New energy station transformer vibration monitoring platform
By employing millimeter-wave radar arrays and intelligent processing chips in the transformer monitoring platform of new energy power plants, combined with digital twin technology and blockchain evidence storage, the problems of high cost and low accuracy in transformer vibration monitoring have been solved, achieving high precision, rapid fault location, and system rationality.
Patent Information
- Application Number
- CN202511565625.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-30
- Publication Date
- 2026-02-10
Smart Images
Figure CN121509482A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power equipment testing technology, and in particular to a vibration monitoring platform for transformers in new energy power plants. Background Technology
[0002] In renewable energy power plants, the installed capacity is gradually increasing, leading to a corresponding increase in the number and capacity of transformers. The integration of numerous power electronic devices generates significant harmonics, making vibration monitoring of transformers in renewable energy power plants even more crucial. Transformer vibration monitoring faces three major challenges: the high cost of deploying traditional sensors, with a single monitoring system costing over 200,000 yuan; low accuracy of the correlation model between vibration data and mechanical faults, often less than 65%; and long average fault warning response time, reaching 48 hours.
[0003] Transformers are critical equipment, and their mechanical vibration directly affects the safety of equipment and systems. However, traditional contact sensors suffer from installation difficulties and electromagnetic interference. Among existing technologies, millimeter-wave radar offers a new approach to vibration monitoring due to its advantages such as non-contact measurement and strong anti-interference capabilities. However, the multipath effect caused by the complex substation environment severely interferes with the accuracy of vibration signals, necessitating innovative solutions.
[0004] Meanwhile, strong electromagnetic interference can degrade the signal-to-noise ratio of electrical sensors; oil vibration can cause distortion of traditional fiber optic monitoring signals, with errors reaching 15%-20%; and multi-source coupling can lead to low fault location accuracy, often less than 60%. Existing technologies use a split-type accelerometer layout, which has drawbacks such as complex installation and poor resistance to oil disturbances.
[0005] The design of the transformer monitoring system in a new energy power station directly affects whether the transformer can work normally; ensuring the rationality and comprehensiveness of the design structure of the transformer monitoring system in a new energy power station is crucial to ensuring the safety of the new energy power station. Summary of the Invention
[0006] This invention provides a vibration monitoring platform for transformers in new energy power plants to achieve millimeter-level monitoring of transformer vibration status.
[0007] This invention provides a vibration monitoring platform for transformers in new energy power plants, comprising: a sensing layer, an edge layer, and a platform layer; the sensing layer, edge layer, and platform layer are communicatively connected; wherein, the sensing layer includes at least one of a millimeter-wave radar array, a contact-type vibration acceleration sensor probe array, and an acoustic emission sensor array, used to collect transformer vibration signals; the edge layer is equipped with an intelligent processing chip, used to perform real-time spectrum analysis and feature extraction on the vibration signals collected by the sensing layer; the platform layer includes a digital twin mapping module, a structural data modeling module, a fault simulation library, and a blockchain storage module; wherein, the digital twin mapping module is used to synchronously deploy acceleration sensor nodes in a virtual model; the structural data modeling module is used to establish a three-dimensional electromagnetic-mechanical coupling model of the transformer using the finite element analysis method; the fault simulation library is used to store the characteristics of various typical fault modes of the transformer; and the blockchain storage module is used to store vibration data and related analysis results on the blockchain.
[0008] This invention divides the transformer vibration monitoring platform for new energy power plants into three layers: a sensing layer, an edge layer, and a platform layer. The sensing layer uses a millimeter-wave radar array to capture vibrations at the micrometer level. Combined with digital twin technology in the platform layer, a virtual-real mapping is constructed, and blockchain technology ensures the reliable uploading of data. The edge layer is equipped with intelligent processing chips; the deployment of edge computing nodes can reduce network transmission load by 80%, ultimately forming a group-level vibration monitoring knowledge graph. This approach ensures the rationality and comprehensiveness of the transformer monitoring system design structure for new energy power plants, playing a crucial role in guaranteeing the safety of these plants.
[0009] In the aforementioned new energy power station transformer vibration monitoring platform, the millimeter-wave radar array adopts a 77GHz frequency-modulated continuous wave radar with a range resolution of no more than 0.04mm and a vibration range of no less than ±50mm.
[0010] By employing a millimeter-wave radar array with a 77GHz frequency-modulated continuous wave radar, and ensuring that its range resolution is no greater than 0.04mm and its vibration range is no less than ±50mm, this invention is significantly superior to traditional radar in terms of accuracy, reliability, and integration.
[0011] In the aforementioned new energy power station transformer vibration monitoring platform, the structural data modeling module determines the resonant frequency range of windings and core components through modal analysis.
[0012] By modeling structural data, the resonant frequency range of windings and core components is determined, ensuring that the determined results are more accurate and usable. At the same time, performance optimization functions can be achieved.
[0013] In the aforementioned new energy power station transformer vibration monitoring platform, the edge layer integrates temperature field monitoring data for compensating and correcting vibration characteristics; among them, an oil temperature change of ±5℃ corresponds to a vibration characteristic offset of 12%.
[0014] By integrating temperature field monitoring data, vibration characteristics are compensated and corrected to ensure that vibration characteristic shifts can be corrected according to stable changes. Simultaneously, a 12% vibration shift is specified for every 5 degrees Celsius change in oil temperature, limiting the value of the vibration shift to ensure that the vibration shift results conform to the actual conditions of the usage scenario.
[0015] In the aforementioned new energy power station transformer vibration monitoring platform, the digital twin mapping module synchronously arranges acceleration sensor nodes in the virtual model, with the position error controlled within ±3mm, and the correlation coefficient between the physical sensor data and the virtual model output is not less than 0.85.
[0016] By synchronously deploying accelerometer sensor nodes in the virtual model, modeling and analysis efficiency is improved, and data consistency and reliability are enhanced. Simultaneously, positional errors are controlled within ±3mm, and the correlation coefficient between physical sensor data and virtual model output is no less than 0.85, further reducing risk and enhancing data consistency.
[0017] In the aforementioned new energy power station transformer vibration monitoring platform, the intelligent processing chip in the edge layer is an AI chip, and the latency of the AI chip for real-time vibration spectrum analysis is less than 50ms.
[0018] The edge layer uses an AI chip as its intelligent processing chip, which is highly intelligent and has low latency, making the real-time spectrum analysis and feature extraction process of vibration signals collected by the sensing layer more reliable.
[0019] In the aforementioned new energy power plant transformer vibration monitoring platform, the blockchain evidence storage module feeds the vibration data back to the equipment manufacturer.
[0020] The blockchain-based evidence storage module is used to feed vibration data back to equipment manufacturers. This not only ensures the recording and transmission of vibration data but also allows manufacturers to obtain vibration data information for equipment optimization.
[0021] The aforementioned new energy power station transformer vibration monitoring platform includes a fault simulation library containing at least one of the following faults: core loosening, winding deformation, magnetostrictive vibration, and insulation aging.
[0022] By constructing a fault database, faults such as core loosening, winding deformation, retraction vibration, and insulation aging are recorded. This allows for precise and rapid fault location when abnormal vibration data is detected, enabling rapid response and handling of faults and ensuring the accuracy of fault detection results.
[0023] Beneficial Effects: This invention divides the transformer vibration monitoring platform for new energy power plants into three layers: a sensing layer, an edge layer, and a platform layer. The sensing layer utilizes a millimeter-wave radar array to capture vibrations at the micrometer level. Combined with digital twin technology in the platform layer, a virtual-real mapping is constructed, and blockchain technology ensures the reliable uploading of data. The edge layer is equipped with intelligent processing chips, and the deployment of edge computing nodes can reduce network transmission load by 80%, ultimately forming a group-level vibration monitoring knowledge graph. This approach ensures the rationality and comprehensiveness of the transformer monitoring system design structure for new energy power plants, playing a crucial role in guaranteeing the safety of these plants. Attached Figure Description
[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0025] Figure 1 This is a schematic diagram of the structure of a new energy power station transformer vibration monitoring platform provided in Embodiment 1 of the present invention;
[0026] Figure 2 This is a schematic diagram of the structure of a new energy power station transformer vibration monitoring platform provided in Embodiment 2 of the present invention;
[0027] Figure 3 This is a schematic diagram of the structure of a new energy power station transformer vibration monitoring platform provided in Embodiment 3 of the present invention;
[0028] Figure 4 This is a structural schematic diagram of a new energy power station transformer vibration monitoring platform provided in Embodiment 4 of the present invention. Detailed Implementation
[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.
[0030] In the following embodiments of the present invention, "and / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (item)" or similar expressions below refer to any combination of these items, including any combination of single (item) or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple. The singular forms "a", "an", "the", "above-mentioned", "said", and "this" are intended to also include expressions such as "one or more" unless there is a clear contrary indication in the context. Also, unless otherwise stated, the ordinal numbers such as "first", "second", etc. mentioned in the embodiments of the present invention are used to distinguish multiple objects and are not used to limit the order, time sequence, priority, or importance of multiple objects.
[0031] Reference to "one embodiment" or "some embodiments" etc. described in the specification of the present invention means that specific features, structures, or characteristics described in connection with that embodiment are included in one or more embodiments of the present invention. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear at different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments" unless otherwise specifically emphasized. The terms "comprise", "include", "have" and their variants all mean "including but not limited to" unless otherwise specifically emphasized.
[0032] Embodiment 1
[0033] Embodiment 1 of the present invention provides a vibration monitoring platform for a new energy power station transformer. The platform includes, as shown below Figure 1 a sensing layer, an edge layer, and a platform layer, and the sensing layer, the edge layer, and the platform layer are communicatively connected.
[0034] Among them, the sensing layer includes at least one of a millimeter-wave radar array, a contact vibration acceleration sensor probe array, and an acoustic emission sensor array, and is used to collect transformer vibration signals.
[0035] The millimeter-wave radar array employs a Multiple Input Multiple Output (MIMO) antenna design, forming a 5×5 monitoring network on the surface of the transformer tank. It analyzes winding displacement using the Doppler effect. Winding displacement includes changes in axial and radial dimensions, valve body displacement, winding deformation, expansion, and inter-turn short circuits. By using the Doppler effect to analyze the presence and type of winding displacement, immediate location of the winding displacement can be achieved, ensuring the stability of the millimeter-wave radar array. It should be noted that the aforementioned 5×5 monitoring network is only one example; other specifications of monitoring networks, such as a 4×4 monitoring network, can also be used, and this invention does not limit this to any particular type.
[0036] The millimeter-wave radar array uses a 77GHz frequency-modulated continuous wave radar with a range resolution of no more than 0.04mm and a vibration range of no less than ±50mm.
[0037] In a preferred embodiment of the present invention, the sensing layer uses a frequency-modulated continuous wave (FMCW) millimeter-wave radar array, the contact-type vibration acceleration sensor probe array is composed of piezoelectric accelerometers with a range of ±50g, and the acoustic emission sensor array is composed of acoustic emission sensors with a frequency band in the 20-400kHz range, ultimately forming a hybrid non-contact and contact monitoring network. However, the above is only a preferred embodiment of the present invention, and other radar arrays, other accelerometers, and other acoustic emission sensor arrays can also be used to construct the structure of the sensing layer of the present invention, which is not limited by the present invention.
[0038] The edge layer is equipped with an intelligent processing chip, which is used to perform real-time spectrum analysis and feature extraction on the vibration signals collected by the sensing layer.
[0039] The intelligent processing chip is an AI chip, and the latency of the AI chip for real-time vibration spectrum analysis is less than 50ms. The edge layer uses an AI chip as its intelligent processing chip, which is highly intelligent and has low latency, making the real-time spectrum analysis and feature extraction process of vibration signals collected by the sensing layer more reliable.
[0040] The edge layer integrates temperature field monitoring data to compensate for and correct vibration characteristics; a change in oil temperature of ±5℃ corresponds to a 12% shift in vibration characteristics. For example, if the initial oil temperature is 80℃ and the changed oil temperature is 85℃, the temperature field monitoring data will compensate for and correct the vibration characteristics, shifting the vibration characteristics by 12%.
[0041] By integrating temperature field monitoring data, vibration characteristics are compensated and corrected to ensure that vibration characteristic shifts can be corrected according to stable changes. Simultaneously, a 12% vibration shift is specified for every 5 degrees Celsius change in oil temperature, limiting the value of the vibration shift to ensure that the vibration shift results conform to the actual conditions of the usage scenario.
[0042] The platform layer includes a digital twin mapping module, a structured data modeling module, a fault simulation library, and a blockchain evidence storage module.
[0043] The system includes a digital twin mapping module for synchronously deploying acceleration sensor nodes in a virtual model; a structural data modeling module for establishing a three-dimensional electromagnetic-mechanical coupling model of the transformer using finite element analysis; a fault simulation library for storing characteristics of various typical fault modes of the transformer; and a blockchain evidence storage module for storing vibration data and related analysis results on the blockchain. It should be noted that the three-dimensional electromagnetic-mechanical coupling model of the transformer is existing technology.
[0044] The digital twin mapping module synchronously deploys acceleration sensor nodes in the virtual model, with the position error controlled within ±3mm, and the correlation coefficient between the physical sensor data and the virtual model output is not less than 0.85.
[0045] The structural data modeling module determines the resonant frequency range of the winding and core components through modal analysis of a three-dimensional electromagnetic-mechanical coupling model. The resonant frequency range of the winding and core components is within the range of 50-1000Hz.
[0046] A fault simulation library is established, containing various typical fault modes. The library includes at least one fault from the following categories: core loosening, winding deformation, magnetostrictive vibration, and insulation aging. Specifically, the characteristic frequency of core loosening is 78-82Hz, the characteristic frequency of winding deformation is 120-150Hz, the acceleration range of magnetostrictive vibration is 0.8-1.2 m / s², and the criterion for insulation aging is tanδ > 0.8%, where tanδ is the tangent of the dielectric loss angle of the insulation. It should be noted that the above characteristic frequencies and fault types are only examples; the fault simulation library of this invention can also include other fault content, and the characteristic frequencies can be adjusted according to actual conditions. This invention does not limit these aspects.
[0047] The blockchain-based evidence storage module feeds vibration data back to equipment manufacturers, meeting their needs for technological innovation and equipment improvement. Equipment manufacturers have incentive mechanisms in place; for example, a RMB reward is automatically triggered for every 1000 valid vibration data points received. This reward is obtained through blockchain data ownership verification.
[0048] The digital twin modeling module constructs an electromagnetic-mechanical coupling model using the multiphysics simulation software COMSOL. Modal analysis shows that the first-order resonant frequency of the iron core is 63.5Hz. A real-time simulator is deployed in ANSYS Twin Builder software, and the correlation coefficient between the physical sensor output and the virtual model output reaches 0.89.
[0049] Example 2
[0050] Embodiment 2 of the present invention provides a vibration monitoring platform for transformers in new energy power plants, based on Embodiment 1. Unlike the hybrid monitoring network in Embodiment 1, Embodiment 2 uses a millimeter-wave radar array to collect transformer vibration signals. The platform is as follows: Figure 2 As shown, the sensing layer includes a millimeter-wave radar array for collecting transformer vibration signals.
[0051] The millimeter-wave radar array uses a 77GHz frequency-modulated continuous wave radar with a range resolution of no more than 0.04mm and a vibration range of no less than ±50mm.
[0052] In a preferred embodiment of the present invention, the sensing layer uses a frequency-modulated continuous wave millimeter-wave radar array. However, the above is only a preferred embodiment of the present invention, and other radar arrays can also be used to construct the structure of the sensing layer of the present invention; the present invention does not limit this to any particular type.
[0053] Example 3
[0054] Embodiment 3 of the present invention provides a vibration monitoring platform for transformers in new energy power plants, based on Embodiment 1. Unlike the hybrid monitoring network in Embodiment 1, Embodiment 2 uses a contact-type vibration accelerometer probe array to collect transformer vibration signals. The platform is as follows: Figure 3 As shown, the sensing layer includes a contact vibration accelerator probe array for acquiring transformer vibration signals.
[0055] In a preferred embodiment of the present invention, the contact vibration acceleration sensor probe array of the sensing layer is constructed using a piezoelectric acceleration sensor with a range of ±50g. However, the above is only a preferred embodiment of the present invention, and other acceleration sensors can also be used to construct the structure of the sensing layer of the present invention; the present invention does not limit this to such applications.
[0056] Example 4
[0057] Embodiment 3 of the present invention provides a vibration monitoring platform for transformers in new energy power plants, based on Embodiment 1. Unlike the hybrid monitoring network in Embodiment 1, Embodiment 2 uses an acoustic emission sensor array to collect transformer vibration signals. The platform is as follows: Figure 4 As shown, the sensing layer includes an array of acoustic emission sensors for collecting transformer vibration signals.
[0058] In a preferred embodiment of the present invention, the acoustic emission sensor array of the sensing layer is composed of acoustic emission sensors with a frequency band in the range of 20-400kHz. However, the above is only a preferred embodiment of the present invention, and other acoustic emission sensor arrays can also be used to construct the structure of the sensing layer of the present invention, and the present invention does not limit this to any particular type.
[0059] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "up," "down," "front," "rear," "left," "right," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only used to explain the relative positional relationship and movement between components in a specific posture. If the specific posture changes, the directional indication will also change accordingly. These terms are used only for the convenience of describing the invention and for simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting the invention.
[0060] Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.
[0061] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.
[0062] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.
Claims
1. A vibration monitoring platform for transformers in new energy power plants, characterized in that, include: The system comprises a perception layer, an edge layer, and a platform layer; these three layers are communicatively connected. The sensing layer includes at least one of a millimeter-wave radar array, a contact vibration acceleration sensor probe array, and an acoustic emission sensor array, used to collect transformer vibration signals; The edge layer is equipped with an intelligent processing chip, which is used to perform real-time spectrum analysis and feature extraction on the vibration signals collected by the sensing layer; The platform layer includes a digital twin mapping module, a structural data modeling module, a fault simulation library, and a blockchain evidence storage module. The digital twin mapping module is used to synchronously deploy acceleration sensor nodes in the virtual model. The structural data modeling module is used to establish a three-dimensional electromagnetic-mechanical coupling model of the transformer using finite element analysis. The fault simulation library stores the characteristics of various typical fault modes of the transformer. The blockchain evidence storage module stores vibration data and related analysis results on the blockchain.
2. The new energy power station transformer vibration monitoring platform according to claim 1, characterized in that, The millimeter-wave radar array uses a 77GHz frequency-modulated continuous wave radar with a range resolution of no more than 0.04mm and a vibration range of no less than ±50mm.
3. The new energy power station transformer vibration monitoring platform according to claim 1, characterized in that, The structural data modeling module determines the resonant frequency range of the winding and core components through modal analysis of the three-dimensional electromagnetic-mechanical coupling model.
4. The vibration monitoring platform for transformers in new energy power plants according to claim 1, characterized in that, The edge layer integrates temperature field monitoring data for compensating and correcting vibration characteristics; where a change in oil temperature of ±5℃ corresponds to a 12% shift in vibration characteristics.
5. The new energy power station transformer vibration monitoring platform according to claim 1, characterized in that, The digital twin mapping module synchronously arranges acceleration sensor nodes in the virtual model, with the position error controlled within ±3mm, and the correlation coefficient between the physical sensor data and the virtual model output is not less than 0.
85.
6. The vibration monitoring platform for transformers in new energy power plants according to claim 1, characterized in that, The intelligent processing chip in the edge layer is an AI chip, and the latency of the AI chip for real-time vibration spectrum analysis is less than 50ms.
7. The new energy power station transformer vibration monitoring platform according to claim 1, characterized in that, The blockchain-based evidence storage module is used to feed the vibration data back to the equipment manufacturer.
8. A multi-element vibration monitoring platform for transformers in new energy power plants according to claim 1, characterized in that, The fault simulation library includes at least one of the following faults: core loosening, winding deformation, magnetostrictive vibration, and insulation aging.