Intelligent regulation and control method and system for static frequency conversion of gas turbine unit

Abstract

The invention relates to the technical field of power electronics and frequency conversion, in particular to an intelligent regulation and control method and system for static frequency conversion of a gas turbine unit. A sensor is used for collecting operation data of the gas turbine unit in real time and preprocessing the operation data, and a statistical analysis algorithm is used for analyzing and processing the operation data in real time to obtain an operation state score; the maintenance demand prediction model is utilized to calculate the operation state score and predict the maintenance demand, according to the maintenance demand prediction result, the intelligent regulation and control strategy is formulated, the response speed of the frequency converter is improved, and by using the static frequency conversion technology, the reliability of the system is remarkably improved, and the maintenance workload is reduced. The overall performance and the application value of the static frequency converter system are remarkably improved, and positive influences are generated on stable operation and economical efficiency of a power system.

Description

Technical Field

[0001] The present invention relates to the field of power electronics and frequency conversion technology, and in particular to an intelligent control method and system for static frequency conversion of a gas turbine unit. Background Art

[0002] As the operating time increases, the performance of the gas turbine unit will gradually decline, and the frequency of failures will also increase. This will not only affect production efficiency, but also lead to increased maintenance costs and increased operating risks. Traditional gas turbine maintenance methods mainly rely on regular maintenance and post-maintenance, that is, inspecting and repairing the equipment at predetermined time intervals, or repairing the equipment after a failure. The existing gas turbine unit maintenance methods and monitoring systems have many shortcomings in improving equipment reliability, reducing maintenance costs, and ensuring production safety. With the continuous development of industrial production, higher requirements are placed on equipment maintenance and management. A more efficient and intelligent maintenance method and monitoring system is needed to solve the shortcomings of traditional maintenance methods and improve the operating efficiency and reliability of equipment.

[0003] Some advanced excitation systems may integrate intelligent monitoring and remote control functions, which can monitor and adjust the operating status of the unit in real time through the network, improve operation and maintenance efficiency and fault diagnosis capabilities. The development trend of gas turbine excitation systems is to continue to develop in the direction of digitalization, intelligence and high efficiency to meet the increasingly complex and demanding power market needs.

[0004] In summary, an intelligent control method for static frequency conversion of a gas turbine unit mainly aims to improve the response speed, accuracy and stability of the excitation system of the gas turbine unit to cope with changes in grid frequency and load. In particular, it is necessary to solve the limitations of traditional systems in energy efficiency and reliability, and achieve more efficient voltage control and operation management through digital control and intelligent monitoring technology. In addition, the stability and economy of the system in long-term operation must also be considered to meet the needs of the modern power market for efficient and reliable power supply. Summary of the invention

[0005] In view of the above problems existing in the prior art, the present invention is proposed.

[0006] Therefore, the technical problem to be solved by the present invention is: by introducing advanced sensor technology and data analysis methods, the monitoring, evaluation and maintenance capabilities of gas turbine units are comprehensively improved to ensure efficient and safe operation of equipment and provide strong technical support for industrial production.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent control method for static frequency conversion of a gas turbine unit, comprising: using sensors to collect operating data of the gas turbine unit in real time, and preprocessing the operating data; using a statistical analysis algorithm to analyze and process the operating data in real time to obtain an operating status score; using a maintenance demand prediction model to calculate the operating status score and predict maintenance needs; and formulating an intelligent control strategy based on the maintenance demand prediction results to improve the response speed of the frequency converter.

[0008] As a preferred solution of the intelligent control method for static frequency conversion of a gas turbine unit described in the present invention, the operating data includes voltage data, current data, pressure data, temperature data, vibration data and load data of the gas turbine unit.

[0009] As a preferred solution of the intelligent control method for static frequency conversion of a gas turbine unit described in the present invention, the preprocessing includes normalizing the operating data, which is expressed as:

[0010]

[0011] Where D(t) represents the running data, t represents the time, and D norm (t) represents the data generated after normalization, μ D represents the mean of the running data D(t), σ D Represents the standard deviation of the running data D(t).

[0012] As a preferred solution of the intelligent control method for static frequency conversion of a gas turbine unit described in the present invention, the statistical analysis algorithm is expressed as:

[0013]

[0014] Among them, S(t) represents the running status score, k represents the positive coefficient, and w i Represents the weight coefficient, F i (t) represents different eigenvalues ​​at time t.

[0015] As a preferred solution of the intelligent control method for static frequency conversion of a gas turbine unit described in the present invention, the maintenance demand prediction model is expressed as:

[0016] M(t)=αS(t)+(1-α)M hist +γD norm (t)

[0017] Where M(t) represents the predicted maintenance demand at time t, α represents the adjustment factor, and M hist It represents the weighted average of the measured data, and γ represents the adjustment factor of the normalized data;

[0018] When M(t)>β, the system determines that the current maintenance state is an emergency maintenance state; when M(t)=β, it is a preventive maintenance state; when M(t)<β, it is a routine maintenance state, where β represents the warning threshold.

[0019] As a preferred solution of the intelligent control method for static frequency conversion of a gas turbine unit described in the present invention, wherein: the formulation of the intelligent control strategy includes, when the system is judged to be in an emergency maintenance state, formulating the intelligent control strategy according to the current maintenance state, performing preliminary adjustments, adjusting the inverter control parameters, improving the response speed, and reducing the system pressure. According to the preliminary adjustment result, if the preliminary adjustment result is that the maintenance is completed, the preliminary adjustment is completed, and a secondary judgment is performed, the operation data is recollected, and a new operation status score S(t) is obtained through a statistical analysis algorithm to determine whether the emergency maintenance state is improved. If the operation status score S(t) decreases, a secondary calculation is performed through a maintenance demand prediction model to obtain that the system enters a preventive maintenance state, and the intelligent control strategy is effective;

[0020] When the system is judged to be in preventive maintenance state, an intelligent control strategy is formulated according to the current maintenance state, and preliminary adjustments are made to adjust the inverter operating frequency to maintain the optimal state and avoid deterioration of the maintenance state. According to the preliminary adjustment results, if the preliminary adjustment results show that the maintenance is completed, the preliminary adjustment is completed, and a secondary judgment is made to re-collect the operating data and obtain a new operating state score S(t) through the statistical analysis algorithm to determine whether the preventive maintenance state has been improved. If the operating state score S(t) decreases, the maintenance demand prediction model is used for secondary calculation to conclude that the system has entered a regular maintenance state, and the intelligent control strategy is effective.

[0021] When the system is judged to be in a routine maintenance state, an intelligent control strategy is formulated according to the current maintenance state, preliminary maintenance is performed, the inverter control parameters are maintained, and the system is kept in stable operation. According to the preliminary maintenance results, if the preliminary maintenance results remain stable, the preliminary maintenance is completed, and a secondary judgment is made. The operating data is collected again, and a new operating status score S(t) is obtained through a statistical analysis algorithm to determine whether the routine maintenance state is stable. If the operating status score S(t) is within the normal range, it is recalculated through the maintenance demand prediction model, and it is concluded that the system is in a routine maintenance state, and the intelligent control strategy is effective.

[0022] As a preferred solution of the intelligent control method for static frequency conversion of a gas turbine unit described in the present invention, the control parameter of the frequency converter is expressed as:

[0023]

[0024] Among them, K new Indicates the new inverter control parameters, K oldrepresents the old inverter control parameter, η represents the learning rate, K represents the inverter control parameter, It represents the gradient of the operating status score S(t) to the control parameter K. By calculating the gradient, the control parameter K is adjusted to reduce the operating status score S(t);

[0025] Adjust the inverter operating frequency as:

[0026]

[0027] Among them, f new Indicates the operating frequency of the new inverter, f old represents the operating frequency of the old inverter, b represents the linear correlation coefficient of the operating status score to the operating frequency, a represents the logarithmic correlation coefficient of the operating status score to the operating frequency, and the extreme value of the function is obtained through iterative calculation to find the optimal operating frequency;

[0028] Maintain the inverter control parameters expressed as:

[0029] K new =K old -η(S(t)-S target )

[0030] Among them, S target Indicates the target operating status score, and determines and maintains the inverter control parameters according to the difference between the operating status score and the target operating status score;

[0031] When the running status score and the target status score are the same, it means that the inverter control parameters are maintained successfully.

[0032] Another object of the present invention is to provide an intelligent control system for static frequency conversion of gas turbine units to improve the economy and efficiency of the static frequency conversion system when multiple units share one device. Specifically, it is necessary to solve technical problems such as large maintenance workload, inflexible equipment installation and layout, system impact during startup, special requirements for motor structure, economy issues, insufficient control strategy, insufficient protection function and compatibility with existing systems. The present invention improves the utilization efficiency and economy of the equipment through innovative design and technical improvements, so that it can more effectively support the operation of multiple units, thereby reducing overall operating costs and improving the sustainability and competitiveness of the system.

[0033] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent control system for static frequency conversion of a gas turbine unit, comprising: a preprocessing module, a state analysis module, a demand prediction module and an intelligent control module;

[0034] The preprocessing module includes the operation of normalizing and preprocessing the collected operation data to ensure the accuracy and effectiveness of subsequent data analysis;

[0035] The state analysis module includes using a statistical analysis algorithm to perform real-time analysis and processing on the operating data to obtain the operating state, and identifying the current state of the gas turbine unit through the data analysis algorithm;

[0036] The demand prediction module includes using a maintenance demand prediction model to calculate the operating status and predict the maintenance demand, and predicting the maintenance demand through the operating data and the operating status results;

[0037] The intelligent control module includes formulating an intelligent control method according to the maintenance demand prediction results, improving the response speed of the inverter, adjusting the working parameters of the inverter through comprehensive analysis of maintenance prediction data, and realizing intelligent control.

[0038] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, steps of an intelligent control method for static frequency conversion of a gas turbine unit are implemented.

[0039] A computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of an intelligent control method for static frequency conversion of a gas turbine unit.

[0040] Beneficial effects of the present invention: By using static frequency conversion technology, the reliability of the system is significantly improved and the maintenance workload is reduced. The present invention also optimizes the installation layout of the equipment and provides flexible options to cope with different space restrictions and environmental requirements, thereby optimizing the layout and use efficiency of the equipment. The improved startup strategy and control technology effectively reduce the impact on the power system during the startup process, enhance the stability and safety of the power grid, and help extend the service life of the equipment. The present invention also expands the function and application scope of static frequency conversion by introducing sophisticated control strategies and enhanced protection functions, supports operation requirements under complex working conditions, and significantly improves the overall performance and application value of the static frequency converter system, which has a positive impact on the stable operation and economy of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0042] Figure 1 A schematic flow chart of an intelligent control method for static frequency conversion of a gas turbine unit provided in accordance with an embodiment of the present invention.

[0043] Figure 2 A maintenance requirement comparison diagram of an intelligent control method for static frequency conversion of a gas turbine unit provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0045] Example 1, reference Figure 1 , is an embodiment of the present invention, which provides an intelligent control method for static frequency conversion of a gas turbine unit, comprising:

[0046] S1: Use sensors to collect the operating data of the gas turbine unit in real time and pre-process the operating data.

[0047] It should be noted that the operating data includes voltage data, current data, pressure data, temperature data, vibration data and load data of the gas turbine unit.

[0048] Furthermore, pressure data is a key parameter of the gas turbine unit. By monitoring the pressure changes in different parts of the gas turbine unit, we can understand the working status of the unit, detect abnormal pressure phenomena in time, and prevent system failures caused by pressure fluctuations.

[0049] Furthermore, the data preprocessing includes normalizing the running data, which is expressed as:

[0050]

[0051] Where D(t) represents the running data, t represents the time, and D norm (t) represents the data generated after normalization, μ D represents the mean of the running data D(t), σ D Represents the standard deviation of the running data D(t).

[0052] By comprehensively analyzing these data, a comprehensive assessment of the operating status of the gas turbine unit can be achieved. The voltage and current data together reflect the electrical operation of the unit, the pressure and temperature data provide the thermodynamic state information of the unit, the vibration data is mainly used to monitor the mechanical operation status of the unit, and the load data helps to optimize the workload distribution of the unit.

[0053] S2: Analyze and process the operation data in real time using statistical analysis algorithms to obtain the operation status.

[0054] It should be noted that the statistical analysis algorithm is expressed as:

[0055]

[0056] Among them, S(t) represents the operating status score, which is set between 0 and 1. (0-0.50 represents normal operating status, and (0.5-1) represents abnormal operating status. When the operating status score reaches 0.5, it means that the system needs to be closely monitored. k represents a positive coefficient, which is used to adjust the model sensitivity. w i Represents the weight coefficient, and F i (t) correlation, reflecting the importance of different features in the running status score, F i (t) represents different characteristic values ​​of time t, such as the operating data of the gas turbine unit during operation, including voltage data, current data, pressure data, temperature data, vibration data and load data. By real-time acquisition and monitoring of these data, the statistical analysis algorithm can integrate these characteristics to evaluate the operating status. By adjusting k and w i Adapt the model to the data to ensure that the scoring results can truly reflect the operating status of the system.

[0057] Furthermore, S(t) is used as the key result output and as the key parameter input in the maintenance demand prediction model, indicating that the output of the data analysis algorithm directly affects the accuracy and effectiveness of the demand prediction model. It also ensures that the prediction model can predict maintenance needs in real time according to the operating status of the system and formulate intelligent control strategies, thereby improving the accuracy and reliability of predicting maintenance needs.

[0058] S3: Use the maintenance demand prediction model to calculate the operating status and predict maintenance needs.

[0059] It should be noted that the maintenance demand forecasting model is expressed as:

[0060] M(t)=αS(t)+(1-α)M hist +γD norm (t)

[0061] Where M(t) represents the predicted maintenance demand at time t, which is related to the warning threshold. α represents the adjustment factor, which can be adjusted according to the specific needs and the importance of the operation data. hist It represents the weighted average of the measured data, which reflects the operating status of the internal combustion engine unit over a period of time and helps predict future maintenance needs. γ represents the adjustment factor of the normalized data, ensuring that data from different sources can be compared on the same scale.

[0062] Furthermore, when M(t)>β, it indicates that the system state is unstable. The system determines that the current maintenance state is an emergency maintenance state, and an abnormal fault has occurred, requiring immediate maintenance to avoid interruption and loss of system operation. When M(t)=β, it indicates that the system operation status is close to the warning line and is in a preventive maintenance state. Abnormal faults may occur in the future, and preventive inspection and maintenance are required to prevent potential abnormal faults and improve system stability. When M(t)<β, it indicates that the system is in good operation and is in a routine maintenance state. There is no obvious risk of abnormal faults and only regular inspection and maintenance are required according to the established maintenance plan. β represents the warning threshold, which is used to distinguish different maintenance states.

[0063] Furthermore, by calculating and monitoring maintenance requirements M(t) in real time, the system can identify potential maintenance needs in advance and arrange preventive maintenance operations to avoid sudden failures.

[0064] S4: Based on the maintenance demand prediction results, formulate intelligent control methods to improve the response speed of the inverter.

[0065] It should be noted that the formulation of the intelligent control strategy includes, when the system is judged to be in an emergency maintenance state, formulating the intelligent control strategy according to the current maintenance state, making preliminary adjustments, adjusting the inverter control parameters, improving the response speed, and reducing the system pressure. According to the preliminary adjustment result, if the preliminary adjustment result is that the maintenance is completed, the preliminary adjustment is completed, and a secondary judgment is made, the operation data is recollected, and a new operation status score S(t) is obtained through a statistical analysis algorithm to determine whether the emergency maintenance state is improved. If the operation status score S(t) decreases, a secondary calculation is performed through the maintenance demand prediction model to obtain that the system enters a preventive maintenance state, and the intelligent control strategy is effective;

[0066] When the system is judged to be in preventive maintenance state, an intelligent control strategy is formulated according to the current maintenance state, and preliminary adjustments are made to adjust the inverter operating frequency to maintain the optimal state and avoid deterioration of the maintenance state. According to the preliminary adjustment results, if the preliminary adjustment results show that the maintenance is completed, the preliminary adjustment is completed, and a secondary judgment is made to re-collect the operating data and obtain a new operating state score S(t) through the statistical analysis algorithm to determine whether the preventive maintenance state has been improved. If the operating state score S(t) decreases, the maintenance demand prediction model is used for secondary calculation to conclude that the system has entered a regular maintenance state, and the intelligent control strategy is effective.

[0067] When the system is judged to be in a routine maintenance state, an intelligent control strategy is formulated according to the current maintenance state, preliminary maintenance is performed, the inverter control parameters are maintained, and the system is kept in stable operation. According to the preliminary maintenance results, if the preliminary maintenance results remain stable, the preliminary maintenance is completed, and a secondary judgment is made. The operating data is collected again, and a new operating status score S(t) is obtained through a statistical analysis algorithm to determine whether the routine maintenance state is stable. If the operating status score S(t) is within the normal range, it is recalculated through the maintenance demand prediction model, and it is concluded that the system is in a routine maintenance state, and the intelligent control strategy is effective.

[0068] Furthermore, the system can identify and determine potential problems through intelligent control strategies, improve the system's response speed in emergency situations, help to respond quickly to abnormal situations, reduce potential damage, and facilitate subsequent maintenance; especially in emergency maintenance states, intelligent control strategies can reduce the operating pressure of the entire system, in preventive maintenance states, intelligent control strategies can ensure operation at the highest efficiency and avoid deterioration of operating conditions, in routine maintenance states, intelligent control systems can reduce the frequency and cost of emergency maintenance. Overall, intelligent control strategies reduce unexpected downtime and maintenance requirements, and improve the efficiency and sustainability of the system.

[0069] The above is a schematic scheme of an intelligent control method for static frequency conversion of a gas turbine unit in this embodiment. It should be noted that the technical scheme of the system of the intelligent control method for static frequency conversion of a gas turbine unit and the technical scheme of the intelligent control method for static frequency conversion of the gas turbine unit mentioned above belong to the same concept, and the details of the technical scheme of the intelligent control system for static frequency conversion of a gas turbine unit in this embodiment that are not described in detail can all be referred to the description of the technical scheme of the intelligent control method for static frequency conversion of a gas turbine unit mentioned above.

[0070] In this embodiment, an intelligent control system for static frequency conversion of a gas turbine unit includes: a preprocessing module, a state analysis module, a demand prediction module and an intelligent control module;

[0071] The preprocessing module includes the operation of normalizing and preprocessing the collected operation data to ensure the accuracy and effectiveness of subsequent data analysis;

[0072] The state analysis module includes using a statistical analysis algorithm to perform real-time analysis and processing on the operating data to obtain the operating state, and identifying the current state of the gas turbine unit through the data analysis algorithm;

[0073] The demand prediction module includes using a maintenance demand prediction model to calculate the operating status and predict the maintenance demand, and predicting the maintenance demand through the operating data and the operating status results;

[0074] The intelligent control module includes formulating an intelligent control method according to the maintenance demand prediction results, improving the response speed of the inverter, adjusting the working parameters of the inverter through comprehensive analysis of maintenance prediction data, and realizing intelligent control.

[0075] This embodiment also provides a computing device, which is suitable for a method for intelligent control of static frequency conversion of a gas turbine unit, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a method for intelligent control of static frequency conversion of a gas turbine unit as proposed in the above embodiment.

[0076] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, an intelligent control method for static frequency conversion of a gas turbine unit as proposed in the above embodiment is implemented.

[0077] The storage medium proposed in this embodiment and the intelligent control method for static frequency conversion of a gas turbine unit proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0078] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0079] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0080] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0081] Example 2, reference Figure 2 , is an embodiment of the present invention. This embodiment provides an intelligent control method and system for static frequency conversion of a gas turbine unit. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0082] Demonstrate how to use sensors and monitoring equipment to collect the operating data of gas turbine units in real time, and formulate intelligent control strategies through statistical analysis algorithms and maintenance demand prediction models to achieve long-term and stable operation of gas turbine units.

[0083] Six similar gas turbine units were selected for the experiment, marked as A, B, C, D, E, and F. Each unit was equipped with voltage, current, pressure, temperature, vibration, and load sensors to monitor operating data in real time. The experiment lasted for one week, and the data sampling frequency was set to once per minute.

[0084] The experiment was divided into two groups. Units A, C, and E adopted the traditional control method, and units B, D, and F applied the intelligent control strategy of the present invention. The collected raw data was normalized by the preprocessing algorithm, and then the operating status score of each unit was calculated using the statistical analysis algorithm. Based on these scores, the maintenance demand prediction model was used to predict the maintenance demand of each unit, and the control parameters and operating frequency of the inverter were adjusted accordingly. The experimental data are recorded in Table 1 below:

[0085] Table 1 Experimental data record table

[0086]

[0087] According to Table 1, the maintenance requirements are quantified to make the table content more intuitive. The maintenance requirements quantification table is obtained as shown in Table 2:

[0088] Table 2 Maintenance requirements quantification table

[0089] Experimental subjects Quantification of maintenance needs Maintenance requirements A 0.75 high B 0.20 Low C 0.60 high D 0.45 Low E 0.80 high F 0.50 middle

[0090] Through the data recording and analysis in the above embodiments, it can be seen that the operating status scores of units A, C, and E using the traditional control method are higher, indicating that they are closer to abnormal operating conditions, and the maintenance requirements are rated as "high", indicating that immediate maintenance is required. In contrast, the operating status scores of units B, D, and F using the intelligent control strategy of the present invention are lower, indicating that their operating conditions are more stable, and the maintenance requirements are rated as "low" and "medium", indicating that the units are in good operating condition and need preventive maintenance.

[0091] The experimental results show that compared with the traditional control method, the intelligent control strategy of the present invention can effectively reduce the operating status score, reduce the need for emergency maintenance, and improve the stability and reliability of the system. This proves the innovation and advantages of the present invention in improving the response speed of the inverter and predicting maintenance needs.

[0092] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent control method for static frequency conversion of a gas turbine unit, characterized in that: include: Use sensors to collect the operating data of the gas turbine unit in real time and pre-process the operating data; Utilize statistical analysis algorithms to analyze and process operating data in real time to obtain operating status scores; Using the maintenance demand prediction model, the operation status score is calculated to predict maintenance demand; According to the maintenance demand prediction results, formulate intelligent control strategies to improve the response speed of the inverter.

2. The intelligent control method for static frequency conversion of a gas turbine unit according to claim 1, characterized in that: The operation data includes voltage data, current data, pressure data, temperature data, vibration data and load data of the combustion engine unit.

3. The intelligent control method for static frequency conversion of a gas turbine unit according to claim 2, characterized in that: The preprocessing includes normalizing the running data, which is expressed as: Where D(t) represents the running data, t represents the time, and D norm (t) represents the data generated after normalization, μ D represents the mean of the running data D(t), σ D Represents the standard deviation of the running data D(t).

4. The intelligent control method for static frequency conversion of a gas turbine unit according to claim 3, characterized in that: The statistical analysis algorithm is expressed as: Among them, S(t) represents the running status score, k represents the positive coefficient, and w i Represents the weight coefficient, F i (t) represents different eigenvalues ​​at time t.

5. The intelligent control method for static frequency conversion of a gas turbine unit according to claim 4, characterized in that: The maintenance demand prediction model is expressed as: M(t)=αS(t)+(1-α)M hist +γD norm (t) Where M(t) represents the predicted maintenance demand at time t, α represents the adjustment factor, and M hist It represents the weighted average of the measured data, and γ represents the adjustment factor of the normalized data; When M(t)>β, the system determines that the current maintenance state is an emergency maintenance state; when M(t)=β, it is a preventive maintenance state; when M(t)<β, it is a routine maintenance state, where β represents the warning threshold.

6. The intelligent control method for static frequency conversion of a gas turbine unit according to claim 5, characterized in that: The formulation of the intelligent control strategy includes, when the system is judged to be in an emergency maintenance state, formulating the intelligent control strategy according to the current maintenance state, making preliminary adjustments, adjusting the inverter control parameters, improving the response speed, and reducing the system pressure. According to the preliminary adjustment result, if the preliminary adjustment result is that the maintenance is completed, the preliminary adjustment is completed, and a secondary judgment is made, the operation data is recollected, and a new operation state score S(t) is obtained through a statistical analysis algorithm to judge whether the emergency maintenance state is improved. If the operation state score S(t) decreases, a secondary calculation is performed through a maintenance demand prediction model to obtain that the system enters a preventive maintenance state, and the intelligent control strategy is effective; When the system is judged to be in preventive maintenance state, an intelligent control strategy is formulated according to the current maintenance state, and preliminary adjustments are made to adjust the inverter operating frequency to maintain the optimal state and avoid deterioration of the maintenance state. According to the preliminary adjustment results, if the preliminary adjustment results show that the maintenance is completed, the preliminary adjustment is completed, and a secondary judgment is made to re-collect the operating data and obtain a new operating state score S(t) through the statistical analysis algorithm to determine whether the preventive maintenance state has been improved. If the operating state score S(t) decreases, the maintenance demand prediction model is used for secondary calculation to conclude that the system has entered a regular maintenance state, and the intelligent control strategy is effective. When the system is judged to be in a routine maintenance state, an intelligent control strategy is formulated according to the current maintenance state, preliminary maintenance is performed, the inverter control parameters are maintained, and the system is kept in stable operation. According to the preliminary maintenance results, if the preliminary maintenance results remain stable, the preliminary maintenance is completed, and a secondary judgment is made. The operating data is collected again, and a new operating status score S(t) is obtained through a statistical analysis algorithm to determine whether the routine maintenance state is stable. If the operating status score S(t) is within the normal range, it is recalculated through the maintenance demand prediction model, and it is concluded that the system is in a routine maintenance state, and the intelligent control strategy is effective.

7. The intelligent control method for static frequency conversion of a gas turbine unit according to claim 6, characterized in that: The adjustment of the inverter control parameters is expressed as: Among them, K new Indicates the new inverter control parameters, K old represents the old inverter control parameter, η represents the learning rate, K represents the inverter control parameter, It represents the gradient of the operating status score S(t) to the control parameter K. By calculating the gradient, the control parameter K is adjusted to reduce the operating status score s(t); Adjust the inverter operating frequency as: Among them, f new Indicates the operating frequency of the new inverter, f old represents the operating frequency of the old inverter, b represents the linear correlation coefficient of the operating status score to the operating frequency, a represents the logarithmic correlation coefficient of the operating status score to the operating frequency, and the extreme value of the function is obtained through iterative calculation to find the optimal operating frequency; Maintain the inverter control parameters expressed as: K new =K old -η(S(t)-S target ) Among them, S target Indicates the target operating status score, and determines and maintains the inverter control parameters according to the difference between the operating status score and the target operating status score; When the running status score and the target status score are the same, it means that the inverter control parameters are maintained successfully.

8. A system based on the intelligent control method of static frequency conversion of a gas turbine unit according to any one of claims 1 to 7, characterized in that: include: Preprocessing module, status analysis module, demand forecasting module and intelligent control module; The preprocessing module includes the operation of normalizing and preprocessing the collected operation data to ensure the accuracy and effectiveness of subsequent data analysis; The state analysis module includes using a statistical analysis algorithm to perform real-time analysis and processing on the operating data to obtain the operating state, and identifying the current state of the gas turbine unit through the data analysis algorithm; The demand prediction module includes using a maintenance demand prediction model to calculate the operating status and predict the maintenance demand, and predicting the maintenance demand through the operating data and the operating status results; The intelligent control module includes formulating an intelligent control method according to the maintenance demand prediction results, improving the response speed of the inverter, adjusting the working parameters of the inverter through comprehensive analysis of maintenance prediction data, and realizing intelligent control.

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 intelligent control method for static frequency conversion of a gas turbine unit 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 an intelligent control method for static frequency conversion of a gas turbine unit according to any one of claims 1 to 7 are implemented.

Images