Water turbine guide vane position fault judgment method and system

Abstract

The invention discloses a water turbine guide vane position fault judgment method and system, and belongs to the technical field of water turbine operation state real-time monitoring and fault analysis, and the method comprises the steps: collecting water turbine guide vane position data, environmental parameters and micro-vibration signals in real time through a non-intrusive mode, and eliminating noise and abnormal values; constructing a health model of a guide vane position, inputting the health model into a comparison module, and identifying a deviation from a real-time model constructed by real-time data; and fault judgment and fault simulation and prediction are carried out on the guide vane according to the deviation result, and a correction scheme is called according to the prediction result. According to the method, the real-time monitoring and fault judgment capability of the position of the guide vane of the water turbine is improved, the safety and the high efficiency of equipment are ensured, a solid data foundation is provided for continuously optimizing a maintenance strategy by establishing a long-acting monitoring and recording mechanism, the water turbine industry is promoted to develop towards a more intelligent and automatic direction, and the development period is shortened. The overall operation efficiency is further improved; and the service life of equipment is prolonged.

Description

Technical Field

[0001] The invention relates to the technical field of real-time monitoring and fault analysis of a water turbine operating state, and in particular to a method and system for judging a water turbine guide vane position fault. Background Art

[0002] As a key equipment in the hydropower generation system, the performance of the turbine is directly related to the efficiency and safety of power production. With the continuous development of modern hydropower generation technology, the design and control system of the turbine are becoming increasingly complex. Under the extremely high requirements of operating efficiency and stability, the application of various new materials and intelligent control technologies makes it possible to optimize the structure and improve the performance of the turbine guide vanes. However, despite the significant progress in technology, turbines still face various fault risks during actual operation. In particular, the guide vane position failure, for example, insufficient closure failure often leads to poor fluid passage. The root cause is that the guide vane is not completely closed, which is easy to cause liquid reflux or vortex. Current monitoring technology tends to ignore this detail and lacks dynamic evaluation of the guide vane closure state. In terms of eccentricity failure, traditional monitoring methods may only focus on the physical position of the guide vane, but do not fully consider the uneven distribution of force during rotation, resulting in excessive wear or even equipment failure. The jamming failure is often due to the failure to timely take into account environmental conditions (such as temperature and flow rate changes), ignoring the impact of the surrounding medium on the performance of the turbine. Therefore, the real-time monitoring and fault diagnosis methods for turbine guide vane position have received increasing attention and become one of the research hotspots.

[0003] Existing fault diagnosis technologies mostly rely on traditional signal acquisition and data processing methods. Although they can respond to faults to a certain extent, they often have obvious shortcomings such as insufficient real-time performance, low accuracy and poor adaptability. For example, some methods judge the fault status of the guide vane through regular inspection or limit warning. However, these methods are prone to misjudgment in complex environments, resulting in work delays or losses. In addition, the existing technology often adopts a single monitoring dimension and fails to make full use of multiple operating parameters (such as micro-vibration signals, environmental parameters, etc.), which limits the in-depth analysis of the fault. Therefore, when accurately judging the abnormal position of the guide vane, an integrated and multi-dimensional method is urgently needed to monitor and analyze the overall operating status of the turbine. The present invention proposes an efficient and accurate method for judging the position of the guide vane of a turbine. Combined with non-invasive data acquisition technology, through dynamic modeling and real-time monitoring, it can effectively identify faults such as insufficient closure, eccentricity and jamming, and covers the influence of multiple parameters and their real-time changes on the performance of the guide vane. In the process of fault identification, the frequency characteristics of the micro-vibration signal are used to extract the fault frequency, which can enhance the judgment of the guide vane position state, thereby improving the accuracy of fault analysis.

[0004] Therefore, the comprehensive monitoring means of the present invention can effectively improve the operating safety and efficiency of the turbine through this multi-dimensional fault monitoring and judgment method, and provide new ideas and references for the future development of hydropower generation technology. Summary of the invention

[0005] In view of the above-mentioned existing problems, the purpose of the present invention is to accurately judge the problems such as insufficient closure, eccentricity and jamming of the guide vanes by real-time collection and analysis of the position data, environmental parameters and micro-vibration signals of the turbine guide vanes, so as to solve the technical difficulties such as reduced power efficiency and equipment damage caused by faults during the operation of the guide vanes, realize effective monitoring and early warning of the operating status of the turbine, and improve its safety and reliability.

[0006] In order to solve the above technical problems, a method for judging the position fault of a turbine guide vane is proposed, comprising:

[0007] The turbine guide vane position data, environmental parameters and micro-vibration signals are collected in real time in a non-invasive manner and noise and outliers are eliminated. A healthy model of the guide vane position is constructed and input into the comparison module to identify deviations from the real-time model constructed with real-time data. The guide vane fault is judged based on the deviation results, and fault simulation and prediction are performed, and correction plans are retrieved based on the prediction results.

[0008] As a preferred solution of the method for judging the position fault of a guide vane of a water turbine described in the present invention, the guide vane position data includes recording the opening and position of the guide vane in real time through an angle sensor, and collecting the difference between the motor drive signal and the actual guide vane position;

[0009] The environmental parameters include obtaining real-time data on the effect of the physical state of water on the guide vane performance through a temperature sensor and a flow meter, and monitoring water level change data through a water level sensor;

[0010] The micro-vibration signal includes using a vibration sensor to record the micro-vibration during the operation of the turbine and performing fast Fourier transform analysis on the micro-vibration signal.

[0011] As a preferred solution of a method for judging the position fault of a guide vane of a water turbine according to the present invention, the fast Fourier transform analysis includes performing a fast Fourier transform on a micro-vibration signal to perform a weight analysis, extracting and analyzing the fault frequency of the micro-vibration signal, and judging the result of the fault frequency:

[0012]

[0013] When F fault >F th When F fault ≤F thWhen , it is considered that the fault frequency is within the allowable range and there is no fault;

[0014] Among them, F fault is the fault characteristic frequency extracted, m is the number of characteristic frequency components, i is the variable index, Ff i is the Fourier transform result of the i-th frequency point, α i is the weight coefficient of the i-th frequency point, Δp i is the phase shift of the frequency, p i is the characteristic frequency f i phase.

[0015] As a preferred solution of the method for judging the position fault of a guide vane of a water turbine described in the present invention, the comparison module includes performing three-dimensional dynamic picture modeling on the healthy model of the guide vane position and the real-time model constructed by the real-time data and displaying the rotation speed of the two models, and overlapping and comparing the graphical modeling of the two models:

[0016] When the dynamic image comparison results of the two models are completely overlapped or the error of the rotation speed of the two models after considering mechanical wear does not exceed 1.5%, the system determines that the guide vane position is within the normal operating range;

[0017] When the dynamic image comparison results of the two models are completely non-overlapping or the rotation speed of the two models is greater than 1.5%, the system determines that the guide vane position is faulty and further analysis of the specific fault mode is required;

[0018] Construct a healthy model H based on environmental parameters, historical guide vane position data, and dynamic feedback, construct a real-time model R based on real-time data, and use the output of the healthy model to calculate the deviation Δ between the real-time model and the healthy model;

[0019] According to the final deviation combined with F fault >F th The final fault judgment is made based on the solution results of the micro-vibration signal that is considered to have the fault frequency.

[0020] As a preferred solution of a method for judging the position fault of a guide vane of a water turbine according to the present invention, the fault judgment includes combining deviation calculation and spectrum analysis to obtain a final fault judgment value MIS fault :

[0021]

[0022] When the final fault judgment value is 1 and the result of extracting the fault frequency is significantly lower than the normal value, it is judged as an insufficient closure fault, and the guide vane is not completely closed, resulting in a loss of fluid dynamic efficiency;

[0023] When the final fault judgment value is 1 and the result of extracting the fault frequency is a mutation, it is determined to be an eccentric fault, and there is a guide vane eccentricity phenomenon, which leads to uneven wear;

[0024] When the final fault judgment value is 1 and the high-frequency component of the result of extracting the fault frequency shows abnormal vibration, it is judged as a stuck fault, indicating that the guide vane is stuck during the rotation process, where Δ th is the threshold of health status.

[0025] As a preferred solution of the method for judging the position fault of a guide vane of a water turbine described in the present invention, the fault simulation and prediction includes: performing future risk simulation prediction on the judged fault mode in a three-dimensional dynamic picture, retrieving a correction plan according to the prediction result, and inputting the correction plan into the health model for correction;

[0026] The future risk simulation prediction includes using a multi-layer adaptive network based on time-varying characteristics, where the input layer receives the guide vane position data, environmental parameters and micro-vibration signals, extracts key features as needed through adaptive neurons, and outputs them as feature sets to generate predicted failure modes;

[0027] Based on the prediction results, determine whether the current fault level will cause irreparable damage or shutdown of the turbine guide vanes and the entire turbine within the next 72 hours;

[0028] When the predicted failure mode is greater than the threshold, it is judged that the above-mentioned consequence will occur within the next 72 hours, and the corresponding correction plan 1 is retrieved;

[0029] When the predicted failure mode is less than or equal to the threshold, it is judged that the aforementioned consequence will not occur within the next 72 hours, and the corresponding correction plan 2 is retrieved.

[0030] As a preferred solution of the method for judging the position fault of a guide vane of a water turbine described in the present invention, wherein: the correction solution 1 includes taking immediate measures to shut down the machine or severely damage the equipment due to the fault, using sensors and ultrasonic detection instruments to deeply evaluate the actual damage of the guide vane, recording and feeding back all data to the fault model for relearning;

[0031] Through the manual control system, according to the real-time monitoring results, the guide vanes are adjusted to the optimal working angle to reduce the impact on the flow rate. The control strategy generated by the training in the 3D modeling simulation is prepared to replace the damaged guide vane parts, and the emergency plan is improved for the identified faults, and subsequent regular inspections and evaluations are set up;

[0032] The second correction plan includes using multi-frequency input signals to test the guide vane response, combining real-time data to quickly adjust the PID parameters of the control system, adjusting the speed and flow of the starting water pump to make the turbine work in a suitable state, combining the prediction results, regularly conducting a comprehensive assessment of the guide vane status, displaying the operating performance through a three-dimensional dynamic view, and regularly formulating step-by-step maintenance plans, focusing on the lubrication and replacement cycles of components, so that all components work in the optimal state. At the same time, a long-term monitoring and recording mechanism is established to form a closed-loop feedback, collect experience and data from all processing processes, and establish a knowledge base for direct reference when predicting future risks.

[0033] Another object of the present invention is to provide a method system for judging the position fault of a guide vane of a water turbine. The present invention realizes rapid and accurate judgment of faults by real-time monitoring and analyzing the guide vane position and related environmental parameters, thereby improving the operational safety and reliability of the water turbine. The system specifically solves the technical difficulties of dynamic monitoring of guide vane position changes, can effectively filter noise and abnormal values, and at the same time build a health model for deviation comparison, realize comprehensive analysis with micro-vibration signals, so as to timely identify potential faults and propose reasonable correction plans, thereby reducing the risk of equipment downtime and maintenance costs.

[0034] As a preferred solution of the hydraulic turbine guide vane position fault judgment system described in the present invention, it is characterized by comprising a data acquisition module, a comparison module, a fault judgment module, and a fault correction module;

[0035] The data acquisition module acquires real-time guide vane position data, environmental parameters and micro-vibration signal data through angle sensors, temperature sensors and flow meters, performs signal processing, and eliminates noise and abnormal values;

[0036] The comparison module receives the processed data from the data acquisition module and constructs a guide vane health model and a real-time model based on environmental and historical data for deviation comparison;

[0037] The fault judgment module performs deviation comparison through the comparison module and performs fault judgment in combination with the micro-vibration signal;

[0038] The fault correction module obtains the fault judgment result through the fault judgment module, generates a future risk simulation according to the fault mode, and proposes correction plan 1 or correction plan 2 according to the prediction result and feeds it back to the system.

[0039] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the method for determining a turbine guide vane position fault are implemented.

[0040] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method for determining a turbine guide vane position fault are implemented.

[0041] Beneficial effects of the present invention: The present invention collects turbine guide vane position data, environmental parameters and micro-vibration signals in real time in a non-invasive manner, and strives to ensure high accuracy and reliability of the data under the influence of noise and abnormal values. Specifically, by using an angle sensor to record the opening of the guide vane, and a temperature and flow meter to obtain the physical state data of the water, the present invention effectively presents the impact of environmental factors on the performance of the guide vane. In addition, through the fast Fourier transform analysis of the micro-vibration signal, it is possible to extract potential fault frequencies, quickly identify and locate faults, and effectively reduce maintenance costs and downtime.

[0042] In terms of fault diagnosis, the present invention constructs a healthy model of the guide vane position and compares it with the model generated by real-time data. In this process, three-dimensional dynamic modeling technology is used to intuitively display the rotation status of the two models. When the models overlap, it indicates that the guide vanes are within the normal working range, avoiding unnecessary maintenance; if there is a deviation, the system will automatically trigger further analysis to ensure timely identification of potential faults and improve the speed and accuracy of fault response. Combined with environmental parameters and historical data, the construction of a healthy model ensures the scientific nature of fault diagnosis and further improves the reliability of fault prediction.

[0043] Through detailed fault judgment and risk prediction, the present invention can quickly identify fault modes such as insufficient closure, eccentricity or jamming, thereby ensuring timely and targeted countermeasures to reduce the risk of equipment damage. By using a multi-layer adaptive network based on time-varying characteristics, the present invention demonstrates a high degree of flexibility and intelligence, making the handling of different fault conditions more efficient. Future risk assessment determines the possibility of a fault by setting a threshold, providing a scientific basis for whether to shut down and repair immediately, thereby minimizing economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0045] Figure 1 An overall flow chart of a method for determining a turbine guide vane position fault provided by an embodiment of the present invention.

[0046] Figure 2A schematic diagram of a module of a turbine guide vane position fault judgment system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0049] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0050] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0051] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0052] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0053] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a method for determining a fault in a guide vane position of a water turbine, comprising:

[0054] The present invention mainly analyzes insufficient closure, eccentricity and jamming failures.

[0055] S1: Collect turbine guide vane position data, environmental parameters and micro-vibration signals in real time in a non-invasive manner and eliminate noise and outliers.

[0056] Specifically, the opening and position of the guide vanes are recorded in real time by an angle sensor, and the difference between the motor drive signal and the actual guide vane position is collected;

[0057] Environmental parameters include real-time data on the impact of water's physical state on guide vane performance obtained through temperature sensors and flow meters, and water level change data monitored through water level sensors;

[0058] The micro-vibration signal includes using a vibration sensor to record the micro-vibration during the operation of the turbine and performing fast Fourier transform analysis on the micro-vibration signal.

[0059] Furthermore, the micro-vibration signal is subjected to fast Fourier transform for weight analysis:

[0060]

[0061]

[0062] Where Ff represents the amplitude of frequency f, N is the total number of signal sampling points, i and n are both variable indexes, St i is the sampling time t i The sample value of the micro-vibration signal, W i represents the contrast of the enhanced frequency component, j is an imaginary unit, c is the rate at which the control weight is weakened, and t0 is the initial sampling time;

[0063] Extract and analyze the fault frequency of the micro-vibration signal and determine the result of the fault frequency:

[0064]

[0065] When F fault >F th When F fault ≤F th When , it is considered that the fault frequency is within the allowable range and there is no fault;

[0066] Among them, F fault is the fault characteristic frequency extracted, m is the number of characteristic frequency components, F(fi ) is the Fourier transform result of the i-th frequency point, α i is the weight coefficient of the i-th frequency point, Δp i is the phase shift of the frequency, p i is the characteristic frequency f i phase.

[0067] S2: constructing a healthy model of the guide vane position and identifying deviations from the real-time model constructed using real-time data in the comparison module.

[0068] Furthermore, a three-dimensional dynamic picture model is performed on the healthy model of the guide vane position and the real-time model constructed by the real-time data, and the rotation speeds of the two models are displayed, and the graphical modeling of the two models is overlapped and compared:

[0069] When the dynamic image comparison results of the two models are completely overlapped or the error of the rotation speed of the two models after considering mechanical wear does not exceed 1.5%, the system determines that the guide vane position is within the normal operating range;

[0070] When the dynamic image comparison results of the two models are completely non-overlapping or the rotation speed of the two models is greater than 1.5%, the system determines that the guide vane position is faulty and further analysis of the specific fault mode is required;

[0071] Construct a health model H based on environmental parameters, historical guide vane position data, and dynamic feedback:

[0072]

[0073] Among them, H is the health status assessment value of the guide vane, M is the number of environmental parameters, and a i is the weight coefficient of the i-th environmental parameter, E i is the i-th environmental parameter, λ is the attenuation factor of the intensity of the control time, t i is a parameter that reflects the evolution of health status over time, θ i POS is the current position and the parameter for adjusting the guide vane angle. h is the historical guide vane position data, C is the constant for adjusting the flexibility of the model;

[0074] Build real-time models built on real-time data R:

[0075]

[0076] Where R is the real-time guide vane status evaluation value, I is the number of real-time data parameters, and b i is the weight coefficient of the i-th real-time data parameter, J i (D t) is the characteristic function of the i-th real-time data, β is the attenuation factor of the real-time data, and A is the number of real-time data points;

[0077] The output of the healthy model is used to calculate the deviation Δ between the real-time model and the healthy model:

[0078]

[0079] Where Δ is the deviation between the healthy model and the real-time model, D t，max is the maximum value of real-time data, D t，mean is the mean of real-time data;

[0080] According to the final deviation combined with F fault >F th The final fault judgment is made based on the solution results of the micro-vibration signal that is considered to have the fault frequency.

[0081] Specifically, the final fault judgment value MIS is obtained by combining deviation calculation and spectrum analysis fault :

[0082]

[0083] When the final fault judgment value is 1 and the result of extracting the fault frequency is significantly lower than the normal value, it is judged as an insufficient closure fault, and the guide vane is not completely closed, resulting in a loss of fluid dynamic efficiency;

[0084] When the final fault judgment value is 1 and the result of extracting the fault frequency is a mutation, it is determined to be an eccentric fault, and there is a guide vane eccentricity phenomenon, which leads to uneven wear;

[0085] When the final fault judgment value is 1 and the high-frequency component of the result of extracting the fault frequency shows abnormal vibration, it is judged as a stuck fault, indicating that the guide vane is stuck during the rotation process, where Δ th is the threshold of health status.

[0086] S3: According to the deviation results, the fault of the guide vane is judged, and fault simulation and prediction are performed, and the correction plan is retrieved according to the prediction results.

[0087] Furthermore, the future risk simulation prediction is carried out for the determined fault mode in the three-dimensional dynamic picture, and the correction plan is retrieved according to the prediction result, and the correction plan is input into the health model for correction;

[0088] The future risk simulation prediction includes using a multi-layer adaptive network based on time-varying characteristics, where the input layer receives the guide vane position data POSt, environmental parameters Et and micro-vibration signal St, extracts key features on demand through adaptive neurons, and outputs a feature set X to generate a predicted fault mode ModeX|T:

[0089]

[0090] Wherein, ModeX|T is the probability of fault occurrence at time t, C2 is a constant for adjusting the sensitivity of the model, ΔPOSt is the rate of change of the guide vane position at time t, ΔEt is at time t, ΔSt is the rate of change of the microvibration signal at time t, and Λ is the reference value of the system;

[0091] Based on the prediction results, determine whether the current fault level will cause irreparable or shutdown consequences to the turbine guide vanes and the entire turbine within the next 72 hours:

[0092]

[0093] Among them, Mode th is the threshold for judging the risk level of failure occurrence, μ represents the average probability of historical failure occurrence, σ represents the standard deviation, the degree of fluctuation of the historical failure rate; γ represents the amplification factor that affects the standard deviation on the threshold adjustment;

[0094] When ModeX|t>Mode th , it is judged that the above-mentioned consequences will occur within the next 72 hours, and the corresponding correction plan 1 will be retrieved;

[0095] When ModeX|t≤Mode th , it is judged that the above-mentioned consequences will not occur within the next 72 hours, and the corresponding correction plan 2 will be retrieved.

[0096] It should be noted that if the fault causes downtime or serious damage to the equipment, immediate measures should be taken to shut down the machine quickly, and the actual damage of the guide vanes should be deeply evaluated using sensors and ultrasonic detection instruments. All data should be recorded and fed back to the fault model for re-learning;

[0097] Through the manual control system, according to the real-time monitoring results, the guide vanes are adjusted to the optimal working angle to reduce the impact on the flow rate. The control strategy generated by the training in the 3D modeling simulation is prepared to replace the damaged guide vane parts, and the emergency plan is improved for the identified faults, and subsequent regular inspections and evaluations are set up;

[0098] The second correction scheme includes using a multi-frequency input signal to test the guide vane response and combining real-time data to quickly adjust the PID parameters of the control system:

[0099] K new =K old 1+δ

[0100] Among them, δ is the fine-tuning coefficient set according to the trend change; adjust the speed and flow rate of the starting water flow pump to make the turbine work in a suitable state, combine the prediction results, conduct a comprehensive assessment of the guide vane status regularly, display the operating performance through a three-dimensional dynamic view, and regularly formulate a step-by-step maintenance plan, focusing on the lubrication and replacement cycle of components, so that all components work in the optimal state. At the same time, establish a long-term monitoring and recording mechanism to form a closed-loop feedback, collect experience and data from all processing processes, and establish a knowledge base for direct call when predicting future risks.

[0101] Embodiment 2, the second embodiment of the present invention, is different from the first two embodiments in that:

[0102] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0103] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0104] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0105] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0106] Example 3, reference Figure 2 , which is the third embodiment of the present invention, and provides a turbine guide vane position fault judgment system, including a data acquisition module 10, a comparison module 20, a fault judgment module 30, and a fault correction module 40;

[0107] The data acquisition module 10 obtains real-time guide vane position data, environmental parameters and micro-vibration signal data through angle sensors, temperature sensors and flow meters, performs signal processing, and eliminates noise and abnormal values;

[0108] The comparison module 20 receives the processed data from the data acquisition module 10 and constructs a guide vane health model and a real-time model based on environmental and historical data for deviation comparison;

[0109] The fault judgment module 30 performs deviation comparison through the comparison module 20 and performs fault judgment in combination with the micro-vibration signal;

[0110] The fault correction module 40 obtains the fault judgment result through the fault judgment module 30, generates a future risk simulation according to the fault mode, and proposes correction plan 1 or correction plan 2 according to the prediction result and feeds it back to the system.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for determining a fault in a guide vane position of a water turbine, characterized in that: include, Collect turbine guide vane position data, environmental parameters and micro-vibration signals in real time in a non-invasive manner and eliminate noise and outliers; Constructing a healthy model of the guide vane position inputs into the comparison module to identify deviations from the real-time model constructed using real-time data; The guide vane fault is judged based on the deviation results, and fault simulation and prediction are performed, and the correction plan is retrieved based on the prediction results.

2. A method for determining a turbine guide vane position fault according to claim 1, characterized in that: The guide vane position data includes recording the opening and position of the guide vane in real time through an angle sensor, and collecting the difference between the motor drive signal and the actual guide vane position; The environmental parameters include obtaining real-time data on the effect of the physical state of water on the guide vane performance through a temperature sensor and a flow meter, and monitoring water level change data through a water level sensor; The micro-vibration signal includes using a vibration sensor to record the micro-vibration during the operation of the turbine and performing fast Fourier transform analysis on the micro-vibration signal.

3. A method for determining a turbine guide vane position fault according to claim 2, characterized in that: The fast Fourier transform analysis includes performing fast Fourier transform on the micro-vibration signal to perform weight analysis, extracting and analyzing the fault frequency of the micro-vibration signal, and determining the result of the fault frequency: When F fault >F th When F fault ≤F th When , it is considered that the fault frequency is within the allowable range and there is no fault; Among them, F fault is the fault characteristic frequency extracted, m is the number of characteristic frequency components, i is the variable index, F(f i ) is the Fourier transform result of the i-th frequency point, α i is the weight coefficient of the i-th frequency point, Δp i is the phase shift of the frequency, p i is the characteristic frequency f i phase.

4. A method for determining a turbine guide vane position fault according to claim 3, characterized in that: The comparison module includes performing three-dimensional dynamic image modeling on the healthy model of the guide vane position and the real-time model constructed by the real-time data and displaying the rotation speeds of the two models, and overlapping and comparing the graphic modeling of the two models: When the dynamic image comparison results of the two models are completely overlapped or the error of the rotation speed of the two models after considering mechanical wear does not exceed 1.5%, the system determines that the guide vane position is within the normal operating range; When the dynamic image comparison results of the two models are completely non-overlapping or the rotation speed of the two models is greater than 1.5%, the system determines that the guide vane position is faulty and further analysis of the specific fault mode is required; Construct a healthy model H based on environmental parameters, historical guide vane position data, and dynamic feedback, construct a real-time model R based on real-time data, and use the output of the healthy model to calculate the deviation Δ between the real-time model and the healthy model; According to the final deviation combined with F fault >F th The final fault judgment is made based on the solution results of the micro-vibration signal that is considered to have the fault frequency.

5. A method for determining a turbine guide vane position fault according to claim 4, characterized in that: The fault judgment includes combining deviation calculation and spectrum analysis to obtain the final fault judgment value MIS fault : When the final fault judgment value is 1 and the result of extracting the fault frequency is significantly lower than the normal value, it is judged as an insufficient closure fault, and the guide vane is not completely closed, resulting in a loss of fluid dynamic efficiency; When the final fault judgment value is 1 and the result of extracting the fault frequency is a mutation, it is determined to be an eccentric fault, and there is a guide vane eccentricity phenomenon, which leads to uneven wear; When the final fault judgment value is 1 and the high-frequency component of the result of extracting the fault frequency shows abnormal vibration, it is judged as a stuck fault, indicating that the guide vane is stuck during the rotation process, where Δ th is the threshold of health status.

6. A method for determining a turbine guide vane position fault according to claim 5, characterized in that: The fault simulation and prediction includes: performing future risk simulation prediction on the determined fault mode in the three-dimensional dynamic picture, retrieving the correction plan according to the prediction result, and inputting the correction plan into the health model for correction; The future risk simulation prediction includes using a multi-layer adaptive network based on time-varying characteristics, where the input layer receives the guide vane position data, environmental parameters and micro-vibration signals, extracts key features as needed through adaptive neurons, and outputs them as feature sets to generate predicted failure modes; Based on the prediction results, determine whether the current fault level will cause irreparable damage or shutdown of the turbine guide vanes and the entire turbine within the next 72 hours; When the predicted failure mode is greater than the threshold, it is judged that the above-mentioned consequence will occur within the next 72 hours, and the corresponding correction plan 1 is retrieved; When the predicted failure mode is less than or equal to the threshold, it is judged that the aforementioned consequence will not occur within the next 72 hours, and the corresponding correction plan 2 is retrieved.

7. A method for determining a fault in a guide vane position of a water turbine according to claim 6, characterized in that: The first correction plan includes taking immediate measures to shut down the machine or severely damage the equipment due to the fault, using sensors and ultrasonic detection instruments to deeply evaluate the actual damage of the guide vanes, and recording and feeding back all data to the fault model for re-learning; Through the manual control system, according to the real-time monitoring results, the guide vanes are adjusted to the optimal working angle to reduce the impact on the flow rate. The control strategy generated by the training in the 3D modeling simulation is prepared to replace the damaged guide vane parts, and the emergency plan is improved for the identified faults, and subsequent regular inspections and evaluations are set up; The second correction plan includes using multi-frequency input signals to test the guide vane response, combining real-time data to quickly adjust the PID parameters of the control system, adjusting the speed and flow of the starting water pump to make the turbine work in a suitable state, combining the prediction results, regularly conducting a comprehensive assessment of the guide vane status, displaying the operating performance through a three-dimensional dynamic view, and regularly formulating step-by-step maintenance plans, focusing on the lubrication and replacement cycles of components, so that all components work in the optimal state. At the same time, a long-term monitoring and recording mechanism is established to form a closed-loop feedback, collect experience and data from all processing processes, and establish a knowledge base for direct reference when predicting future risks.

8. A system using a method for determining a turbine guide vane position fault according to any one of claims 1 to 7, characterized in that: It includes data acquisition module, comparison module, fault judgment module and fault correction module; The data acquisition module acquires real-time guide vane position data, environmental parameters and micro-vibration signal data through angle sensors, temperature sensors and flow meters, performs signal processing, and eliminates noise and abnormal values; The comparison module receives the processed data from the data acquisition module and constructs a guide vane health model and a real-time model based on environmental and historical data for deviation comparison; The fault judgment module performs deviation comparison through the comparison module and performs fault judgment in combination with the micro-vibration signal; The fault correction module obtains the fault judgment result through the fault judgment module, generates a future risk simulation according to the fault mode, and proposes correction plan 1 or correction plan 2 according to the prediction result and feeds it back to the system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for determining a turbine guide vane position fault according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for determining a turbine guide vane position fault according to any one of claims 1 to 7 are implemented.

Images