Multi-source signal fusion water turbine cavitation monitoring device and cavitation evaluation method

Abstract

The invention provides a multi-source signal fusion water turbine cavitation monitoring device and a cavitation evaluation method, and relates to the technical field of hydroelectric application, the device comprises a thermistor sensor, a noise sensor, a pressure pulsation sensor, a vibration sensor, a throw sensor and a signal processing terminal; the thermistor sensor, the noise sensor, the pressure pulsation sensor, the vibration sensor and the throw sensor are all connected with the signal processing terminal. The thermistor sensor is used for transmitting a transient temperature field signal of the blade to the signal processing terminal; the noise sensor is used for collecting cavitation noise signals and transmitting the cavitation noise signals to the signal processing terminal; the pressure pulsation sensor is used for collecting draft tube pressure fluctuation signals and transmitting the signals to the signal processing terminal. The vibration sensor is used for collecting unit vibration and is connected to the signal processing terminal. The throw sensor is used for collecting a spindle throw signal and accessing the spindle throw signal to the signal processing terminal; and the signal processing terminal is used for signal fusion, feature analysis and cavitation level judgment.

Description

Technical Field

[0001] This invention relates to the field of hydropower application technology, and in particular to a multi-source signal fusion device for monitoring cavitation in a hydro turbine and a method for evaluating cavitation. Background Technology

[0002] Cavitation is a common physical phenomenon in the operation of hydraulic turbines. When the local water pressure is lower than the saturated vapor pressure, cavitation bubbles are generated in the water and undergo a process of formation, development, and collapse. This process releases high-temperature, high-pressure microjets and shock waves, which, over time, can cause cavitation erosion, efficiency loss, and vibration in turbine components, seriously affecting operational safety. Furthermore, cavitation is difficult to observe directly in its early stages, and its development process exhibits nonlinear and stochastic characteristics. Therefore, precise and effective monitoring technologies are urgently needed to mitigate these risks.

[0003] Currently, the industry mainly uses traditional vibration sensors, sway sensors, acoustic emission sensors, and pressure sensors to monitor cavitation in hydro turbines. Among them, vibration and sway sensors reflect the operating status by indirectly measuring the unit vibration caused by turbulence, while acoustic emission sensors and pressure sensors are used to capture cavitation-related intensity signals and mechanical response signals, respectively.

[0004] However, existing monitoring methods have significant limitations: they cannot accurately reflect the degree of cavitation; vibration and sway sensors can only monitor indirectly, and vibration values ​​do not change significantly, making early warning difficult; by the time vibration values ​​exceed the standard, cavitation is already quite severe. Furthermore, they lack the ability to capture thermodynamic characteristics; vibration and pressure sensors can only monitor mechanical responses and cannot directly obtain information on the localized high temperatures and other thermal effects generated when cavitation bubbles collapse. Summary of the Invention

[0005] In view of the shortcomings of the prior art, the purpose of this invention is to provide a cavitation evaluation method that can solve the problems of existing technologies, such as the inability to accurately reflect the degree of cavitation, the inability of vibration and sway sensors to monitor cavitation indirectly with no significant change in vibration values, making early warning difficult, and the inability to provide early warning when vibration values ​​exceed the standard, resulting in severe cavitation. Furthermore, it lacks the ability to capture thermodynamic features, and vibration and pressure sensors can only monitor mechanical responses, failing to directly obtain information on the localized high temperatures and other thermal effects generated when cavitation bubbles collapse.

[0006] A first aspect of this invention provides a multi-source signal fusion device for monitoring cavitation in a hydro turbine, comprising: Thermistor sensors, noise sensors, pressure pulsation sensors, vibration sensors, sway sensors, and signal processing terminals.

[0007] The thermistor sensor, noise sensor, pressure pulsation sensor, vibration sensor, and sway sensor are all connected to the signal processing terminal.

[0008] Thermistor sensors are used to transmit the captured transient temperature field signal of the blade to the signal processing terminal.

[0009] The noise sensor is used to collect cavitation noise signals and transmit them to the signal processing terminal.

[0010] The pressure pulsation sensor is used to collect pressure fluctuation signals in the tailrace pipe and transmit these signals to the signal processing terminal.

[0011] Vibration sensors are used to collect unit vibration data and transmit the unit vibration data to a signal processing terminal.

[0012] The spindle oscillation sensor is used to acquire the spindle oscillation signal and connect the spindle oscillation signal to the signal processing terminal.

[0013] The signal processing terminal receives multi-channel synchronous signals through an integrated data acquisition card and performs signal fusion, feature analysis, and cavitation level determination through an embedded processor.

[0014] A second aspect of this invention provides a cavitation evaluation method applied to the multi-source signal fusion turbine cavitation monitoring device of the first aspect, comprising: S1: Obtain the temperature of each area of ​​the water turbine.

[0015] S2: Using a thermistor sensor, identify areas of the turbine where the temperature is higher than the preset temperature, i.e., cavitation heat zones.

[0016] S3: Calculate the ratio of the area of ​​the cavitation heat zone to the area of ​​the turbine to determine the cavitation heat zone area ratio.

[0017] S4: Determine the quantization thresholds for multi-source signals, which specifically include: temperature threshold, cavitation hot zone area ratio threshold, abrasion depth threshold, vibration threshold, sway threshold, pressure pulsation threshold, and noise threshold.

[0018] S5: Real-time measurement parameters of the turbine are collected through a turbine cavitation monitoring device that integrates multi-source signals.

[0019] S6: By comparing the real-time measurement parameters and the quantization threshold of the multi-source signals, the cavitation degree of the turbine is obtained.

[0020] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: In this embodiment of the invention, a turbine cavitation monitoring device using multi-source signal fusion can accurately reflect the degree of cavitation in a turbine by comparing real-time measurement parameters with multi-source signal quantization thresholds. Simultaneously, by using a thermistor sensor and combining it with the characteristics of cavitation bubble collapse, the hot spot fluctuation frequency associated with the collapse frequency can be extracted, allowing direct acquisition of information on localized high temperatures and other thermal effects generated during cavitation bubble collapse. Attached Figure Description

[0021] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. Obviously, the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without any creative effort.

[0022] Figure 1 This is a schematic diagram of the structure of a multi-source signal fusion turbine cavitation monitoring device provided in an embodiment of the present invention.

[0023] Figure 2 This is a schematic flowchart of a cavitation evaluation method provided in an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions 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. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] The cavitation evaluation method provided by the present invention will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0026] Reference manual attached Figure 1 The diagram shows a structural schematic of a multi-source signal fusion hydro turbine cavitation monitoring device provided in an embodiment of the present invention.

[0027] This invention provides a multi-source signal fusion cavitation monitoring device for a water turbine, comprising: a thermistor sensor, a noise sensor, a pressure pulsation sensor, a vibration sensor, a sway sensor, and a signal processing terminal.

[0028] The thermistor sensor, noise sensor, pressure pulsation sensor, vibration sensor, and sway sensor are all connected to the signal processing terminal.

[0029] Thermistor sensors are used to transmit the captured transient temperature field signal of the blade to the signal processing terminal.

[0030] The noise sensor is used to collect cavitation noise signals and transmit them to the signal processing terminal.

[0031] The pressure pulsation sensor is used to collect pressure fluctuation signals in the tailrace pipe and transmit these signals to the signal processing terminal.

[0032] Vibration sensors are used to collect unit vibration data and transmit the unit vibration data to a signal processing terminal.

[0033] The spindle oscillation sensor is used to acquire the spindle oscillation signal and connect the spindle oscillation signal to the signal processing terminal.

[0034] The signal processing terminal receives multi-channel synchronous signals through an integrated data acquisition card and performs signal fusion, feature analysis, and cavitation level determination through an embedded processor.

[0035] In this embodiment of the invention, the multi-source signal fusion turbine cavitation monitoring device collects multi-source signals such as temperature, noise, and pressure pulsation through multiple sensors and transmits them synchronously to the signal processing terminal. After fusion analysis and feature extraction, the cavitation level is determined. This not only breaks through the limitations of traditional single signal monitoring, but also accurately captures the thermodynamic characteristics and mechanical response of cavitation, realizing early warning, accurate positioning, and real-time intelligent assessment, significantly improving the comprehensiveness, reliability, and practicality of turbine cavitation monitoring.

[0036] In one possible implementation, the thermistor sensor specifically includes multiple thermistor sensors.

[0037] Furthermore, based on the size and shape of the turbine blades, multiple thermistor sensors are evenly embedded on the surface of the turbine blades to capture the transient temperature field distribution during the collapse of cavitation bubbles.

[0038] Specifically, noise sensors are located in the turbine chamber and at the tailrace inlet. Pressure pulsation sensors are installed at the tailrace inlet. Vibration sensors are located on the top cover to collect unit vibration signals. Swing sensors are located at the turbine main shaft to collect unit swing signals.

[0039] In this embodiment of the invention, the thermistor sensor arrangement involves multiple thermistors evenly distributed and buried on the blade surface to accurately capture the transient temperature field of cavitation and achieve regional positioning. Various types of sensors are arranged in key locations such as the water turbine chamber and tailrace pipe according to functional requirements, which can efficiently collect interference-free target signals and provide accurate data support for multi-source fusion analysis, cavitation quantitative evaluation and early warning, greatly improving the comprehensiveness, pertinence and reliability of monitoring.

[0040] Reference manual attached Figure 2 The diagram shows a flowchart of a cavitation evaluation method provided by an embodiment of the present invention.

[0041] This invention provides a cavitation evaluation method, applied to the aforementioned multi-source signal fusion turbine cavitation monitoring device, which may include the following steps: S1: Obtain the temperature of each area of ​​the water turbine.

[0042] S2: Using a thermistor sensor, identify areas of the turbine where the temperature is higher than the preset temperature, i.e., cavitation heat zones.

[0043] In this embodiment of the invention, thermistor sensors evenly distributed on the surface of the blades are used to accurately identify cavitation hot zones with temperatures higher than a preset temperature, directly capturing the core thermodynamic characteristics of cavitation bubble collapse. This not only makes up for the shortcomings of traditional monitoring in capturing thermal effects, but also provides accurate raw data for subsequent cavitation area quantification and regional positioning, and can also identify nascent cavitation in advance, greatly improving the targeting of monitoring and early warning capabilities.

[0044] In one possible implementation, after S2, the following is also included: By using a thermistor sensor and combining the characteristics of cavitation bubble collapse, the hot spot fluctuation frequency associated with the collapse frequency is extracted.

[0045] In this embodiment of the invention, transient temperature data is captured by a thermistor sensor, and the hot spot fluctuation frequency associated with the collapse frequency is extracted by combining the collapse characteristics of cavitation bubbles. This not only directly captures the core thermodynamic characteristics of cavitation and makes up for the shortcoming of traditional technology that cannot associate with the essential frequency of cavitation, but also provides a key basis for subsequent multi-signal frequency comparison and verification, significantly improving the accuracy of cavitation identification and the reliability of intelligent prediction.

[0046] S3: Calculate the ratio of the area of ​​the cavitation heat zone to the area of ​​the turbine to determine the cavitation heat zone area ratio.

[0047] Specifically, the formula for calculating the cavitation heat zone area ratio is:

[0048] in, R Indicates the cavitation heat zone area ratio. S Indicates the area of ​​the cavitation heat zone. S 0 represents the area of ​​the water turbine.

[0049] In this embodiment of the invention, the cavitation hot zone area ratio is determined by calculating the ratio of the cavitation hot zone area to the surface area of ​​a single turbine blade. This transforms the cavitation range from a qualitative description into a quantitative indicator, making up for the deficiency of traditional technologies in being unable to quantify the degree of cavitation. It provides an objective and accurate core basis for subsequent cavitation degree classification, significantly improving the scientific nature and operability of monitoring and evaluation.

[0050] S4: Determine the quantization thresholds for multi-source signals, which specifically include: temperature threshold, cavitation hot zone area ratio threshold, abrasion depth threshold, vibration threshold, sway threshold, pressure pulsation threshold, and noise threshold.

[0051] Specifically, the method for determining the erosion depth threshold is as follows: when the thermal sensor is functioning normally, the switch signal is set to 0. When the thermal sensor fails, the switch signal is set to 1.

[0052] For example, considering that the average annual surface water temperature is roughly in the range of 0-30℃, and taking into account the error, the temperature threshold T0 is set to 45℃ with an amplification factor of 1.5.

[0053] The cavitation hot zone area ratio threshold R0 is taken from DL / T444-2020 Guidelines for the Assessment of Corrosion of Reaction Turbines, 6.1.4 The corrosion area of ​​a single blade of the runner should not exceed 15% of the surface area of ​​a single blade.

[0054] The vibration threshold A0, swing threshold B0, pressure pulsation threshold P0, and noise threshold N0 shall be implemented in accordance with the relevant provisions in GB / T15468-2020 Basic Technical Conditions for Hydropower Turbines, and will not be repeated here.

[0055] It should be noted that those skilled in the art can set the quantization threshold for multi-source signals according to actual needs, and this invention does not limit such settings.

[0056] In this embodiment of the invention, multiple key indicators such as temperature and cavitation heat zone area ratio are comprehensively covered. The quantitative thresholds are scientifically set in combination with the actual surface water temperature, industry standards and sensor operating conditions. This not only ensures the rationality and authority of the thresholds, but also provides an objective and unified reference standard for subsequent cavitation degree classification, effectively avoiding subjective errors and greatly improving the standardization and accuracy of monitoring and evaluation.

[0057] S5: Real-time measurement parameters of the turbine are collected through a turbine cavitation monitoring device that integrates multi-source signals.

[0058] The real-time measurement parameters specifically include: the turbine's real-time temperature T, the real-time cavitation heat zone area ratio R, the real-time vibration threshold A, the real-time swing threshold B, the real-time pressure pulsation threshold P, the real-time noise threshold N, and the real-time erosion depth H.

[0059] In this embodiment of the invention, relying on a multi-source signal fusion monitoring device, real-time parameters such as temperature, vibration, and sway are collected simultaneously, covering cavitation-related thermodynamic and mechanical response characteristics. The data is comprehensive and timely, providing accurate and complete raw data support for subsequent multi-source signal fusion analysis, cavitation degree classification, and intelligent prediction, effectively avoiding the limitations of single parameter collection.

[0060] S6: By comparing the real-time measurement parameters and the quantization threshold of the multi-source signals, the cavitation degree of the turbine is obtained.

[0061] The evaluation of cavitation level specifically includes: The real-time cavitation hot zone area ratio R, real-time vibration threshold A, real-time swing threshold B, real-time pressure pulsation threshold P, and real-time noise threshold N are defined as the remaining parameters.

[0062] The threshold values ​​for cavitation hot zone area ratio, vibration threshold, swing threshold, pressure pulsation threshold, and noise threshold are defined as the threshold values ​​for the remaining parameters.

[0063] When the real-time temperature T of the turbine is less than the temperature threshold, the real-time erosion depth H is equal to 0, and the other parameters do not exceed the threshold of the other parameters, the degree of cavitation is non-cavitation.

[0064] When the real-time temperature T of the turbine is greater than the temperature threshold, the real-time erosion depth H is equal to 0, and the other parameters do not exceed the threshold of the other parameters, the degree of cavitation is primary cavitation.

[0065] When the real-time temperature T of the turbine is greater than the temperature threshold, the real-time erosion depth H is equal to 0, and one of the other parameters exceeds the corresponding value of the other parameter threshold, the cavitation degree is local cavitation.

[0066] When the real-time temperature T of the turbine is greater than the temperature threshold, the real-time erosion depth H is equal to 0, and two of the other parameters exceed the corresponding items in the other parameter thresholds, the cavitation degree is medium cavitation.

[0067] When the real-time temperature T of the turbine is greater than the temperature threshold and the real-time erosion depth H is equal to 1, or when the real-time temperature T of the turbine is greater than the temperature threshold and three or more of the other parameters exceed the corresponding items of the other parameter thresholds, the cavitation degree is severe cavitation.

[0068] Specifically, because cavitation is accompanied by high temperature and high pressure, it occurs only when the real-time temperature exceeds a temperature threshold. The more severe the cavitation, the greater the unstable energy generated, which will affect other parameters.

[0069] In this embodiment of the invention, the essential characteristic of cavitation accompanied by high temperature is taken as the core premise for judgment. By comparing real-time parameters with multi-source quantification thresholds, and combining the erosion depth state and the number of other parameters exceeding the threshold, the degree of cavitation is judged in a graded manner. The logic is rigorous, the grading is comprehensive and in line with the development law of cavitation. It not only avoids misjudgment by a single indicator, but also accurately quantifies the severity of cavitation at different stages, providing a clear and reliable basis for targeted operation and maintenance of the unit.

[0070] Furthermore, the cavitation region is located using thermistors evenly distributed on the blades.

[0071] In one possible implementation, after S6, the following is also included: S7: Compare and verify the hot spot fluctuation frequency with the frequencies of noise, pressure pulsation, vibration, and sway.

[0072] It should be noted that by comparing the frequency of hot spot fluctuations, which are directly related to cavitation collapse, with the frequencies of noise, pressure pulsation, vibration, and sway signals, cross-validation of multi-source features is achieved. This effectively eliminates irrelevant interference such as water flow turbulence, verifies the validity of cavitation determination results, and significantly improves the accuracy and reliability of cavitation identification and level evaluation.

[0073] S8: Conduct turbine operation tests under different operating conditions, determine cavitation characteristics based on the collected test data, and establish a cavitation characteristic database.

[0074] It should be noted that by conducting turbine operation tests covering different operating conditions, comprehensive cavitation-related data under real operating scenarios were collected. Cavitation features were systematically extracted and a database was established, providing rich and realistic training samples for deep learning algorithms. This laid a solid foundation for real-time determination and prediction of cavitation status, and significantly improved the accuracy, versatility, and applicability of subsequent intelligent evaluation.

[0075] S9: Through deep learning algorithms, the unit parameters in the cavitation feature database are mapped and associated with the cavitation features under the corresponding operating conditions, so as to determine and predict the degree of cavitation in the turbine operation process in real time.

[0076] Specifically, the unit parameters include: load, head, and guide vane opening.

[0077] It should be noted that by using deep learning algorithms, the unit parameters in the cavitation feature database are deeply mapped and associated with the corresponding cavitation features. This not only enables real-time and accurate determination of the cavitation level, but also allows for early prediction of its development trend. This overcomes the limitations of traditional monitoring due to its lag, significantly improves the level of intelligence in monitoring, and provides strong support for timely operation and maintenance of the unit and avoidance of fault risks.

[0078] In this embodiment of the invention, irrelevant interference is eliminated by frequency comparison verification and the validity of the judgment results is verified. Based on the cavitation feature database constructed from multi-condition test data, a deep learning algorithm is used to achieve a deep mapping between unit parameters and cavitation features. This not only breaks through the limitations of the lag in traditional monitoring, but also solves the problem of the one-sidedness of single signal evaluation. It greatly improves the accuracy of cavitation identification, the level of intelligence in evaluation, and the foresight of trend prediction, providing scientific and timely support for turbine operation and maintenance decisions.

[0079] The cavitation evaluation method provided in this application can be implemented by a multi-source signal fusion turbine cavitation monitoring device. This application uses the example of a multi-source signal fusion turbine cavitation monitoring device implementing the cavitation evaluation method to illustrate the multi-source signal fusion turbine cavitation monitoring device provided in this application.

[0080] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0081] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0082] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0083] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0084] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0085] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0086] If the aforementioned functions are implemented as 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 this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0087] This invention provides a readable storage medium comprising: storing a program or instructions on the readable storage medium, wherein when the program or instructions are executed by a processor, the program or instructions implement the steps of the above-described cavitation evaluation method and achieve the same technical effect. To avoid repetition, this invention will not elaborate further.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the protection scope of the present invention.

Claims

1. A multi-source signal fusion device for monitoring cavitation in a hydro turbine, characterized in that, include: Thermistor sensors, noise sensors, pressure pulsation sensors, vibration sensors, sway sensors, and signal processing terminals; The thermistor sensor, the noise sensor, the pressure pulsation sensor, the vibration sensor, and the sway sensor are all connected to the signal processing terminal; The thermistor sensor is used to transmit the captured transient temperature field signal of the blade to the signal processing terminal; The noise sensor is used to collect cavitation noise signals and transmit the cavitation noise signals to the signal processing terminal; The pressure pulsation sensor is used to collect pressure fluctuation signals in the tailwater pipe and transmit the pressure fluctuation signals in the tailwater pipe to the signal processing terminal. The vibration sensor is used to collect the unit vibration and connect the unit vibration to the signal processing terminal; The spindle oscillation sensor is used to collect spindle oscillation signals and connect the spindle oscillation signals to the signal processing terminal; The signal processing terminal receives multi-channel synchronous signals through an integrated data acquisition card and performs signal fusion, feature analysis, and cavitation level determination through an embedded processor.

2. The multi-source signal fusion turbine cavitation monitoring device according to claim 1, characterized in that, The thermistor sensor specifically includes multiple thermistor sensors.

3. A cavitation evaluation method, characterized in that, The method applied to the multi-source signal fusion turbine cavitation monitoring device according to any one of claims 1 to 2 includes: S1: Obtain the temperature of each area of ​​the water turbine; S2: Using the thermistor sensor, identify the areas of the turbine where the temperature is higher than a preset temperature, i.e., the cavitation heat zone. S3: Calculate the ratio of the area of ​​the cavitation heat zone to the area of ​​the water turbine, and determine the cavitation heat zone area ratio; S4: Determine the quantization threshold of the multi-source signal, wherein the quantization threshold of the multi-source signal specifically includes: temperature threshold, cavitation hot zone area ratio threshold, abrasion depth threshold, vibration threshold, sway threshold, pressure pulsation threshold, and noise threshold; S5: The turbine cavitation monitoring device, which integrates multi-source signals, collects real-time measurement parameters of the turbine. S6: Compare the real-time measurement parameters with the multi-source signal quantization threshold to obtain the cavitation degree of the turbine.

4. The cavitation evaluation method according to claim 3, characterized in that, Following S2, it also includes: By using the thermistor sensor and combining the characteristics of cavitation bubble collapse, the hot spot fluctuation frequency associated with the collapse frequency is extracted.

5. The cavitation evaluation method according to claim 3, characterized in that, The formula for calculating the cavitation heat zone area ratio is: in, R Indicates the cavitation heat zone area ratio. S Indicates the area of ​​the cavitation heat zone. S 0 represents the area of ​​the water turbine.

6. The cavitation evaluation method according to claim 3, characterized in that, The method for determining the abrasion depth threshold is as follows: when the thermal sensor is normal, the switch signal is 0; when the thermal sensor fails, the switch signal is 1.

7. The cavitation evaluation method according to claim 3, characterized in that, The real-time measurement parameters specifically include: real-time turbine temperature T, real-time cavitation heat zone area ratio R, real-time vibration threshold A, real-time sway threshold B, real-time pressure pulsation threshold P, real-time noise threshold N, and real-time abrasion depth H.

8. The cavitation evaluation method according to claim 7, characterized in that, The cavitation degree evaluation specifically includes: The real-time cavitation heat zone area ratio R, the real-time vibration threshold A, the real-time swing threshold B, the real-time pressure pulsation threshold P, and the real-time noise threshold N are defined as the remaining parameters; The cavitation hot zone area ratio threshold, the vibration threshold, the swing threshold, the pressure pulsation threshold, and the noise threshold are defined as the thresholds for the remaining parameters; When the real-time temperature T of the turbine is less than the temperature threshold, the real-time erosion depth H is equal to 0, and the other parameters do not exceed the threshold of the other parameters, the degree of cavitation is no cavitation. When the real-time temperature T of the turbine is greater than the temperature threshold, the real-time erosion depth H is equal to 0, and the other parameters do not exceed the threshold of the other parameters, the degree of cavitation is primary cavitation; When the real-time temperature T of the turbine is greater than the temperature threshold, the real-time erosion depth H is equal to 0, and one of the remaining parameters exceeds the corresponding item in the threshold of the remaining parameters, the degree of cavitation is local cavitation. When the real-time temperature T of the turbine is greater than the temperature threshold, the real-time erosion depth H is equal to 0, and two of the remaining parameters exceed the corresponding items in the remaining parameter threshold, the cavitation degree is medium cavitation. When the real-time temperature T of the turbine is greater than the temperature threshold and the real-time erosion depth H is equal to 1, or when the real-time temperature T of the turbine is greater than the temperature threshold and three or more of the other parameters exceed the corresponding items of the other parameter thresholds, the cavitation degree is severe cavitation.

9. The cavitation evaluation method according to claim 3, characterized in that, Following S6, it also includes: S7: Verify the hot spot fluctuation frequency by comparing it with the frequencies of noise, pressure pulsation, vibration, and sway. S8: Conduct turbine operation tests under different operating conditions, determine cavitation characteristics based on the collected test data, and establish a cavitation characteristic database; S9: Using a deep learning algorithm, the unit parameters in the cavitation feature database are mapped and associated with the cavitation features under the corresponding operating conditions, and the degree of cavitation during the operation of the turbine is determined and predicted in real time.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the cavitation evaluation method as described in any one of claims 3 to 9.

Images