Wind generating set bearing self-powered intelligent monitoring method and system based on phase change material temperature control and thermoelectric effect

Abstract

The invention discloses a wind generating set bearing self-powered intelligent monitoring method and system based on phase change material temperature control and a thermoelectric effect, and relates to the technical field of state monitoring and fault diagnosis of wind power generation equipment. The method comprises the steps that when it is detected that bearing power supply voltage is abnormal, the abnormal working condition grade is recognized, and a target monitoring mode is matched; in the mode, a high-frequency vibration signal is monitored, the vibration heat production amount is calculated, and a vibration-heat release curve is established in combination with the temperature control characteristic of the phase change material; predicting the output voltage of the thermoelectric module based on the curve, and determining a target heat release rate curve of the phase change material according to inertial data of voltage change; and finally, controlling the heat release of the phase change material according to the target curve to stabilize the output voltage of the thermoelectric module. By means of the mode, heat is generated through vibration of the bearing under the working condition that external power supply is abnormal, stable electric energy is provided for the monitoring system through intelligent heat management, and the reliability and the self-maintaining capacity of the monitoring system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of wind power generation equipment state monitoring and fault diagnosis, in particular to a wind turbine generator unit bearing self-powered intelligent monitoring method and system based on phase change material temperature control and thermoelectric effect. BACKGROUND

[0002] The wind turbine generator unit usually works in harsh and remote environments, and the failure rate of its core components, the main bearing and the gearbox bearing, is high, and the maintenance cost is huge. In the prior art, online monitoring of bearings relies on vibration and temperature sensors, but these systems have obvious shortcomings: Power supply problem: wired power supply wiring is complex and costly; battery power supply needs to be replaced regularly and is inconvenient to maintain.

[0003] Sensor deployment restrictions: Traditional sensors usually require external power supply and signal lines, making it difficult to install them on rotating parts.

[0004] Single monitoring dimension: Single vibration or temperature signal cannot fully and early reflect the complex failure of the bearing.

[0005] Insufficient energy utilization: A large amount of friction heat is generated during bearing operation, while there is abundant wind energy around the unit, which is not effectively collected and utilized in the existing monitoring system.

[0006] In the prior art, although there have been attempts to use TEG for energy collection, the TEG power generation efficiency is severely dependent on temperature difference stability. The fluctuation of bearing working conditions causes the surface temperature to change dramatically, making the TEG output power unstable and difficult to directly and continuously power the subsequent circuit. In addition, pure temperature or vibration monitoring has limited accuracy and early warning.

[0007] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0008] The main purpose of the present application is to provide a wind turbine generator unit bearing self-powered intelligent monitoring method and system based on phase change material temperature control and thermoelectric effect, aiming to solve the technical problem of unstable bearing power supply in the prior art.

[0009] To achieve the above purpose, the present application provides a wind turbine generator unit bearing self-powered intelligent monitoring method based on phase change material temperature control and thermoelectric effect, the method comprising: When the power supply voltage state information of the wind turbine generator unit bearing is abnormal, identifying the abnormal working condition level and matching the corresponding target monitoring mode according to the abnormal working condition level; In the target monitoring mode, high-frequency vibration signals are monitored, vibration heat generation is determined according to the high-frequency vibration signals, and a vibration-heat release curve is established according to the vibration heat generation and temperature control characteristics of the phase change material; A predicted output voltage of the thermoelectric module is predicted based on the vibration-heat release curve, inertia data of voltage variation is determined according to the predicted output voltage, and a target heat release rate curve of the phase change material is determined according to the inertia data; The phase change material is controlled to release heat based on the target heat release rate curve, so as to stabilize the output voltage of the thermoelectric module.

[0010] In an embodiment, when the power supply voltage state information of the wind turbine generator set bearing is a power supply voltage anomaly, an abnormal working condition level is identified, and the step of matching the corresponding target monitoring mode according to the abnormal working condition level comprises: When the power supply voltage state information of the wind turbine generator set bearing is a power supply voltage anomaly, a power supply voltage sequence in a current sampling period is determined, and a peak voltage and a valley voltage in the power supply voltage sequence are determined; A peak-to-peak voltage is determined according to the peak voltage and the valley voltage; The peak-to-peak voltage is mapped to an abnormal working condition level table to obtain an abnormal working condition level; The corresponding target monitoring mode is matched according to the abnormal working condition level.

[0011] In an embodiment, the step of monitoring high-frequency vibration signals in the target monitoring mode, determining vibration heat generation according to the high-frequency vibration signals, and establishing a vibration-heat release curve according to the vibration heat generation and temperature control characteristics of the phase change material comprises: In the target monitoring mode, high-frequency vibration signals of vibration acceleration sensors distributed in multiple quadrants of the bearing are collected; The high-frequency vibration signals are subjected to frequency spectrum analysis and packet decomposition to extract vibration energy of the bearing; Vibration heat generation is obtained based on a vibration energy-heat generation conversion coefficient and the vibration energy; Temperature control characteristics of the phase change material are determined, and a vibration-heat release curve is established according to the temperature control characteristics and the vibration heat generation.

[0012] In an embodiment, the step of subjecting the high-frequency vibration signals to frequency spectrum analysis and packet decomposition to extract vibration energy of the bearing comprises: The high-frequency vibration signals are subjected to fast Fourier transform to obtain energy distribution of the high-frequency vibration signals in multiple characteristic frequency bands; The high-frequency vibration signals are subjected to full-band subdivision by using a wavelet packet decomposition algorithm to extract detail sub-band signals related to bearing fault characteristic frequencies; An energy value of each of the detail sub-band signals is calculated, and the energy values are fused with energy distribution of a corresponding characteristic frequency band to obtain vibration energy of the bearing.

[0013] In an embodiment, the step of determining the temperature control characteristic of the phase change material, and establishing a vibration-heat release curve according to the temperature control characteristic and the vibration heat generation amount comprises: determining the temperature control characteristic of the phase change material, and calculating a theoretical heat absorption rate of the phase change material according to the real-time heat generation amount and the current phase change state of the phase change material; constructing a thermodynamic differential equation with time as a variable according to the heat dissipation environment parameter of the bearing and the theoretical heat absorption rate; solving the thermodynamic differential equation to simulate a vibration-heat release curve representing a dynamic process of heat absorption and release of the phase change material driven by vibration heat generation.

[0014] In an embodiment, the step of determining a target heat release rate curve of the phase change material according to the inertia data comprises: establishing an optimization function of voltage output stability based on the inertia data; reversely solving a target heat release rate sequence based on the optimization function; smoothing and physically constraining the target heat release rate sequence to generate a target heat release rate curve.

[0015] In an embodiment, the step of smoothing and physically constraining the target heat release rate sequence to generate a target heat release rate curve comprises: smoothing the target heat release rate sequence by using a filter to obtain a smoothed sequence; physically constraining the smoothed sequence by a rate upper limit and a change gradient according to a maximum heat absorption and release capacity and a thermal response time constant of the phase change material; when a numerical point in the smoothed sequence exceeds a physical constraint range, correcting the numerical point to a boundary value, and generating a target heat release rate curve based on the corrected numerical point.

[0016] In an embodiment, the step of controlling the phase change material to release heat based on the target heat release rate curve comprises: converting the target heat release rate curve into a control timing instruction; controlling a heat release rate of the phase change material according to the control timing instruction, so that the phase change material releases heat.

[0017] In an embodiment, when the power supply voltage state information of the wind turbine generator set bearing is abnormal, the step of identifying an abnormal working condition level according to the target monitoring mode corresponding to the abnormal working condition level before the step of matching the target monitoring mode is further included. Based on the preset acquisition frequency, the real-time power supply voltage sequence of the wind turbine generator set bearing is acquired, and the voltage fluctuation characteristics of the real-time power supply voltage sequence are extracted. The voltage fluctuation characteristics are input into an abnormal grading model to obtain voltage fluctuation grading information. The voltage fluctuation grading information is detected to obtain the power supply voltage state information.

[0018] In addition, to achieve the above-mentioned purpose, the present application also proposes a wind turbine generator set bearing self-power intelligent monitoring system based on phase change material temperature control and thermoelectric effect, which comprises: The state monitoring module is used to identify an abnormal working condition level when the power supply voltage state information of the wind turbine generator set bearing is abnormal, and to match the target monitoring mode corresponding to the abnormal working condition level. The thermal correlation modeling module is used to monitor high-frequency vibration signals under the target monitoring mode, to determine vibration heat generation according to the high-frequency vibration signals, and to establish a vibration-heat release curve according to the vibration heat generation and the temperature control characteristics of the phase change material. The output prediction module is used to predict the predicted output voltage of the thermoelectric module based on the vibration-heat release curve, to determine the inertia data of the voltage change according to the predicted output voltage, and to determine the target heat release rate curve of the phase change material according to the inertia data. The temperature control execution module is used to control the phase change material to release heat based on the target heat release rate curve, so as to stabilize the output voltage of the thermoelectric module.

[0019] In addition, to achieve the above-mentioned purpose, the present application also proposes a wind turbine generator set bearing self-power intelligent monitoring device based on phase change material temperature control and thermoelectric effect, which comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the wind turbine generator set bearing self-power intelligent monitoring method based on phase change material temperature control and thermoelectric effect as described above.

[0020] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the wind turbine generator set bearing self-power intelligent monitoring method based on phase change material temperature control and thermoelectric effect as described above.

[0021] In addition, to achieve the above-mentioned object, the application further provides a computer program product, which comprises a computer program, and the computer program realizes the steps of the wind turbine generator bearing self-powered intelligent monitoring method based on phase change material temperature control and thermoelectric effect as above when executed by a processor.

[0022] The application provides a wind turbine generator bearing self-powered intelligent monitoring method based on phase change material temperature control and thermoelectric effect. When the bearing power supply voltage is detected to be abnormal, the abnormal working condition level is identified and the target monitoring mode is matched. In this mode, the high-frequency vibration signal is monitored and the vibration heat production is calculated, and the vibration-heat release curve is established in combination with the temperature control characteristics of the phase change material. The output voltage of the thermoelectric module is predicted based on the curve, the target heat release rate curve of the phase change material is determined according to the inertia data of the voltage change, and finally the heat release of the phase change material is controlled according to the target curve to stabilize the output voltage of the thermoelectric module. In the above manner, the application realizes that in the external power supply abnormal working condition, the bearing vibration heat production is utilized, the intelligent thermal management is used to provide stable power for the monitoring system, and the reliability and self-maintenance capability of the monitoring system are improved. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the application and, together with the specification, serve to explain the principles of the application.

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without creative labor.

[0025] Figure 1 Flowchart of the wind turbine generator bearing self-powered intelligent monitoring method based on phase change material temperature control and thermoelectric effect in Embodiment One of the application; Figure 2 Vibration-heat release curve of the wind turbine generator bearing self-powered intelligent monitoring method in Embodiment One of the application based on phase change material temperature control and thermoelectric effect; Figure 3 Module structure schematic diagram of the wind turbine generator bearing self-powered intelligent monitoring system based on phase change material temperature control and thermoelectric effect in the embodiment of the application; Figure 4 Device structure schematic diagram of the hardware running environment involved in the wind turbine generator bearing self-powered intelligent monitoring method based on phase change material temperature control and thermoelectric effect in the embodiment of the application.

[0026] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0027] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0028] In order to better understand the technical solutions of the present application, the specific embodiments will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] The main solution of the embodiments of the present application is: when the power supply voltage state information of the wind turbine bearing is abnormal, the abnormal working condition level is identified, and the corresponding target monitoring mode is matched according to the abnormal working condition level; In the target monitoring mode, the high-frequency vibration signal is monitored, the vibration heat generation is determined according to the high-frequency vibration signal, and the vibration-heat release curve is established according to the vibration heat generation and the temperature control characteristics of the phase change material; Based on the vibration-heat release curve, the predicted output voltage of the thermoelectric module is predicted, the inertia data of the voltage change is determined according to the predicted output voltage, and the target heat release rate curve of the phase change material is determined according to the inertia data; Based on the target heat release rate curve, the phase change material is controlled to release heat, so that the thermoelectric module stably outputs voltage.

[0030] At present, wind turbine is usually operated in harsh and remote environment, and the failure rate of the main bearing and gearbox bearing, which are the core components of the transmission chain, is high, and the maintenance cost is huge. In the prior art, the online monitoring of the bearing mainly depends on vibration and temperature sensors, but these systems have obvious shortcomings: Power supply problem: wired power supply wiring is complex and costly; battery power supply needs to be replaced regularly, which is inconvenient to maintain.

[0031] Sensor deployment restrictions: traditional sensors usually need external power supply and signal lines, which are difficult to install on rotating parts.

[0032] Single monitoring dimension: single vibration or temperature signal is difficult to fully and early reflect the complex failure of the bearing.

[0033] Insufficient energy utilization: a large amount of friction heat is generated during the operation of the bearing, and there is abundant wind energy around the unit, which is not effectively collected and utilized in the existing monitoring system.

[0034] While there have been attempts to utilize TEGs for energy harvesting in existing technologies, their power generation efficiency is heavily dependent on temperature stability. Fluctuations in bearing operating conditions cause drastic changes in their surface temperature, resulting in unstable TEG output power and making it difficult to directly and continuously power subsequent circuits. Furthermore, simple temperature or vibration monitoring has limited accuracy and early warning capabilities.

[0035] This application provides a solution that identifies the level of abnormal operating condition and matches a target monitoring mode when an abnormal bearing power supply voltage is detected. In this mode, high-frequency vibration signals are monitored and the heat generated by vibration is calculated. A vibration-heat release curve is established by combining the temperature control characteristics of the phase change material (PCM). The output voltage of the thermoelectric module is predicted based on this curve, and the target heat release rate curve of the PCM is determined based on the inertial data of voltage changes. Finally, the heat release of the PCM is controlled according to the target curve to stabilize the output voltage of the thermoelectric module. Through this method, this application achieves stable power supply to the monitoring system by utilizing the bearing's own vibration to generate heat under abnormal external power supply conditions, thereby improving the reliability and self-sustaining capability of the monitoring system.

[0036] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone; or an electronic device capable of performing the above functions, such as a wind turbine bearing self-powered intelligent monitoring device based on phase change material temperature control and thermoelectric effect. This embodiment does not specifically limit it in this regard. The following uses a wind turbine bearing self-powered intelligent monitoring device based on phase change material temperature control and thermoelectric effect as an example to describe this embodiment and the following embodiments.

[0037] All actions involving the acquisition of signals, information, or data in this application are carried out in accordance with the relevant data protection laws and policies of the country where the application is located, and with the authorization of the owner of the relevant device.

[0038] This application provides an intelligent monitoring method for the self-powered bearings of wind turbine generators based on phase change material temperature control and thermoelectric effects, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the intelligent monitoring method for self-powered bearings of wind turbine generators based on phase change material temperature control and thermoelectric effect, as described in this application.

[0039] In this embodiment, the intelligent monitoring method for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect includes steps S10~S40: Step S10: When the power supply voltage status information of the wind turbine generator bearing is abnormal, identify the abnormal operating condition level and match the corresponding target monitoring mode according to the abnormal operating condition level.

[0040] It should be noted that the power supply voltage status information refers to the judgment conclusion reflecting whether the power supply voltage of the bearing monitoring system is within the normal operating range after continuous collection and analysis by sensors; the abnormal operating condition level is a quantitative classification of the severity of voltage abnormality, for example, it can be divided into different levels such as slight, moderate and severe according to indicators such as voltage drop amplitude and fluctuation frequency; the target monitoring mode refers to the specific working strategy dynamically activated by the system according to different abnormality levels, which determines the frequency of subsequent data collection, the density of analysis and the intensity of control execution, aiming to achieve a balance between monitoring efficiency and energy consumption under abnormal conditions.

[0041] First, the power supply voltage sequence is acquired in real time through a voltage sampling circuit, and key features are extracted using digital signal processing algorithms. Then, the feature values ​​are compared with a preset threshold range to determine the status information. When an abnormal power supply voltage is confirmed, the system calls upon a built-in expert knowledge base or a pre-trained lightweight classification model to quickly map the abnormal operating condition to a preset level based on real-time calculated peak-to-valley differences, fluctuation periods, and other specific parameters. Finally, by querying the level-mode mapping table, the system automatically triggers and switches to the corresponding target monitoring mode. The level-mode mapping table is typically predefined during the system design phase based on different reliability requirements and energy consumption constraints. For example, the sampling rate is reduced to save energy during minor anomalies, while a high-frequency diagnostic mode is activated during severe anomalies.

[0042] In one feasible implementation, the step of identifying the abnormal operating condition level and matching the corresponding target monitoring mode according to the abnormal operating condition level when the power supply voltage status information of the wind turbine generator bearing indicates an abnormal power supply voltage includes: When the power supply voltage status information of the wind turbine generator bearing indicates an abnormal power supply voltage, determine the power supply voltage sequence within the current sampling period, and determine the peak voltage and valley voltage in the power supply voltage sequence; The peak-to-peak voltage is determined based on the peak voltage and the valley voltage; The peak-to-peak voltage is mapped to an abnormal operating condition level table to obtain the abnormal operating condition level; Match the corresponding target monitoring mode according to the abnormal operating condition level.

[0043] It should be noted that the supply voltage sequence refers to a set of discrete voltage values ​​arranged in chronological order, obtained by continuously sampling the supply voltage of the bearing monitoring system at a fixed frequency using an ADC (analog-to-digital converter) within a specific time window (i.e., the sampling period). Peak voltage and valley voltage are the maximum and minimum values ​​in a given supply voltage sequence, respectively. This refers to the maximum value in the sequence, representing the peak voltage within a period; valley voltage. It is the minimum value in the sequence, representing the voltage valley value within the period.

[0044] Peak-to-peak voltage The difference between peak voltage and valley voltage, i.e. Peak-to-peak voltage directly reflects the maximum fluctuation range of the supply voltage within the current sampling period. The abnormal operating condition level table is a predefined lookup mapping table that establishes the correspondence between peak-to-peak voltage and abnormal operating condition levels. This table is based on historical data, system withstand tests, and engineering experience, and clearly defines the abnormality level corresponding to different voltage fluctuation ranges, such as Level 1 - Slight, Level 2 - Moderate, and Level 3 - Severe.

[0045] In the specific implementation, firstly, the ADC module of the system microcontroller (MCU) will sample at a fixed frequency. The supply voltage is collected within a sampling window of duration T, resulting in a sequence containing N sampling points. The program then uses a simple comparison algorithm to traverse the sequence and quickly find its maximum value. and minimum value And calculate the peak-to-peak voltage. This process can be formally represented as:

[0046] Next, the calculated The value is compared with an abnormal condition level table stored in the system's non-volatile memory (such as Flash). This table typically sets multiple threshold ranges, for example: if If so, it is level 0 (normal); if If so, it is classified as Level 1 (minor anomaly); if If so, it is classified as Level 2 (Severe Anomaly). The system uses a table lookup operation to classify consecutive... The values ​​are discretized into specific abnormal operating condition levels.

[0047] Finally, based on the determined level of abnormal operating conditions, the system indexes another level-mode configuration table and dynamically loads the corresponding target monitoring mode parameters. These parameters may include the sampling rate of the vibration sensor, the complexity of the signal processing algorithm, and the frequency of data upload. For example, level 1 may correspond to an energy-saving monitoring mode (reduced sampling rate), while level 2 corresponds to an enhanced diagnostic mode (maximum sampling rate, enabling full-band analysis). In this way, the system can intelligently adjust resource allocation when power supply is abnormal, ensuring critical monitoring functions while minimizing power consumption and improving continuous operation under adverse power conditions.

[0048] In one feasible implementation, before the step of identifying the abnormal operating condition level and matching the corresponding target monitoring mode according to the abnormal operating condition level when the power supply voltage status information of the wind turbine generator bearing indicates an abnormal power supply voltage, the method further includes: The real-time power supply voltage sequence of the wind turbine generator bearing is collected based on a preset acquisition frequency, and the voltage fluctuation characteristics of the real-time power supply voltage sequence are extracted. The voltage fluctuation characteristics are input into the anomaly classification model to obtain voltage fluctuation classification information; The voltage fluctuation classification information is detected to obtain the power supply voltage status information.

[0049] In its implementation, the system first uses the analog-to-digital converter (ADC) of the microcontroller (MCU) to continuously sample the supply voltage at a preset sampling frequency (e.g., 1kHz), forming a time series. Subsequently, instead of directly using the original voltage value, more representative voltage fluctuation characteristics are extracted. These characteristics aim to characterize abnormal voltage behavior in multiple dimensions, and may include, for example, the effective voltage value (RMS), calculated using the following formula:

[0050] RMS is used to determine the deviation of the overall voltage level; voltage fluctuation rate, i.e. This is used to quantify the amplitude of fluctuations; and the energy of short-term fluctuations can be approximated by calculating the variance of the sequence.

[0051] Next, this set of multi-dimensional feature vectors is input into a pre-trained anomaly classification model. This model can be a lightweight machine learning classifier, such as a support vector machine (SVM) or decision tree. Its advantage lies in its ability to learn the complex nonlinear relationships between different anomaly patterns (such as momentary voltage drops, sustained low voltage, and high-frequency noise interference) and feature combinations. Based on the learned decision boundaries, the model outputs a discrete voltage fluctuation classification, such as "0 - Normal", "1 - Slight fluctuation", and "2 - Severe anomaly". Compared to simple methods that rely solely on peak-to-peak values, this model integrates multiple features, effectively reducing false alarms (such as misjudgments caused by individual pulse interference).

[0052] Finally, the system checks the hierarchical information output by the model. This is typically achieved through a simple conditional statement: if hierarchical information != "0 - Normal"; then power supply voltage status information = "Power supply voltage abnormal". This step converts the multi-level classification results given by the model into a binary trigger signal.

[0053] Step S20: In the target monitoring mode, monitor the high-frequency vibration signal, determine the vibration heat generation based on the high-frequency vibration signal, and establish a vibration-heat release curve based on the vibration heat generation and the temperature control characteristics of the phase change material.

[0054] It should be noted that high-frequency vibration signals refer to vibration responses that are much higher than the unit's rotational frequency (usually several kilohertz) collected by an accelerometer installed on the bearing housing. They are often used to capture the impact caused by early minor damage to components such as bearing raceways and rolling elements. Vibration heat generation is quantified by processing the high-frequency vibration signals with a specific algorithm to determine the theoretical heat power generated by the additional friction and impact caused by the aggravation of abnormal vibration.

[0055] In one feasible implementation, the steps of monitoring high-frequency vibration signals under the target monitoring mode, determining vibration heat generation based on the high-frequency vibration signals, and establishing a vibration-heat release curve based on the vibration heat generation and the temperature control characteristics of the phase change material include: In the target monitoring mode, high-frequency vibration signals from vibration acceleration sensors distributed in multiple quadrants of the bearing are collected; The high-frequency vibration signal is subjected to spectrum analysis and packet decomposition to extract the vibration energy of the bearing; The vibration heat generation is obtained based on the vibration energy-heat generation conversion coefficient and the vibration energy. The temperature control characteristics of the phase change material are determined, and a vibration-heat release curve is established based on the temperature control characteristics and the vibration-generated heat.

[0056] It should be understood that in order to comprehensively capture the stress and vibration state of the bearing in all directions, multiple sensors installed around the bearing housing are usually installed at 90-degree or 120-degree intervals with the bearing center as the origin.

[0057] It should be noted that the vibration energy-heat generation conversion coefficient is a proportionality coefficient (unit: W / (m² / s²) or equivalent unit) obtained through bench tests or theoretical modeling, used to convert the dimensions of vibration energy into heat generation power in a thermodynamic sense. This coefficient serves as a bridge connecting mechanical vibration and thermal effects.

[0058] In its implementation, the system first synchronously reads sensor signals distributed across multiple quadrants of the bearing. These signals are then fused (e.g., by selecting the maximum energy value or performing vector synthesis) to overcome signal amplitude modulation caused by variations in the bearing load area, ensuring that the extracted vibration energy accurately reflects the overall vibration intensity. Subsequently, the fused high-frequency vibration signals undergo parallel spectrum analysis and packet decomposition. Spectrum analysis quickly identifies the characteristic frequency bandwidths of each bearing component (inner ring, outer ring, rolling elements), while packet decomposition focuses on these bandwidths to further separate the impact components obscured by noise. Vibration energy ( The calculation can combine the results of both methods, for example, by summing the squares of the coefficients of a specific fault band after decomposing the small packet: ,in This represents the small packet decomposition coefficient within the target frequency band.

[0059] Obtain vibrational energy Then, multiply it by a pre-calibrated vibration energy to heat generation conversion coefficient. This allows us to estimate the additional heat power generated by abnormal vibration, i.e., the heat generated by vibration. The calculation formula is: .coefficient The calibration needs to be obtained by back-calculating the vibration energy and actual frictional heat loss under known operating conditions.

[0060] Finally, based on the temperature control characteristics of phase change materials, including specific heat capacity... Phase transition latent heat Phase transition temperature range and thermal conductivity A simplified lumped-parameter thermal model is established. This model simplifies the bearing as a heat source and the phase change material as an endothermic body; its heat balance equation can be expressed as: ,in For the quality of phase change materials, The rate of change of liquid phase fraction. This represents heat loss to the environment. By solving this equation, we can simulate heat loss under different conditions. The temperature change curve of the lower phase change material, namely the vibration-heat release curve, visually demonstrates how the phase change material balances vibration-generated heat through heat absorption, thereby evaluating its temperature control effect.

[0061] In one feasible implementation, the step of performing spectral analysis and packet decomposition on the high-frequency vibration signal to extract the vibration energy of the bearing includes: Perform a fast Fourier transform on the high-frequency vibration signal to obtain the energy distribution of the high-frequency vibration signal in multiple characteristic frequency bands; The high-frequency vibration signal was subdivided into full-band subdivisions using wavelet packet decomposition algorithm to extract detail subband signals related to the bearing fault characteristic frequencies. The energy value of each detailed sub-band signal is calculated, and the energy value is weighted and fused with the energy distribution of the corresponding characteristic frequency band to obtain the vibration energy of the bearing.

[0062] In the specific implementation, firstly, the high-frequency vibration signal is collected... Perform a Fast Fourier Transform (FFT) to obtain its power spectral density. or amplitude spectrum The system will preset multiple frequency bands related to the fault characteristic frequencies calculated from the bearing's geometric parameters and rotational speed. Then, the energy within each characteristic frequency band is calculated through numerical integration. : or

[0063] At the same time, wavelet packet decomposition algorithms are used in parallel to process the same original signal. Perform a depth decomposition of 3 to 5 levels. This divides the entire Nyquist frequency range into several ( Each sub-band is an orthogonal sub-band of equal width (where j is the number of decomposition levels). Then, based on the characteristic frequencies of bearing failures, specific sub-bands containing these frequency components are precisely located. The energy values ​​of these target sub-bands are calculated. As mentioned earlier, this is obtained by calculating the sum of squares of the subband coefficients. The advantage of WPD is that it can concentrate the broadband impulse response energy caused by faults into a few subbands, thereby effectively filtering out out-of-band noise and improving the signal-to-noise ratio.

[0064] Finally, a weighted fusion is performed. The weighting strategy is crucial; for example, the energy extracted by WPD can be given a higher weight. Because it is more sensitive to impact characteristics; while the energy weights of FFT Lower, used as a background reference. Final bearing vibration energy. It can be represented as:

[0065] in, This fusion strategy combines the advantages of both methods, resulting in a final vibration energy estimate that includes both macroscopic frequency distribution information and enhanced microscopic impact information specific to the fault, laying a solid foundation for subsequent accurate calculation of vibration heat generation.

[0066] In one feasible implementation, the step of determining the temperature control characteristics of the phase change material and establishing a vibration-heat release curve based on the temperature control characteristics and the vibration-generated heat includes: Determine the temperature control characteristics of the phase change material, and calculate the theoretical heat absorption rate of the phase change material based on the real-time heat generation and the current phase change state of the phase change material; Based on the heat dissipation environment parameters of the bearing and the theoretical heat absorption rate, a thermodynamic differential equation with time as the variable is constructed. Solving the aforementioned thermodynamic differential equation, we can simulate and obtain the vibration-heat release curve, which characterizes the dynamic process of heat absorption and release of the phase change material under vibration-driven heat generation.

[0067] In the specific implementation, refer to Figure 2 ,Figure 2 This is the vibration-heat release curve. The system needs to determine the temperature control characteristics of the phase change material, including its specific heat capacity in both solid and liquid states. Phase transition latent heat Phase transition temperature range Typically, it refers to a range rather than a point, and thermal conductivity. Theoretical heat absorption rate The calculation is highly dependent on the current phase transition state of the phase transition material, which is a piecewise process: Sensible and endothermic states in solid or liquid phase change materials: when the overall temperature of the phase change material... Below the phase transition initiation temperature Or above the phase transition end temperature At this time, heat absorption is only in the form of sensible heat, and the formula is:

[0068] Solid-liquid coexistence phase change endothermic: when In In the liquidus region, the material undergoes a phase transition, absorbing a large amount of latent heat. At this point, the rate of heat absorption is related to the liquidus fraction. Related to the rate of change of (liquid mass fraction, from 0 to 1), Liquid phase ratio The relationship with temperature can be expressed as a linear or experimentally calibrated function. To describe.

[0069] Next, based on the heat dissipation environment parameters (such as ambient temperature) Convection heat transfer coefficient between bearing and environment Heat exchange area (etc.) Construct the thermodynamic differential equations. This system can usually be simplified to a lumped-parameter model, whose energy balance equation is:

[0070] in: The heat generated by vibration is used as a heat source input. This is the heat loss from the bearing to the environment. The last item is the sensible heat absorbed by the bearing body as its temperature rises.

[0071] To simplify and focus on the behavior of phase change materials, the bearing temperature is often assumed. With phase change material temperature Tight coupling (ideal thermal contact) can make Thus, the equation can be rewritten as about Differential equation:

[0072] Finally, solve the thermodynamic differential equation. Numerical methods (such as the fourth-order Runge-Kutta method) are employed, with initial conditions (such as...) Under time The solution is obtained through iterative steps. The solution results are as follows. Or directly output The curve showing how heat changes over time is the vibration-heat release curve. This curve clearly demonstrates the heat generation during continuous vibration. Driven by this, we can intuitively assess how phase change materials dynamically absorb heat (manifested as a gradual temperature rise or a stable temperature) and how they release heat after vibrations are reduced, thereby providing a direct evaluation of their temperature suppression performance on bearings.

[0073] Step S30: Based on the vibration-heat release curve, predict the predicted output voltage of the thermoelectric module, determine the inertial data of voltage change according to the predicted output voltage, and determine the target heat release rate curve of the phase change material according to the inertial data.

[0074] Understandably, firstly, the vibration-heat release curve, i.e., the heat flow output of the phase change material, is considered. The physical model input into the thermoelectric module describes the Seebeck effect, i.e., temperature difference. Linear relationship with output voltage V: This allows for the calculation of the predicted future output voltage. Next, through analysis The trend of change (e.g., calculating its first derivative) Alternatively, system identification can be performed to quantify its dynamic response characteristics, i.e., the inertial data of voltage changes (such as the equivalent time constant). Finally, the control algorithm uses this inertial data to deduce, with the optimization objective of ensuring smooth voltage changes and avoiding impact on energy storage or electrical equipment, an ideal target heat release rate curve that matches the system's thermal inertia is calculated. This curve will serve as the direct setpoint for the next stage of active thermal management of phase change materials.

[0075] In one feasible implementation, the step of determining the target heat release rate curve of the phase change material based on the inertial data includes: An optimization function for voltage output stability is established based on the aforementioned inertial data; The target heat release rate sequence is solved in reverse based on the optimization function; The target heat release rate sequence is smoothed and physically constrained to generate a target heat release rate curve.

[0076] In the specific implementation, firstly, an optimization function for voltage output stability is established based on inertial data. The system's inertial data (e.g., the identified first-order inertial time constant of the thermoelectric system) is used. This indicates a lag in voltage changes. The optimization function aims to minimize the output voltage. The objective is to determine the fluctuations. A common optimization objective function is... It can be formalized as:

[0077] in, It is the control variable to be determined (target heat release rate). This indicates a penalty for drastic changes in voltage, ensuring stability; To make the voltage track a desired reference value. (e.g., maximum power point voltage); and This is a weighting coefficient used to balance smoothness and tracking accuracy.

[0078] Secondly, the target heat release rate sequence is solved inversely based on the optimization function. This is typically transformed into an optimal control problem. Due to thermoelectric voltage... Through physical models ( ) and thermodynamic models and Correspondingly, we can solve the above optimization problem in the discrete-time domain. Using variational methods or model predictive control (MPC) frameworks, the continuous-time problem can be discretized into solutions at each sampling time point. Solving a quadratic programming (QP) problem yields a series of discrete target heat release rate values ​​over a future time domain, i.e., a sequence. .

[0079] Finally, the target heat release rate sequence is smoothed and physically constrained. The initially obtained sequence may contain high-frequency jitter or values ​​exceeding physical limits. Therefore, a digital filter (such as a moving average filter) is needed to smooth it. Simultaneously, physical constraint verification must be performed to ensure that each... All of these are within the limits allowed by the phase change material's capabilities and the system structure, i.e., they satisfy... Finally, these processed and verified discrete sequence points are interpolated (e.g., by spline interpolation) to generate a continuous, smooth, and physically feasible target heat release rate curve. , as control instructions for the actuator.

[0080] In one feasible implementation, the step of smoothing and physically constraining the target heat release rate sequence to generate the target heat release rate curve includes: The target heat release rate sequence is smoothed using a filter to obtain a smoothed sequence. Based on the maximum heat absorption and release capacity and thermal response time constant of the phase change material, the smoothed sequence is subjected to physical constraint verification of the rate upper limit and the change gradient. When a numerical point in the smoothed sequence exceeds the physical constraint range, the numerical point is corrected to a boundary value, and a target heat release rate curve is generated based on the corrected numerical point.

[0081] In the specific implementation, firstly, a filter is used for smoothing. The target heat release rate sequence is obtained directly from the optimization algorithm. (in Discrete-time indices may contain high-frequency jitter due to numerical computation or model mismatch. Direct use of this sequence may cause actuators (such as pumps and fans) to operate frequently, leading to oscillations or wear. Therefore, a digital low-pass filter is needed for smoothing. A commonly used and computationally efficient choice is a first-order infinite impulse response (IIR) filter, which has the following form: Among them, the filter coefficients This determines the smoothness. The smaller the value, the stronger the smoothing effect, but the greater the instruction delay.

[0082] Secondly, physical constraint verification is performed. The smoothed sequence It must undergo a dual test of physical feasibility. The first is the upper limit constraint on the rate, namely… Here The phase change material's thermophysical properties (such as thermal conductivity and latent heat) and the maximum capacity of the heat exchange system (such as the maximum flow rate of the fluid) are both considered. Secondly, there is the constraint of the change gradient, i.e. This constraint reflects the system's thermal response time constant, meaning that the rate of change of heat flux cannot exceed the dynamic response capability of the heat dissipation / heating mechanism, preventing the system from being unable to keep up with changes in commands that occur too quickly.

[0083] Finally, boundary correction is performed and the curve is generated. This applies to any numerical point in the sequence that exceeds the above constraints. The system will correct it to the closest boundary value. For example, if a value at a certain point is greater than... Then set it to If its rate of change exceeds The value at the previous time step will then be corrected by a maximum permissible amount of change. After this series of smoothing and constraint processes, the final discrete sequence can then be used to generate a continuous, smooth, and physically accurate target heat release rate curve through linear interpolation or spline interpolation. This provides a reliable basis for the final control execution.

[0084] Step S40: Control the phase change material to release heat based on the target heat release rate curve, so as to stabilize the output voltage of the thermoelectric module.

[0085] It should be noted that the system uses the target heat release rate curve as the setpoint and monitors the actual heat flow rate or temperature change rate at the interface between the phase change material and the hot end of the thermoelectric module in real time through sensors (such as thermocouples), and uses this as a feedback signal. The controller (such as a PID controller or a more advanced model predictive controller, MPC) compares the target value with the actual value, calculates the control quantity (such as adjusting the speed of the liquid pump or the duty cycle of the fan), drives the actuator to change the heat transfer intensity, thereby dynamically adjusting the solidification / melting rate of the phase change material, so that its actual heat release closely tracks the target curve, and ultimately achieves smooth and stable control of the output power quality of the thermoelectric module.

[0086] In one feasible implementation, the step of controlling the heat release of the phase change material based on the target heat release rate curve includes: The target heat release rate curve is converted into control timing commands; According to the control timing instructions, the heat release rate of the phase change material is controlled so that the phase change material releases heat.

[0087] In practical implementation, the system first performs feedforward control based on a preset static model that characterizes the relationship between "heat release rate and control quantity". For example, if the controlled object is a pump that drives the coolant circulation, its model might be approximated as follows: ,in yes The PWM duty cycle instruction at any given time. It is the gain coefficient. It is the bias constant. This set of feedforward instructions provides the system with a fast, initial response.

[0088] However, due to model inaccuracies and external disturbances, feedforward control alone cannot guarantee accurate tracking of the target heat release rate. Therefore, a feedback control loop (typically a PI or PID controller) is introduced to eliminate steady-state errors and suppress disturbances. The controller adjusts the control based on the target heat release rate. The actual heat release rate estimated by means of sensors (such as thermocouples, which are used to calculate the temperature difference). Deviation between This is used to generate the compensation control quantity. Taking a PI controller as an example, its output is... ,in and For control parameters, The sampling period is [number]. Finally, the control timing instructions for driving the actuator are [determined]. (or the corresponding PWM signal) is determined by both the feedforward amount and the feedback compensation amount: This set of timing instructions is periodically sent to the power drive circuit, thereby precisely controlling the heat exchange intensity, realizing closed-loop regulation of the heat release rate of the phase change material, and ultimately achieving the goal of stabilizing the thermoelectric output voltage.

[0089] This embodiment provides an intelligent monitoring method for the self-powered operation of wind turbine generator bearings based on the temperature control and thermoelectric effect of phase change materials. When an abnormal bearing power supply voltage is detected, the method identifies the level of the abnormal condition and matches a target monitoring mode. In this mode, high-frequency vibration signals are monitored and the heat generated by vibration is calculated. A vibration-heat release curve is established by combining the temperature control characteristics of the phase change material. Based on this curve, the output voltage of the thermoelectric module is predicted, and the target heat release rate curve of the phase change material is determined based on the inertial data of voltage changes. Finally, the heat release of the phase change material is controlled according to the target curve to stabilize the output voltage of the thermoelectric module. Through this method, this application achieves stable power supply to the monitoring system by utilizing the heat generated by the bearing's own vibration under abnormal external power supply conditions, thereby improving the reliability and self-sustaining capability of the monitoring system.

[0090] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the intelligent monitoring method for self-powered bearings of wind turbine generators based on phase change material temperature control and thermoelectric effect. Any simple modifications based on this technical concept are within the protection scope of this application.

[0091] This application also provides an intelligent monitoring system for self-powered bearings of wind turbine generators based on phase change material temperature control and thermoelectric effects. Please refer to [reference needed]. Figure 3 The intelligent monitoring system for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect includes: The status monitoring module 10 is used to identify the abnormal operating condition level when the power supply voltage status information of the wind turbine generator bearing is abnormal, and to match the corresponding target monitoring mode according to the abnormal operating condition level. The thermal correlation modeling module 20 is used to monitor high-frequency vibration signals under the target monitoring mode, determine vibration heat generation based on the high-frequency vibration signals, and establish a vibration-heat release curve based on the vibration heat generation and the temperature control characteristics of the phase change material. The output prediction module 30 is used to predict the predicted output voltage of the thermoelectric module based on the vibration-heat release curve, determine the inertial data of voltage change based on the predicted output voltage, and determine the target heat release rate curve of the phase change material based on the inertial data. The temperature control execution module 40 is used to control the phase change material to release heat based on the target heat release rate curve, so as to make the thermoelectric module output voltage stably.

[0092] In one feasible implementation, the status monitoring module 10 is further configured to determine the power supply voltage sequence within the current sampling period and determine the peak voltage and valley voltage in the power supply voltage sequence when the power supply voltage status information of the wind turbine generator bearing is abnormal. The peak-to-peak voltage is determined based on the peak voltage and the valley voltage; The peak-to-peak voltage is mapped to an abnormal operating condition level table to obtain the abnormal operating condition level; Match the corresponding target monitoring mode according to the abnormal operating condition level.

[0093] In one feasible implementation, the thermal correlation modeling module 20 is also used to acquire high-frequency vibration signals from vibration acceleration sensors distributed in multiple quadrants of the bearing under the target monitoring mode. The high-frequency vibration signal is subjected to spectrum analysis and packet decomposition to extract the vibration energy of the bearing; The vibration heat generation is obtained based on the vibration energy-heat generation conversion coefficient and the vibration energy. The temperature control characteristics of the phase change material are determined, and a vibration-heat release curve is established based on the temperature control characteristics and the vibration-generated heat.

[0094] In one feasible implementation, the thermal correlation modeling module 20 is further used to perform a fast Fourier transform on the high-frequency vibration signal to obtain the energy distribution of the high-frequency vibration signal in multiple characteristic frequency bands. The high-frequency vibration signal was subdivided into full-band subdivisions using wavelet packet decomposition algorithm to extract detail subband signals related to the bearing fault characteristic frequencies. The energy value of each detailed sub-band signal is calculated, and the energy value is weighted and fused with the energy distribution of the corresponding characteristic frequency band to obtain the vibration energy of the bearing.

[0095] In one feasible implementation, the thermal correlation modeling module 20 is also used to determine the temperature control characteristics of the phase change material and calculate the theoretical heat absorption rate of the phase change material based on the real-time heat generation and the current phase change state of the phase change material. Based on the heat dissipation environment parameters of the bearing and the theoretical heat absorption rate, a thermodynamic differential equation with time as the variable is constructed. Solving the aforementioned thermodynamic differential equation, we can simulate and obtain the vibration-heat release curve, which characterizes the dynamic process of heat absorption and release of the phase change material under vibration-driven heat generation.

[0096] In one feasible implementation, the output prediction module 30 is further configured to establish an optimization function for voltage output stability based on the inertial data; The target heat release rate sequence is solved in reverse based on the optimization function; The target heat release rate sequence is smoothed and physically constrained to generate a target heat release rate curve.

[0097] In one feasible implementation, the output prediction module 30 is further configured to use a filter to smooth the target heat release rate sequence to obtain a smoothed sequence; Based on the maximum heat absorption and release capacity and thermal response time constant of the phase change material, the smoothed sequence is subjected to physical constraint verification of the rate upper limit and the change gradient. When a numerical point in the smoothed sequence exceeds the physical constraint range, the numerical point is corrected to a boundary value, and a target heat release rate curve is generated based on the corrected numerical point.

[0098] In one feasible implementation, the temperature control execution module 40 is further configured to convert the target heat release rate curve into control timing instructions; According to the control timing instructions, the heat release rate of the phase change material is controlled so that the phase change material releases heat.

[0099] In one feasible implementation, the status monitoring module 10 is further configured to collect the real-time power supply voltage sequence of the wind turbine generator bearing based on a preset acquisition frequency, and extract the voltage fluctuation characteristics of the real-time power supply voltage sequence. The voltage fluctuation characteristics are input into the anomaly classification model to obtain voltage fluctuation classification information; The voltage fluctuation classification information is detected to obtain the power supply voltage status information.

[0100] The intelligent monitoring system for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect provided in this application adopts the intelligent monitoring method for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect in the above embodiments, which can solve the technical problem of unstable bearing power supply. Compared with the prior art, the beneficial effects of the intelligent monitoring system for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect provided in this application are the same as the beneficial effects of the intelligent monitoring method for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect provided in the above embodiments. Furthermore, other technical features of the intelligent monitoring system for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0101] This application provides an intelligent monitoring device for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect. The intelligent monitoring device for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect includes: at least one processor; and a memory communicatively connected to at least one processor; wherein the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor to enable at least one processor to execute the intelligent monitoring method for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect in the above embodiment 1.

[0102] The following is for reference. Figure 4 This document illustrates a structural schematic diagram of a wind turbine bearing self-powered intelligent monitoring device based on phase change material temperature control and thermoelectric effect, suitable for implementing embodiments of this application. The wind turbine bearing self-powered intelligent monitoring device based on phase change material temperature control and thermoelectric effect in this application embodiment can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The intelligent monitoring device for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0103] like Figure 4As shown, the intelligent monitoring device for self-powered bearings of wind turbine generators based on phase change material temperature control and thermoelectric effect may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the intelligent monitoring device for self-powered bearings of wind turbine generators based on phase change material temperature control and thermoelectric effect. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the wind turbine bearing self-powered intelligent monitoring device based on phase change material temperature control and thermoelectric effects to exchange data with other devices wirelessly or via wired communication. Although the figure shows a wind turbine bearing self-powered intelligent monitoring device with various systems based on phase change material temperature control and thermoelectric effects, it should be understood that implementing or possessing all the systems shown is not required. More or fewer systems can be implemented alternatively.

[0104] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0105] The intelligent monitoring device for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect provided in this application adopts the intelligent monitoring method for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect in the above embodiments, which can solve the technical problem of intelligent monitoring of self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect. Compared with the prior art, the beneficial effects of the intelligent monitoring device for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect provided in this application are the same as the beneficial effects of the intelligent monitoring method for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect provided in the above embodiments, and other technical features in the intelligent monitoring device for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect are the same as the features disclosed in the previous embodiment method, and will not be repeated here.

[0106] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0107] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0108] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the intelligent monitoring method for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect in the above embodiments.

[0109] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0110] The aforementioned computer-readable storage medium may be included in the intelligent monitoring device for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect; or it may exist independently and not assembled into the intelligent monitoring device for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effect.

[0111] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the wind turbine generator bearing self-powered intelligent monitoring device based on phase change material temperature control and thermoelectric effect, the wind turbine generator bearing self-powered intelligent monitoring device based on phase change material temperature control and thermoelectric effect will: when the power supply voltage status information of the wind turbine generator bearing is abnormal, identify the abnormal operating condition level and match the corresponding target monitoring mode according to the abnormal operating condition level; In the target monitoring mode, high-frequency vibration signals are monitored, vibration heat generation is determined based on the high-frequency vibration signals, and a vibration-heat release curve is established based on the vibration heat generation and the temperature control characteristics of the phase change material. Based on the vibration-heat release curve, the predicted output voltage of the thermoelectric module is predicted, the inertial data of voltage change is determined according to the predicted output voltage, and the target heat release rate curve of the phase change material is determined according to the inertial data. The phase change material is controlled to release heat based on the target heat release rate curve, so that the thermoelectric module can output a stable voltage.

[0112] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0113] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0114] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0115] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described intelligent monitoring method for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effects. This method can solve the technical problem of intelligent monitoring of self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effects. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the intelligent monitoring method for self-powered wind turbine bearings based on phase change material temperature control and thermoelectric effects provided in the above embodiments, and will not be elaborated upon here.

[0116] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described intelligent monitoring method for self-powered bearings of wind turbine generators based on phase change material temperature control and thermoelectric effects.

[0117] The computer program product provided in this application can solve the technical problem of intelligent monitoring of self-powered bearings in wind turbine generators based on phase change material temperature control and thermoelectric effect. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the intelligent monitoring method for self-powered bearings in wind turbine generators based on phase change material temperature control and thermoelectric effect provided in the above embodiments, and will not be repeated here.

[0118] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A self-powered intelligent monitoring method for wind turbine generator set bearings based on phase change material temperature control and thermoelectric effect, characterized in that, The wind turbine generator unit bearing self-powered intelligent monitoring method based on the phase change material temperature control and thermoelectric effect comprises: When the power supply voltage state information of the wind turbine generator unit bearing is abnormal, an abnormal working condition level is identified, and a corresponding target monitoring mode is matched according to the abnormal working condition level; In the target monitoring mode, high-frequency vibration signals are monitored, vibration heat generation is determined according to the high-frequency vibration signals, and a vibration-heat release curve is established according to the vibration heat generation and the temperature control characteristics of the phase change material; The predicted output voltage of the thermoelectric module is predicted based on the vibration-heat release curve, the inertia data of the voltage change is determined according to the predicted output voltage, and the target heat release rate curve of the phase change material is determined according to the inertia data; The phase change material is controlled to release heat based on the target heat release rate curve, so that the thermoelectric module stably outputs voltage.

2. The method of claim 1, wherein, The step of identifying the abnormal working condition level according to the abnormal power supply voltage state information of the wind turbine generator unit bearing and matching the corresponding target monitoring mode comprises: When the power supply voltage state information of the wind turbine generator unit bearing is abnormal, the power supply voltage sequence in the current sampling period is determined, and the peak voltage and the valley voltage in the power supply voltage sequence are determined; The peak-to-peak voltage is determined according to the peak voltage and the valley voltage; The peak-to-peak voltage is mapped to an abnormal working condition level table to obtain an abnormal working condition level; The corresponding target monitoring mode is matched according to the abnormal working condition level.

3. The method of claim 1, wherein, The step of monitoring high-frequency vibration signals in the target monitoring mode, determining vibration heat generation according to the high-frequency vibration signals, and establishing a vibration-heat release curve according to the vibration heat generation and the temperature control characteristics of the phase change material comprises: In the target monitoring mode, high-frequency vibration signals of vibration acceleration sensors distributed in multiple quadrants of the bearing are collected; The high-frequency vibration signals are subjected to frequency spectrum analysis and packet decomposition to extract the vibration energy of the bearing; Based on the vibration energy-heat generation conversion coefficient and the vibration energy, the vibration heat generation is obtained; The temperature control characteristics of the phase change material are determined, and the vibration-heat release curve is established according to the temperature control characteristics and the vibration heat generation.

4. The method of claim 3, wherein, The step of performing frequency spectrum analysis and packet decomposition on the high-frequency vibration signals to extract the vibration energy of the bearing comprises: Fast Fourier transform is performed on the high-frequency vibration signals to obtain the energy distribution of the high-frequency vibration signals in multiple characteristic frequency bands; The high-frequency vibration signals are subjected to full-band subdivision by using a wavelet packet decomposition algorithm to extract detail sub-band signals related to the bearing fault characteristic frequency; The energy values of each detail sub-band signal are calculated, and the energy values are weighted and fused with the energy distribution of the corresponding characteristic frequency band to obtain the vibration energy of the bearing.

5. The method of claim 3, wherein, The step of determining the temperature control characteristics of the phase change material and establishing the vibration-heat release curve according to the temperature control characteristics and the vibration heat generation comprises: The temperature control characteristics of the phase change material are determined, and the theoretical heat absorption rate of the phase change material is calculated according to the real-time heat generation and the current phase change state of the phase change material; Based on the heat dissipation environment parameters of the bearing and the theoretical heat absorption rate, a thermodynamic differential equation with time as the variable is constructed. Solving the aforementioned thermodynamic differential equation, we can simulate and obtain the vibration-heat release curve, which characterizes the dynamic process of heat absorption and release of the phase change material under vibration-driven heat generation.

6. The method of claim 1, wherein, The steps for determining the target heat release rate curve of the phase change material based on the inertial data include: An optimization function for voltage output stability is established based on the aforementioned inertial data; The target heat release rate sequence is solved in reverse based on the optimization function; The target heat release rate sequence is smoothed and physically constrained to generate a target heat release rate curve.

7. The method of claim 6, wherein, The step of smoothing and physically constraining the target heat release rate sequence to generate the target heat release rate curve includes: The target heat release rate sequence is smoothed using a filter to obtain a smoothed sequence. Based on the maximum heat absorption and release capacity and thermal response time constant of the phase change material, the smoothed sequence is subjected to physical constraint verification of the rate upper limit and the change gradient. When a numerical point in the smoothed sequence exceeds the physical constraint range, the numerical point is corrected to a boundary value, and a target heat release rate curve is generated based on the corrected numerical point.

8. The method of claim 1, wherein, The step of controlling the heat release of the phase change material based on the target heat release rate curve includes: The target heat release rate curve is converted into control timing commands; According to the control timing instructions, the heat release rate of the phase change material is controlled so that the phase change material releases heat.

9. The method of claim 1, wherein, Before the step of identifying the abnormal operating condition level and matching the corresponding target monitoring mode according to the abnormal operating condition level when the power supply voltage status information of the wind turbine generator bearing is abnormal, the method further includes: The real-time power supply voltage sequence of the wind turbine generator bearing is collected based on a preset acquisition frequency, and the voltage fluctuation characteristics of the real-time power supply voltage sequence are extracted. The voltage fluctuation characteristics are input into the anomaly classification model to obtain voltage fluctuation classification information; The voltage fluctuation classification information is detected to obtain the power supply voltage status information.

10. A self-powered intelligent monitoring system for bearings of a wind turbine generator unit based on temperature control of a phase change material and thermoelectric effect, characterized in that, The wind turbine generator bearing self-powered intelligent monitoring system based on phase change material temperature control and thermoelectric effect includes: The status monitoring module is used to identify the abnormal operating condition level when the power supply voltage status information of the wind turbine generator bearing is abnormal, and to match the corresponding target monitoring mode according to the abnormal operating condition level. The thermal correlation modeling module is used to monitor high-frequency vibration signals under the target monitoring mode, determine the vibration heat generation based on the high-frequency vibration signals, and establish a vibration-heat release curve based on the vibration heat generation and the temperature control characteristics of the phase change material. An output prediction module is used to predict the predicted output voltage of the thermoelectric module based on the vibration-heat release curve, determine the inertial data of voltage change based on the predicted output voltage, and determine the target heat release rate curve of the phase change material based on the inertial data. The temperature control execution module is used to control the phase change material to release heat based on the target heat release rate curve, so as to make the thermoelectric module output voltage stably.

Images