Intelligent monitoring method and system for condenser vacuum system of thermal power unit

Abstract

Disclosed are an intelligent monitoring method and system for a condenser vacuum system of a thermal power unit. The method comprises: collecting operating data of a condenser vacuum system, and performing preprocessing; extracting features from the preprocessed data, and performing anomaly recognition; and on the basis of an anomaly detection output result, adjusting operating parameters of the vacuum system. In the monitoring method and system provided in the present invention, temperature features reflect the heat exchange effect of a system, quality features reflect the operating load and cooling effect of the system, and vacuum system features reflect the overall operating state of the vacuum system; when an anomaly score S exceeds 0.3, the automatic adjustment of the system is realized; and an adjustment amount is calculated on the basis of the current anomaly score and the features, thereby ensuring that the system quickly restores to a normal state.

Description

A method and system for intelligent monitoring of the vacuum system of a condenser in a thermal power unit Technical Field

[0001] This invention relates to the field of thermal power unit monitoring technology, specifically to an intelligent monitoring method and system for the vacuum system of a thermal power unit condenser. Background Technology

[0002] As thermal power units play an increasingly important role in the global energy structure, related technologies are also continuously developing. The efficient operation of thermal power units relies on the coordinated work of multiple subsystems, among which the condenser vacuum system is a key component ensuring efficient and stable operation. Traditional vacuum system monitoring methods mainly rely on periodic manual inspections and simple parameter alarms. However, these methods have many shortcomings, especially in terms of real-time performance and accuracy, which are insufficient to meet the operational requirements of modern thermal power units. In recent years, with the development of sensor technology, data processing technology, and intelligent algorithms, data-driven intelligent monitoring methods have gradually gained attention and application, providing new ideas and means for real-time monitoring and fault diagnosis of vacuum systems.

[0003] Although modern thermal power units have gradually adopted intelligent monitoring technology, existing vacuum system monitoring technologies still have some shortcomings. First, traditional methods often have relatively simple data acquisition and processing, failing to fully extract and utilize multi-dimensional and multi-type operational data, resulting in insufficient monitoring accuracy and sensitivity. Second, existing technologies mainly rely on simple threshold judgments and rule-based alarms for anomaly identification, which cannot effectively identify complex and potential anomalies, easily leading to false alarms or missed alarms. Furthermore, existing methods often lack systematicity and automation in anomaly handling and parameter adjustment, failing to achieve timely and accurate responses and adjustments. Therefore, there is an urgent need for a more advanced and intelligent monitoring method capable of comprehensively and efficiently monitoring the operating status of the condenser vacuum system of thermal power units, and achieving precise anomaly identification and parameter adjustment.

[0004] Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by this invention is to address the shortcomings of existing technologies, such as simple data acquisition and processing, low monitoring accuracy, weak anomaly identification capabilities, and a lack of systematic and automated parameter adjustment. Through comprehensive data preprocessing and feature extraction, the quality and comprehensiveness of monitoring data are improved; through sophisticated anomaly identification methods, high sensitivity and high accuracy in identifying system anomalies are achieved; and through parameter adjustment based on anomaly scoring, automated system response and optimization are realized, ensuring the stable and efficient operation of the condenser vacuum system in thermal power units.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for intelligent monitoring of the vacuum system of a condenser in a thermal power unit, comprising: collecting operating data of the condenser vacuum system and performing preprocessing.

[0008] Features are extracted from the preprocessed data to identify anomalies.

[0009] Adjust the operating parameters of the vacuum system based on the anomaly detection output.

[0010] As a preferred embodiment of the intelligent monitoring method for the condenser vacuum system of thermal power units described in this invention, the acquisition of condenser vacuum system operating data includes using sensors to collect vacuum degree, cooling water temperature, steam quality, cooling water quality, vacuum pump operating status, ambient temperature, and exhaust temperature.

[0011] Preprocessing includes data cleaning, data smoothing, and data standardization.

[0012] Data cleaning involves interpolating and filling in missing values ​​using the average of data from different time points.

[0013] Data smoothing uses the moving average method to smooth time series data, reducing volatility, and is expressed as:

[0014] Among them, S t Y represents the smoothed data. t-i This represents the original data, and n represents the moving average window size. Data standardization normalizes the data to a range of 0 to 1, represented as:

[0015] Where X represents the original data, X′ represents the normalized data, and X... min X represents the minimum value of the data. max This indicates the maximum value of the data.

[0016] As a preferred embodiment of the intelligent monitoring method for the condenser vacuum system of a thermal power unit according to the present invention, the feature extraction of the preprocessed data includes: firstly, extracting temperature features by combining the preprocessed cooling water temperature, ambient temperature, and exhaust temperature, as shown below:

[0017] Among them, F T T represents temperature characteristics. c (t) represents the cooling water temperature as a function of time t, where T a (t) represents the ambient temperature as a function of time t, where T e (t) represents the exhaust temperature as a function of time t.

[0018] Quality characteristics are extracted by combining the pretreated steam quality and cooling water quality, and are expressed as follows:

[0019] Among them, F Q Q represents a quality characteristic. s (i) represents the steam mass at time i, Q c (i) represents the cooling water quality at the i-th moment, and n represents the total number of time points for data collection.

[0020] The combined characteristics of the extracted vacuum level and the vacuum pump's operating status are expressed as follows:

[0021] Among them, F V P represents the characteristics of a vacuum system. v (t) represents the vacuum degree as a function of time t, S v (t) represents the operating state of the vacuum pump as a function of time t.

[0022] Vacuum degree as a function of time t P v (t) is represented as: P v (t)=P0e -λt +κsin(ωt)+μ

[0023] Among them, P v (t) represents the vacuum degree at time t, P0 represents the initial vacuum degree, λ represents the rate constant of vacuum degree decay with time, κ represents the amplitude constant of periodic fluctuation, ω represents the angular frequency of periodic fluctuation, and μ represents the vacuum degree reference value under steady state.

[0024] The vacuum pump operating state function is a discrete function, S v When (t) is 1, it indicates that the vacuum pump is running. v When (t) is 0, it indicates that the vacuum pump has stopped.

[0025] As a preferred embodiment of the intelligent monitoring method for the condenser vacuum system of a thermal power unit according to the present invention, the anomaly identification includes standardizing three features and calculating the relationship term between them based on the standardized features, expressed as:

[0026] Among them, F T F' represents the standardized temperature characteristic. Q ′ represents the standardized quality characteristic, F V ′ represents the standardized vacuum system characteristics, t represents time, and θ represents the smoothing factor, which controls the interaction between characteristics.

[0027] As a preferred embodiment of the intelligent monitoring method for the vacuum system of the condenser of a thermal power unit according to the present invention, the abnormality identification further includes calculating an abnormality identification index, including temperature characteristic items, mass characteristic items and vacuum system characteristic items.

[0028] The temperature characteristic term is represented as:

[0029] The quality characteristic is represented as:

[0030] The characteristic terms of a vacuum system are represented as follows:

[0031] By merging the feature terms, the final anomaly detection index is obtained:

[0032] To optimize the anomaly detection index, an information filtering function is introduced, expressed as:

[0033] Among them, A opt This represents the optimized anomaly detection index.

[0034] As a preferred embodiment of the intelligent monitoring method for the condenser vacuum system of a thermal power unit according to the present invention, the anomaly detection output result includes a final anomaly score expressed as:

[0035] Where S represents the anomaly score, with the result ranging from 0 to 1.

[0036] When S < 0.3, there is a minor anomaly in the system operation, but no immediate action is required; continued monitoring is necessary.

[0037] When S≥0.3, the system malfunctions and requires adjustment.

[0038] As a preferred embodiment of the intelligent monitoring method for the vacuum system of the condenser of a thermal power unit according to the present invention, the adjustment of the vacuum system operating parameters includes adjusting the vacuum degree, cooling water quality and cooling water temperature.

[0039] The adjustment amount is calculated based on the current anomaly score and vacuum degree characteristics:

[0040] Wherein, ΔP v Indicates the vacuum adjustment amount. This represents the vacuum adjustment coefficient, which controls the adjustment level. The cooling water quality adjustment amount is calculated based on the current anomaly score and quality characteristics.

[0041] Where, ΔQ c Indicates the amount of cooling water quality adjustment. This indicates the cooling water quality adjustment coefficient, which controls the adjustment level.

[0042] Based on the current anomaly score and temperature characteristics, calculate the cooling water temperature adjustment amount:

[0043] Where, ΔT c Indicates the amount of cooling water temperature adjustment. This indicates the cooling water temperature adjustment coefficient, which controls the adjustment level.

[0044] Adjust the vacuum pump's operating status and efficiency, cooling water quality, and cooling water inlet and outlet temperature difference based on the three adjustment parameters. Repeat the anomaly score calculation and observe whether the score drops below the safe range.

[0045] A smart monitoring system for the vacuum system of a condenser in a thermal power unit, characterized in that it includes:

[0046] The preprocessing module collects and preprocesses the operating data of the condenser vacuum system.

[0047] The anomaly detection module extracts features from the preprocessed data to identify anomalies.

[0048] Optimize system modules and adjust vacuum system operating parameters based on anomaly detection output results.

[0049] A computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method described above.

[0050] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0051] The beneficial effects of this invention are as follows: temperature characteristics reflect the system's heat exchange efficiency; mass characteristics reflect the system's workload and cooling effect; and vacuum system characteristics reflect the overall operating status of the vacuum system. Our invention comprehensively and accurately monitors all aspects of system operation. When the anomaly score S exceeds 0.3, automated system adjustments are implemented. Adjustment amounts are calculated based on the current anomaly score and characteristics, ensuring the system quickly returns to normal operation. The system can make timely and precise adjustments when anomalies occur, avoiding system failures and decreased operating efficiency. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0053] Figure 1 is an overall flowchart of an intelligent monitoring method for the vacuum system of a thermal power unit condenser provided in the first embodiment of the present invention. Detailed Implementation

[0054] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. 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 protection scope of the present invention.

[0055] Example 1

[0056] Referring to Figure 1, an embodiment of the present invention provides a method for intelligent monitoring of the vacuum system of a condenser in a thermal power unit, comprising:

[0057] S1: Collect and preprocess the operating data of the condenser vacuum system.

[0058] Sensors are used to collect data on vacuum level, cooling water temperature, steam quality, cooling water quality, vacuum pump operating status, ambient temperature, and exhaust temperature.

[0059] Preprocessing includes data cleaning, data smoothing, and data standardization.

[0060] Data cleaning involves interpolating and filling in missing values ​​using the average of data from different time points.

[0061] Data smoothing uses the moving average method to smooth time series data, reducing volatility, and is expressed as:

[0062] Among them, S t Y represents the smoothed data. t-i This represents the original data, and n represents the moving average window size. Data standardization normalizes the data to a range of 0 to 1, represented as:

[0063] Where X represents the original data, X′ represents the normalized data, and X... min X represents the minimum value of the data. max This indicates the maximum value of the data.

[0064] S2: Extract features from the preprocessed data and perform anomaly identification.

[0065] First, temperature features are extracted by combining the pre-processed cooling water temperature, ambient temperature, and exhaust temperature, and expressed as follows:

[0066] Among them, F T T represents temperature characteristics. c (t) represents the cooling water temperature as a function of time t, where T a (t) represents the ambient temperature as a function of time t, where T e (t) represents the exhaust temperature as a function of time t.

[0067] It should be noted that the exponential decay term T c (t)·e -t Simulates the decay of cooling water temperature over time, reflecting changes in the system's cooling effect. (Square root term) It reflects the proportional relationship between ambient temperature and exhaust temperature, demonstrating the nonlinear characteristics of temperature change.

[0068] Furthermore, this formula comprehensively considers changes in cooling water temperature, ambient temperature, and exhaust temperature, enhancing its sensitivity to nonlinear temperature variations. It better reflects the dynamic temperature changes of the system, aiding in anomaly detection.

[0069] Quality characteristics are extracted by combining the pretreated steam quality and cooling water quality, and are expressed as follows:

[0070] Among them, F Q Q represents a quality characteristic. s (i) represents the steam mass at time i, Q c (i) represents the cooling water quality at time i, and n represents the total number of time points for data collection.

[0071] It should be noted that fractional terms This measures the proportional relationship between steam flow rate and cooling water flow rate. (Logarithmic term log(Q)) s (i)Q c (i) Introduce a logarithmic function to enhance sensitivity to large-scale flow changes.

[0072] Furthermore, this formula effectively extracts the dynamic variation characteristics of steam flow and cooling water flow. The use of fractional and logarithmic functions enhances its ability to capture nonlinear changes in flow rate. It can reflect the interaction between system load and cooling effect.

[0073] The combined characteristics of the extracted vacuum level and the vacuum pump's operating status are expressed as follows:

[0074] Among them, F V P represents the characteristics of a vacuum system. v (t) represents the vacuum degree as a function of time t, S v (t) represents the operating state of the vacuum pump as a function of time t.

[0075] It should be noted that fractional terms Combining vacuum level and vacuum pump operating status, the Sigmoid function is used. The effect of smooth state switching on vacuum level. The sine term sin(t) is introduced to simulate the periodic fluctuations of vacuum level.

[0076] Furthermore, this formula combines vacuum level and vacuum pump operating status to provide a comprehensive assessment of the system's vacuum condition. The use of sigmoid and sinusoidal functions enhances sensitivity to nonlinear and periodic variations. It accurately reflects the dynamic operation of the vacuum system, providing a reliable basis for anomaly detection and parameter adjustment.

[0077] Vacuum degree as a function of time t P v (t) is represented as: P v (t)=P0e -λt +κsin(ωt)+μ

[0078] Among them, P v (t) represents the vacuum degree at time t, P0 represents the initial vacuum degree, λ represents the rate constant of vacuum degree decay with time, κ represents the amplitude constant of periodic fluctuation, ω represents the angular frequency of periodic fluctuation, and μ represents the vacuum degree reference value under steady state.

[0079] The vacuum pump operating state function is a discrete function, S v When (t) is 1, it indicates that the vacuum pump is running. v When (t) is 0, it indicates that the vacuum pump has stopped.

[0080] The three features are standardized, and the relationship term between them is calculated based on the standardized features, as follows:

[0081] Among them, F T F' represents the standardized temperature characteristic. Q ′ represents the standardized quality characteristic, F V ′ represents the standardized vacuum system characteristics, t represents time, and θ represents the smoothing factor, which controls the interaction between characteristics.

[0082] Calculate the anomaly identification index, including temperature characteristic, mass characteristic, and vacuum system characteristic.

[0083] The temperature characteristic term is represented as:

[0084] It should be noted that this formula utilizes the time integral of temperature characteristics, combined with exponential and cosine functions, to reflect the periodic and nonlinear characteristics of temperature changes. The cosine function makes the temperature characteristics exhibit periodic changes in the time dimension, while the exponential function amplifies the influence of the temperature characteristics. This enhances the sensitivity to periodic fluctuations in temperature characteristics and can capture nonlinear changes in temperature characteristics, providing a more refined description for anomaly detection.

[0085] The quality characteristic is represented as:

[0086] It should be noted that this formula combines the time integral of flow characteristics with logarithmic and sine functions to reflect the fluctuations and nonlinear relationships of flow characteristics. The logarithmic function is sensitive to large-scale variations, while the sine function captures periodic changes in flow. This approach can handle a wide range of variations in flow characteristics, improving the ability to identify nonlinear and periodic fluctuations in flow characteristics.

[0087] The characteristic terms of a vacuum system are represented as follows:

[0088] This formula reflects the smooth transition of vacuum system characteristics between different states through time integration and the Sigmoid function. The Sigmoid function ensures the smoothness of vacuum system characteristics during changes in operating state, thus smoothing the changes in vacuum system characteristics during state transitions and improving the sensitivity to the stability and abnormal states of the vacuum system characteristics.

[0089] By merging the feature terms, the final anomaly detection index is obtained:

[0090] To optimize the anomaly detection index, an information filtering function is introduced, expressed as:

[0091] Among them, A opt This represents the optimized anomaly detection index.

[0092] It should be noted that this formula effectively filters out noise and unstable factors, making the anomaly identification results more reliable.

[0093] S3: Adjust the operating parameters of the vacuum system based on the anomaly detection output.

[0094] The final anomaly score is expressed as follows:

[0095] Where S represents the anomaly score, with the result ranging from 0 to 1.

[0096] It should be noted that the final anomaly score is calculated using time integration and a normalization function. The logarithmic function and normalization factor ensure that the score is between 0 and 1, providing a clear anomaly assessment result.

[0097] When S < 0.3, there is a minor anomaly in the system operation, but no immediate action is required; continued monitoring is necessary.

[0098] When S≥0.3, the system malfunctions and requires adjustment.

[0099] The parameters that need to be adjusted are vacuum level, cooling water quality, and cooling water temperature.

[0100] The adjustment amount is calculated based on the current anomaly score and vacuum degree characteristics:

[0101] Wherein, ΔP v Indicates the vacuum adjustment amount. This represents the vacuum adjustment coefficient, which controls the adjustment level. The cooling water quality adjustment amount is calculated based on the current anomaly score and quality characteristics.

[0102] Where, ΔQ c Indicates the amount of cooling water quality adjustment. This indicates the cooling water quality adjustment coefficient, which controls the adjustment level.

[0103] Based on the current anomaly score and temperature characteristics, calculate the cooling water temperature adjustment amount:

[0104] Where, ΔT c Indicates the amount of cooling water temperature adjustment. This indicates the cooling water temperature adjustment coefficient, which controls the adjustment level.

[0105] Adjust the vacuum pump's operating status and efficiency, cooling water quality, and cooling water inlet and outlet temperature difference based on the three adjustment parameters. Repeat the anomaly score calculation and observe whether the score drops below the safe range.

[0106] The above embodiments also include an intelligent monitoring system for the vacuum system of a thermal power unit condenser, specifically:

[0107] The preprocessing module collects and preprocesses the operating data of the condenser vacuum system.

[0108] The anomaly detection module extracts features from the preprocessed data to identify anomalies.

[0109] Optimize system modules and adjust vacuum system operating parameters based on anomaly detection output results.

[0110] The computer device can be a server. This computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data cluster data for a power monitoring system. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method.

[0111] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0112] Example 2

[0113] One embodiment of the present invention provides an intelligent monitoring method and system for the vacuum system of a condenser in a thermal power unit. To verify the beneficial effects of the present invention, a simulation experiment is conducted for scientific demonstration.

[0114] The experimental subject was the condenser vacuum system of a thermal power plant. The system includes multiple subsystems and sensors to collect key parameters such as vacuum level, cooling water temperature, steam quality, cooling water quality, vacuum pump operating status, ambient temperature, and exhaust temperature.

[0115] In the preparation phase of the experiment, the sensors were first calibrated to ensure the accuracy of data acquisition. Then, a data acquisition module and a preprocessing module were installed to collect and process the operating data of the condenser vacuum system. The experiment was divided into two phases: the first phase used traditional monitoring methods, relying solely on simple parameter alarms and manual checks; the second phase used the intelligent monitoring method of this invention, achieving intelligent monitoring through data preprocessing, feature extraction, anomaly identification, and parameter adjustment.

[0116] Before the experiment, the initial readings of each sensor were recorded, and all equipment was ensured to be operating normally. During the experiment, data for each parameter was recorded every 10 minutes, for a total of 7 recordings. After data acquisition, traditional methods directly determine abnormalities through parameter alarms, while the method of this invention processes the data through the following steps:

[0117] The collected data is cleaned, smoothed, and standardized. Data cleaning uses interpolation to fill in missing values, data smoothing uses the moving average method, and data standardization normalizes the data to the range of 0-1. Temperature, mass, and vacuum system features are extracted. Temperature features are combined with cooling water temperature, ambient temperature, and exhaust temperature; mass features are combined with steam mass and cooling water mass; and vacuum system features are combined with vacuum level and vacuum pump operating status. Complex interaction terms between features are calculated, and an anomaly detection index is calculated based on the standardized features. An optimized information filtering function is introduced to improve the accuracy of anomaly detection. When the anomaly score S exceeds 0.3, adjustment amounts are calculated based on the score results, and the vacuum level, cooling water mass, and cooling water temperature are adjusted respectively to restore the system to normal operating status.

[0118] During the experiment, the system operation data under the traditional monitoring method and the method of this invention were recorded respectively, and the effects of the two methods were compared and analyzed. As shown in Tables 1 and 2.

[0119] Table 1. Experimental Results of Our Invention

[0120] Table 2 Experimental results of traditional methods

[0121] By comparing the data in the two tables above, it is clear that there are differences in the system operation status between the method of this invention and the traditional monitoring method.

[0122] The vacuum level obtained using the traditional method gradually decreased from an initial 6500 Pa to 6150 Pa, and continued to decrease after the fourth recording. This indicates that the vacuum level continuously decreased during system operation, but this was not identified and adjusted in time, leading to a decline in system efficiency.

[0123] The vacuum level of the method of this invention gradually decreased from an initial 6500 Pa. However, after the fourth recording, the vacuum pump stopped operating, and the system automatically identified the anomaly and adjusted the vacuum level to ensure that the vacuum level fluctuated within a reasonable range. This demonstrates that the method of this invention can promptly identify and adjust anomalies, maintaining stable system operation.

[0124] Traditional methods gradually increase the cooling water temperature from an initial 25°C to 32°C, failing to effectively control the temperature rise and resulting in a decrease in system cooling efficiency.

[0125] Although the cooling water temperature rose after the fourth recording, the system promptly reduced the temperature by adjusting the cooling water quality and temperature, ensuring stable cooling performance. This demonstrates the significant advantages of the method in temperature control.

[0126] Traditional methods show that the continuous increase in steam quality and cooling water quality indicates an increase in system load, but this has not been effectively adjusted, leading to a heavier burden on system operation.

[0127] In this invention, the steam and cooling water quality were adjusted after the fourth recording. By optimizing system parameters, stable system operation under high load was ensured. This demonstrates that the method of this invention is more flexible and efficient in handling load changes.

[0128] Traditional vacuum pumps operate continuously without being optimized for system conditions, which may lead to increased energy consumption and equipment wear.

[0129] When an abnormal vacuum level is detected, the vacuum pump automatically stops operating. By optimizing and adjusting other parameters, the system ensures stable operation, reducing energy consumption and equipment wear. This demonstrates the significant advantages of the method in energy management and equipment protection.

[0130] In summary, the method of this invention can promptly identify system anomalies and ensure stable system operation by automatically adjusting system parameters. Traditional methods, on the other hand, mainly rely on parameter alarms and manual checks, resulting in slow response times and difficulty in timely handling of anomalies.

[0131] This invention's method comprehensively analyzes the system's operational status through feature extraction and interactive computation of multi-dimensional data, improving the accuracy and sensitivity of monitoring. Traditional methods, on the other hand, are relatively singular and cannot fully capture changes in the system's operational status.

[0132] This invention reduces energy consumption and equipment wear by intelligently adjusting the operating status of the vacuum pump and other system parameters, thereby improving system operating efficiency. Traditional methods cannot effectively optimize energy management, easily leading to resource waste and equipment damage.

[0133] The method of this invention can effectively control the cooling water temperature, ensure stable cooling effect, and avoid system overheating. Traditional methods are relatively passive in temperature control, which can easily lead to poor cooling effect.

[0134] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent monitoring method for a vacuum system of a steam condenser of a thermal power unit, characterized in that, The method comprises the following steps: collecting vacuum system operation data of a condensing gas machine, and performing preprocessing; extracting features from the preprocessed data, and performing abnormality identification; adjusting vacuum system operation parameters based on the abnormality detection output result.

2. The intelligent monitoring method for vacuum system of a power plant condenser according to claim 1, characterized in that: The collecting of the vacuum system operation data of the condensing gas machine comprises using sensors to collect vacuum degree, cooling water temperature, steam quality, cooling water quality, vacuum pump operation state, ambient temperature and exhaust temperature. The preprocessing comprises data cleaning, data smoothing and data standardization. The data cleaning uses the average value of data at the previous and subsequent time points to fill in the missing values. Data smoothing uses the moving average method to smooth the time series, reduce fluctuations, and is expressed as: where S t represents smoothed data, Y t-i represents original data, and n represents a moving average window size; Data standardization normalizes data to between 0 and 1, expressed as: where X represents original data, X' represents normalized data, X min represents the minimum value of the data, X max represents the maximum value of the data.

3. The intelligent monitoring method for vacuum system of a power plant condenser according to claim 2, characterized in that: The extracting features from the preprocessed data includes, first, temperature feature extraction, combining the preprocessed cooling water temperature, ambient temperature and exhaust temperature, expressed as: where F T represents the temperature characteristic, T c (t) represents the cooling water temperature as a function of time t, T a (t) represents the ambient temperature as a function of time t, T e (t) represents the exhaust gas temperature as a function of time t; Quality feature extraction is performed in combination with the pre-processed steam quality and cooling water quality, and is expressed as: where F Q represents a mass characteristic, Q s (i) represents the steam mass at the i-th time, Q c (i) represents the i-th The cooling water quality at the time point n represents the total number of time points of the collected data. The extraction of the vacuum degree and the vacuum pump running state features are combined and represented as: where F V represents the vacuum system characteristics, P v (t) represents the vacuum degree as a function of time t, S v (t) represents the vacuum pump operating state as a function of time t; The vacuum degree as a function of time t P v (t) is represented as: P v (t) = P0e -λt + κ sin(ωt) + μ where P v (t) represents the vacuum level at time t, P0represents the initial vacuum level, λ represents the rate constant of the decay of the vacuum level with time, κ represents the amplitude constant of the periodic fluctuation, ω represents the angular frequency of the periodic fluctuation, and μ represents the reference value of the vacuum level in the steady state. The vacuum pump operating state function is a discrete function, S v (t) = 1 means that the vacuum pump is running, S v (t) = 0 means that the vacuum pump is stopped.

4. The intelligent monitoring method for vacuum system of a power plant condenser according to claim 3, characterized in that: The performing of the anomaly identification includes normalizing the three features, calculating a relationship term between the normalized features, and representing as: where F T ' denotes the normalized temperature feature, F Q ' denotes the normalized mass feature, F V ' denotes the normalized vacuum system feature, t denotes time, and Θ denotes a smoothing factor that controls the influence of interactions between features.

5. The intelligent monitoring method of the vacuum system of the condenser of the thermal power generating unit according to claim 4, characterized in that: The abnormality identification further comprises calculating an abnormality identification index, which comprises a temperature feature item, a quality feature item and a vacuum system feature item. The temperature feature is expressed as: The quality feature item is expressed as: The vacuum system features are represented as: Merging the feature items, a final anomaly recognition index is obtained: The abnormality recognition index is optimized, and an information filtering function is introduced, which is expressed as: wherein A opt represents the optimized abnormality recognition index.

6. The intelligent monitoring method of a power plant condenser vacuum system according to claim 5, characterized in that: The abnormality detection output result includes a final abnormality score expressed as: S represents the abnormality score, and the result is between 0 and 1. When S<0.3, there is a slight abnormality in the system operation, but no immediate measures need to be taken, and the monitoring continues. When S≥0.3, the system operation is abnormal, and adjustment needs to be made.

7. The intelligent monitoring method of a vacuum system of a condenser of a thermal power generating unit according to claim 6, characterized in that: The adjustment of the vacuum system operation parameters comprises adjusting the vacuum degree, the cooling water quality and the cooling water temperature. The adjustment amount is calculated according to the current abnormality score and the vacuum degree feature: where ΔP v represents the vacuum degree adjustment amount, and κ1 represents a vacuum degree adjustment coefficient, which controls the adjustment degree. A cooling water quality adjustment amount is calculated based on the current abnormality score and the quality feature: where ΔQ c represents the cooling water mass adjustment amount, and κ2 represents a cooling water mass adjustment coefficient, which controls the adjustment degree. Based on the current abnormality score and temperature feature, a cooling water temperature adjustment amount is calculated: where ΔT c represents the cooling water temperature adjustment amount, and κ3 represents a cooling water temperature adjustment coefficient, which controls the adjustment degree. According to the three adjustment amounts, the working state and efficiency of the vacuum pump, the cooling water quality and the cooling water inlet and outlet temperature difference are adjusted; the abnormality score is repeatedly calculated to observe whether the score falls within the safe range. 8.An intelligent monitoring system for a condenser vacuum system of a thermal power unit, which adopts the method according to any one of claims 1-7, and characterized in that: a preprocessing module, which collects vacuum system operation data of a condensing gas machine, and performs preprocessing; an abnormality identification module, which extracts features from the preprocessed data, and performs abnormality identification; an optimization system module, which adjusts vacuum system operation parameters based on the abnormality detection output result. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method according to any one of claims 1-7.

Images