Intelligent quantitative evaluation method for low-frequency oscillation danger level of thermal power generating unit

Abstract

The invention discloses an intelligent quantitative evaluation method for the low-frequency oscillation danger level of a thermal power generating unit. The method comprises the following steps: S1, collecting low-frequency oscillation intelligent evaluation related data of the thermal power generating unit; s2, preprocessing the acquired low-frequency oscillation intelligent evaluation related data of the thermal power generating unit; s3, establishing a danger level quantification model; s4, inputting the preprocessed thermal power generating unit low-frequency oscillation intelligent evaluation related data into the sub-item indexes of the danger level quantitative model for calculation to obtain sub-item index values; s5, according to the influence degree of the subitem index values on the comprehensive danger value, different proportions are distributed and substituted into the danger degree quantification model, and the comprehensive danger value is obtained. According to the method, four factors including vibration intensity, time, equipment state and power grid influence are considered at the same time, and the one-sided problem that only the vibration amplitude is seen in a traditional method is solved; the calculation weight is automatically adjusted according to the monitoring equipment operation temperature, the equipment aging degree and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of power equipment safety monitoring, and in particular relates to an intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power unit. Background Art

[0002] During peak-shaving operation, thermal power plants may experience low-frequency oscillations in their speed control systems due to mechanical or grid issues. Traditional methods assess risk based solely on vibration amplitude, ignoring factors such as vibration duration and equipment aging. Consequently, persistent, small vibrations can be more dangerous than brief, large ones. Summary of the Invention

[0003] Aiming at the problem that existing low-frequency oscillation risk assessment methods for thermal power plants lack the assessment of vibration duration and equipment aging degree, the present invention provides an intelligent quantitative assessment method for the risk degree of low-frequency oscillation of thermal power plants.

[0004] In order to achieve the above technical objectives, the technical solutions adopted by the present invention are as follows:

[0005] An intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power unit comprises the following steps:

[0006] S1. Collect data related to intelligent evaluation of low-frequency oscillation of thermal power units;

[0007] S2. Preprocessing the collected data related to the intelligent evaluation of low-frequency oscillation of thermal power units;

[0008] S3. Establish a quantitative model for the degree of danger;

[0009] S4. Inputting the pre-processed data related to the intelligent assessment of low-frequency oscillation of thermal power units into the sub-index of the hazard degree quantification model for calculation to obtain the sub-index value;

[0010] S5. According to the degree of influence of the sub-item indicator values ​​on the comprehensive risk value, different proportions are allocated and brought into the risk degree quantification model to obtain the comprehensive risk value.

[0011] Furthermore, the relevant data for intelligent evaluation of low-frequency oscillation of thermal power units include vibration amplitude, vibration duration, equipment fatigue index and unit frequency fluctuation amplitude.

[0012] Furthermore, the vibration amplitude is measured by installing a laser vibrometer on the surface of the turbine rotor to measure the torsional amplitude;

[0013] The vibration duration is obtained by subtracting the initial vibration moment from the vibration stop moment;

[0014] The equipment fatigue index is calculated by monitoring the equipment's cumulative operating time and the bearing temperature collected by the temperature sensor;

[0015] The unit frequency fluctuation amplitude is recorded by the grid monitor at the unit's grid connection point.

[0016] Furthermore, preprocessing uses filtering technology to filter out noise signals and retain vibration signals.

[0017] Furthermore, sub-indicators include vibration intensity index, time accumulation index, equipment fatigue index and power grid impact index.

[0018] Furthermore, the vibration intensity index calculation formula is:

[0019]

[0020] VSI is the vibration severity index;

[0021] Time accumulation index calculation formula:

[0022]

[0023] TCI is the time cumulative index;

[0024] Equipment fatigue index calculation formula:

[0025] EFI = bearing temperature rise + 0.5 × cumulative rotor running hours

[0026] EFI is the equipment fatigue index;

[0027] Grid impact index calculation formula:

[0028]

[0029] GII is the grid impact index.

[0030] Furthermore, the comprehensive risk value calculation formula is:

[0031] Danger value = W1*VSI+W2*TCI+W3*EFI+W4*GII,

[0032] Among them, W1, W2, W3 and W4 are the weight coefficients of vibration intensity index, time accumulation index, equipment fatigue index and power grid impact index to the comprehensive risk value respectively.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] It simultaneously considers four major factors: vibration intensity, time, equipment status, and grid impact, solving the one-sided problem of traditional methods that only consider "vibration amplitude"; and automatically adjusts the calculation weight based on the operating temperature of the monitoring equipment, the degree of equipment aging, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The figure is an overall flow chart of an intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power unit according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to embodiments and drawings. The contents mentioned in the embodiments are not intended to limit the present invention.

[0037] like Figure 1 As shown, this embodiment provides an intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power unit, comprising the following steps:

[0038] S1. Collect data related to intelligent evaluation of low-frequency oscillation of thermal power units;

[0039] S2. Preprocessing the collected data related to the intelligent evaluation of low-frequency oscillation of thermal power units;

[0040] S3. Establish a quantitative model for the degree of danger;

[0041] S4. Inputting the pre-processed data related to the intelligent assessment of low-frequency oscillation of thermal power units into the sub-index of the hazard degree quantification model for calculation to obtain the sub-index value;

[0042] S5. According to the degree of influence of the sub-item indicator values ​​on the comprehensive risk value, different proportions are allocated and brought into the risk degree quantification model to obtain the comprehensive risk value.

[0043] The relevant data for intelligent evaluation of low-frequency oscillation of thermal power units include vibration amplitude, vibration duration, equipment fatigue index and unit frequency fluctuation amplitude.

[0044] Vibration amplitude: The torsional amplitude is measured by installing a laser vibrometer on the surface of the turbine rotor;

[0045] The vibration duration is obtained by subtracting the initial vibration moment from the vibration stop moment;

[0046] The equipment fatigue index is calculated by monitoring the equipment's cumulative operating time and the bearing temperature collected by the temperature sensor;

[0047] The unit frequency fluctuation amplitude is recorded by the grid monitor at the unit's grid connection point.

[0048] Preprocessing uses filtering technology to filter out noise signals and retain vibration signals.

[0049] Sub-indicators include vibration intensity index, time accumulation index, equipment fatigue index and power grid impact index.

[0050] Vibration intensity index calculation formula:

[0051]

[0052] VSI is the vibration severity index;

[0053] Time accumulation index calculation formula:

[0054]

[0055] TCI is the time cumulative index;

[0056] Equipment fatigue index calculation formula:

[0057] EFI = bearing temperature rise + 0.5 × cumulative rotor running hours

[0058] EFI is the equipment fatigue index;

[0059] Grid impact index calculation formula:

[0060]

[0061] GII is the grid impact index.

[0062] Comprehensive risk value calculation formula:

[0063] Danger value = W1*VSI+W2*TCI+W3*EFI+W4*GII,

[0064] Where W1, W2, W3, and W4 are the weight coefficients of the vibration intensity index, time accumulation index, equipment fatigue index, and power grid impact index to the comprehensive hazard value. The sum of W1, W2, W3, and W4 is 1.

[0065] Compared with the prior art, the present invention has the following beneficial effects:

[0066] It simultaneously considers four major factors: vibration intensity, time, equipment status, and grid impact, solving the one-sided problem of traditional methods that only consider "vibration amplitude"; and automatically adjusts the calculation weight based on the operating temperature of the monitoring equipment, the degree of equipment aging, etc.

[0067] The above describes in detail the intelligent quantitative assessment method for the risk level of low-frequency oscillations in thermal power plants provided by this application. The description of the specific embodiments is intended only to facilitate understanding of the method and its core concept. It should be noted that those skilled in the art may make various improvements and modifications to this application without departing from the principles of this application, and such improvements and modifications fall within the scope of protection of the claims of this application.

Claims

1. An intelligent quantitative assessment method for the risk level of low-frequency oscillation of thermal power units, characterized by: Including steps: S1. Collect data related to intelligent evaluation of low-frequency oscillation of thermal power units; S2. Preprocessing the collected data related to the intelligent evaluation of low-frequency oscillation of thermal power units; S3. Establish a quantitative model for the degree of danger; S4. Inputting the pre-processed data related to the intelligent assessment of low-frequency oscillation of thermal power units into the sub-index of the hazard degree quantification model for calculation to obtain the sub-index value; S5. According to the degree of influence of the sub-item indicator values ​​on the comprehensive risk value, different proportions are allocated and brought into the risk degree quantification model to obtain the comprehensive risk value.

2. The intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power plant according to claim 1 is characterized in that: The relevant data for intelligent evaluation of low-frequency oscillation of thermal power units include vibration amplitude, vibration duration, equipment fatigue index and unit frequency fluctuation amplitude.

3. The intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power plant according to claim 2 is characterized in that: Vibration amplitude: The torsional amplitude is measured by installing a laser vibrometer on the surface of the turbine rotor; The vibration duration is obtained by subtracting the initial vibration moment from the vibration stop moment; The equipment fatigue index is calculated by monitoring the equipment's cumulative operating time and the bearing temperature collected by the temperature sensor; The unit frequency fluctuation amplitude is recorded by the grid monitor at the unit's grid connection point.

4. The intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power plant according to claim 3 is characterized in that: Preprocessing uses filtering technology to filter out noise signals and retain vibration signals.

5. The intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power plant according to claim 4 is characterized in that: Sub-indicators include vibration intensity index, time accumulation index, equipment fatigue index and power grid impact index.

6. The intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power plant according to claim 5, characterized in that: Vibration intensity index calculation formula: VSI is the vibration severity index; Time accumulation index calculation formula: TCI is the time cumulative index; Equipment fatigue index calculation formula: EFI = bearing temperature rise + 0.5 × cumulative rotor running hours EFI is the equipment fatigue index; Grid impact index calculation formula: GII is the grid impact index.

7. The intelligent quantitative assessment method for the risk level of low-frequency oscillation of a thermal power plant according to claim 6 is characterized in that: Comprehensive risk value calculation formula: Danger value = W1*VSI+W2*TCI+W3*EFI+W4*GII, Among them, W1, W2, W3 and W4 are the weight coefficients of vibration intensity index, time accumulation index, equipment fatigue index and power grid impact index to the comprehensive risk value respectively.

Images