above silo temperature and humidity filtering information, and the above silo tilt filtering information respectively to obtain silo strain feature information, silo corrosion feature information, and silo tilt feature information. Then, input the above silo strain feature information, silo corrosion feature information, and silo tilt feature information into a pre-trained silo anomaly recognition model to obtain silo anomaly recognition information. Among them, the above silo strain filtering information, the above silo temperature and humidity filtering information, and the above silo tilt filtering information can be respectively subjected to feature extraction processing through a preset feature extraction algorithm to obtain silo strain feature information, silo corrosion feature information, and silo tilt feature information. The above pre-trained silo anomaly recognition model can be a pre-trained neural network model that takes silo strain feature information, silo corrosion feature information, and silo tilt feature information as inputs and silo anomaly recognition information as outputs.

[0043] As an example, the above preset feature extraction algorithm may include, but is not limited to, at least one of the following: relative corrosion degree calculation formula and LAMMPS (Large-scale Atomic / Molecular Massively Parallel Simulator) algorithm. The above silo anomaly recognition information may be, but is not limited to, at least one of the following: information indicating "the silo structure is deformed" or information indicating "the silo is healthy".

[0044] Thus, by analyzing the corrosion condition, local buckling deformation, and overall tilt change of the silo structure through data, the stability of the structure is evaluated. Extract corrosion-related parameters from the data of temperature sensors and humidity sensors, and calculate the corrosion rate and corrosion degree. Extract strain values from the data of strain sensors. Calculate the stress distribution and evaluate the local buckling deformation. Extract the tilt angle from the data of tilt sensors. Calculate the overall tilt change of the silo structure.

[0045] Optionally, the above data processing unit 105 can be further configured to perform the following steps:

[0046] In the first step, filter the above silo strain information to obtain silo strain filtered information. Among them, the above silo strain information can be filtered through a preset filtering algorithm to obtain silo strain filtered information.

[0047] As an example, the above preset filtering algorithm may be, but is not limited to, at least one of the following: Kalman filtering algorithm or wavelet transform algorithm.

[0048] In the second step, interpolate the above silo strain filtering information to obtain the silo strain filtering information. Specifically, the above silo strain filtering information can be interpolated through a preset interpolation algorithm to obtain the silo strain filtering information.

[0049] As an example, the above preset interpolation algorithm can be the Lagrange interpolation algorithm.

[0050] In the third step, filter the above silo temperature and humidity information to obtain the silo temperature and humidity filtering information. Specifically, the above silo temperature and humidity information can be filtered through the above preset filtering algorithm to obtain the silo temperature and humidity filtering information.

[0051] In the fourth step, interpolate the above silo temperature and humidity filtering information to obtain the silo temperature and humidity filtering information. Specifically, the above silo temperature and humidity filtering information can be interpolated through the above preset interpolation algorithm to obtain the silo temperature and humidity filtering information.

[0052] In the fifth step, filter the above silo tilt angle information to obtain the silo tilt filtering information. Specifically, the above silo tilt angle information can be filtered through the above preset filtering algorithm to obtain the silo tilt filtering information.

[0053] In the sixth step, interpolate the above silo tilt filtering information to obtain the silo tilt filtering information. Specifically, the above silo tilt filtering information can be interpolated through the above preset interpolation algorithm to obtain the silo tilt filtering information.

[0054] Optionally, the above data processing unit 105 can be further configured to perform the following steps:

[0055] In the first step, collect the initial strain sensor information set. Specifically, the initial strain sensor information can be collected from each strain sensor through wired or wireless connection to obtain the initial strain sensor information set. The initial strain sensor information in the above initial strain sensor information set can characterize the configuration information of a strain sensor.

[0056] It should be noted that the above wireless connection methods can include but are not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other currently known or future-developed wireless connection methods.

[0057] Step 2: Generate the initial installation position information of the strain sensors. Among them, the initial installation position information of the strain sensors can be randomly generated. The above-mentioned initial installation position information of the strain sensors can characterize the installation positions of the respective strain sensors in the silo (for example, the center of the top of the silo).

[0058] Step 3: Based on the above-mentioned initial strain sensor information set, perform optimization processing on the above-mentioned initial installation position information of the strain sensors to obtain the optimized installation position information of the strain sensors. Among them, based on the above-mentioned initial strain sensor information set, the above-mentioned initial installation position information of the strain sensors can be optimized through a preset optimization algorithm to obtain the optimized installation position information of the strain sensors.

[0059] As an example, the above-mentioned preset optimization algorithm can be a particle swarm algorithm.

[0060] Thus, optimization algorithms such as the particle swarm algorithm are used to automatically reconstruct and analyze the grating spectrum, extract eigenvalue and optimize the central wavelength, avoid wavelength overlap, and reduce the cross-sensitivity problem between displacement and strain. Select packaging materials with durability and corrosion resistance, and adopt reliable packaging technology to ensure the long-term stable operation of the sensor in harsh environments. Select high-quality fiber optic jumpers and connectors to minimize the optical signal transmission loss and improve the data transmission efficiency.

[0061] Step 4: Send the above-mentioned optimized installation position information of the strain sensors to the installation control terminal of the strain sensors to adjust the installation positions of the respective strain sensors in the strain sensor assembly. Among them, the above-mentioned installation control terminal of the strain sensors can be a terminal for installing the strain sensors.

[0062] Optionally, the above-mentioned data processing unit 105 can be further configured to perform the following steps:

[0063] Step 1: Obtain a sample silo information set. Among them, the sample silo information in the above-mentioned sample silo information set includes: sample silo strain characteristic information, sample silo corrosion characteristic information, sample silo tilt characteristic information, and sample silo anomaly information. Specifically, the sample silo information set can be obtained from a storage terminal. The above-mentioned storage terminal can be a terminal for storing the sample silo information set.

[0064] Step 2: Select target sample silo information from the above-mentioned sample silo information set and perform the following training sub-steps:

[0065] The first sub-step is to input the sample silo strain characteristic information, sample silo corrosion characteristic information, and sample silo tilt characteristic information included in the target sample silo information into the spatial feature extraction sub-model included in the initial silo anomaly recognition model to obtain the initial silo spatial feature information. Among them, the above initial semantic feature extraction model also includes: a time feature extraction sub-model. Among them, the sample silo information can be randomly selected from the above sample silo information set as the target sample silo information.

[0066] As an example, the above spatial feature extraction sub-model can be a CNN (Convolutional Neural Networks) model. The above time feature extraction sub-model can be an LSTM (Long Short-Term Memory) model.

[0067] The second sub-step is to input the initial silo spatial feature information into the time feature extraction sub-model included in the initial silo anomaly recognition model to obtain the initial silo time feature information.

[0068] The third sub-step is to determine the anomaly recognition accuracy value of the sample silo anomaly information included in the target sample silo information and the initial silo time feature information based on a preset loss function.

[0069] As an example, the above preset loss function can be but is not limited to one of the following: cross-entropy loss function, least squares function, or categorical cross-entropy loss function.

[0070] The fourth sub-step is to, in response to determining that the anomaly recognition accuracy value is less than the target threshold, determine the initial silo anomaly recognition model as the silo anomaly recognition model.

[0071] As an example, the above target threshold can be 0.01.

[0072] Optionally, the above data processing unit 105 can be further configured to: in response to determining that the anomaly recognition accuracy value is greater than or equal to the target threshold, adjust the relevant parameters in the initial silo anomaly recognition model, determine the adjusted initial silo anomaly recognition model as the initial silo anomaly recognition model, and select the target sample silo information from the sample silo information that has not been selected in the above sample silo information set for re-executing the above training steps. Among them, the relevant parameters in the initial silo anomaly recognition model can be adjusted through a preset adjustment algorithm. Then, the sample silo information can be randomly selected from the sample silo information that has not been selected in the above sample silo information set as the target sample silo information.

[0073] As an example, the above preset adjustment algorithm can be but is not limited to one of the following: backpropagation algorithm or stochastic gradient algorithm.

[0074] Therefore, historical monitoring data can be utilized to train a deep learning model based on the obtained data, optimize the model parameters, and improve the prediction accuracy. Corrosion, buckling deformation, and inclination thresholds are set, and when the monitoring value exceeds the threshold, an alarm is triggered and the abnormal data is recorded. A model combining CNN and LSTM (referred to as the CNN-LSTM model) is usually used to process data with spatial and temporal characteristics. For the corrosion, buckling deformation, and inclination changes of the silo structure, the spatially distributed data collected by sensors (such as strain distribution, corrosion distribution) can be used as the input of CNN to capture spatial characteristics; at the same time, LSTM is used to process the time series data (such as the inclination angle and strain value changing over time) to capture temporal characteristics.

[0075] As an example, the above process for determining the silo anomaly recognition model can refer to Figure 4 the schematic diagram of the generation process of the silo anomaly recognition model shown in some embodiments of the silo structure deformation monitoring and health assessment system according to the present application. As Figure 4 shown, the above data processing unit 105 can first perform data processing to divide the data into a training set and a test set. Then, the data in the training set is input into the CNN-LSTM model. Among them, the CNN part can successively be the convolutional layer 1, pooling layer 1, convolutional layer 2, and pooling layer 2. The LSTM part can successively be the input layer, hidden layer, fully connected layer, and output layer. Then, the prediction results output by the model are verified for accuracy together with the test set data. When the accuracy verification passes, the trained model is used as the silo anomaly recognition model. When the accuracy verification fails, the CNN-LSTM model is trained again.

[0076] The above-mentioned various embodiments of the present application have the following beneficial effects: Through the silo structure deformation monitoring and health assessment system of some embodiments of the present application, the safety of the silo can be improved. Specifically, the reasons for the reduction of the safety of the silo are as follows: The fiber Bragg grating sensor has a problem of wavelength cross-sensitivity, making it difficult to accurately distinguish displacement and strain. In addition, how to achieve simultaneous monitoring of multiple parameters (strain, displacement, tilt) and how to extract effective features for damage identification are still technical problems to be solved urgently. Based on this, the silo structure deformation monitoring and health assessment system of some embodiments of the present application includes: a strain sensor assembly, a temperature and humidity sensor assembly, a tilt sensor assembly, a data acquisition unit, and a data processing unit. Among them, the above-mentioned strain sensor assembly is arranged on the silo wall, silo bottom, and support structure. Among them, the various strain sensors in the above-mentioned strain sensor assembly are spaced apart by a certain distance, and the strain sensors in the above-mentioned strain sensor assembly are fiber Bragg grating sensors; the above-mentioned temperature and humidity sensor assembly is arranged on the top and bottom of the silo. Among them, the various temperature and humidity sensors in the above-mentioned temperature and humidity sensor assembly are spaced apart by a certain distance, and the temperature and humidity sensors in the above-mentioned temperature and humidity sensor assembly are fiber Bragg grating sensors; the above-mentioned tilt sensor assembly is arranged on the top and bottom of the silo. Among them, the various tilt sensors in the above-mentioned tilt sensor assembly are spaced apart by a certain distance, and the tilt sensors in the above-mentioned tilt sensor assembly are fiber Bragg grating sensors; the above-mentioned data acquisition unit is respectively communicatively connected to each strain sensor in the above-mentioned strain sensor assembly, each temperature and humidity sensor in the above-mentioned temperature and humidity sensor assembly, and each tilt sensor in the above-mentioned tilt sensor assembly; the above-mentioned data processing unit is communicatively connected to the above-mentioned data acquisition unit. Therefore, some silo structure deformation monitoring and health assessment systems of the present application can monitor with high precision: By optimizing the design of fiber Bragg grating sensors and signal processing algorithms, high-precision monitoring of silo structure deformation is achieved. Multi-parameter monitoring: It can simultaneously monitor multiple parameters such as strain, displacement, and tilt to ensure the comprehensiveness and accuracy of data. Intelligent evaluation: Through a deep learning model, dynamic prediction and real-time monitoring of the structural health status are achieved, improving the intelligent level of the monitoring system. Durability and stability: Durable and corrosion-resistant packaging materials and packaging technologies are used to ensure the long-term stable operation of the sensors in harsh environments.

[0077] The above-mentioned technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the above-mentioned technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0078] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A silo structure deformation monitoring and health assessment system, characterized in that: The silo structure deformation monitoring and health assessment system includes: a strain sensor assembly, a temperature and humidity sensor assembly, a tilt sensor assembly, a data acquisition unit and a data processing unit, wherein: The strain sensor assembly is arranged on the cylinder wall, cylinder bottom and supporting structure of the silo, wherein each strain sensor in the strain sensor assembly is spaced a certain distance apart, and the strain sensor in the strain sensor assembly is a fiber grating sensor; The temperature and humidity sensor assembly is arranged on the top and bottom of the silo, wherein each temperature and humidity sensor in the temperature and humidity sensor assembly is spaced a certain distance apart, and the temperature and humidity sensors in the temperature and humidity sensor assembly are fiber grating sensors; The tilt sensor assembly is arranged on the top and the bottom of the silo, wherein each tilt sensor in the tilt sensor assembly is spaced a certain distance apart, and the tilt sensors in the tilt sensor assembly are fiber grating sensors; The data acquisition unit is respectively connected to each strain sensor in the strain sensor assembly, each temperature and humidity sensor in the temperature and humidity sensor assembly, and each tilt sensor in the tilt sensor assembly; The data processing unit is communicatively connected with the data acquisition unit.

2. The silo structure deformation monitoring and health assessment system according to claim 1 is characterized in that: The silo structure deformation monitoring and health assessment system also includes: an optical cable; The data acquisition unit includes: a communication interface component; At least one communication interface in the communication interface assembly included in the data acquisition unit is communicatively connected to each strain sensor in the strain sensor assembly via an optical cable; At least one communication interface in the communication interface assembly included in the data acquisition unit is communicatively connected to each tilt sensor in the tilt sensor assembly via an optical cable; At least one communication interface in the communication interface assembly included in the data acquisition unit is communicatively connected to each temperature and humidity sensor in the temperature and humidity sensor assembly via an optical cable; The data processing unit is connected to the data acquisition unit via an optical cable.

3. The silo structure deformation monitoring and health assessment system according to claim 2 is characterized by: The strain sensor assembly is configured to: collect silo strain information, and send the silo strain information to the data acquisition unit; The temperature and humidity sensor assembly is configured to: collect silo temperature and humidity information, and send the silo temperature and humidity information to the data acquisition unit; The tilt sensor assembly is configured to: collect silo tilt angle information, and send the silo tilt angle information to the data acquisition unit; The data acquisition unit is configured to: in response to receiving the silo strain information, the silo temperature and humidity information, and the silo tilt angle information, send the silo strain information, the silo temperature and humidity information, and the silo tilt angle information to the data processing unit; The data processing unit is configured to: pre-process the silo strain information, the silo temperature and humidity information, and the silo tilt angle information, respectively, to obtain silo strain filtering information, silo temperature and humidity filtering information, and silo tilt filtering information; perform feature extraction processing on the silo strain filtering information, the silo temperature and humidity filtering information, and the silo tilt filtering information, respectively, to obtain silo strain feature information, silo corrosion feature information, and silo tilt feature information; input the silo strain feature information, silo corrosion feature information, and silo tilt feature information into a pre-trained silo anomaly recognition model to obtain silo anomaly recognition information.

4. The silo structure deformation monitoring and health assessment system according to claim 3 is characterized in that: The data processing unit is further configured to: Performing filtering processing on the silo strain information to obtain silo strain filtering information; Performing interpolation processing on the silo strain filtering information to obtain silo strain filtering information; Filtering the silo temperature and humidity information to obtain silo temperature and humidity filtering information; Interpolating the silo temperature and humidity filtering information to obtain silo temperature and humidity filtering information; Filtering the silo tilt angle information to obtain silo tilt filtering information; Interpolation processing is performed on the silo tilt filtering information to obtain silo tilt filtering information.

5. The silo structure deformation monitoring and health assessment system according to claim 3 is characterized in that: The data processing unit is further configured to: Collecting an initial strain sensor information set; Generate initial strain sensor installation position information; Based on the initial strain sensor information set, optimizing the initial strain sensor installation position information to obtain strain sensor installation position optimization information; The strain sensor installation position optimization information is sent to the strain sensor installation control terminal to adjust the installation position of each strain sensor in the strain sensor assembly.

Images