Water-turbine generator set deformation field monitoring method, device and system and storage medium

Abstract

The invention discloses a water-turbine generator set deformation field monitoring method, device and system based on a three-dimensional point cloud model and a storage medium, and the method comprises the steps: obtaining three-dimensional point cloud data of a water-turbine generator set every preset period, and carrying out the preprocessing of the three-dimensional point cloud data, and obtaining point cloud initial data; performing feature extraction on the point cloud initial data to obtain point cloud feature data, and performing three-dimensional reconstruction based on the point cloud initial data and the point cloud feature data to obtain a three-dimensional model; and judging whether deformation risk data exists in the point cloud feature data, and if the deformation risk data exists, performing deformation early warning on the deformation risk data in the three-dimensional model. According to the method, the three-dimensional point cloud data is acquired for preprocessing and feature extraction, the three-dimensional model of the water-turbine generator set is established, deformation early warning monitoring is performed in the three-dimensional model by analyzing the deformation risk of the extracted point cloud feature data, and accurate monitoring of the deformation field of the water-turbine generator set is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twin models, and in particular to a method, device, system and storage medium for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model. Background Art

[0002] Hydropower generation is a method of generating electricity by building a hydropower station on a dam and converting the potential energy of water into electrical energy. As the core power source of a hydropower station, the stable operation and efficient maintenance of a hydropower generator set are crucial to ensuring power supply and improving energy efficiency. However, due to long-term water flow impact, load fluctuations, mechanical vibrations, wear of mechanical parts inside the unit, and complex environmental factors, the components of the hydropower generator set will inevitably deform and form a deformation field. In order to prevent the deformation field from affecting the normal operation of the hydropower generator set, the deformation field of the hydropower generator set needs to be accurately monitored and effectively controlled.

[0003] At present, the deformation field of hydro-turbine generator sets is mainly monitored by monitoring the operating vibration signal and the axis swing of the unit. However, this monitoring method is greatly affected by factors such as the sensor installation position, measurement accuracy and sensitivity, and the complexity of the vibration signal is difficult to accurately extract and process, which makes it difficult to accurately monitor the deformation field of the hydro-turbine generator set, making it impossible to effectively control the deformation field and posing operational risks. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, system and medium for monitoring the deformation field of a hydro-turbine generator set based on a three-dimensional point cloud model, aiming to solve the technical problem of how to accurately monitor the deformation field of a hydro-turbine generator set in the prior art.

[0005] To achieve the above object, the present invention provides a method for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model, the method comprising:

[0006] At each preset period, three-dimensional point cloud data of the hydro-generator set is acquired, and the three-dimensional point cloud data is pre-processed to obtain initial point cloud data;

[0007] Performing feature extraction on the initial point cloud data to obtain point cloud feature data, and performing three-dimensional reconstruction based on the initial point cloud data and the point cloud feature data to obtain a three-dimensional model;

[0008] It is determined whether there is deformation risk data in the point cloud feature data. If there is deformation risk data, a deformation warning is performed on the deformation risk data in the three-dimensional model.

[0009] Preferably, the step of determining whether there is deformation risk data in the point cloud feature data comprises:

[0010] Filtering target point cloud data corresponding to a preset measuring point position from the point cloud feature data, and analyzing whether the preset measuring point position has at least one of the characteristics of cracks, wear, and corrosion according to the target point cloud data;

[0011] If there is at least one of the characteristics of cracks, wear and corrosion, it is determined that there is deformation risk data in the point cloud feature data;

[0012] If there are no characteristics of cracks, wear and corrosion, it is determined that there is no deformation risk data in the point cloud feature data.

[0013] Preferably, the step of determining whether there is deformation risk data in the point cloud feature data comprises:

[0014] Obtaining force characteristic data and deformation characteristic data corresponding to a preset measuring point position in the point cloud characteristic data, and generating a force change rate corresponding to the force characteristic data based on historical force characteristic data, and generating a deformation change rate corresponding to the deformation characteristic data based on historical deformation characteristic data;

[0015] Determine whether the force change rate is greater than a preset force threshold, and whether the deformation change rate is greater than a preset deformation threshold;

[0016] If the force change rate is greater than a preset force threshold and / or the deformation change rate is greater than a preset deformation threshold, it is determined that deformation risk data exists in the point cloud feature data;

[0017] If the force change rate is not greater than a preset force threshold, and the deformation change rate is not greater than a preset deformation threshold, it is determined that there is no deformation risk data in the point cloud feature data.

[0018] Preferably, if there is deformation risk data, the step of providing deformation warning for the deformation risk data in the three-dimensional model comprises:

[0019] If deformation risk data exists, determining the risk type of the deformation risk data;

[0020] If the risk type is an existing risk, the risk level corresponding to the deformation risk data is generated according to at least one of the characteristics of cracks, wear and corrosion.

[0021] If the risk type is a predicted risk, a risk level corresponding to the deformation risk data is generated according to a force difference between the force change rate and a preset force threshold, and / or a deformation difference between the deformation change rate and a preset deformation threshold;

[0022] Determine a warning color corresponding to the risk type and risk level, and a model position of the deformation risk data in a three-dimensional model, and render the model position with the warning color to perform a deformation warning for the deformation risk data based on the rendering of the warning color.

[0023] Preferably, the step of rendering the model position in the warning color comprises:

[0024] Acquire a unit position in the hydro-generator unit corresponding to the model position;

[0025] Calling a preset risk template, and adding the unit position, the deformation risk data, the risk type and the risk level to the preset risk template to generate a risk report;

[0026] The risk report is output.

[0027] Preferably, the step of preprocessing the three-dimensional point cloud data to obtain initial point cloud data comprises:

[0028] Performing statistical filtering on the three-dimensional point cloud data to remove noise data in the three-dimensional point cloud data to obtain first-type preprocessed data;

[0029] Deduplication is performed on the first type of preprocessed data to obtain second type of preprocessed data;

[0030] It is determined whether there are hole data in the second type of pre-processed data. If there are hole data, interpolation processing is performed on the hole data in the second type of pre-processed data to obtain the initial point cloud data.

[0031] Preferably, the step of obtaining the three-dimensional point cloud data of the hydro-generator set comprises:

[0032] emitting laser light and projecting light patterns to the hydro-generator set based on a laser emitting device;

[0033] Acquire the reflection time or phase difference of the laser reflected by the hydro-generator set, and acquire the reflection pattern corresponding to the light pattern;

[0034] generating first three-dimensional point cloud data according to the reflection time or phase difference, and generating second three-dimensional point cloud data according to the reflection pattern;

[0035] The first three-dimensional point cloud data and the second three-dimensional point cloud data are generated as the three-dimensional point cloud data.

[0036] Furthermore, in order to achieve the above-mentioned purpose, the present invention also provides a deformation field monitoring device for a hydro-generator set based on a three-dimensional point cloud model, the deformation field monitoring device for a hydro-generator set comprising:

[0037] An acquisition module is used to acquire three-dimensional point cloud data of the hydro-generator set at preset intervals, and pre-process the three-dimensional point cloud data to obtain initial point cloud data;

[0038] A reconstruction module, used for performing feature extraction on the initial point cloud data to obtain point cloud feature data, and performing three-dimensional reconstruction based on the initial point cloud data and the point cloud feature data to obtain a three-dimensional model;

[0039] The early warning module is used to determine whether there is deformation risk data in the point cloud feature data. If there is deformation risk data, deformation early warning is performed on the deformation risk data in the three-dimensional model.

[0040] Furthermore, to achieve the above-mentioned object, the present invention also provides a hydro-generator set deformation field monitoring system based on a three-dimensional point cloud model, the hydro-generator set deformation field monitoring system comprising a storage, a processor, a communication bus and a control program stored in the storage:

[0041] The communication bus is used to realize the connection and communication between the processor and the storage;

[0042] The processor is used to execute the control program to implement the steps of the above-mentioned method for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model.

[0043] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a storage medium, on which a control program is stored, and when the control program is executed by a processor, the steps of the deformation field monitoring method of a hydro-turbine generator set based on a three-dimensional point cloud model as described above are implemented.

[0044] The present invention provides a method, device, system and storage medium for monitoring the deformation field of a hydro-turbine generator set based on a three-dimensional point cloud model. A preset period for monitoring the hydro-turbine generator set is pre-set. At each preset period, the three-dimensional point cloud data of the hydro-turbine generator set is obtained, and the three-dimensional point cloud data is pre-processed to obtain the initial point cloud data; then, feature extraction is performed on the initial point cloud data to obtain point cloud feature data, and three-dimensional reconstruction is performed based on the initial point cloud data and the point cloud feature data to obtain a three-dimensional model; it is determined whether there is deformation risk data in the point cloud feature data, and if there is deformation risk data, deformation warning is performed on the deformation risk data in the three-dimensional model. In this way, by obtaining the three-dimensional point cloud data for pre-processing and feature extraction, a three-dimensional model of the hydro-turbine generator set is established, and by analyzing the deformation risk of the extracted point cloud feature data, deformation warning monitoring is performed in the three-dimensional model, thereby avoiding the data used for monitoring being affected by the acquisition equipment and the problem that the data is difficult to extract and process, and realizing accurate monitoring of the deformation field of the hydro-turbine generator set. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of a first embodiment of a method for monitoring deformation field of a hydro-generator set based on a three-dimensional point cloud model according to the present invention;

[0046] Figure 2 It is a flow chart of a second embodiment of a method for monitoring deformation field of a hydro-generator set based on a three-dimensional point cloud model according to the present invention;

[0047] Figure 3 It is a module schematic diagram of an embodiment of a device for monitoring deformation field of a hydro-generator set based on a three-dimensional point cloud model according to the present invention;

[0048] Figure 4 It is a structural schematic diagram of the hardware operating environment involved in an embodiment of a hydro-generator set deformation field monitoring system based on a three-dimensional point cloud model of the present invention.

[0049] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0051] The present invention provides a method for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model. Figure 1 , Figure 1 It is a flow chart of the first embodiment of the method for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model of the present invention.

[0052] The embodiment of the present invention provides an embodiment of a method for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model. It should be noted that although a logical sequence is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order than that shown here. Specifically, the method for monitoring the deformation field of a hydro-generator set in this embodiment includes:

[0053] Step S10, acquiring three-dimensional point cloud data of the hydro-generator set at preset intervals, and preprocessing the three-dimensional point cloud data to obtain initial point cloud data.

[0054] The method for monitoring the deformation field of a hydro-turbine generator set based on a three-dimensional point cloud model in this embodiment can be applied to the control center of a deformation monitoring system. In addition to the control center, the deformation warning system can also be connected to a laser emitting device for emitting laser light, or to a drone platform. The drone platform can be connected to multiple drones, each of which is equipped with a high-precision laser emitting device for emitting laser light to the hydro-turbine generator set. A preset period is set in advance based on the deformation period of each unit equipment in the historical hydro-turbine generator set, and the three-dimensional point cloud data of the hydro-turbine generator set is obtained through the laser emitting device at intervals of the preset period.

[0055] Furthermore, the three-dimensional point cloud data can be composed of two parts, one of which is the data generated by the hydro-generator set reflecting the directly emitted laser, and the other is the data generated by the hydro-generator set reflecting the light pattern emitted by the laser. The two types of data have different three-dimensional characteristics, which can make the obtained three-dimensional point cloud data more accurate. Specifically, the step of obtaining the three-dimensional point cloud data of the hydro-generator set includes:

[0056] Step S11, emitting laser and projecting light pattern to the hydro-generator set based on the laser emitting device;

[0057] Step S12, obtaining the reflection time or phase difference of the laser reflected by the hydro-generator set, and obtaining a reflection pattern corresponding to the light pattern;

[0058] Step S13, generating first three-dimensional point cloud data according to the reflection time or phase difference, and generating second three-dimensional point cloud data according to the reflection pattern;

[0059] Step S14: generating the first three-dimensional point cloud data and the second three-dimensional point cloud data into the three-dimensional point cloud data.

[0060] Furthermore, a laser is emitted to the hydro-generator set by a laser emission device for scanning, and the hydro-generator set reflects the emitted laser, and the emission time or phase difference of the reflection is obtained, and then the first three-dimensional point cloud data is generated according to the reflection time or phase difference. In addition, a light pattern is projected to the hydro-generator set by a laser emission device, and the light pattern can be pre-set according to the characteristics of the hydro-generator set, for example, set to a plane, a grid or a more complex image. The light pattern is projected onto the hydro-generator set to form a projection, and then the projection is photographed and transmitted to the control center by a camera device connected to the control center in communication, forming a reflection pattern corresponding to the light pattern, and the second three-dimensional point cloud data is generated by the triangulation principle based on the pattern distortion and deformation reflected by the reflection pattern.

[0061] Among them, the first three-dimensional point cloud data is generated by laser scanning, which can realize accurate scanning of complex shapes and large-sized equipment, and can capture subtle changes in the surface of blades in hydro-turbine generator sets, including cracks, wear, etc. The second three-dimensional point cloud data is generated by structured light scanning, which is suitable for scenes with high details and texture information. For example, in key components such as the volute and guide vanes of hydro-turbine generator sets, it can capture the detailed features of the surface of the components, such as tiny defects and corrosion. In this embodiment, the first three-dimensional point cloud data and the second three-dimensional point cloud data are jointly generated as unit point cloud data to accurately reflect the detailed features of each component in the hydro-turbine generator set and improve the accuracy of monitoring each component.

[0062] Furthermore, the acquired three-dimensional point cloud data usually introduces noise points due to environmental factors or defects of the equipment itself. Therefore, in order to ensure the accuracy of the three-dimensional point cloud data, the three-dimensional point cloud data needs to be preprocessed to obtain accurate initial point cloud data. Among them, the preprocessing includes at least filtering, deduplication, interpolation and other processing. Specifically, the step of preprocessing the three-dimensional point cloud data to obtain the initial point cloud data includes:

[0063] Step S15, performing statistical filtering on the three-dimensional point cloud data to remove noise data in the three-dimensional point cloud data to obtain first type of pre-processed data;

[0064] Step S16, removing duplicates from the first type of preprocessed data to obtain second type of preprocessed data;

[0065] Step S17, determining whether there are void data in the second type of pre-processed data, and if there are void data, performing interpolation processing on the void data in the second type of pre-processed data to obtain the initial point cloud data.

[0066] Furthermore, in the preprocessing process, the 3D point cloud data is first subjected to statistical filtering and median filtering. Among them, statistical filtering is used to remove outlier noise points in the 3D point cloud data. By setting parameters such as the number of neighborhood points and the mean distance threshold, outlier noise points that are inconsistent with the distribution of most 3D point cloud data are identified and removed, and denoising of the 3D point cloud data is achieved to improve the accuracy of the 3D point cloud data.

[0067] Furthermore, after the three-dimensional point cloud data is processed by statistical filtering, the first type of pre-processed data is obtained, and the first type of pre-processed data is deduplicated, that is, the repeated data points are identified and removed to obtain the second type of pre-processed data. Thereafter, the second type of pre-processed data is identified to determine whether there are void data therein. Among them, void data is data that is missing in the three-dimensional point cloud data due to scanning blind spots, blind spots of vision, object occlusion, etc., and this type of missing data will affect the subsequent three-dimensional reconstruction and analysis work. Therefore, if it is determined that there are void data in the second type of pre-processed data, the void data is interpolated and repaired to fill the voids in the three-dimensional point cloud data through interpolation repair. The specific interpolation repair method can be any one of interpolation repair based on radial basis function, cubic spline interpolation repair, interpolation repair based on compact support radial basis function, contour interval difference repair, or high-precision surface model interpolation repair, without limitation. By performing difference repair on the second type of pre-processed data, the initial point cloud data is obtained. Of course, if it is determined that there is no hole data in the second type of pre-processed data, the second type of pre-processed data can be directly used as the initial point cloud data.

[0068] Step S20, performing feature extraction on the initial point cloud data to obtain point cloud feature data, and performing three-dimensional reconstruction based on the initial point cloud data and the point cloud feature data to obtain a three-dimensional model.

[0069] Furthermore, feature extraction is performed on the initial point cloud data. Specifically, key components and components of particular concern in the hydro-turbine generator set can be pre-set, and the data corresponding to such components and the data of easily deformable components in the hydro-turbine generator set can be extracted from the initial point cloud data as point cloud feature data. Then, a three-dimensional model is reconstructed based on the extracted point cloud feature data and the initial point cloud data to obtain a three-dimensional model. The three-dimensional modeling method can be a grid-based reconstruction, such as Delaunay triangulation reconstruction and Poisson reconstruction. Delaunay triangulation has good shape quality and robustness, can automatically adapt to three-dimensional point cloud data of different densities, and can generate high-quality triangular meshes. Poisson reconstruction can restore a smooth and continuous surface model by solving the Poisson equation. By combining the two, a fine grid structure is constructed to generate a highly realistic three-dimensional model.

[0070] Step S30, determining whether there is deformation risk data in the point cloud feature data, and if there is deformation risk data, performing deformation warning for the deformation risk data in the three-dimensional model.

[0071] Furthermore, it is determined whether there is deformation risk data in the point cloud feature data. If there is deformation risk data, the corresponding position of such data in the three-dimensional model is determined, and then a deformation warning is issued for the deformation risk data at the position in the three-dimensional model. The warning method may be to display the deformation risk data at the position in the three-dimensional model, or to output warning information, etc., which is not limited.

[0072] The method for monitoring the deformation field of a hydro-turbine generator set based on a three-dimensional point cloud model implemented in this embodiment pre-sets a preset period for monitoring the hydro-turbine generator set, obtains the three-dimensional point cloud data of the hydro-turbine generator set at each preset period, and pre-processes the three-dimensional point cloud data to obtain the initial point cloud data; then extracts features from the initial point cloud data to obtain point cloud feature data, and performs three-dimensional reconstruction based on the initial point cloud data and the point cloud feature data to obtain a three-dimensional model; determines whether there is deformation risk data in the point cloud feature data, and if there is deformation risk data, performs deformation warning on the deformation risk data in the three-dimensional model. In this way, by obtaining the three-dimensional point cloud data for pre-processing and feature extraction, a three-dimensional model of the hydro-turbine generator set is established, and by analyzing the deformation risk of the extracted point cloud feature data, deformation warning monitoring is performed in the three-dimensional model, avoiding the data used for monitoring being affected by the acquisition equipment, and the problem that the data is difficult to extract and process, and realizing accurate monitoring of the deformation field of the hydro-turbine generator set.

[0073] For further information, please refer to Figure 2 Based on the first embodiment of the method for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model of the present invention, a second embodiment of the method for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model of the present invention is proposed.

[0074] The difference between the second embodiment of the deformation field monitoring system for a hydro-generator set based on a three-dimensional point cloud model and the first embodiment of the deformation field monitoring system for a hydro-generator set based on a three-dimensional point cloud model is that the step of determining whether there is deformation risk data in the point cloud feature data comprises:

[0075] Step S31, selecting target point cloud data corresponding to a preset measuring point position from the point cloud feature data, and analyzing whether the preset measuring point position has at least one of the characteristics of crack, wear and corrosion according to the target point cloud data;

[0076] Step S32, if there is at least one of the characteristics of cracks, wear and corrosion, it is determined that there is deformation risk data in the point cloud feature data;

[0077] Step S33: If there are no characteristics of cracks, wear and corrosion, it is determined that there is no deformation risk data in the point cloud feature data.

[0078] Furthermore, in this embodiment, the judgment of deformation risk data can be based on the deformation risk that has occurred in the hydro-turbine generator, and the deformation risk includes cracks, wear, and corrosion. Specifically, the pre-set special attention components in the hydro-turbine generator set are used as preset measuring point positions, and the target point cloud data corresponding to the preset measuring point position is screened out from the point cloud feature data. Then, the target point cloud data is analyzed to determine whether the preset measuring point position has any of the characteristics of cracks, wear, and corrosion.

[0079] Among them, the analysis of the target point cloud data can be performed through a pre-trained analysis model. The model is pre-trained with a large amount of crack sample data, wear sample data and corrosion sample data to obtain an analysis model that can identify crack features, wear features and corrosion features. If the analysis model analyzes that the preset measuring point position has any one of the characteristics of cracks, wear and corrosion, it means that cracks, wear or corrosion have appeared in the special attention components of the hydro-generator set, which may affect the safe and effective operation of the hydro-generator set, thereby determining that there is deformation risk data in the point cloud feature data. On the contrary, if the preset analysis model analyzes and identifies that the target point cloud data does not have the characteristics of cracks, wear and corrosion, it means that there are no cracks, wear and corrosion in the special attention components of the hydro-generator set, and the hydro-generator set can operate safely and effectively, thereby determining that there is no deformation risk data in the point cloud feature data. In this way, the deformation risks such as cracks, wear and corrosion that have appeared in the hydro-generator are identified and determined.

[0080] In addition, this embodiment can also predict the deformation risk that may occur in the hydro-generator set according to the characteristic trend of the point cloud feature data. Specifically, the step of determining whether there is deformation risk data in the point cloud feature data includes:

[0081] Step S34, obtaining force characteristic data and deformation characteristic data corresponding to the preset measuring point position in the point cloud characteristic data, and generating a force change rate corresponding to the force characteristic data based on the historical force characteristic data, and generating a deformation change rate corresponding to the deformation characteristic data based on the historical deformation characteristic data;

[0082] Step S35, determining whether the force change rate is greater than a preset force threshold, and whether the deformation change rate is greater than a preset deformation threshold;

[0083] Step S36, if the force change rate is greater than a preset force threshold and / or the deformation change rate is greater than a preset deformation threshold, it is determined that deformation risk data exists in the point cloud feature data;

[0084] Step S37: If the force change rate is not greater than the preset force threshold, and the deformation change rate is not greater than the preset deformation threshold, it is determined that there is no deformation risk data in the point cloud feature data.

[0085] Furthermore, the point cloud feature data includes force feature data and deformation feature data for preset measuring point positions, indicating the force magnitude and deformation magnitude predicted for the hydro-turbine generator set at the preset measuring point positions. The historical point cloud feature data acquired in the previous preset period also includes historical force feature data and historical deformation feature data for the preset measuring point positions. Based on the time sequence of each historical force feature data, each historical force feature data and force feature data are generated as a force change rate. At the same time, based on the time sequence of each historical deformation feature data, each historical deformation feature data and deformation feature data are generated as a deformation change rate.

[0086] Furthermore, in order to indicate the magnitude of the force change rate and the deformation change rate, a preset force threshold and a preset deformation threshold are pre-set. The force change rate is compared with the preset force threshold to determine whether the force change rate is greater than the preset force threshold, and the deformation change rate is compared with the preset deformation threshold to determine whether the deformation change rate is greater than the preset deformation threshold. If the force change rate is greater than the preset force threshold, and / or the deformation change rate is greater than the preset deformation threshold, it means that the force change at the preset measuring point position is large and / or the deformation change is large, and the continued operation of the turbine wind turbine generator set may be at risk, so it is determined that there is deformation risk data in the point cloud feature data. On the contrary, if it is determined that the force change rate is not greater than the preset force threshold and the deformation change rate is not greater than the preset deformation threshold, it is determined that there is no deformation risk data in the point cloud feature data. In this way, the future force and deformation trend of the turbine generator set is predicted through the force and deformation magnitude in the point cloud feature data, and the possible risks are predicted and warned.

[0087] Furthermore, for the warning of the existence of deformation risk data, different forms of warnings can be given according to different types and risk levels. Specifically, if there is deformation risk data, the step of giving deformation warning to the deformation risk data in the three-dimensional model includes:

[0088] Step a1: if there is deformation risk data, determining the risk type of the deformation risk data;

[0089] Step a2: if the risk type is an existing risk, generating a risk level corresponding to the deformation risk data according to at least one of the characteristics of cracks, wear and corrosion

[0090] Step a3: if the risk type is a predicted risk, then generating a risk level corresponding to the deformation risk data according to the force difference between the force change rate and a preset force threshold, and / or the deformation difference between the deformation change rate and a preset deformation threshold;

[0091] Step a4, determining the warning color corresponding to the risk type and risk level, and the model position of the deformation risk data in the three-dimensional model, and rendering the model position with the warning color to perform deformation warning for the deformation risk data based on the rendering of the warning color.

[0092] Furthermore, after determining that deformation risk data exists in the point cloud feature data, the risk type of the deformation risk data is determined. The risk type includes the above-mentioned existing risks and predicted risks. The existing risks are regarded as existing risks, and the predicted risks are regarded as predicted risks, and each corresponds to a different risk identifier.

[0093] Furthermore, if the risk type is determined to be an existing risk based on the risk identification, it means that the target point cloud data screened from the point cloud feature data has at least one of the features of cracks, wear and corrosion, and the risk level of deformation risk is generated based on the number and size of the features of such cracks, wear and corrosion. The greater the number and the larger the features, the higher the risk level generated. If the risk identification indicates that the risk type is a predicted risk, the force difference between the force change rate and the preset force threshold, and / or the deformation difference between the deformation change rate and the preset deformation threshold are generated, and then the risk level of deformation risk data is generated based on the force difference and / or deformation difference. The force difference indicates the change in the force change rate relative to the preset force threshold, and the deformation difference indicates the change in the deformation change rate relative to the preset deformation threshold. The larger the change, the higher the risk level.

[0094] Furthermore, in order to distinguish between different risk types and risk levels, different warning colors are pre-set for different risk types and risk levels. The warning color corresponding to the generated risk type and risk level is determined, and the model position of the deformation risk data in the three-dimensional model is determined, and then the model position is rendered with the warning color. By rendering to form a distinguishing color, a warning is issued for the risk corresponding to the deformation risk data existing at the model position.

[0095] Furthermore, in order to facilitate the operation and maintenance personnel to check the risks of the hydro-turbine wind turbine, while rendering the model position in the three-dimensional model with the warning color, the deformation risk data can also be generated as a risk report. Specifically, after the step of rendering the model position with the warning color, the following steps are included:

[0096] Step b1, obtaining the unit position in the hydro-generator unit corresponding to the model position;

[0097] Step b2, calling a preset risk template, and adding the unit position, the deformation risk data, the risk type and the risk level to the preset risk template to generate a risk report;

[0098] Step b3: output the risk report.

[0099] Furthermore, the physical location of the model position in the hydro-turbine generator set is searched, and the physical location is the unit position where the hydro-turbine generator set actually has risks. In addition, a preset risk template for production risk reporting is pre-set, the preset risk template is called, and the template plate corresponding to the unit position, deformation risk data, risk type and risk level in the preset risk template is determined. Then, the unit position, deformation risk data, risk type and risk level are added to the corresponding template plates to generate a risk report. The risk report is sent to the relevant operation and maintenance personnel so that the operation and maintenance personnel can view the risk report and maintain the risks in the hydro-turbine generator set.

[0100] This embodiment determines the deformation of the hydro-turbine generator set and issues early warning of the relevant risk level based on the existing risks of the hydro-turbine generator set and the predicted risks that may occur in the future, thereby improving the efficiency of operation and maintenance while making the risk warning of the hydro-turbine generator set more comprehensive and accurate.

[0101] In addition, the embodiment of the present invention also provides a deformation field monitoring device for a hydro-generator set based on a three-dimensional point cloud model, please refer to Figure 3 , Figure 3 The module schematic diagram of the embodiment of the hydraulic generator set deformation field monitoring device based on the three-dimensional point cloud model of the present invention. The hydraulic generator set deformation field monitoring device based on the three-dimensional point cloud model includes:

[0102] The acquisition module 10 is used to acquire the three-dimensional point cloud data of the hydro-generator set at every preset period, and pre-process the three-dimensional point cloud data to obtain initial point cloud data;

[0103] A reconstruction module 20 is used to extract features from the initial point cloud data to obtain point cloud feature data, and to perform three-dimensional reconstruction based on the initial point cloud data and the point cloud feature data to obtain a three-dimensional model;

[0104] The early warning module 30 is used to determine whether there is deformation risk data in the point cloud feature data. If there is deformation risk data, a deformation early warning is performed on the deformation risk data in the three-dimensional model.

[0105] The specific implementation of the hydro-generator set deformation field monitoring device based on the three-dimensional point cloud model of the present invention is basically the same as the various embodiments of the above-mentioned hydro-generator set deformation field monitoring method based on the three-dimensional point cloud model, and will not be repeated here.

[0106] In addition, the embodiment of the present invention also provides a deformation field monitoring system for a hydro-generator set based on a three-dimensional point cloud model. Figure 4 , Figure 4 It is a structural schematic diagram of the equipment hardware operating environment involved in the embodiment of the hydraulic generator set deformation field monitoring system based on the three-dimensional point cloud model of the present invention.

[0107] like Figure 4 As shown, the deformation field monitoring system of the hydro-generator set based on the three-dimensional point cloud model may also include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a storage 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The storage 1005 may be a high-speed RAM storage, or a stable storage (non-volatile memory), such as a disk storage. The storage 1005 may also be a storage device independent of the aforementioned processor 1001.

[0108] Those skilled in the art will understand that Figure 4 The hardware structure of the deformation field monitoring system for a hydro-turbine generator set based on a three-dimensional point cloud model shown in the figure does not constitute a limitation of the deformation field monitoring system for a hydro-turbine generator set based on a three-dimensional point cloud model, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0109] like Figure 4 As shown, the storage 1005 as a storage medium may include an operating system, a network communication module, a user interface module and a control program. The operating system is a program for managing and controlling the deformation field monitoring system and software resources of the hydro-generator set based on the three-dimensional point cloud model, and supports the operation of the network communication module, the user interface module, the control program and other programs or software; the network communication module is used to manage and control the network interface 1004; the user interface module is used to manage and control the user interface 1003.

[0110] exist Figure 4In the hardware structure of the deformation field monitoring system of the turbine generator set based on the three-dimensional point cloud model shown in the figure, the network interface 1004 is mainly used to connect to other system servers and communicate data with other system servers; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; the processor 1001 can call the control program stored in the storage 1005 and perform the following operations:

[0111] At each preset period, three-dimensional point cloud data of the hydro-generator set is acquired, and the three-dimensional point cloud data is pre-processed to obtain initial point cloud data;

[0112] Performing feature extraction on the initial point cloud data to obtain point cloud feature data, and performing three-dimensional reconstruction based on the initial point cloud data and the point cloud feature data to obtain a three-dimensional model;

[0113] It is determined whether there is deformation risk data in the point cloud feature data. If there is deformation risk data, a deformation warning is performed on the deformation risk data in the three-dimensional model.

[0114] Furthermore, the step of determining whether there is deformation risk data in the point cloud feature data includes:

[0115] Filtering target point cloud data corresponding to a preset measuring point position from the point cloud feature data, and analyzing whether the preset measuring point position has at least one of the characteristics of cracks, wear, and corrosion according to the target point cloud data;

[0116] If there is at least one of the characteristics of cracks, wear and corrosion, it is determined that there is deformation risk data in the point cloud feature data;

[0117] If there are no characteristics of cracks, wear and corrosion, it is determined that there is no deformation risk data in the point cloud feature data.

[0118] Furthermore, the step of determining whether there is deformation risk data in the point cloud feature data includes:

[0119] Obtaining force characteristic data and deformation characteristic data corresponding to a preset measuring point position in the point cloud characteristic data, and generating a force change rate corresponding to the force characteristic data based on historical force characteristic data, and generating a deformation change rate corresponding to the deformation characteristic data based on historical deformation characteristic data;

[0120] Determine whether the force change rate is greater than a preset force threshold, and whether the deformation change rate is greater than a preset deformation threshold;

[0121] If the force change rate is greater than a preset force threshold and / or the deformation change rate is greater than a preset deformation threshold, it is determined that deformation risk data exists in the point cloud feature data;

[0122] If the force change rate is not greater than a preset force threshold, and the deformation change rate is not greater than a preset deformation threshold, it is determined that there is no deformation risk data in the point cloud feature data.

[0123] Furthermore, if there is deformation risk data, the step of performing deformation warning on the deformation risk data in the three-dimensional model includes:

[0124] If deformation risk data exists, determining the risk type of the deformation risk data;

[0125] If the risk type is an existing risk, the risk level corresponding to the deformation risk data is generated according to at least one of the characteristics of cracks, wear and corrosion.

[0126] If the risk type is a predicted risk, a risk level corresponding to the deformation risk data is generated according to a force difference between the force change rate and a preset force threshold, and / or a deformation difference between the deformation change rate and a preset deformation threshold;

[0127] Determine a warning color corresponding to the risk type and risk level, and a model position of the deformation risk data in a three-dimensional model, and render the model position with the warning color to perform a deformation warning for the deformation risk data based on the rendering of the warning color.

[0128] Further, after the step of rendering the model position in the warning color, the processor 1001 may call the control program stored in the storage 1005 and perform the following operations:

[0129] Acquire a unit position in the hydro-generator unit corresponding to the model position;

[0130] Calling a preset risk template, and adding the unit position, the deformation risk data, the risk type and the risk level to the preset risk template to generate a risk report;

[0131] The risk report is output.

[0132] Furthermore, the step of preprocessing the three-dimensional point cloud data to obtain initial point cloud data includes:

[0133] Performing statistical filtering on the three-dimensional point cloud data to remove noise data in the three-dimensional point cloud data to obtain first-type preprocessed data;

[0134] Deduplication is performed on the first type of preprocessed data to obtain second type of preprocessed data;

[0135] It is determined whether there are hole data in the second type of pre-processed data. If there are hole data, interpolation processing is performed on the hole data in the second type of pre-processed data to obtain the initial point cloud data.

[0136] Furthermore, the step of obtaining the three-dimensional point cloud data of the hydro-generator set includes:

[0137] emitting laser light and projecting light patterns to the hydro-generator set based on a laser emitting device;

[0138] Acquire the reflection time or phase difference of the laser reflected by the hydro-generator set, and acquire the reflection pattern corresponding to the light pattern;

[0139] generating first three-dimensional point cloud data according to the reflection time or phase difference, and generating second three-dimensional point cloud data according to the reflection pattern;

[0140] The first three-dimensional point cloud data and the second three-dimensional point cloud data are generated as the three-dimensional point cloud data.

[0141] The specific implementation of the hydro-generator set deformation field monitoring system based on the three-dimensional point cloud model of the present invention is basically the same as the various embodiments of the above-mentioned hydro-generator set deformation field monitoring method based on the three-dimensional point cloud model, and will not be repeated here.

[0142] The embodiment of the present invention further provides a storage medium having a control program stored thereon, and when the control program is executed by a processor, the steps of the above-mentioned method for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model are implemented.

[0143] The storage medium of the present invention may be a computer-readable storage medium, and its implementation is substantially the same as the above-mentioned embodiments of the method for monitoring the deformation field of a hydro-generator set based on a three-dimensional point cloud model, and will not be described in detail herein.

[0144] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims. All equivalent structures or equivalent process changes made using the contents of the specification and drawings of the present invention, or directly or indirectly used in other related technical fields, are protected by the present invention.

Claims

1. A method for monitoring deformation field of a hydro-generator set based on a three-dimensional point cloud model, characterized in that: The method for monitoring the deformation field of a hydro-generator set comprises: At each preset period, three-dimensional point cloud data of the hydro-generator set is acquired, and the three-dimensional point cloud data is pre-processed to obtain initial point cloud data; Performing feature extraction on the initial point cloud data to obtain point cloud feature data, and performing three-dimensional reconstruction based on the initial point cloud data and the point cloud feature data to obtain a three-dimensional model; It is determined whether there is deformation risk data in the point cloud feature data. If there is deformation risk data, a deformation warning is performed on the deformation risk data in the three-dimensional model.

2. The method for monitoring deformation field of a hydro-generator set according to claim 1, characterized in that: The step of determining whether there is deformation risk data in the point cloud feature data comprises: Filtering target point cloud data corresponding to a preset measuring point position from the point cloud feature data, and analyzing whether the preset measuring point position has at least one of the characteristics of cracks, wear, and corrosion according to the target point cloud data; If there is at least one of the characteristics of cracks, wear and corrosion, it is determined that there is deformation risk data in the point cloud feature data; If there are no characteristics of cracks, wear and corrosion, it is determined that there is no deformation risk data in the point cloud feature data.

3. The method for monitoring deformation field of a hydro-generator set according to claim 1, characterized in that: The step of determining whether there is deformation risk data in the point cloud feature data comprises: Obtaining force characteristic data and deformation characteristic data corresponding to a preset measuring point position in the point cloud characteristic data, and generating a force change rate corresponding to the force characteristic data based on historical force characteristic data, and generating a deformation change rate corresponding to the deformation characteristic data based on historical deformation characteristic data; Determine whether the force change rate is greater than a preset force threshold, and whether the deformation change rate is greater than a preset deformation threshold; If the force change rate is greater than a preset force threshold and / or the deformation change rate is greater than a preset deformation threshold, it is determined that deformation risk data exists in the point cloud feature data; If the force change rate is not greater than a preset force threshold, and the deformation change rate is not greater than a preset deformation threshold, it is determined that there is no deformation risk data in the point cloud feature data.

4. The method for monitoring deformation field of a hydro-generator set according to claim 1, characterized in that: If there is deformation risk data, the step of performing deformation warning on the deformation risk data in the three-dimensional model includes: If deformation risk data exists, determining the risk type of the deformation risk data; If the risk type is an existing risk, the risk level corresponding to the deformation risk data is generated according to at least one of the characteristics of cracks, wear and corrosion. If the risk type is a predicted risk, a risk level corresponding to the deformation risk data is generated according to a force difference between the force change rate and a preset force threshold, and / or a deformation difference between the deformation change rate and a preset deformation threshold; Determine a warning color corresponding to the risk type and risk level, and a model position of the deformation risk data in a three-dimensional model, and render the model position with the warning color to perform a deformation warning for the deformation risk data based on the rendering of the warning color.

5. The method for monitoring deformation field of a hydro-generator set according to claim 4, characterized in that: The step of rendering the model position in the warning color comprises: Acquire a unit position in the hydro-generator unit corresponding to the model position; Calling a preset risk template, and adding the unit position, the deformation risk data, the risk type and the risk level to the preset risk template to generate a risk report; The risk report is output.

6. The method for monitoring deformation field of a hydro-generator set according to any one of claims 1 to 5, characterized in that: The step of preprocessing the three-dimensional point cloud data to obtain initial point cloud data comprises: Performing statistical filtering on the three-dimensional point cloud data to remove noise data in the three-dimensional point cloud data to obtain first-type preprocessed data; Deduplication is performed on the first type of preprocessed data to obtain second type of preprocessed data; It is determined whether there are hole data in the second type of pre-processed data. If there are hole data, interpolation processing is performed on the hole data in the second type of pre-processed data to obtain the initial point cloud data.

7. The method for monitoring deformation field of a hydro-generator set according to any one of claims 1 to 5, characterized in that: The step of obtaining the three-dimensional point cloud data of the hydro-generator set comprises: emitting laser light and projecting light patterns to the hydro-generator set based on a laser emitting device; Acquire the reflection time or phase difference of the laser reflected by the hydro-generator set, and acquire the reflection pattern corresponding to the light pattern; generating first three-dimensional point cloud data according to the reflection time or phase difference, and generating second three-dimensional point cloud data according to the reflection pattern; The first three-dimensional point cloud data and the second three-dimensional point cloud data are generated as the three-dimensional point cloud data.

8. A deformation field monitoring device for a hydro-generator set based on a three-dimensional point cloud model, characterized in that: The deformation field monitoring device of the hydro-generator set comprises: An acquisition module is used to acquire three-dimensional point cloud data of the hydro-generator set at preset intervals, and pre-process the three-dimensional point cloud data to obtain initial point cloud data; A reconstruction module, used for performing feature extraction on the initial point cloud data to obtain point cloud feature data, and performing three-dimensional reconstruction based on the initial point cloud data and the point cloud feature data to obtain a three-dimensional model; The early warning module is used to determine whether there is deformation risk data in the point cloud feature data. If there is deformation risk data, deformation early warning is performed on the deformation risk data in the three-dimensional model.

9. A deformation field monitoring system for a hydro-generator set based on a three-dimensional point cloud model, characterized in that: The deformation field monitoring system of the hydro-generator set includes a storage, a processor, a communication bus and a control program stored in the storage: The communication bus is used to realize the connection and communication between the processor and the storage; The processor is used to execute the control program to implement the steps of the hydro-generator set deformation field monitoring system based on a three-dimensional point cloud model as described in any one of claims 1-7.

10. A storage medium, characterized in that: The storage medium stores a control program, and when the control program is executed by the processor, the steps of the deformation field monitoring system of a hydro-generator set based on a three-dimensional point cloud model as described in any one of claims 1 to 7 are implemented.

Images