Signal envelope extraction method and device, and state monitoring method of wind turbine generator

Abstract

The application provides a signal envelope line extraction method and device, a wind turbine generator state monitoring method and device, wherein the signal envelope line extraction method comprises: obtaining an intensity value of a signal of a wind turbine generator in a current period; wherein the signal comprises at least one of a rotating speed signal, a vibration signal, a temperature signal, a pressure signal, a stress signal and a load signal of the wind turbine generator; calculating an upper envelope value and a lower envelope value corresponding to the signal in the current period according to the intensity value; and extracting an envelope line of the signal according to the upper envelope values and the lower envelope values of multiple periods, thereby providing a basis for more accurately obtaining the running state of the wind turbine generator.

Description

Technical Field

[0001] This invention relates to the field of wind power technology, specifically to a signal envelope extraction method and apparatus, and a wind turbine status monitoring method and apparatus. Background Technology

[0002] Wind energy is a green, environmentally friendly, and renewable energy source. Given the current global energy shortage and the strong emphasis on environmental protection, the vigorous development and utilization of wind power generation is a common trend. Wind turbine units have become increasingly mature after years of development. While wind power generation technology has developed rapidly, high maintenance costs have become a significant factor affecting its economic viability. Failures of major components often lead to prolonged shutdowns of the entire unit. Therefore, condition monitoring of the unit, and real-time monitoring of the operating information of major components to promptly identify potential faults, is of great importance to wind farms.

[0003] The current signal used to determine the operating status of wind turbines must first be filtered to eliminate the influence of noise on the control system. Then, a fast algorithm for online discrete Fourier transform (FFT) is used to extract specific frequencies, such as the first-order vibration frequency of the tower and the third-order in-plane frequency. The wind turbine generator is then judged to be abnormal based on the amplitude of the specific frequency.

[0004] Currently, wind turbine control and alarm systems are developing towards greater precision and customization. Digital filters can handle most possible operating conditions of wind turbines; however, with increasing demands for control accuracy and turbine customization, traditional digital filters are fundamentally unable to respond promptly to some turbine faults. For example, when the turbine speed fluctuates due to certain faults, or when the vibration intensity in a certain direction of the turbine produces near-periodic, undamped vibrations due to a fault, the aforementioned methods cannot respond to these problems and can only be judged manually. However, these problems often lead to abnormal turbine operation and even the risk of tower collapse. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a signal envelope extraction method, apparatus, and wind turbine status monitoring method and apparatus, providing a basis for more accurately obtaining the operating status of wind turbines.

[0006] Therefore, the embodiments of the present invention provide the following technical solutions:

[0007] In a first aspect, the present invention provides a method for extracting a signal envelope, comprising: acquiring the intensity value of a signal in the current period, that is, the input of a real-time envelope calculation function is the real-time value of the signal in the current period; the signal includes at least one of a wind turbine rotation speed signal, a vibration signal, a temperature signal, a pressure signal, a stress signal, and a load signal; calculating an upper envelope value and a lower envelope value corresponding to the signal in the current period based on the intensity value; and extracting the envelope of the signal based on the upper envelope values ​​and lower envelope values ​​of multiple periods.

[0008] By taking the above steps, the envelope of the signal related to the wind turbine is obtained, which provides a basis for judging the operating status of the wind turbine. Compared with the existing technology that uses the specific frequency amplitude of the signal as the basis for judging whether the wind turbine generator is abnormal, the above steps use the envelope of the signal as the basis for judging the operating status of the wind turbine, which is not accurate.

[0009] There are multiple implementations for calculating the upper and lower envelope values ​​corresponding to the signal within the current period based on the intensity value. An example is provided below. In one optional embodiment, N values ​​are obtained, for example, these N values ​​range from the 0th value to the (N-1)th value; where N is greater than or equal to f. c / f t positive integers, f c f is the operating frequency of the wind turbine controller. t The maximum effective frequency of the signal is defined as N values, which are the real-time intensity values ​​of the signal in the previous N periods of the current period. The intensity value is compared with the N values. If the intensity value is greater than any of the N values, the intensity value is used as the upper envelope value of the current period. If the intensity value is less than any of the N values, the intensity value is used as the lower envelope value of the current period. Otherwise, the upper envelope value of the previous period is used as the upper envelope value of the current period, and the lower envelope value of the previous period is used as the lower envelope value of the current period.

[0010] Based on the above embodiments, in a specific optional embodiment, the real-time upper and lower envelope values ​​can be calculated using a sliding window algorithm. Specifically, when the current calculation cycle begins, data N is first taken and the output results are classified using a decision tree. Each node in the decision tree contains two branches. If the result is "yes," the process proceeds to the next node; if it is "no," the real-time envelope calculation output for the current cycle (also called the "current envelope value," which can be divided into the "current upper envelope value" and the "current lower envelope value") is equal to the output of the previous cycle. When calculating the real-time upper envelope value, it is compared whether data N is greater than data N-1 in the sliding window queue. If "no," the previous output value is maintained, and the calculation ends. If "yes," it is compared whether data N is greater than data N-2 in the sliding window queue, and this process is repeated until all data in the sliding window queue has been compared. If the comparison result is still "yes," data N is output as the current upper envelope value. When calculating the real-time lower envelope value, the process is the same as that for calculating the real-time upper envelope value, but the judgment method is different. It compares whether the data N is less than the data N-1 in the sliding window queue. If "no", the previous output value is kept and the calculation ends. If "yes", it compares whether the data N is less than the data N-2 in the sliding window queue, and so on, until all the data in the sliding window queue has been compared. If the comparison result is still "yes", the data N is output as the current lower envelope value.

[0011] In a second aspect, the present invention provides a method for monitoring the status of a wind turbine, comprising: extracting the envelope of a signal using any of the signal envelope extraction methods described in the first aspect; and determining the operating status of the wind turbine based on the signal envelope.

[0012] By taking the above steps, the envelope of the signal related to the wind turbine is obtained, and the operating status of the wind turbine is determined based on the envelope. Compared with the existing technology that judges whether the wind turbine generator is abnormal based on the specific frequency amplitude of the signal, which is not accurate, the above steps use the envelope of the signal as the basis for judging the operating status of the wind turbine, thus improving the accuracy of judging the operating status of the wind turbine.

[0013] There are many ways to implement the above-mentioned method of determining the operating status of the wind turbine based on the signal envelope. In one optional embodiment, the difference between the upper envelope value and the lower envelope value in the current period is calculated; when the difference is greater than a predetermined threshold, the wind turbine is determined to be abnormal.

[0014] In a third aspect, the present invention provides a signal envelope extraction device, comprising: an acquisition module for acquiring the intensity value of a signal in the current period; wherein the signal includes at least one of a wind turbine rotation speed signal, a vibration signal, a temperature signal, a pressure signal, a stress signal, and a load signal; a calculation module for calculating an upper envelope value and a lower envelope value corresponding to the signal in the current period based on the intensity value; and an extraction module for extracting the envelope of the signal based on the upper envelope values ​​and lower envelope values ​​of multiple periods.

[0015] Optionally, the calculation module includes: an acquisition unit, configured to acquire N values; wherein N is greater than or equal to f. c / f t positive integers, f c f is the operating frequency of the wind turbine controller. t The maximum effective frequency of the signal is defined as follows: the N values ​​are the real-time intensity values ​​of the signal in the previous N periods of the current period; a comparison unit is used to compare the intensity value with the N values; a setting unit is used to set the intensity value as the upper envelope value of the current period when the intensity value is greater than any of the N values; and to set the intensity value as the lower envelope value of the current period when the intensity value is less than any of the N values; otherwise, the upper envelope value of the previous period is used as the upper envelope value of the current period, and the lower envelope value of the previous period is used as the lower envelope value of the current period.

[0016] In a fourth aspect, the present invention provides a wind turbine state monitoring device, comprising: a signal envelope extraction device as provided in the third aspect and a determination module; the determination module is used to determine the operating state of the wind turbine based on the signal envelope.

[0017] Optionally, the determining module includes: a calculation unit for calculating the difference between the upper envelope value and the lower envelope value in the current period; and a determining unit for determining that the wind turbine is abnormal when the difference is greater than a predetermined threshold.

[0018] In a fifth aspect, the present invention provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the signal envelope extraction method or the wind turbine state monitoring method described in either the first or second aspect above.

[0019] A sixth aspect of the present invention provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the signal envelope extraction method or the wind turbine state monitoring method described in either the first or second aspect above.

[0020] The technical solution of the present invention has the following advantages:

[0021] This invention provides a signal envelope extraction method, apparatus, wind turbine state monitoring method, apparatus, electronic device, and computer-readable storage medium. The signal envelope extraction method includes: acquiring the intensity value of a signal from a wind turbine in the current cycle; wherein the signal includes at least one of a wind turbine rotation speed signal, vibration signal, temperature signal, pressure signal, stress signal, and load signal; calculating the upper and lower envelope values ​​corresponding to the signal in the current cycle based on the intensity value; and extracting the signal envelope based on the upper and lower envelope values ​​from multiple cycles, thereby providing a basis for more accurately acquiring the operating state of the wind turbine. Attached Figure Description

[0022] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a signal envelope extraction method according to an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of real-time envelope calculation according to an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of a sliding window queue of length N according to an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram illustrating the calculation of the real-time envelope value for each computation cycle according to an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of the real-time envelope of a temperature signal according to an embodiment of the present invention;

[0028] Figure 6 This is a schematic diagram of the real-time envelope of a vibration signal according to an embodiment of the present invention;

[0029] Figure 7 This is a schematic diagram of the upper envelope of the absolute value of the vibration signal according to an embodiment of the present invention;

[0030] Figure 8 This is a flowchart of a wind turbine condition monitoring method according to an embodiment of the present invention;

[0031] Figure 9 This is a structural block diagram of a signal envelope extraction device according to an embodiment of the present invention;

[0032] Figure 10 This is a structural block diagram of a wind turbine condition monitoring device according to an embodiment of the present invention;

[0033] Figure 11 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0034] 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. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] To meet the increasing demands for precise control of wind turbine operation and the growing requirements for customized wind turbines, this embodiment provides a signal envelope extraction method, which can be used for processing signals related to wind turbines. Figure 1 This is a flowchart of a signal envelope extraction method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0036] Step S101: Obtain the signal strength value of the wind turbine in the current cycle. Wind turbine controllers typically operate in cycles; this cycle time is generally called the calculation cycle or operating cycle. Figure 2 As shown, the input to the real-time envelope calculation function is the real-time value of the signal in the current cycle; where the signal can be a signal related to the wind turbine, such as a speed signal, vibration signal, temperature signal, pressure signal, stress signal, or load signal.

[0037] Step S102: Calculate the upper and lower envelope values ​​corresponding to the aforementioned signal within the current period based on the intensity value. For example... Figure 2 As shown, the input to the real-time envelope calculation function is the real-time value of the signal in the current cycle. After calculation, the real-time upper envelope value and lower envelope value are output. The real-time upper (lower) envelope value of the current running cycle is also called the current upper (lower) envelope value.

[0038] Step S103: Extract the envelope of the signal based on the upper and lower envelope values ​​from multiple cycles. Connecting the peak points of a time-series signal yields an upper (positive) line and a lower (negative) line, which are called the envelope lines. After calculations over multiple cycles, the upper and lower envelope lines are formed from the real-time upper and lower envelope values ​​obtained in steps 101 and 102 above.

[0039] By taking the above steps, the envelope of the signal related to the wind turbine is obtained, which provides a basis for judging the operating status of the wind turbine. Compared with the existing technology that uses the specific frequency amplitude of the signal as the basis for judging whether the wind turbine generator is abnormal, the above steps use the envelope of the signal as the basis for judging the operating status of the wind turbine, which is not accurate.

[0040] There are multiple ways to calculate the upper and lower envelope values ​​corresponding to the signal within the current period based on the intensity value. An example is provided below. In one optional embodiment, N values ​​are obtained, ranging from the 0th value to the (N-1th)th value. The maximum effective frequency of the signal is determined; portions of the signal's spectrum above the maximum effective frequency are not considered. For example, if the signal is a cabin vibration signal, the maximum effective frequency is assumed to be f. t Then the envelope frequency f should satisfy the relationship f ≤ f t Calculate the sliding window length N. Assuming the controller's calculation cycle is 20ms, its operating frequency is... Then N / f should be satisfied. c =1 / f≥1 / f t That is, N≥f c / f t N is the sliding window length required to calculate the envelope. That is, N is greater than or equal to f. c / f t positive integers, f c f is the operating frequency of the wind turbine controller. t f is the maximum effective frequency of the signal. t The vibration frequency of a typical tower is around 1-2 Hz, which is determined during the overall design of the wind turbine. The intensity value is compared with N values. If the intensity value is greater than any of the N values, it is used as the upper envelope value for the current cycle; if the intensity value is less than any of the N values, it is used as the lower envelope value for the current cycle; otherwise, the upper envelope value of the previous cycle is used as the upper envelope value for the current cycle, and the lower envelope value of the previous cycle is used as the lower envelope value for the current cycle.

[0041] Based on the above embodiments, in a specific optional embodiment, the real-time upper and lower envelope values ​​can be calculated using a sliding window algorithm. Sliding window data storage: The most recent N values ​​are stored in a queue of length N using a sliding window approach, where the newest data is N, and the oldest data is in the queue, represented as data 1, such as... Figure 3 As shown. Specifically, when the current calculation cycle begins, data N is first taken and the output results are classified using a decision tree. Each node in the decision tree contains two branches. If the result is "yes," it proceeds to the next node; if it is "no," the real-time envelope calculation output of the current cycle (also called the "current upper envelope value") is equal to the output of the previous cycle. The specific calculation process for calculating the real-time upper envelope value is as follows: Figure 4 The calculation of the upper envelope shows that the comparison involves checking if the data N is greater than the data N-1 in the sliding window queue. If "no", the previous output value is retained, and the calculation ends. If "yes", the comparison involves checking if the data N is greater than the data N-2 in the sliding window queue, and this process is repeated until all data in the sliding window queue has been compared. If the comparison result is still "yes", then the data N is output as the current upper envelope value. The calculation of the real-time lower envelope value follows the same process as the real-time upper envelope value calculation, but the judgment method differs. The specific calculation process for the lower envelope is as follows: Figure 4 The calculation of the lower envelope shows that the comparison data N is less than the data N-1 in the sliding window queue. If "no", the previous output value is retained and the calculation ends. If "yes", the comparison data N is less than the data N-2 in the sliding window queue, and this process is repeated until all the data in the sliding window queue is compared. If the comparison result is still "yes", the data N is output as the current lower envelope value.

[0042] Real-time envelope extraction of temperature signals based on decision tree envelope, such as... Figure 5 As shown; the real-time envelope of the vibration signal is extracted based on the envelope of the decision tree, as follows. Figure 6 As shown; the real-time envelope of the vibration signal after taking the absolute value is extracted based on the envelope of the decision tree, as shown in the figure. Figure 7 As shown.

[0043] Each calculation cycle generates a corresponding upper (lower) envelope value. After the calculation of the real-time envelope value based on the decision tree, the envelope value will definitely be able to enclose all the data in the sliding window queue. The output result of continuous calculation will also be a real-time envelope line that encloses the signal curve.

[0044] In one optional embodiment, the steps described above for obtaining N values ​​involve obtaining the real-time intensity values ​​of the signal over the first N periods. The length of the stored information N affects the accuracy of the envelope. Simply put, if N = 1, the envelope is equivalent to real-time data acquisition; as N gradually increases, the included frequency gradually decreases. Therefore, in a preferred embodiment, N is greater than or equal to f. c / f t The use of positive integers ensures the accuracy of the envelope, further improving the judgment of the wind turbine's operating status. In non-real-time data processing technology, there are many methods for solving the envelope, and the results are more accurate. If a certain signal does not have high real-time requirements, the delayed envelope can be calculated offline instead of the real-time envelope.

[0045] This embodiment provides a method for monitoring the condition of a wind turbine. Figure 8 This is a flowchart of a wind turbine condition monitoring method according to an embodiment of the present invention, such as... Figure 8 As shown, the process includes the following steps:

[0046] Step S801: Extract the signal envelope using the signal envelope extraction method for wind turbine generators described in the above embodiment;

[0047] Step S802: Determine the operating status of the wind turbine unit based on the signal envelope.

[0048] Through the above steps, the envelope of signals related to the wind turbine is obtained. The operating status of the wind turbine is then determined based on this envelope. Compared to existing technologies that rely on the amplitude of specific signal frequencies to determine whether the wind turbine generator is malfunctioning, which yields inaccurate results, the above steps use the signal envelope as the basis for judging the wind turbine's operating status, thus improving the accuracy of the judgment. Using real-time upper and lower envelopes can identify faults that current methods cannot detect, such as interference with temperature signals. The envelope also provides trends in the wind turbine's operating data. By analyzing these trends and the amplitude of the curve, it's possible to determine whether the operating status before reaching a threshold is normal. For example, if the nacelle vibration exhibits constant-amplitude or divergent oscillations before reaching a fault threshold, this is also an abnormal state and can be determined using the envelope.

[0049] While the Fast Fourier Transform (FFT) requires more resources to produce more accurate results, wind turbine control systems often lack sufficient resources for it, resulting in inaccurate results. The envelope algorithm, on the other hand, eliminates the need to convert time-series signals to frequency-domain signals, obtaining results directly from the time-series signals, thus yielding more accurate results.

[0050] There are many ways to implement the above-mentioned method of determining the operating status of a wind turbine based on the signal envelope. In one optional embodiment, the difference between the upper and lower envelope values ​​within the current period is calculated; when the difference is greater than a predetermined threshold, the wind turbine is determined to be abnormal. Specifically, with Figure 5Taking the real-time envelope of a temperature signal as an example, interference during temperature detection can cause large fluctuations in the detected value. Existing programs lack a method to assess this interference. In this optional embodiment, by determining whether the difference between the upper and lower real-time envelopes exceeds a certain threshold, the severity of the interference signal can be assessed, prompting warnings and fault reports. For instance, when the difference between the upper and lower real-time envelopes is less than 1 degree Celsius, the interference is considered minor and requires no warning; greater than 1 degree Celsius indicates a relatively serious interference requiring a warning; greater than 2 degrees Celsius indicates severe interference and a fault requiring immediate attention; and greater than 1 degree Celsius for more than 1 minute indicates severe interference, but the prolonged duration necessitates further action, also constituting a fault requiring immediate attention. Figure 6 Taking the real-time envelope of a vibration signal as an example, the upper and lower envelopes can be used as the maximum and minimum values ​​of vibration over a period of time. When a wind turbine operates, resonance occurs, which is reflected in the vibration signal, causing the amplitude of the vibration to gradually increase. Current methods involve determining that the vibration is too large and shutting down the wind turbine when the vibration signal exceeds a certain threshold (e.g., 0.15g). However, before a fault occurs, the wind turbine may operate under resonance for a long time before triggering the vibration fault threshold, which significantly impacts the unit's load and fatigue. Using a real-time envelope, the difference between the upper and lower real-time envelopes can be judged to be greater than a certain threshold, such as 0.1g. If the difference is greater than 0.1g and persists for one minute, the vibration can be considered persistently excessive, requiring a shutdown for inspection to avoid prolonged operation under resonant vibration conditions. Figure 7 Taking the upper envelope of the absolute value of a vibration signal as an example, when the signal vibrates around 0, the upper envelope can be used instead of the upper and lower envelopes after taking the absolute value, thus reducing the amount of computation.

[0051] In addition, the envelope of a signal has many other uses, such as curve fitting, trend prediction, expert diagnosis, etc. Due to the limited computing power and storage space of wind turbine control, complex calculations cannot be performed. The calculated upper (lower envelope) can be transmitted to a Supervisory Control and Data Acquisition (SCADA) system or a wind farm group control system. The host computer with more powerful computing capabilities can then perform more complex calculations to obtain the operating status of the wind turbine.

[0052] This embodiment also provides a signal envelope extraction device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementations, or a combination of software and hardware, are also possible and contemplated.

[0053] like Figure 9 As shown, the signal envelope extraction device includes: an acquisition module 91, used to acquire the intensity value of a signal in the current cycle; wherein the signal includes signals related to the wind turbine, and the signal includes at least one of the following: speed signal, vibration signal, temperature signal, pressure signal, stress signal, and load signal; a calculation module 92, used to calculate the upper envelope value and lower envelope value corresponding to the signal in the current cycle based on the intensity value; and an extraction module 93, used to extract the envelope of the signal based on the upper envelope value and lower envelope value of multiple cycles.

[0054] Optionally, the calculation module includes: an acquisition unit for acquiring N values; wherein N is greater than or equal to f. c / f t positive integers, f c f is the operating frequency of the wind turbine controller. t The maximum effective frequency of the signal is defined by a comparison unit, which compares the intensity value with the N values. A setting unit is configured to, when the intensity value is greater than any of the N values, use the intensity value as the upper envelope value of the current period; when the intensity value is less than any of the N values, use the intensity value as the lower envelope value of the current period; otherwise, use the upper envelope value of the previous period as the upper envelope value of the current period and the lower envelope value of the previous period as the lower envelope value of the current period.

[0055] Optionally, the acquisition unit is also used to acquire the real-time intensity value of the signal for the first N periods.

[0056] In this embodiment, the signal envelope extraction device is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0057] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0058] This embodiment also provides a wind turbine condition monitoring device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0059] like Figure 10As shown, the wind turbine's status monitoring device includes: an extraction device 101, used to extract the signal envelope through the aforementioned wind turbine signal envelope extraction device; and a determination module 102, used to determine the wind turbine's operating status based on the signal envelope.

[0060] Optionally, the determining module includes: a calculation unit for calculating the difference between the upper envelope value and the lower envelope value in the current period; and a determining unit for determining that the wind turbine is abnormal when the difference is greater than a predetermined threshold.

[0061] In this embodiment, the wind turbine condition monitoring device is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0062] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0063] like Figure 11 As shown, the terminal may include: at least one processor 1101, such as a CPU (Central Processing Unit), at least one communication interface 1103, memory 1104, and at least one communication bus 1102. The communication bus 1102 is used to implement communication between these components. The communication interface 1103 may include a display screen and a keyboard; optionally, the communication interface 1103 may also include a standard wired interface or a wireless interface. The memory 1104 may be high-speed RAM (Random Access Memory) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 1104 may also be at least one storage device located remotely from the aforementioned processor 1101. The processor 1101 may be combined with... Figure 9 or Figure 10 The described apparatus has a set of program codes stored in memory 1104, and processor 1101 calls the program codes stored in memory 1104 to execute a signal envelope extraction method or a wind turbine state monitoring method.

[0064] The communication bus 1102 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 1102 can be divided into an address bus, a data bus, and a control bus, etc. For ease of representation, Figure 11 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0065] The memory 1104 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 1104 may also include a combination of the above types of memory.

[0066] The processor 1101 can be a central processing unit (CPU), a network processor (NP), or a combination of CPU and NP.

[0067] The processor 1101 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0068] Optionally, memory 1104 is also used to store program instructions. Processor 1101 can call the program instructions to implement the functions described in this application. Figure 1Alternatively, the signal envelope extraction method or the wind turbine status monitoring method shown in 8 embodiments.

[0069] This invention also provides a non-transitory computer storage medium storing computer-executable instructions that can execute the signal envelope extraction method or the wind turbine state monitoring method in any of the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0070] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for condition monitoring of a wind turbine generator set, characterized in that, include: The intensity value of the wind turbine's signal in the current cycle is obtained; wherein the signal includes at least one of the wind turbine's speed signal, vibration signal, temperature signal, pressure signal, stress signal, and load signal; Calculate the upper and lower envelope values ​​corresponding to the signal within the current period based on the intensity value; The envelope of the signal is extracted based on the upper and lower envelope values ​​of multiple periods; The operating status of the wind turbine is determined based on the signal envelope; Calculating the upper and lower envelope values ​​corresponding to the signal within the current period based on the intensity value includes: Get N values; where N is greater than or equal to positive integers, The operating frequency of the wind turbine controller. The maximum effective frequency of the signal; the N values ​​are the real-time intensity values ​​of the signal in the previous N periods of the current period; Compare the intensity value with the N values; When the intensity value is greater than any of the N values, the intensity value is used as the upper envelope value of the current period; when the intensity value is less than any of the N values, the intensity value is used as the lower envelope value of the current period; otherwise, the upper envelope value of the previous period is used as the upper envelope value of the current period, and the lower envelope value of the previous period is used as the lower envelope value of the current period. Determining the operating status of the wind turbine based on the signal envelope includes: Calculate the difference between the upper envelope value and the lower envelope value within the current period; The wind turbine is determined to be abnormal when the difference is greater than a predetermined threshold.

2. A condition monitoring device for a wind turbine generator set, characterized in that, include: The acquisition module is used to acquire the intensity value of the wind turbine's signal in the current cycle; wherein the signal includes at least one of the wind turbine's speed signal, vibration signal, temperature signal, pressure signal, stress signal, and load signal; The calculation module is used to calculate the upper envelope value and lower envelope value corresponding to the signal in the current period based on the intensity value; An extraction module is used to extract the envelope of the signal based on the upper and lower envelope values ​​of multiple periods; The determination module is used to determine the operating status of the wind turbine based on the signal envelope extracted by the signal envelope extraction device. The computing module includes: The acquisition unit is used to acquire N values; where N is greater than or equal to positive integers, The operating frequency of the wind turbine controller. The maximum effective frequency of the signal; the N values ​​are the real-time intensity values ​​of the signal in the previous N periods of the current period; A comparison unit is used to compare the intensity value with the N values; The setting unit is configured to: when the intensity value is greater than any of the N values, use the intensity value as the upper envelope value of the current period; when the intensity value is less than any of the N values, use the intensity value as the lower envelope value of the current period; otherwise, use the upper envelope value of the previous period as the upper envelope value of the current period and the lower envelope value of the previous period as the lower envelope value of the current period. The determining module includes: The calculation unit is used to calculate the difference between the upper envelope value and the lower envelope value within the current period; A determining unit is used to determine that the wind turbine is abnormal when the difference is greater than a predetermined threshold.

3. An electronic device, characterized in that, include: At least one processor; The system also includes a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the processor, which are executed by the at least one processor to cause the at least one processor to perform the wind turbine condition monitoring method of claim 1.

4. A computer-readable storage medium storing computer instructions thereon, characterized in that, The instruction is executed by the processor using the wind turbine state monitoring method described in claim 1.

Images