Hydropower station unit safety early warning method and related equipment

Abstract

The invention relates to the technical field of hydropower station detection and early warning, in particular to a hydropower station unit safety early warning method and related equipment, and the method comprises the steps: collecting vibration data in real time, analyzing the vibration state of a unit, timely finding the abnormality of the vibration state of the unit, and carrying out early warning. Based on the vibration data of normal operation and the fault historical data, the vibration characteristic model is constructed, the vibration threshold value is scientifically set, the accuracy and practicability of the early warning system are improved, and the health state of the unit can be comprehensively evaluated by defining the comprehensive fault severity index and combining multiple vibration characteristic parameters.

Description

Technical Field

[0001] The present application relates to the technical field of monitoring and early warning of hydropower stations, and in particular to a safety early warning method for hydropower station units and related equipment. Background Art

[0002] The hydropower station unit is the core equipment of hydroelectric power generation. During the operation of the hydropower station unit, the main shaft and coupling in the turbine are key components for transmitting torque and rotational motion. Their operating status is crucial to the performance and safety of the entire unit. However, due to long-term operation in a high-speed, high-load environment, the main shaft and coupling are prone to wear, misalignment, cracks and other faults, which are often accompanied by increased vibration. Traditional monitoring methods mainly rely on regular shutdown inspections, which is not only time-consuming and labor-intensive, but also unable to monitor the operating status of the unit in real time, which can easily lead to missed detection of faults or delayed processing, thus affecting the normal operation and safety of the unit.

[0003] Therefore, it is necessary to develop a safety warning method that can monitor the vibration status in real time, so as to issue a warning in time when the vibration is abnormal, and provide a basis for the maintenance and troubleshooting of the unit. Summary of the invention

[0004] In order to monitor the vibration status in real time and issue a warning in time when the vibration is abnormal, the present application provides a safety warning method and related equipment for a hydropower station unit.

[0005] In the first aspect, the present application provides a safety early warning method for a hydropower station unit, which adopts the following technical solution: A safety early warning method for a hydropower station unit, comprising obtaining first vibration data collected by the unit in real time; Transmitting the first vibration data to a data processing center for data processing and analysis, and outputting analysis results; Acquiring a vibration threshold, and determining a vibration state of the unit based on the vibration threshold and the analysis result; Outputting the vibration status report; If the vibration state is detected to be abnormal, an alarm signal is issued through the early warning system and fault diagnosis information is provided; Implement corresponding maintenance measures based on the fault diagnosis information.

[0006] Furthermore, a safety early warning method for a hydropower station unit, in acquiring first vibration data collected in real time, includes: Based on the structure and vibration characteristics of the unit, determine the appropriate monitoring points to install vibration sensors; Continuously collecting vibration signals according to a preset sampling frequency according to the vibration sensor; Preliminarily screening the collected second vibration data by using a preset data quality standard to obtain valid vibration data; The valid vibration data is preprocessed to obtain the first vibration data.

[0007] Furthermore, a safety early warning method for a hydropower station unit, in obtaining a vibration threshold, includes: Analyze the third vibration data of the normal operation of the unit and identify the key vibration characteristic parameters that characterize the normal working state of the unit; Based on the unit's fault history data and simulated fault test results, determine the vibration characteristic parameter change patterns corresponding to different fault types; According to the vibration characteristic parameter variation pattern, determining the relationship between the key vibration characteristic parameter and the fault severity, and constructing a vibration characteristic model; The vibration threshold is set based on the vibration characteristic model.

[0008] Furthermore, a safety early warning method for a hydropower station unit, in determining the relationship between key vibration characteristic parameters and fault severity, comprises the following steps: S1. Define a comprehensive fault severity index S, which is a combination of multiple key vibration characteristic parameters and their respective fault severity relationships, and can be expressed as: S=ω1*F1+ω2*F2+ω3*F3+…+ωn*Fn, where S is the comprehensive fault severity index, ω1, ω2, ω3, …, ωn are weight coefficients of each characteristic parameter, and F1, F2, F3, …, Fn are fault severity values ​​corresponding to each characteristic parameter; S2. For the amplitude characteristic parameter A, the relationship between it and the fault severity F1 can be expressed as: F1=k1*(A-A0)+F01, where A is the amplitude value monitored in real time, A0 is the amplitude reference value under normal conditions, k1 is the proportional coefficient between the amplitude change and the fault severity, and F01 is the initial value of the fault severity; S3. For the frequency characteristic parameter f, the relationship between it and the fault severity F2 can be expressed as: F2=α1*(f-f0)^2+F02, where f is the frequency value monitored in real time, f0 is the frequency reference value under normal conditions, α1 is the coefficient between the frequency change and the fault severity, and F02 is the initial value of the fault severity; S4. For the phase characteristic parameter φ, the relationship between it and the fault severity F3 can be expressed as: F3=β1*|Δφ|+F03, where Δφ is the phase change value monitored in real time, β1 is the coefficient between the phase change and the fault severity, and F03 is the initial value of the fault severity; S5. Determine each weight coefficient ω1, ω2, ω3, …, ωn through statistical analysis and machine learning algorithm to reflect the relative importance of different vibration characteristic parameters in the comprehensive fault severity index; S6. Based on the comprehensive fault severity index S and the preset threshold, determine whether the vibration state of the unit is abnormal, so as to achieve accurate early warning of the unit.

[0009] Furthermore, a safety early warning method for a hydropower station unit, in constructing a vibration characteristic model, includes: Through the random forest algorithm, multiple decision trees are constructed to make predictions. Each decision tree consists of randomly selected features and sample points. Collecting the third vibration data into a data set and dividing it into a training set and a test set; Using a random forest algorithm to train the third vibration data in the training set to construct the vibration feature model; Using the vibration characteristic model to predict the third vibration data in the test set, and obtaining a prediction result; Based on the prediction results, the parameters of the vibration characteristic model are adjusted.

[0010] Furthermore, a safety early warning method for a hydropower station unit, in determining the vibration state of the unit, includes: Performing time domain analysis on the first vibration data to extract corresponding amplitude, frequency and phase; Performing frequency domain analysis on the first vibration data to identify harmonic components and frequency distribution in the operation of the unit; Using data processing technology, transform the vibration signal in the first vibration data to obtain a frequency spectrum; Performing spectrum analysis on the spectrum graph to extract corresponding frequency peaks and frequency ranges; Comparing the vibration threshold, determining whether the vibration signal exceeds a normal range; Combining the time domain analysis and frequency domain analysis results, determining the vibration state of the unit; If the vibration status is abnormal, output a vibration status report.

[0011] Furthermore, a safety early warning method for a hydropower station unit, after issuing an alarm signal through an early warning system, further comprises: Transmitting the vibration status report and fault diagnosis information to a remote monitoring center in real time via the Internet; Encryption technology is used to ensure the security of data transmission and prevent data from being illegally obtained or tampered with.

[0012] In a second aspect, the present application provides a safety early warning device for a hydropower station unit, comprising: A first vibration data acquisition module is used to acquire first vibration data collected by the unit in real time; An analysis result output module, used for transmitting the first vibration data to a data processing center for data processing and analysis, and outputting analysis results; A vibration state determination module, used for obtaining a vibration threshold, and determining the vibration state of the unit based on the vibration threshold and the analysis result; An output vibration status report module, used for outputting the vibration status report; An alarm module is used to send out an alarm signal through the early warning system and provide fault diagnosis information if the vibration state is detected to be abnormal; The maintenance implementation module is used to implement corresponding maintenance measures according to the fault diagnosis information.

[0013] In a third aspect, the present disclosure provides a computer device including a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of a hydropower station unit safety warning method in any of the above-mentioned embodiments when executing the computer program.

[0014] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a hydropower station unit safety warning method in any of the above-mentioned embodiments.

[0015] The above-mentioned safety early warning method for hydropower station units can timely detect abnormal vibration status of the unit and issue early warnings by collecting vibration data in real time and analyzing the vibration status of the unit. Based on the vibration data of normal operation and the fault history data, a vibration characteristic model is constructed, and the vibration threshold is scientifically set, which improves the accuracy and practicality of the early warning system. In addition, by defining a comprehensive fault severity index and combining multiple vibration characteristic parameters, the health status of the unit can be comprehensively evaluated. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The first flow chart of a safety early warning method for a hydropower station unit in an embodiment.

[0017] Figure 2 The second flow chart of a safety early warning method for a hydropower station unit in an embodiment.

[0018] Figure 3 The figure is a schematic structural diagram of a safety early warning device for a hydropower station unit in one embodiment.

[0019] Figure 4 Schematic diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0020] The following is combined with Figure 1—4 Further detailed description of the present application. In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0022] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0023] Embodiment 1 Please refer to Figure 1 In one embodiment of the present application, a hydropower station unit safety early warning method includes steps S110 to S160.

[0024] Step S110: Acquire the first vibration data collected by the unit in real time.

[0025] The first vibration data refers to data that has been pre-processed.

[0026] The function of step S110 is that the method monitors the vibration state of the hydropower station unit in real time, and provides basic data support for subsequent safety warning analysis by obtaining the first vibration data during the operation of the unit.

[0027] Step S120: transmitting the first vibration data to a data processing center for data processing and analysis, and outputting the analysis result.

[0028] The data processing refers to performing in-depth processing and analysis on the first vibration data.

[0029] Specifically, deep processing refers to identifying and classifying the first vibration data, and assigning different data in the input first vibration data to predefined categories, which then provides convenience for extracting features from different data.

[0030] The purpose of step S120 is that the method effectively improves the accuracy and usability of the data by deeply processing the first vibration data.

[0031] Step S130: Obtain a vibration threshold, and determine the vibration state of the unit based on the vibration threshold and the analysis result.

[0032] Specifically, set the vibration threshold, conduct a quantitative assessment of the vibration level of the unit, monitor the vibration data of the unit in real time, compare it with the preset vibration threshold, and determine whether the unit is operating within the safe range. For example, monitor the vibration of a turbine generator in a hydropower station. The radial vibration threshold of the turbine generator bearing is set to the normal operating range: 50µm, warning range: 100µm, and alarm range: 150µm. The axial vibration threshold of the bearing is set to: normal operating range: 30µm, warning range: 60µm, and alarm range: 90µm. If the vibration data monitored is the radial vibration of the bearing: 80µm, and the axial vibration of the bearing: 45µm. The radial vibration of the bearing is 80µm, which exceeds the normal operating range (50µm) but does not reach the warning range (100µm). This indicates that the vibration level is already high and needs attention. It is estimated whether the next section of vibration data is abnormal. No alarm is taken for the time being. The axial vibration of the bearing is 45µm, which is within the normal operating range (30µm), indicating that the axial vibration is at a normal level.

[0033] The function of step S130 is that the method can effectively evaluate the vibration state of the unit by obtaining the vibration threshold and combining it with the analysis result.

[0034] Step S140: Output a vibration status report.

[0035] The purpose of step S140 is that the method provides detailed records and basis for the management and maintenance of the unit by generating a vibration status report.

[0036] Step S150: If the vibration state is detected to be abnormal, an alarm signal is issued through the early warning system and fault diagnosis information is provided.

[0037] Specifically, when the vibration state is detected to be abnormal, the early warning system immediately sends out an alarm signal, and determines the current fault problem and fault location based on the abnormal vibration state and filter. For example, a turbine generator set in a hydropower station has abnormal vibration during operation, and the early warning system sends out an alarm and provides the following fault diagnosis information: Assume that the hydropower station unit has abnormal vibration during operation. Through the vibration sensor installed on the unit, we collected the following digital vibration data: Vibration data of hydropower station unit: Peak-to-peak value of vibration displacement (μm): Normal operation: 50-100, abnormal operation: 150-200. Effective value of vibration velocity (mm / s): Normal operation: 2.0-3.5, abnormal operation: 5.0-7.0. Vibration acceleration (m / s²): Normal operation: 0.05-0.15, abnormal operation: 0.25-0.35. Vibration frequency analysis (Hz): Rotor frequency (1 times): 50 (assuming the unit speed is 3000rpm), Blade passing frequency (BPF): 150 (assuming the number of blades is 6 and the speed is 3000rpm), Hydraulic excitation frequency: 100 (may be caused by water flow instability). Bearing temperature (°C): Normal operation: 30-40, abnormal operation: 50-60.

[0038] The fault diagnosis analysis is: Vibration displacement peak to peak: An increase in displacement may indicate looseness or misalignment in the unit structure.

[0039] Vibration velocity rms value: An increase in the velocity rms value indicates that the unit may have mechanical imbalance or bearing failure.

[0040] Vibration acceleration: Increased acceleration is often associated with higher vibration frequencies and may indicate the presence of a shock or high-frequency vibration source.

[0041] Vibration frequency analysis: Increased vibration at 1 times the rotor frequency may indicate rotor imbalance.

[0042] Increased vibration at the blade passing frequency (BPF) may indicate a blade-flow interaction problem, such as blade damage or flow instability.

[0043] An increase in vibration at the hydraulic excitation frequency may indicate a hydraulic excitation phenomenon.

[0044] Bearing temperature: Increased bearing temperature may indicate poor bearing lubrication or excessive bearing wear.

[0045] Based on the above vibration data, it can be inferred that the unit has loose structure and misalignment, which leads to increased vibration displacement; rotor imbalance or bearing failure leads to increased effective value of vibration velocity; high-frequency vibration sources, such as hydraulic excitation or blade damage, lead to increased vibration acceleration.

[0046] The purpose of step S150 is that the method can perform more accurate fault diagnosis through vibration data, thereby reducing the potential risk of equipment damage.

[0047] Step S160: Implement corresponding maintenance measures according to the fault diagnosis information.

[0048] The purpose of step S160 is that the method uses fault diagnosis information to promptly maintain problems existing in the unit to ensure the reliability and safety of the equipment.

[0049] In one embodiment, if Figure 2 As shown, in step S110, that is, in acquiring the first vibration data collected in real time, the following steps are included: Step S210: Based on the structure and vibration characteristics of the unit, determine appropriate monitoring points to install vibration sensors.

[0050] Step S220: continuously collecting vibration signals according to a preset sampling frequency using the vibration sensor.

[0051] Step S230: Preliminary screening of the collected second vibration data is performed using a preset data quality standard to obtain valid vibration data.

[0052] Step S240: pre-processing the effective vibration data to obtain first vibration data.

[0053] Specifically, after the vibration sensor is installed, vibration data is continuously collected at a fixed frequency to obtain the second vibration data, and the noise and invalid data generated by other factors are eliminated to obtain the effective vibration data. The effective vibration data is filtered and denoised, mainly by low-pass filtering, high-pass filtering and band-pass filtering. When the wear of the turbine bearing causes the vibration to increase, the vibration is a low-frequency vibration. The low-frequency vibration signal is retained by a low-pass filter. By analyzing the changes in the low-frequency vibration signal, the health of the bearing can be monitored. When the rotor starts or stops, the rotor may produce rapid vibration changes. A high-pass filter is used to remove the low-frequency background vibration, and all vibration signals higher than the low frequency are retained for analyzing the transient vibration when the rotor starts or stops. The first vibration data is obtained after filtering and denoising, which improves the availability of the data.

[0054] The purpose of steps S210 to S240 is to obtain a useful and clean data source for subsequent data analysis through continuous sampling, preliminary screening and preprocessing steps.

[0055] In one embodiment, if Figure 2 As shown, in step S130, that is, in obtaining the vibration threshold, the following steps are included: Step S310: Analyze the third vibration data of the normal operation of the unit to identify key vibration characteristic parameters that characterize the normal operation state of the unit.

[0056] Step S320: Based on the fault history data of the unit and the simulated fault test results, determine the vibration characteristic parameter change patterns corresponding to different fault types.

[0057] Step S330: Determine the relationship between the key vibration characteristic parameters and the fault severity according to the vibration characteristic parameter variation pattern, and construct a vibration characteristic model.

[0058] Step S340: Setting a vibration threshold based on the vibration characteristic model.

[0059] Among them, the key vibration characteristic parameters include kurtosis, waveform index, pulse index, peak factor, margin factor and frequency domain characteristics.

[0060] Specifically, the third vibration data of the normal operation of the unit is analyzed, and the key vibration characteristic parameters are identified to provide a normal data standard for the operation of the unit. The key vibration characteristic data, such as kurtosis, waveform index, pulse index, peak factor, margin factor and frequency domain characteristics, correspond to different captured data respectively. Kurtosis mainly measures the peak degree of the vibration signal and mainly reflects the impact characteristics of the signal. The waveform index mainly describes the shape of the vibration signal and mainly distinguishes different fault types. The pulse index is used to reflect the impact component in the signal and is related to the fault of components such as bearings. The peak factor is the ratio of the signal peak value to the root mean square value, which is used to detect the peak abnormality of the signal. For example, when the hydroelectric generator is operating normally, the third vibration data is collected. By analyzing the third vibration data, the key vibration characteristic parameters are identified as peak value, root mean square value and frequency component. Under normal circumstances, the peak value of the vibration signal is less than 5mm / s, the RMS value is about 2mm / s, and the dominant frequency is 20Hz. By analyzing historical fault data and simulated fault tests, we found the following fault types and their corresponding vibration characteristic parameter change patterns: Bearing wear: causes the peak value to increase, the RMS value to increase, and high-frequency components to appear (such as new frequency components near 1000Hz).

[0061] Belt slack: causes a slight increase in the RMS value and a decrease in the amplitude of the dominant frequency.

[0062] Based on the above change pattern, we constructed a model that describes the relationship between key vibration characteristic parameters (peak value, RMS, frequency content) and fault severity. For example: If the peak exceeds 10mm / s, it may be an early sign of bearing wear.

[0063] If the RMS value exceeds 4mm / s and the dominant frequency amplitude decreases, the drive belt may be loose. Based on the vibration characteristic model, we set the following vibration thresholds: Peak threshold: 7mm / s (between normal and early failure), RMS threshold: 3mm / s (also between normal and incipient failure).

[0064] If the peak value is found to reach 8mm / s, the RMS threshold is 2.5mm / s, and the dominant frequency remains at 20Hz in the monitoring data, then the vibration characteristic model indicates early signs of bearing wear and it is necessary to pay attention to and confirm the status of the bearing.

[0065] The purpose of steps S310 to S340 is that the method improves the safety and reliability of unit operation by constructing a relationship model between key vibration characteristic parameters and fault severity.

[0066] In one embodiment, in step S330, i.e., in determining the relationship between the key vibration characteristic parameter and the fault severity, the following steps are included: Step S410: define a comprehensive fault severity index S, where the severity index is a combination of multiple key vibration characteristic parameters and their respective fault severity relationships, and can be expressed as: S=ω1*F1+ω2*F2+ω3*F3+…+ωn*Fn, wherein S is the comprehensive fault severity index, ω1, ω2, ω3,…, ωn are weight coefficients of each characteristic parameter, and F1, F2, F3,…, Fn are the fault severity values ​​corresponding to each characteristic parameter.

[0067] Step S420: For the amplitude characteristic parameter A, the relationship between it and the fault severity F1 can be expressed as: F1=k1*(A-A0)+F01, where A is the amplitude value monitored in real time, A0 is the amplitude reference value under normal conditions, k1 is the proportional coefficient between the amplitude change and the fault severity, and F01 is the initial value of the fault severity.

[0068] Step S430: For the frequency characteristic parameter f, the relationship between it and the fault severity F2 can be expressed as: F2=α1*(f-f0)^2+F02, where f is the frequency value monitored in real time, f0 is the frequency reference value under normal conditions, α1 is the coefficient between the frequency change and the fault severity, and F02 is the initial value of the fault severity.

[0069] Step S440: For the phase characteristic parameter φ, the relationship between it and the fault severity F3 can be expressed as: F3=β1*|Δφ|+F03, where Δφ is the phase change value monitored in real time, β1 is the coefficient between the phase change and the fault severity, and F03 is the initial value of the fault severity.

[0070] Step S450: Determine the weight coefficients ω1, ω2, ω3, ..., ωn through statistical analysis and machine learning algorithms to reflect the relative importance of different vibration characteristic parameters in the comprehensive fault severity index.

[0071] Step S460: Based on the comprehensive fault severity index S and a preset threshold, determine whether the vibration state of the unit is abnormal, thereby achieving accurate early warning of the unit.

[0072] Specifically, a comprehensive indicator is created to integrate the influence of multiple key vibration characteristic parameters into a single value. The impact of amplitude changes, frequency changes, and phase changes on the severity of faults can be quantified. Weights are then assigned to different vibration characteristic parameters through statistical analysis and machine learning algorithms. The comprehensive fault severity index S is compared with the preset threshold to comprehensively judge the abnormal vibration state of the unit.

[0073] The purpose of steps S410 to S460 is that the method accurately quantifies the relationship between characteristic vibration parameters and fault severity through a mathematical model, thereby achieving accurate early warning of the unit.

[0074] In one embodiment, in step S330, i.e., in constructing the vibration characteristic model, the following steps are included: Step S510: Using the random forest algorithm, multiple decision trees are constructed to perform predictions, each of which is composed of randomly selected features and sample points.

[0075] Step S520: collect the third vibration data into a data set, and divide it into a training set and a test set.

[0076] Step S530: using a random forest algorithm to train the third vibration data in the training set to construct a vibration feature model.

[0077] Step S540: predicting the third vibration data in the test set using the vibration characteristic model to obtain a prediction result.

[0078] Step S550: adjusting the parameters of the vibration characteristic model based on the prediction result.

[0079] Among them, the random forest algorithm is an ensemble learning algorithm based on decision trees, which improves the overall prediction performance by combining the prediction results of multiple decision tree models.

[0080] Specifically, the collected third vibration data set is first divided into two parts, one for training the vibration feature model and the other for verifying the performance of the vibration feature model. In the training set, the random forest algorithm can randomly select features and data, reducing the risk of overfitting. After building a model for identifying vibration data features, the test set predicts the trained vibration feature model, and the accuracy of the vibration feature model is evaluated by comparing the prediction results with the actual data. Based on the prediction results of the test set, the vibration feature model is tuned.

[0081] The purpose of steps S510 to S550 is that this method combines the powerful prediction ability of the random forest algorithm with data-driven model optimization to improve the accuracy of the prediction and enhance the robustness of the model.

[0082] In one embodiment, in step S130, i.e., in determining the vibration state of the unit, the following steps are included: Step S610: Perform time domain analysis on the first vibration data to extract the corresponding amplitude, frequency and phase.

[0083] Step S620: Perform frequency domain analysis on the first vibration data to identify harmonic components and frequency distribution during unit operation.

[0084] Step S630: using data processing technology to transform the vibration signal in the first vibration data to obtain a frequency spectrum.

[0085] Step S640: Perform spectrum analysis on the spectrum graph to extract the corresponding frequency peak and frequency range.

[0086] Step S650: Compare the vibration threshold to determine whether the vibration signal exceeds the normal range.

[0087] Step S660: Determine the vibration state of the unit by combining the time domain analysis and frequency domain analysis results.

[0088] Step S670: If the vibration state is abnormal, output a vibration state report.

[0089] Specifically, effective features are extracted from the first vibration data through time domain analysis and frequency domain analysis, and then the vibration data is quickly transformed using data processing technology to obtain an intuitive spectrum diagram. The frequency peak and frequency range are extracted from the spectrum diagram and compared with the preset vibration threshold. The results of the time domain and frequency domain analysis are combined to determine the vibration state of the generator and generate a vibration state report.

[0090] The purpose of steps S610 to S670 is that the method determines the vibration state of the unit through a comprehensive analysis of the vibration data.

[0091] In one embodiment, in step S150, that is, in sending an alarm signal through the early warning system, the following steps are included: Step S710: Transmitting the vibration status report and fault diagnosis information to a remote monitoring center in real time via the Internet.

[0092] Step S720: Encryption technology is used to ensure data transmission security and prevent data from being illegally obtained or tampered with.

[0093] Specifically, real-time transmission of vibration status reports and fault diagnosis information is achieved through the Internet, so that the remote monitoring center can obtain the operating status of the equipment in a timely manner and respond quickly. Encryption technology is used to ensure the security of information during data transmission and prevent sensitive data from being leaked or unauthorized access.

[0094] The purpose of step S710 and step S720 is that the method supports remote decision-making and improves the maintenance efficiency of the unit.

[0095] Embodiment 2 In this embodiment, a hydropower station unit safety warning device is provided, and a hydropower station unit safety warning device corresponds to a hydropower station unit safety warning method in the above embodiment. Figure 3 As shown, a safety early warning device for a hydropower station unit includes a first vibration data acquisition module 110, an analysis result output module 120, a vibration state determination module 130, a vibration state output report module 140, an alarm module 150 and a maintenance implementation module 160. The functional modules are described in detail as follows: The first vibration data acquisition module 110 is used to acquire first vibration data collected by the unit in real time.

[0096] The analysis result output module 120 is used to transmit the first vibration data to a data processing center for data processing and analysis, and output the analysis result.

[0097] The vibration state determination module 130 is used to obtain a vibration threshold, and determine the vibration state of the unit based on the vibration threshold and the analysis result.

[0098] The vibration status outputting module 140 is used to output a vibration status report.

[0099] The alarm module 150 is used to send out an alarm signal through the early warning system and provide fault diagnosis information if the detected vibration state is abnormal.

[0100] The maintenance implementation module 160 is used to implement corresponding maintenance measures according to the fault diagnosis information.

[0101] For the specific definition of a hydropower station unit safety warning device, please refer to the definition of a hydropower station unit safety warning method mentioned above, which will not be repeated here. Each module in the above-mentioned hydropower station unit safety warning device can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the device in the form of hardware, or can be stored in the memory in the device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0102] Embodiment 3 In this embodiment, a computer device is provided. Its internal structure diagram can be shown as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program, and the non-volatile storage medium is deployed with a database, which is used to store all data involved in a safety early warning method for a hydropower station unit. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with other computer devices that deploy application software. When the computer program is executed by the processor, a safety early warning method for a hydropower station unit is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0103] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0104] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a hydropower station unit safety early warning method described in any of the above embodiments when executing the computer program.

[0105] Embodiment 4 In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a hydropower station unit safety early warning method described in any of the above embodiments are implemented.

[0106] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0107] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A safety early warning method for a hydropower station unit, characterized in that: include: Acquire the first vibration data collected by the unit in real time; Transmitting the first vibration data to a data processing center for data processing and analysis, and outputting analysis results; Acquiring a vibration threshold, and determining a vibration state of the unit based on the vibration threshold and the analysis result; Outputting the vibration status report; If the vibration state is detected to be abnormal, an alarm signal is issued through the early warning system and fault diagnosis information is provided; Implement corresponding maintenance measures based on the fault diagnosis information.

2. A safety early warning method for a hydropower station unit according to claim 1, characterized in that: The step of acquiring the first vibration data collected in real time includes: Based on the structure and vibration characteristics of the unit, determine the appropriate monitoring points to install vibration sensors; Continuously collecting vibration signals according to a preset sampling frequency according to the vibration sensor; Preliminarily screening the collected second vibration data by using a preset data quality standard to obtain valid vibration data; The valid vibration data is preprocessed to obtain the first vibration data.

3. A safety early warning method for a hydropower station unit according to claim 1, characterized in that: The step of obtaining the vibration threshold includes: Analyze the third vibration data of the normal operation of the unit and identify the key vibration characteristic parameters that characterize the normal working state of the unit; Based on the unit's fault history data and simulated fault test results, determine the vibration characteristic parameter change patterns corresponding to different fault types; According to the vibration characteristic parameter variation pattern, determining the relationship between the key vibration characteristic parameter and the fault severity, and constructing a vibration characteristic model; The vibration threshold is set based on the vibration characteristic model.

4. A safety early warning method for a hydropower station unit according to claim 3, characterized in that: Determining the relationship between the key vibration characteristic parameter and the fault severity comprises the following steps: S1. Define a comprehensive fault severity index S, which is a combination of multiple key vibration characteristic parameters and their respective fault severity relationships, and can be expressed as: S=ω1*F1+ω2*F2+ω3*F3+…+ωn*Fn, where S is the comprehensive fault severity index, ω1, ω2, ω3, …, ωn are weight coefficients of each characteristic parameter, and F1, F2, F3, …, Fn are fault severity values ​​corresponding to each characteristic parameter; S2. For the amplitude characteristic parameter A, the relationship between it and the fault severity F1 can be expressed as: F1=k1*(A-A0)+F01, where A is the amplitude value monitored in real time, A0 is the amplitude reference value under normal conditions, k1 is the proportional coefficient between the amplitude change and the fault severity, and F01 is the initial value of the fault severity; S3. For the frequency characteristic parameter f, the relationship between it and the fault severity F2 can be expressed as: F2=α1*(f-f0)^2+F02, where f is the frequency value monitored in real time, f0 is the frequency reference value under normal conditions, α1 is the coefficient between the frequency change and the fault severity, and F02 is the initial value of the fault severity; S4. For the phase characteristic parameter φ, the relationship between it and the fault severity F3 can be expressed as: F3=β1*|Δφ|+F03, where Δφ is the phase change value monitored in real time, β1 is the coefficient between the phase change and the fault severity, and F03 is the initial value of the fault severity; S5. Determine each weight coefficient ω1, ω2, ω3, …, ωn through statistical analysis and machine learning algorithm to reflect the relative importance of different vibration characteristic parameters in the comprehensive fault severity index; S6. Based on the comprehensive fault severity index S and the preset threshold, determine whether the vibration state of the unit is abnormal, so as to achieve accurate early warning of the unit.

5. A safety early warning method for a hydropower station unit according to claim 3, characterized in that: The construction of the vibration characteristic model includes: Through the random forest algorithm, multiple decision trees are constructed to make predictions. Each decision tree consists of randomly selected features and sample points. Collecting the third vibration data into a data set and dividing the data set into a training set and a test set; Using a random forest algorithm to train the third vibration data in the training set to construct the vibration feature model; Using the vibration characteristic model to predict the third vibration data in the test set, and obtaining a prediction result; Based on the prediction results, the parameters of the vibration characteristic model are adjusted.

6. A safety early warning method for a hydropower station unit according to claim 1, characterized in that: Determining the vibration state of the unit includes: Performing time domain analysis on the first vibration data to extract corresponding amplitude, frequency and phase; Performing frequency domain analysis on the first vibration data to identify harmonic components and frequency distribution in the operation of the unit; Using data processing technology, transform the vibration signal in the first vibration data to obtain a frequency spectrum; Performing spectrum analysis on the spectrum graph to extract corresponding frequency peaks and frequency ranges; Comparing the vibration threshold, determining whether the vibration signal exceeds a normal range; Combining the time domain analysis and frequency domain analysis results, determining the vibration state of the unit; If the vibration status is abnormal, output a vibration status report.

7. A safety early warning method for a hydropower station unit according to claim 1, characterized in that: The sending of an alarm signal by the early warning system also includes: Transmitting the vibration status report and fault diagnosis information to a remote monitoring center in real time via the Internet; Encryption technology is used to ensure the security of data transmission and prevent data from being illegally obtained or tampered with.

8. A safety early warning device for a hydropower station unit, characterized in that: include: A first vibration data acquisition module is used to acquire first vibration data collected by the unit in real time; An analysis result output module, used for transmitting the first vibration data to a data processing center for data processing and analysis, and outputting analysis results; A vibration state determination module, used for obtaining a vibration threshold, and determining the vibration state of the unit based on the vibration threshold and the analysis result; An output vibration status report module, used for outputting the vibration status report; An alarm module is used to send out an alarm signal through the early warning system and provide fault diagnosis information if the vibration state is detected to be abnormal; The maintenance implementation module is used to implement corresponding maintenance measures according to the fault diagnosis information.

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 the method 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 the method according to any one of claims 1 to 7 are implemented.

Images