Intelligent online monitoring system and method for electromechanical installation

Abstract

The invention relates to the field of mechanical and electrical installation, and particularly discloses an intelligent online monitoring system and method for mechanical and electrical installation. Firstly, a pipeline image collected by a camera, supporting force data, collected by a pressure sensor, of a spring support and hanger on a pipeline at multiple preset time points and environment temperature values, collected by a temperature sensor, of the pipeline at the multiple preset time points are obtained, then feature extraction and correlation analysis are conducted on the three parts through the deep learning technology, and then the pipeline image, the supporting force data and the environment temperature values are obtained. And finally, whether thermal displacement of the pipeline occurs is judged through a classifier, so that real-time monitoring of the running state of the pipeline is achieved, the system can quickly respond to any potential abnormal condition or problem, the monitoring efficiency and accuracy of the pipeline system are improved, and safe running and long-term stability of the pipeline are guaranteed.

Description

Technical Field

[0001] The present application relates to the field of electromechanical installation, and more specifically, to an intelligent online monitoring system and method for electromechanical installation. Background Art

[0002] Mechanical and electrical installation is a key task that ensures the smooth installation, commissioning and operation of buildings and industrial facilities and equipment through mechanical, electrical and electronic technologies. This covers power systems, lighting, ventilation and air conditioning, water supply and drainage systems, and safety control systems, and is essential to ensure the normal operation of building functions.

[0003] In electromechanical installation, supports and hangers are a vital component. They are mainly used to constrain and control the movement and vibration of building components, especially in the installation of air conditioning and heating ducts, water pipes, steam pipes, cable trays and bus ducts. As a variable support, spring hangers can provide constant support force when the pipeline undergoes thermal displacement based on the principle of moment balance, avoid deformation of the pipeline due to thermal displacement, ensure the stability of the pipeline in the vertical direction, and not introduce additional stress.

[0004] However, in high temperature environments, the elastic modulus of spring supports and hangers decreases, which may lead to insufficient support force, thus affecting the stability of the pipeline. It is often difficult for workers to detect and adjust the support force of the supports and hangers in time, which leads to thermal displacement of the pipeline. Therefore, improvement measures need to be taken to cope with the impact of high temperature environments on the performance of spring supports and hangers, and ensure their ability to support pipelines stably in the long term.

[0005] Therefore, an intelligent online monitoring system and method for electromechanical installations is desired. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an intelligent online monitoring system and method for electromechanical installation, which first obtains the pipeline image collected by the camera, the supporting force data of the spring support bracket on the pipeline at multiple predetermined time points collected by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, and then uses deep learning technology to perform feature extraction and correlation analysis on the three, and finally uses a classifier to determine whether the pipeline has thermal displacement, thereby realizing real-time monitoring of the pipeline operation status, so that the system can quickly respond to any potential abnormal conditions or problems, thereby improving the monitoring efficiency and accuracy of the pipeline system, and ensuring the safe operation and long-term stability of the pipeline.

[0007] According to one aspect of the present application, there is provided an intelligent online monitoring system for electromechanical installation, comprising:

[0008] The electromechanical installation pipeline data acquisition module is used to acquire pipeline images acquired by the camera, supporting force data of the spring support and hanger on the pipeline at multiple predetermined time points acquired by the pressure sensor, and ambient temperature values ​​at multiple predetermined time points acquired by the temperature sensor;

[0009] The electromechanical installation pipeline data extraction module is used to extract the pipeline image displacement feature vector and the spring support force change correlation feature matrix from the pipeline image collected by the camera, the support force data of the spring support hanger on the pipeline at multiple predetermined time points collected by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor;

[0010] The pipeline thermal displacement judgment module is used to judge whether the pipeline has thermal displacement based on the pipeline image displacement feature vector and the spring support force change correlation feature matrix.

[0011] According to another aspect of the present application, there is provided an intelligent online monitoring method for electromechanical installation, comprising:

[0012] Acquire pipeline images collected by a camera, supporting force data of the spring hanger on the pipeline at multiple predetermined time points collected by a pressure sensor, and ambient temperature values ​​at multiple predetermined time points collected by a temperature sensor;

[0013] Extracting pipeline image displacement feature vectors and spring support force change correlation feature matrices from the pipeline image captured by the camera, the support force data of the spring support hanger on the pipeline at multiple predetermined time points captured by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points captured by the temperature sensor;

[0014] Based on the pipeline image displacement feature vector and the spring support force change correlation feature matrix, it is determined whether thermal displacement occurs in the pipeline.

[0015] Compared with the prior art, the present application provides an intelligent online monitoring system and method for electromechanical installation, which first obtains the pipeline image captured by the camera, the supporting force data of the spring support bracket on the pipeline at multiple predetermined time points captured by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points captured by the temperature sensor, and then uses deep learning technology to perform feature extraction and correlation analysis on the three, and finally uses a classifier to determine whether thermal displacement occurs in the pipeline, thereby realizing real-time monitoring of the pipeline operation status, allowing the system to quickly respond to any potential abnormal conditions or problems, thereby improving the monitoring efficiency and accuracy of the pipeline system, and ensuring the safe operation and long-term stability of the pipeline. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 4 is a block diagram of an intelligent online monitoring system for electromechanical installation according to an embodiment of the present application.

[0018] Figure 2 The block diagram is a data extraction module for electromechanical installation pipelines in an intelligent online monitoring system for electromechanical installations according to an embodiment of the present application.

[0019] Figure 3 4 is a block diagram of a pipeline thermal displacement judgment module in an intelligent online monitoring system for electromechanical installation according to an embodiment of the present application.

[0020] Figure 4 The figure is a flow chart of an intelligent online monitoring method for electromechanical installation according to an embodiment of the present application.

[0021] Figure 5 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0023] Figure 1 FIG. 1 is a block diagram of an intelligent online monitoring system for electromechanical installation according to an embodiment of the present application. Figure 1 As shown, according to an embodiment of the present application, an intelligent online monitoring system 100 for electromechanical installation includes: an electromechanical installation pipeline data acquisition module 110, which is used to acquire a pipeline image captured by a camera, supporting force data of a spring support and hanger on the pipeline at multiple predetermined time points captured by a pressure sensor, and ambient temperature values ​​at multiple predetermined time points captured by a temperature sensor; an electromechanical installation pipeline data extraction module 120, which is used to extract a pipeline image displacement feature vector and a spring supporting force change associated feature matrix from the pipeline image captured by the camera, the supporting force data of a spring support and hanger on the pipeline at multiple predetermined time points captured by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points captured by the temperature sensor; a pipeline thermal displacement judgment module 130, which is used to judge whether thermal displacement occurs in the pipeline based on the pipeline image displacement feature vector and the spring supporting force change associated feature matrix.

[0024] In the above-mentioned intelligent online monitoring system 100 for electromechanical installation, the electromechanical installation pipeline data acquisition module 110 is used to obtain the pipeline image collected by the camera, the supporting force data of the spring support and hanger on the pipeline at multiple predetermined time points collected by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor. It should be understood that electromechanical installation is a vital task, using mechanical, electrical and electronic technologies to ensure the smooth installation, commissioning and operation of buildings and industrial facilities and equipment. It covers multiple aspects such as power systems, lighting, ventilation and air conditioning, water supply and drainage systems, and safety control systems, and is crucial to ensure the normal operation of building functions. In the field of electromechanical installation, support and hanger are an indispensable component. Its main function is to constrain and control the movement and vibration of building components, especially in the installation of air conditioning and heating ducts, water pipes, steam pipes, cable trays and bus ducts. As an adjustable support and hanger, the spring support and hanger can provide a constant support force when the pipeline undergoes thermal displacement based on the principle of moment balance, effectively avoiding deformation of the pipeline due to thermal expansion, ensuring the stability of the pipeline in the vertical direction, and not introducing additional stress. Therefore, in the technical solution of the present application, by acquiring the pipeline image captured by the camera, the supporting force data of the spring support bracket on the pipeline at multiple predetermined time points collected by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, and combining with deep learning technology, it is determined whether the pipeline has thermal displacement, so as to ensure that the pipeline is efficiently monitored during operation, and potential problems are discovered and resolved in a timely manner, thereby improving the efficiency and accuracy of pipeline system monitoring and ensuring the safe operation and long-term stability of the pipeline.

[0025] Specifically, the pipeline image is collected by the camera to monitor the real-time status and possible abnormal conditions of the pipeline. By analyzing the image, the displacement, deformation or damage of the pipeline can be detected, and necessary maintenance measures can be discovered and taken in time to ensure the normal operation and long-term use of the equipment. The pressure sensor collects the supporting force data of the spring support on the pipeline. These data reflect the mechanical support of the pipeline at different time points, including the load distribution and structural stability of the pipeline. By monitoring the changes in the supporting force, the health status of the pipeline structure can be evaluated, possible structural problems can be predicted and repaired in time to avoid losses caused by equipment damage or shutdown. The ambient temperature data collected by the temperature sensor provides real-time information about the environment around the equipment. The ambient temperature has an important influence on the operating stability and material properties of electromechanical equipment. By monitoring the changes in the ambient temperature, the potential impact of possible temperature fluctuations on the operation of the equipment can be warned, the equipment operating parameters can be optimized, and the working efficiency and life of the equipment can be improved. By obtaining pipeline images, supporting force data and ambient temperature values, the intelligent online monitoring system can fully understand the operating status and environmental background of electromechanical equipment, discover potential problems in time and perform preventive maintenance, ensure the safe and reliable operation of the equipment, and improve the overall management efficiency and economy of the equipment.

[0026] In the above-mentioned intelligent online monitoring system 100 for electromechanical installation, the electromechanical installation pipeline data extraction module 120 is used to extract pipeline image displacement feature vectors and spring support force change correlation feature matrices from the pipeline image collected by the camera, the support force data of the spring hanger on the pipeline at multiple predetermined time points collected by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor. It should be understood that in this way, real-time monitoring and intelligent analysis of the electromechanical installation system can be effectively realized, the accuracy and efficiency of equipment management can be improved, and the safe operation and long-term stability of the equipment can be guaranteed.

[0027] Figure 2 FIG. 1 is a block diagram of a data extraction module for electromechanical installation pipelines in an intelligent online monitoring system for electromechanical installation according to an embodiment of the present application. Figure 2As shown, in a specific embodiment of the present application, the electromechanical installation pipeline data extraction module 120 includes: a pipeline image feature extraction unit 121, used to extract features from the pipeline image collected by the camera to obtain the pipeline image displacement feature vector; a support force data feature construction unit 122, used to construct the support force data of the spring support hanger on the pipeline at multiple predetermined time points collected by the pressure sensor and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor to obtain a spring support hanger support force input vector and a support force ambient temperature input vector; a support force data feature encoding unit 123, used to feature encode the spring support hanger support force input vector and the support force ambient temperature input vector to obtain the spring support force change correlation feature matrix.

[0028] It should be understood that as an important part of industrial equipment, the operating status of the pipeline system directly affects production efficiency and safety. The pipeline image captured by the camera contains real-time visual information of the pipeline, which can reflect the position, shape and potential physical deformation of the pipeline. Through feature extraction, representative numerical features can be extracted from the image, such as edge detection, texture analysis, color distribution, etc. These features can be used to describe the shape and structural state of the pipeline at different time points. By comparing and analyzing the displacement feature vectors at different time points, the movement pattern and change trend of the pipeline can be established to provide data support for preventive maintenance.

[0029] Furthermore, the supporting force data of the spring hanger on the pipeline collected by the pressure sensor and the ambient temperature value collected by the temperature sensor are constructed to comprehensively analyze the mechanical response and environmental impact of the pipeline system under different working conditions, thereby improving the safety, stability and efficiency of the equipment. Among them, the supporting force data of the spring hanger on the pipeline is collected in real time by the pressure sensor. These data record the pressure or supporting force of the hanger on the pipeline, reflecting the mechanical support of the pipeline structure under different loads. By constructing the supporting force input vector, these data can be integrated into numerical features, such as average supporting force, maximum / minimum supporting force, supporting force change rate, etc., so as to further analyze the bearing capacity and load distribution of the pipeline structure. Temperature changes will cause thermal expansion and contraction of pipeline materials, thereby affecting the morphological stability and supporting force distribution of the pipeline. Through the ambient temperature value collected by the temperature sensor, constructing the supporting force ambient temperature input vector can associate the temperature data with the supporting force data, and analyze the changing trend of the pipeline supporting force under different temperature conditions. This analysis helps to evaluate the stability of the pipeline in different seasons or operating conditions, optimize the design and installation plan of the hanger, and ensure the safe operation of the pipeline in various temperature environments.

[0030] Furthermore, feature encoding is performed on the spring support force input vector and the support force ambient temperature input vector, aiming to deeply understand the mechanical response and environmental impact of the pipeline system under different working conditions, so as to optimize the safety, stability and reliability of the equipment. The spring support force input vector contains the mechanical support data of the support on the pipeline collected by the pressure sensor. These data are converted into numerical features such as average support force, force distribution, and support force change rate through specific feature extraction and encoding techniques. These features can reflect the mechanical response of the pipeline under different workloads and help identify the stability and potential abnormal changes of the pipeline support state. The support force ambient temperature input vector is constructed based on the ambient temperature data collected by the temperature sensor. Temperature changes will affect the thermal expansion and contraction characteristics of the pipeline material, thereby affecting the morphological stability and support force distribution of the pipeline structure. Through feature encoding, the ambient temperature data is converted into the environmental background information of the pipeline support force, revealing the trend of the impact of temperature changes on the pipeline support force. This analysis helps to understand the structural changes of the pipeline under different temperature conditions, optimize the pipeline design and support configuration, and ensure the stability and safety of the pipeline under various environmental conditions.

[0031] In a specific embodiment of the present application, the pipeline image feature extraction unit 121 includes: passing the pipeline image captured by the camera through a pipeline image displacement convolutional neural network as a feature encoder to obtain a pipeline image displacement feature map; downsampling the pipeline image displacement feature map to obtain the pipeline image displacement feature vector.

[0032] It should be understood that as part of the critical infrastructure, the operating status of the pipeline system directly affects the safety and efficiency of industrial production. The pipeline images collected by the camera contain visual information of the pipeline at different time points, which reflects the position, shape and changes of the pipeline. As a feature encoder, the pipeline image displacement convolutional neural network can use deep learning technology to extract high-level abstract feature representations such as edges, textures, shapes, etc. from complex image data. These features can effectively describe the slight deformation and movement of the pipeline. The generation of pipeline image displacement feature maps is not limited to static analysis at a single time point, but to model and analyze the dynamic changes of the pipeline through time series pipeline image data. By training the neural network model, different types of pipeline deformation or structural problems can be identified, providing timely warnings and decision support for operation and maintenance personnel. This image analysis method based on deep learning not only improves the accuracy and efficiency of pipeline structure monitoring, but also provides new technical means for the maintenance and management of pipeline systems. Specifically, each layer of the pipeline image displacement convolutional neural network used as a feature encoder performs convolution processing, mean pooling processing based on the local feature matrix, and nonlinear activation processing on the input data in the forward transfer of the layer, so that the last layer of the pipeline image displacement convolutional neural network used as a feature encoder outputs the pipeline image displacement feature map, wherein the input of the pipeline image displacement convolutional neural network used as a feature encoder is the pipeline image captured by the camera.

[0033] Furthermore, the displacement feature maps of pipeline images are usually extracted through deep learning models such as convolutional neural networks. These feature maps may have high spatial resolution and dimensions, and contain rich image feature information, such as edges, textures, shape changes, etc. However, directly using the complete feature map for analysis will increase the complexity of calculation and storage, and may also introduce unnecessary redundant information. Downsampling can effectively reduce the dimension and data volume of the feature map while retaining the main feature information. Common downsampling methods include average pooling and maximum pooling, which can merge the values ​​of each region in the feature map or extract the most significant feature points without losing important information. For example, average pooling averages the values ​​of each region, while maximum pooling selects the maximum value in each region as a representative. These feature vectors can effectively summarize the deformation and motion state of the pipeline at different time points, providing basic data support for real-time monitoring and anomaly detection of the system. In addition, downsampling also helps to reduce computing costs and storage requirements, and improve the efficiency and response speed of the system when processing large-scale data.

[0034] In a specific embodiment of the present application, the support force data feature construction unit 122 includes: converting the support force data of the spring support bracket on the pipeline at multiple predetermined time points collected by the pressure sensor into the spring support bracket support force input vector; arranging the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor into the support force ambient temperature input vector.

[0035] It should be understood that the pressure sensor can accurately measure the support force or pressure of the spring hanger on the pipeline through real-time monitoring. This data is usually recorded in the form of a time series and may contain multiple measurement points at different locations or different hangers. Converting this data into a support force input vector means integrating the measurement results at each time point into a numerical vector, which may include statistical characteristics such as average support force, maximum / minimum support force, and rate of change of support force. This conversion makes the data easier to analyze and compare, which can help engineers quickly evaluate the load-bearing capacity and structural health of the pipeline system.

[0036] Furthermore, the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor are intended to analyze and understand the impact of ambient temperature on the support force of spring hangers, thereby optimizing the stability and reliability of the pipeline system. Ambient temperature is an important external factor in the operation of the pipeline system, and has a direct impact on the thermal expansion and contraction properties and elastic modulus of the pipeline material. Changes in temperature can cause slight changes in the size and shape of the pipeline material and its hangers, which in turn affects the distribution and stability of the support force. Therefore, by collecting and recording ambient temperature data at multiple time points and arranging them as input vectors, a working model of the pipeline system under different temperature conditions can be established. This data representation helps engineers and operators understand the structural response characteristics of the pipeline at different temperatures, such as the trend of support force changes and possible critical temperature points.

[0037] In a specific embodiment of the present application, the support force data feature encoding unit 123 includes: calculating the transfer matrix between the spring support hanger support force input vector and the support force ambient temperature input vector to obtain the support hanger support force change association matrix; passing the support hanger support force change association matrix through a support hanger support force change convolutional neural network model based on the use of mutually transposed convolution kernels to obtain the spring support force change association feature matrix.

[0038] It should be understood that the support force input vector contains the support force data of the spring hanger at different time points, while the ambient temperature input vector contains the ambient temperature data at the corresponding time points. By calculating the transfer matrix between the two, it is possible to reveal how the ambient temperature changes affect the change pattern of the support force of the hanger. Each element in the transfer matrix represents the contribution or correlation of the ambient temperature change to the support force change, which can help understand the actual impact of temperature changes on the pipeline structure.

[0039] Furthermore, the support force change correlation matrix of the hanger support force is transformed into a support force change convolutional neural network model based on the use of mutually transposed convolution kernels in order to deeply explore and understand the complex nonlinear relationship between the support force change and the ambient temperature, thereby improving the accurate monitoring and prediction capabilities of the pipeline system support structure. The support force change correlation matrix reflects the influence of ambient temperature changes on the support force of the hanger. Through convolutional neural networks, especially using mutually transposed convolution kernels (Transpose Convo l ut ion), features can be effectively extracted from these relationships. Mutually transposed convolution kernels allow the network to learn to back propagate in feature mapping, thereby obtaining more advanced feature expressions in the upper layer of the convolutional neural network, which is very helpful for modeling complex relationships. The support force change convolutional neural network model can extract temporal and spatial feature information from the time series support force change data. Through convolution and pooling operations, the network can capture the spatial pattern of support force changes (for example, the relationship between different hangers) and temporal dynamics (response pattern with ambient temperature changes), thereby effectively characterizing these complex correlation features. Specifically, each layer of the support and hanger support force variation convolutional neural network model based on the use of mutually transposed convolution kernels respectively performs the following on the input data in the forward transfer of the layer: performing convolution processing, pooling processing and nonlinear processing based on a first two-dimensional convolution kernel on the input data to obtain a first activation feature map; and performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed of each other; wherein the input of the first layer of the support and hanger support force variation convolutional neural network model based on the use of mutually transposed convolution kernels is the support and hanger support force variation association matrix, and the output of the last layer of the support and hanger support force variation convolutional neural network model based on the use of mutually transposed convolution kernels is the spring support force variation association feature matrix.

[0040] In a specific embodiment of the present application, the support and hanger support force change association matrix is ​​passed through a support and hanger support force change convolutional neural network model based on mutually transposed convolution kernels to obtain the spring support force change association feature matrix, including: each layer of the support and hanger support force change convolutional neural network model based on mutually transposed convolution kernels respectively performs the following on the input data in the forward transfer of the layer: performing convolution processing based on a first two-dimensional convolution kernel, pooling processing and nonlinear processing on the input data to obtain a first activation feature map; and performing convolution processing based on a second two-dimensional convolution kernel, pooling processing and nonlinear activation processing on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed of each other; wherein the input of the first layer of the support and hanger support force change convolutional neural network model based on mutually transposed convolution kernels is the support and hanger support force change association matrix, and the output of the last layer of the support and hanger support force change convolutional neural network model based on mutually transposed convolution kernels is the spring support force change association feature matrix.

[0041] It should be understood that supports and hangers play an important role in engineering structures, and their supporting force is affected by environmental factors such as temperature changes. The support force change association matrix of the support hanger reflects the change pattern of the supporting force of different supports and hangers at different temperatures. These data are usually represented in matrix form, with each row corresponding to a support hanger and each column corresponding to a time step or temperature point. The support force change model of the support hanger based on the convolutional neural network utilizes mutually transposed convolution kernels. This design allows specific feature extraction and processing during the forward transmission of the network to adapt to the processing requirements of time series data. In the first layer of the model, the support force change association matrix of the support hanger is used as input, and after convolution processing, pooling processing and nonlinear processing of the first two-dimensional convolution kernel, a first activation feature map is generated. These operations help to extract the spatial and temporal patterns in the support force change, such as the correlation between different supports and hangers and their response speed. Then, the first activation feature map obtained after the first layer of processing is used as the input of the next layer, and is again processed by convolution processing, pooling processing and nonlinear activation processing based on the second two-dimensional convolution kernel that is transposed to generate a second activation feature map. This process can further extract more advanced and abstract features, such as more complex spatiotemporal correlation patterns or the dynamic characteristics of the support force changes of the hangers at different temperatures. By using the hanger support force change convolutional neural network model based on mutually transposed convolution kernels, useful information can be effectively extracted from complex support force data, and deeper insights and optimization solutions can be provided for the structural health monitoring and operation and maintenance management of the pipeline system.

[0042] In the above-mentioned intelligent online monitoring system 100 for electromechanical installation, the pipeline thermal displacement judgment module 130 is used to judge whether the pipeline has thermal displacement based on the pipeline image displacement feature vector and the spring support force change correlation feature matrix. It should be understood that the pipeline image displacement feature vector provides visual information about the pipeline surface and the surrounding environment. These feature vectors can be extracted from the pipeline surface image by computer vision technology, including but not limited to displacement, deformation, cracks or deformation. This information reflects the changes that may occur on the outside of the pipeline under operating and environmental conditions, such as thermal expansion or contraction effects caused by temperature changes. The spring support force change correlation feature matrix provides the support force change pattern of the internal support structure of the pipeline. These patterns reflect the response of the pipeline support system under different temperatures or working conditions, such as the support force change trend and relative relationship of each support bracket. Through deep learning models or statistical analysis, key support force features can be extracted from these matrices for health monitoring and anomaly detection of pipeline structures. Combining the pipeline image displacement feature vector and the spring support force change correlation feature matrix can achieve a comprehensive evaluation of whether the pipeline has thermal displacement. Combined with the support force response data in the spring support force change correlation feature matrix, it can be inferred that this deformation may be caused by thermal displacement caused by temperature change. Especially in large-scale pipeline networks, this comprehensive analysis capability can help engineers quickly identify and locate potential problem areas and take preventive measures in advance to avoid possible equipment damage or system failure.

[0043] Figure 3 FIG. 1 is a block diagram of a pipeline thermal displacement judgment module in an intelligent online monitoring system for electromechanical installation according to an embodiment of the present application. Figure 3 As shown, in a specific embodiment of the present application, the pipeline thermal displacement judgment module 130 includes: a pipeline thermal displacement feature fusion unit 131, which is used to fuse the pipeline image displacement feature vector and the spring support force change correlation feature matrix to obtain a pipeline thermal displacement judgment classification feature vector; a pipeline thermal displacement feature fusion unit 132, which is used to perform local distribution balance correction on the pipeline thermal displacement judgment classification feature vector based on subclass label related metrics to obtain an optimized pipeline thermal displacement judgment classification feature vector; a pipeline thermal displacement judgment classification unit 133, which is used to pass the optimized pipeline thermal displacement judgment classification feature vector through a classifier to obtain a classification result, and the classification result is used to judge whether thermal displacement occurs in the pipeline.

[0044] It should be understood that fusing these two types of feature data into a pipeline thermal displacement judgment classification feature vector means taking advantage of multi-source data for comprehensive analysis and comprehensive judgment. For example, these feature vectors can be integrated and processed by machine learning models such as support vector machines (SVM) or deep learning models such as multi-layer perceptrons (MLP) to identify and classify the possibility of thermal displacement of the pipeline. The advantage of this comprehensive analysis is that it can comprehensively consider the detailed features of the external visual information of the pipeline and the response of the internal support structure.

[0045] Furthermore, in the technical solution of the present application, it is considered that the image quality of the pipeline image may be inconsistent due to factors such as the camera resolution, installation angle, and lighting conditions, which affects the accuracy of feature extraction. The supporting force and ambient temperature of the spring support bracket may fluctuate due to various factors such as pipeline materials, environmental conditions, and equipment aging, resulting in inconsistent distribution of the input vector at different time points. : The pipeline image displacement convolutional neural network may not be able to fully capture all image features related to thermal displacement, or the sensitivity to certain features is different, resulting in differences in the distribution of feature vectors in local areas. When the pipeline image displacement feature vector and the spring support force change correlation feature matrix are fused, the importance and weights of different features may not be properly processed, resulting in inconsistency in some local areas of the fused pipeline thermal displacement judgment classification feature vector, which in turn causes the pipeline thermal displacement judgment classification feature vector to have a class harmony offset relative to the predetermined class label of the classifier when it is classified by the classifier, affecting the classification iteration effect. Based on this, the pipeline thermal displacement judgment classification feature vector is subjected to a local distribution balancing correction based on the subclass label related metric.

[0046] The pipeline thermal displacement judgment classification feature vector is subjected to local distribution equalization correction based on subclass label related metrics to obtain an optimized pipeline thermal displacement judgment classification feature vector, including: determining a weight learning parameter matrix of the classifier; extracting each column vector in the weight learning parameter matrix to obtain a set of weight learning parameter column vectors; and using the following optimization formula to respectively calculate the metric correlation prediction factor between each weight learning parameter column vector in the set of weight learning parameter column vectors and the pipeline thermal displacement judgment classification feature vector to obtain a metric correlation prediction factor modulation vector, wherein the optimization formula is:

[0047]

[0048] Among them, V i represents each weight learning parameter column vector in the set of weight learning parameter column vectors, V c represents the pipeline thermal displacement judgment classification feature vector, It means subtracting by position. is the superposition norm of the two norms of the eigenvectors, ‖·‖ F is the Frobenius norm of the eigenvector, M p represents the weight learning parameter matrix, exp(·) represents the exponential operation with the natural constant e as the base, V p Representing the metric correlation prediction factor modulation vector; taking the metric correlation prediction factor modulation vector as the weight vector, calculating the position point multiplication between the metric correlation prediction factor modulation vector and the pipeline thermal displacement judgment classification feature vector to obtain the optimized pipeline thermal displacement judgment classification feature vector.

[0049] In the technical solution of the present application, considering that there are local distribution differences in the pipeline thermal displacement judgment classification feature vector, when it is classified by the classifier, there will be a class harmony offset relative to the predetermined class label of the classifier, which affects the classification iteration effect. Based on this, in the technical solution of the present application, the pipeline thermal displacement judgment classification feature vector is corrected for local distribution balance based on the subclass label related metric, which uses the superposition paradigm of the two norms between each column vector in the weight learning parameter matrix of the classifier and the pipeline thermal displacement judgment classification feature vector as the subclass label related metric integral factor and the matrix norm of the weight learning parameter of the classifier as the differential factor, and then uses the association paradigm between the subclass label related metric integral factor and the differential factor to perform bidirectional linear manifold modulation on the pipeline thermal displacement judgment classification feature vector, thereby improving the local feature distribution consistency of the pipeline thermal displacement judgment classification feature vector by adaptively stretching and compressing the pipeline thermal displacement judgment classification feature vector, thereby reducing the harmony offset of the pipeline thermal displacement judgment classification feature vector relative to the predetermined class label of the classifier, thereby improving the accuracy of the classification result.

[0050] Furthermore, the optimized pipeline thermal displacement judgment classification feature vector integrates the displacement features of the pipeline surface image and the internal support force change features. The optimized pipeline thermal displacement judgment classification feature vector reflects the state changes of the pipeline under different operating conditions. Through feature extraction and selection, the optimized pipeline thermal displacement judgment classification feature vector captures the key deformation mode and support force response, providing rich input information for the classifier. By learning the patterns and rules in historical data, the classifier can effectively identify abnormal or abnormal conditions, such as whether the pipeline expands or contracts due to temperature changes. The classifier can make judgments quickly after receiving new data to realize real-time monitoring of the pipeline operation status. This real-time performance is crucial to preventing pipeline problems from occurring, and timely measures can be taken to avoid potential damage or accidents.

[0051] In summary, the embodiment of the present application first obtains the pipeline image captured by the camera, the supporting force data of the spring support bracket on the pipeline at multiple predetermined time points collected by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor, and then uses deep learning technology to perform feature extraction and correlation analysis on the three. Finally, a classifier is used to determine whether thermal displacement occurs in the pipeline, thereby realizing real-time monitoring of the pipeline operation status, allowing the system to quickly respond to any potential abnormal conditions or problems, thereby improving the monitoring efficiency and accuracy of the pipeline system and ensuring the safe operation and long-term stability of the pipeline.

[0052] As described above, the intelligent online monitoring system 100 for electromechanical installation according to the embodiment of the present application can be implemented in various terminal devices. In one example, the intelligent online monitoring system 100 for electromechanical installation can be integrated into the terminal device as a software module and / or a hardware module. For example, the intelligent online monitoring system 100 for electromechanical installation can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the intelligent online monitoring system 100 for electromechanical installation can also be one of the many hardware modules of the terminal device.

[0053] Alternatively, in another example, the intelligent online monitoring system 100 for electromechanical installation and the terminal device may also be separate devices, and the intelligent online monitoring system 100 for electromechanical installation may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0054] Figure 4 FIG. 1 is a flow chart of an intelligent online monitoring method for electromechanical installation according to an embodiment of the present application. Figure 4 As shown, according to an embodiment of the present application, an intelligent online monitoring method for electromechanical installation includes: S110, acquiring a pipeline image captured by a camera, supporting force data of a spring support and hanger on the pipeline at multiple predetermined time points captured by a pressure sensor, and ambient temperature values ​​at multiple predetermined time points captured by a temperature sensor; S120, extracting a pipeline image displacement feature vector and a spring supporting force change associated feature matrix from the pipeline image captured by the camera, the supporting force data of a spring support and hanger on the pipeline at multiple predetermined time points captured by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points captured by the temperature sensor; S130, judging whether thermal displacement occurs in the pipeline based on the pipeline image displacement feature vector and the spring supporting force change associated feature matrix.

[0055] Here, those skilled in the art will appreciate that the specific operations of each step in the above-mentioned intelligent online monitoring method for electromechanical installation have been described in the above reference. Figures 1 to 3The intelligent online monitoring system for electromechanical installations has been described in detail, and therefore, its repeated description will be omitted.

[0056] Below, reference Figure 5 To describe an electronic device according to an embodiment of the present application.

[0057] Figure 5 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0058] The processor 11 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application; the memory 12 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).

[0059] The memory 12 can store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 12, and the processor 11 is called to execute the intelligent online monitoring method for electromechanical installation in the embodiments of this application;

[0060] Input / output interface 13, used to implement information input and output;

[0061] The communication interface 14 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0062] A bus 15 that transmits information between the various components of the device (e.g., the processor 11, the memory 12, the input / output interface 13, and the communication interface 14);

[0063] The processor 11 , the memory 12 , the input / output interface 13 and the communication interface 14 are connected to each other in communication within the device via a bus 15 .

[0064] An embodiment of the present application further provides a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the above-mentioned intelligent online monitoring method for electromechanical installation is implemented.

[0065] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0066] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0067] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0068] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0069] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0070] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0071] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0072] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0073] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-On lyMemory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs. The preferred embodiment of the embodiment of the present application is described above with reference to the accompanying drawings, and the scope of rights of the embodiment of the present application is not limited thereto. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of rights of the embodiments of the present application.

Claims

1. An intelligent online monitoring system for electromechanical installation, characterized in that: include: The electromechanical installation pipeline data acquisition module is used to acquire pipeline images acquired by the camera, supporting force data of the spring support and hanger on the pipeline at multiple predetermined time points acquired by the pressure sensor, and ambient temperature values ​​at multiple predetermined time points acquired by the temperature sensor; The electromechanical installation pipeline data extraction module is used to extract the pipeline image displacement feature vector and the spring support force change correlation feature matrix from the pipeline image collected by the camera, the support force data of the spring support hanger on the pipeline at multiple predetermined time points collected by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor; The pipeline thermal displacement judgment module is used to judge whether the pipeline has thermal displacement based on the pipeline image displacement feature vector and the spring support force change correlation feature matrix.

2. The intelligent online monitoring system for electromechanical installation according to claim 1, characterized in that: The electromechanical installation pipeline data extraction module comprises: A pipeline image feature extraction unit, used for extracting features from the pipeline image captured by the camera to obtain a displacement feature vector of the pipeline image; A supporting force data feature construction unit, used to construct the supporting force data of the spring hanger on the pipeline at multiple predetermined time points collected by the pressure sensor and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor to obtain a spring hanger supporting force input vector and a supporting force ambient temperature input vector; The support force data feature encoding unit is used to perform feature encoding on the spring hanger support force input vector and the support force ambient temperature input vector to obtain the spring support force change correlation feature matrix.

3. The intelligent online monitoring system for electromechanical installation according to claim 2, characterized in that: The pipeline image feature extraction unit comprises: Passing the pipeline image captured by the camera through a pipeline image displacement convolutional neural network as a feature encoder to obtain a pipeline image displacement feature map; The pipeline image displacement feature map is downsampled to obtain the pipeline image displacement feature vector.

4. The intelligent online monitoring system for electromechanical installation according to claim 3, characterized in that: The supporting force data feature construction unit comprises: Converting the supporting force data of the spring hanger on the pipeline at multiple predetermined time points collected by the pressure sensor into the supporting force input vector of the spring hanger; The ambient temperature values ​​at a plurality of predetermined time points collected by the temperature sensor are arranged as the support force ambient temperature input vector.

5. The intelligent online monitoring system for electromechanical installation according to claim 4, characterized in that: The bearing force data feature encoding unit comprises: Calculating the transfer matrix between the spring support and hanger support force input vector and the support force ambient temperature input vector to obtain a support and hanger support force change correlation matrix; The support and hanger support force variation association matrix is ​​passed through a support and hanger support force variation convolutional neural network model based on mutually transposed convolution kernels to obtain the spring support force variation association feature matrix.

6. The intelligent online monitoring system for electromechanical installation according to claim 5, characterized in that: The support and hanger support force change correlation matrix is ​​passed through a support and hanger support force change convolutional neural network model based on mutually transposed convolution kernels to obtain the spring support force change correlation feature matrix, including: Each layer of the support and hanger support force variation convolutional neural network model based on the use of mutually transposed convolution kernels performs the following operations on the input data in the forward transmission of the layer: Performing convolution processing, pooling processing, and nonlinear processing based on a first two-dimensional convolution kernel on the input data to obtain a first activation feature map; and Performing convolution processing, pooling processing, and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed of each other; Among them, the input of the first layer of the support bracket support force change convolutional neural network model based on the use of mutually transposed convolution kernels is the support bracket support force change association matrix, and the output of the last layer of the support bracket support force change convolutional neural network model based on the use of mutually transposed convolution kernels is the spring support force change association feature matrix.

7. The intelligent online monitoring system for electromechanical installation according to claim 6, characterized in that: The pipeline thermal displacement judgment module includes: A pipeline thermal displacement feature fusion unit, used to fuse the pipeline image displacement feature vector and the spring support force change correlation feature matrix to obtain a pipeline thermal displacement judgment classification feature vector; A pipeline thermal displacement feature optimization unit, used for performing a local distribution balance correction on the pipeline thermal displacement judgment classification feature vector based on a subclass label related metric to obtain an optimized pipeline thermal displacement judgment classification feature vector; The pipeline thermal displacement judgment classification unit is used to pass the optimized pipeline thermal displacement judgment classification feature vector through a classifier to obtain a classification result, and the classification result is used to judge whether thermal displacement occurs in the pipeline.

8. The intelligent online monitoring system for electromechanical installation according to claim 7, characterized in that: The pipeline thermal displacement characteristic optimization unit comprises: Determining a weight learning parameter matrix of the classifier; Extracting each column vector in the weight learning parameter matrix to obtain a set of weight learning parameter column vectors; Respectively calculating the metric correlation prediction factor between each weight learning parameter column vector in the set of weight learning parameter column vectors and the pipeline thermal displacement judgment classification feature vector to obtain a metric correlation prediction factor modulation vector; The metric correlation prediction factor modulation vector is used as a weight vector, and the position point multiplication between the metric correlation prediction factor modulation vector and the pipeline thermal displacement judgment classification feature vector is calculated to obtain the optimized pipeline thermal displacement judgment classification feature vector.

9. An intelligent online monitoring method for electromechanical installation, characterized in that: include: Acquire pipeline images collected by a camera, supporting force data of the spring hanger on the pipeline at multiple predetermined time points collected by a pressure sensor, and ambient temperature values ​​at multiple predetermined time points collected by a temperature sensor; Extracting pipeline image displacement feature vectors and spring support force change correlation feature matrices from the pipeline image captured by the camera, the support force data of the spring support hanger on the pipeline at multiple predetermined time points captured by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points captured by the temperature sensor; Based on the pipeline image displacement feature vector and the spring support force change correlation feature matrix, it is determined whether thermal displacement occurs in the pipeline.

10. The intelligent online monitoring method for electromechanical installation according to claim 9, characterized in that: Extracting pipeline image displacement feature vectors and spring support force change correlation feature matrices from the pipeline image captured by the camera, the support force data of the spring support hanger on the pipeline at multiple predetermined time points captured by the pressure sensor, and the ambient temperature values ​​at multiple predetermined time points captured by the temperature sensor, including: Performing feature extraction on the pipeline image captured by the camera to obtain a displacement feature vector of the pipeline image; The supporting force data of the spring hanger on the pipeline at multiple predetermined time points collected by the pressure sensor and the ambient temperature values ​​at multiple predetermined time points collected by the temperature sensor are constructed to obtain a spring hanger supporting force input vector and a supporting force ambient temperature input vector; The spring hanger support force input vector and the support force ambient temperature input vector are feature encoded to obtain the spring support force change associated feature matrix.

Images