On-line monitoring and evaluating system for frequency modulation and peak regulation parameters

Abstract

The invention relates to a frequency modulation and peak regulation parameter on-line monitoring and evaluating system, and the system comprises a power grid data model which is used for obtaining the difference value between the actual output of a generator set in an initial state and a dispatching issuing value, thereby obtaining the initial power difference value prediction of the generator set; the power prediction model is used for configuring state parameters corresponding to state variables by taking the initial power difference value of the generator set and the monitoring data of the generator set in a real-time operation state as the state variables, and obtaining the power difference value prediction of the current generator set under the set state parameters; the controller is used for optimizing and correcting an AGC (Automatic Gain Control) instruction according to the power difference value of the generator set and a particle swarm algorithm; and the monitoring module is used for monitoring the allocation result of dynamic allocation of the AGC generator set in real time, acquiring corresponding frequency modulation and peak regulation data, and evaluating the stability of the regional power grid within a set time period according to the frequency modulation and peak regulation data.

Description

Technical Field

[0001] The present invention relates to the technical field of on-line monitoring of frequency modulation and peak regulation parameters, and in particular to an on-line monitoring and evaluation system for frequency modulation and peak regulation parameters. Background Art

[0002] Due to the influence of its own energy structure and user-side load characteristics and other factors, the power grid faces a high proportion of coal-fired power generation capacity in the province. The power grid has put forward more stringent requirements on the auxiliary services provided by grid-connected units, and the assessment and evaluation standards for primary frequency regulation and automatic power generation control of grid-connected units are also clearer and stricter. The development of an online monitoring system for frequency regulation and peak-shaving parameters on the power plant side can timely discover problems in the frequency and peak-shaving process of grid-connected units, which will help improve the ability of generator sets to support the safe and stable operation of the power grid and increase the frequency regulation compensation income of generator sets. Summary of the invention

[0003] In view of this, an object of the present invention is to provide an online monitoring and evaluation system for frequency modulation and peak regulation parameters to solve the problems raised in the background technology.

[0004] The main purpose of this application is to provide an online monitoring and evaluation system for frequency and peak regulation parameters, including:

[0005] A power grid data model, wherein the power grid data model is configured to: use multivariate variables constructed in a set input matrix as input configuration (I), use power grid structure characteristic parameters and control coefficients of an AGC system as model parameters (II), and use the adjusted output of a generator set and the exchange power of a tie line as output configuration (III), and input the multivariate variables into the input matrix according to a set rule according to a set configuration module for prediction, thereby obtaining a difference between the actual output of the generator set in an initial state and a value issued by a dispatcher, thereby obtaining a prediction of the initial power difference of the generator set;

[0006] A power prediction model is connected to the power grid data model, and the power prediction model is configured to: use the initial power difference of the generator set and the monitoring data of the real-time operation state of the generator set as state variables, configure the state parameters corresponding to the state variables, and obtain the power difference prediction of the current generator set under the set state parameters;

[0007] A controller is connected to the power prediction model, optimizes and corrects the AGC instructions according to the power difference of the generator set according to the particle swarm algorithm, and dynamically allocates the AGC generator set corresponding to the active power gap of the regional power grid in combination with the AGC regulation rate, response time, regulation accuracy and grid regulation rate of the generator set;

[0008] The monitoring module monitors the dynamic deployment results of the AGC generator sets in real time, obtains the corresponding frequency and peak regulation data, and evaluates the stability of the regional power grid within the set time period based on the frequency and peak regulation data.

[0009] Furthermore, the input configuration using the multivariate variables constructed in the set input matrix includes:

[0010] The difference data between the actual output of the power plant in the same period of history and the value issued by the dispatcher is used as the first variable and configured into the first matrix unit of the input matrix according to the set first configuration channel;

[0011] The preset scheduling value is used as a second variable and configured into a second matrix unit of the input matrix according to a set second configuration channel;

[0012] The state data of the historical operation of the power grid is used as the third variable and configured into the third matrix unit of the input matrix according to the set third configuration channel.

[0013] Furthermore, the grid structure characteristic parameters include: power line parameters, reactor parameters, transformer parameters, generator parameters, load parameters, and system inertia time constant.

[0014] Furthermore, the control coefficients of the AGC system include: a frequency regulation coefficient, a voltage regulation coefficient and a load distribution coefficient of the generator set.

[0015] Furthermore, the configuration module includes:

[0016] The logic controller calls the structure script of the input matrix to obtain the matrix structure of the input matrix and encodes the matrix structure of the input matrix;

[0017] The configuration manager is connected to the logic controller. Under the control of the logic controller, the input matrix is ​​used as a configuration management object. Several configuration channels are configured according to the matrix structure of the input matrix to configure the multivariate variables into the matrix units set by the input matrix according to the matching configuration channels.

[0018] Furthermore, the logic controller associates the matrix units set by the input matrix with a plurality of configuration channels according to the coding correspondence of the matrix structure.

[0019] Furthermore, the difference data between the actual output of the power plant and the dispatched value in the same period of history and the status data of the historical operation of the power grid are obtained in the following way;

[0020] Constructing a historical database, dividing the historical database into a first data storage block and a second data storage block, and configuring the first data storage block and the second data storage block to perform synchronous caching processing according to a set collection rule;

[0021] The data cached in the first data storage block and the second data storage block are pre-processed by a set cleaning module to remove data with inconsistent data formats.

[0022] The cleaned data is identified by using the K-Medoids algorithm for the data stored in the first data storage block and the second data storage block, and the identification results are extracted to obtain the corresponding data features;

[0023] The data features are divided according to the segmentation points in the same way as the collection rules.

[0024] The segmentation points are stored in the first data storage block and the second data storage block as storage nodes.

[0025] Furthermore, the collection rule is to use the collection time set when the actual output of the power plant and the dispatched value are collected as the synchronous collection time of the state data of the historical operation of the power grid;

[0026] At the same time, an independent channel is established based on the data source collected during power grid operation to collect data and perform data format conversion processing, and different formats of data from different collection sources have been converted into the same format data.

[0027] Furthermore, the cleaning module screens the data according to the set data format and clears the data in an unrecognizable data format.

[0028] Furthermore, the K-Medoids algorithm is used to divide the acquisition data transmitted by the same acquisition channel according to the acquisition time setting as the segmentation point.

[0029] The present application can predict the initial power difference of the generator set in the AGC input control state according to data such as fuel blending, historical operation adjustments and historical equipment maintenance, and use the initial power difference of the generator set and the monitoring data of the real-time operation state of the generator set as state variables, configure the state parameters corresponding to the state variables, and obtain the power difference prediction of the current generator set under the set state parameters. It can optimize the coordinated control and thermal logic of various protections that affect the unit's load-changing capacity, and through real-time monitoring and analysis and management of the power generation side machine-grid coordination performance indicators, the primary frequency regulation compensation capacity of the grid-connected generator set is evaluated in real time to achieve the primary frequency regulation contribution rate and small disturbance pass rate of the operating unit, thereby comprehensively improving the unit's rapid load-changing capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the framework principle of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Reference Figure 1 The present application discloses an online monitoring and evaluation system for frequency regulation and peak regulation parameters, including: a power grid data model, wherein the power grid data model is configured to: use multivariate variables constructed in a set input matrix as input configuration (I), use power grid structure characteristic parameters and control coefficients of an AGC system as model parameters (II), and use the output of a generator set after adjustment and the exchange power of a tie line as output configuration (III), and input the multivariate variables into the input matrix according to a set rule according to a set configuration module for prediction, thereby obtaining the difference between the actual output of the generator set in the initial state and the value issued by the dispatcher, thereby obtaining a prediction of the initial power difference of the generator set;

[0033] A power prediction model is connected to the power grid data model, and the power prediction model is configured to: use the initial power difference of the generator set and the monitoring data of the real-time operation state of the generator set as state variables, configure the state parameters corresponding to the state variables, and obtain the power difference prediction of the current generator set under the set state parameters;

[0034] A controller is connected to the power prediction model, optimizes and corrects the AGC instructions according to the power difference of the generator set according to the particle swarm algorithm, and dynamically allocates the AGC generator set corresponding to the active power gap of the regional power grid in combination with the AGC regulation rate, response time, regulation accuracy and grid regulation rate of the generator set;

[0035] The monitoring module monitors the dynamic deployment results of the AGC generator sets in real time, obtains the corresponding frequency and peak regulation data, and evaluates the stability of the regional power grid within the set time period based on the frequency and peak regulation data.

[0036] In the normal operation of the power system, the dispatch center will issue power command values ​​(dispatching issued values) to the generator set based on comprehensive considerations such as load demand and grid stability. The generator set should adjust its actual output according to this command as much as possible. However, due to the physical characteristics of the generator set itself and the influence of various complex factors inside and outside the system, the actual output often differs from the dispatching issued value. Generally speaking, a generator set is mainly composed of power parts and generators and other equipment, which are restricted by various factors during operation. To calculate the difference between the two, it is first necessary to obtain the data of the actual output of the generator set and the dispatching issued value. Generally, these key data are obtained through the generator set monitoring system. Such monitoring systems usually cover the measurement functions of various key parts and operating parameters of the generator set. For example, for thermal power units, sensors can be installed at the generator end, steam pipes, cooling water systems and other locations to accurately collect raw data such as voltage, current, temperature, and pressure. Then, the actual output is calculated from these raw data through various algorithms and models. The dispatching issued value can be directly obtained from the relevant system of the power grid dispatch center. In the power grid dispatching system, dispatching instructions for different generator sets will be generated and recorded in real time for easy query and call.

[0037] The load and stability of the power grid also have a significant impact on the prediction of the power difference of the generator set. When the load of the power grid changes dramatically, the dispatch center will frequently adjust the dispatch value of the generator set, but the response speed of the generator set is not instantaneous, and the difference between the actual output and the dispatch value is generated during the adjustment process. For example, during the morning peak period, the power load suddenly increases a lot, and the generator set needs to gradually increase its output, but it may not be able to keep up with the dispatch instructions for a while, so that the power difference before and after the peak period will show complex fluctuations. In addition, factors such as the network structure and line loss of the power grid will also affect the efficiency of the generator set in receiving dispatch instructions and outputting electricity, indirectly causing the difference between the actual output and the dispatch value.

[0038] To obtain the initial power difference prediction of the generator set, a common way is to establish a prediction model based on historical data through data mining. By collecting the data of the actual output of the generator set in the past and the dispatched value, the historical power difference sequence is first calculated. When obtaining these historical data, it is necessary to cover data under various operating conditions, such as normal operating conditions, fault conditions, and conditions under different load levels. Then, after processing the data, such as feature extraction, data normalization and other preprocessing operations, a suitable prediction model can be selected. In order to select the best model, it is generally necessary to go through the accuracy evaluation link. Taking the neural network as an example, the processed historical power difference data can be divided according to a certain proportion (for example, 80% as a training set and 20% as a test set) for training and testing the neural network, and the structure (such as the number of layers, the number of neurons, etc.) and parameters (such as learning rate, weight initialization, etc.) of the neural network are adjusted to enable the neural network to achieve better prediction accuracy on the test set. After obtaining the trained prediction model, input the relevant influencing factor data at the current moment or the upcoming moment (such as the current unit status data, environmental data, grid operation status data, etc.), and the model can predict the future initial power difference of the generator set based on these input feature data.

[0039] The configuration module can be regarded as a system management unit, which is responsible for managing various settings, parameters and rules related to prediction. The configuration module determines the operation mode of many links in the entire prediction process. It can set the parameter range of various input variables (such as variables representing the status of the generator set, environmental factor variables, etc.), data collection frequency, data storage format and path and other related settings. And it can also determine the category, structure and parameter selection related settings of the prediction model.

[0040] Furthermore, the input configuration using the multivariate variables constructed in the set input matrix includes:

[0041] The difference data between the actual output of the power plant in the same period of history and the value issued by the dispatcher is used as the first variable and configured into the first matrix unit of the input matrix according to the set first configuration channel;

[0042] The preset scheduling value is used as a second variable and configured into a second matrix unit of the input matrix according to a set second configuration channel;

[0043] The state data of the historical operation of the power grid is used as the third variable and configured into the third matrix unit of the input matrix according to the set third configuration channel.

[0044] Furthermore, the grid structure characteristic parameters include: power line parameters, reactor parameters, transformer parameters, generator parameters, load parameters, and system inertia time constant.

[0045] Among them, the power line parameters mainly include resistance, inductance (reactance), conductance (susceptance), etc. These parameters are evenly distributed along the length of the line. Specifically: Resistance: related to the length and material of the wire, indicating the energy loss when the current passes through the line. Inductance (reactance): The ability to hinder the flow of current, usually calculated by the reactance per unit length of each phase wire. Conductance (susceptance): Determined by the leakage current and corona phenomenon along the insulator, as well as the capacitance between the wires and between the wires and the ground.

[0046] The main parameter of the reactor is its reactance value, which is used to limit the short-circuit current. The reactor is composed of an inductor coil with very small resistance, and its equivalent circuit can be represented by reactance. The reactance value of the reactor can be obtained by the rated voltage, rated current and reactance percentage on the nameplate.

[0047] The parameters of the transformer include resistance, conductance, reactance and susceptance. These parameters are usually obtained based on the short-circuit test data and no-load test data provided by the manufacturer on the transformer nameplate. Specific parameters include: Rated capacity: the maximum capacity of the transformer when it is in long-term operation. Rated voltage: the working voltage that the transformer can withstand when it is in long-term operation. Rated current: the working current allowed to pass for a long time under the conditions of rated capacity and allowable temperature rise. Short-circuit voltage: also known as impedance voltage, which is the percentage of the ratio of the primary voltage to the rated voltage when the secondary winding of the transformer is short-circuited. No-load current: the current passing through the primary winding when the transformer is at the rated voltage on the primary side and the secondary winding is unloaded. No-load loss (iron loss): the loss when the secondary side of the transformer is open and the rated voltage is applied to the primary side. Short-circuit loss (copper loss): the loss caused by the resistance of the transformer coil.

[0048] The parameters of the generator are usually provided by the manufacturer, including the rated capacity, rated active power, rated power factor, rated voltage and reactance percentage of the generator.

[0049] Load parameters can usually be expressed in terms of constant power.

[0050] The system inertia time constant is a parameter that reflects the inertia characteristics of the power system. It is related to the rotational inertia of the system's rotating equipment (such as generators) and the total installed capacity. This parameter is an important indicator for analyzing the dynamic behavior and stability of the power system.

[0051] Furthermore, the control coefficients of the AGC system include: a frequency regulation coefficient, a voltage regulation coefficient and a load distribution coefficient of the generator set.

[0052] The frequency regulation coefficient is an important parameter that reflects the generator set's ability to respond to system frequency changes. It determines how the generator set adjusts its output power to restore the frequency to the normal range when the system frequency deviates from the rated value. In the AGC system, the frequency regulation coefficient directly affects the system's frequency stability.

[0053] The voltage regulation factor is a parameter that measures the generator set's ability to respond to system voltage changes. It determines how the generator set adjusts its reactive power output to restore the voltage to the normal range when the system voltage deviates from the rated value. Voltage regulation is important for ensuring the voltage stability and power quality of the power system.

[0054] The load sharing factor refers to how the total load is reasonably distributed among the generator sets in a multi-unit power system based on their characteristics and current operating status. This factor ensures that while meeting system demand, each unit can operate efficiently and economically, avoiding overloading or underloading of individual units.

[0055] Furthermore, the configuration module includes:

[0056] The logic controller calls the structure script of the input matrix to obtain the matrix structure of the input matrix and encodes the matrix structure of the input matrix;

[0057] The configuration manager is connected to the logic controller. Under the control of the logic controller, the input matrix is ​​used as a configuration management object. Several configuration channels are configured according to the matrix structure of the input matrix to configure the multivariate variables into the matrix units set by the input matrix according to the matching configuration channels.

[0058] Furthermore, the logic controller associates the matrix units set by the input matrix with a plurality of configuration channels according to the coding correspondence of the matrix structure.

[0059] Furthermore, the difference data between the actual output of the power plant and the dispatched value in the same period of history and the status data of the historical operation of the power grid are obtained in the following way;

[0060] Constructing a historical database, dividing the historical database into a first data storage block and a second data storage block, and configuring the first data storage block and the second data storage block to perform synchronous caching processing according to a set collection rule;

[0061] The data cached in the first data storage block and the second data storage block are pre-processed by a set cleaning module to remove data with inconsistent data formats.

[0062] The cleaned data is identified by using the K-Medoids algorithm for the data stored in the first data storage block and the second data storage block, and the identification results are extracted to obtain the corresponding data features;

[0063] The data features are divided according to the segmentation points in the same way as the collection rules.

[0064] The segmentation points are stored in the first data storage block and the second data storage block as storage nodes.

[0065] Furthermore, the collection rule is to use the collection time set when the actual output of the power plant and the dispatched value are collected as the synchronous collection time of the state data of the historical operation of the power grid;

[0066] At the same time, an independent channel is established to collect data from the data source during power grid operation and convert the data format, so that data of different formats from different collection sources can be converted into data of the same format. Power grid operation data collection mainly comes from various links of power production and power use, such as power generation, transmission, transformation, distribution, power consumption and dispatching. The collected raw data may contain multiple formats and need to be filtered, cleaned, converted and standardized in order to convert it into standard data formats and units.

[0067] Furthermore, the cleaning module screens the data according to the set data format and clears the data in an unrecognizable data format.

[0068] Furthermore, the K-Medoids algorithm is used to divide the collected data transmitted by the same collection channel according to the collection time setting as the segmentation point. In data collection and processing, it is often necessary to extract information about data features from continuous data transmitted by the same collection channel. In order to process and analyze these data more effectively, it is usually necessary to divide the data according to the collection time setting as the segmentation point. Data segmentation can not only reduce the complexity of data processing, but also improve the accuracy of data analysis and mining. Assume that the collected data transmitted from the same collection channel has a data format of (collection time, data value). The data needs to be divided according to the collection time setting as the segmentation point so that the data points in each segment have similar characteristics.

[0069] The present application can predict the initial power difference of the generator set in the AGC input control state according to data such as fuel blending, historical operation adjustments and historical equipment maintenance, and use the initial power difference of the generator set and the monitoring data of the real-time operation state of the generator set as state variables, configure the state parameters corresponding to the state variables, and obtain the power difference prediction of the current generator set under the set state parameters. It can optimize the coordinated control and thermal logic of various protections that affect the unit's load-changing capacity, and through real-time monitoring and analysis and management of the power generation side machine-grid coordination performance indicators, the primary frequency regulation compensation capacity of the grid-connected generator set is evaluated in real time to achieve the primary frequency regulation contribution rate and small disturbance pass rate of the operating unit, thereby comprehensively improving the unit's rapid load-changing capacity.

[0070] Through the big data platform, a historical database is established. Through statistics and preprocessing of historical data, the improved K-Medoids algorithm is used to extract data from the identification results. The collected data transmitted by an acquisition channel is divided into segmentation points according to the acquisition time setting. According to the piecewise linearization optimization method, the unit operation is optimized and adjusted, which can reduce the fluctuation of main parameters such as unit pressure while ensuring the assessment accuracy; linearity analysis and error analysis of the identification method are performed based on the identification method of characteristic flow area. The error of the identification result based on the regression calculation of Grubbs and fine screen is less than 1.8%; by retrieving the test data The historical data of the superior dispatching organization AGC system or the subordinate dispatching organization AGC system of the trial dispatching organization AGC system is used to build the target AGC system power grid data model according to the difference between the actual output of the power plant in the same period in history and the dispatching value, and the Kalman filtering algorithm is used to predict the power difference. Then, the AGC instructions are corrected with the predicted structure. Combined with the unit AGC regulation rate, response time, regulation accuracy and other indicators, various types of unit combinations are reasonably deployed according to the grid regulation rate requirements, and dynamic deployment of AGC units based on the active power gap of the regional power grid is implemented to ensure that the requirements of the power grid are met.

[0071] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. Frequency modulation and peak regulation parameter online monitoring and evaluation system, characterized in that: include: A power grid data model, wherein the power grid data model is configured to: use multivariate variables constructed in a set input matrix as input configuration (I), use power grid structure characteristic parameters and control coefficients of an AGC system as model parameters (II), and use the adjusted output of a generator set and the exchange power of a tie line as output configuration (III), and input the multivariate variables into the input matrix according to a set rule according to a set configuration module for prediction, thereby obtaining a difference between the actual output of the generator set in an initial state and a value issued by a dispatcher, thereby obtaining a prediction of the initial power difference of the generator set; A power prediction model is connected to the power grid data model, and the power prediction model is configured to: use the initial power difference of the generator set and the monitoring data of the real-time operation state of the generator set as state variables, configure the state parameters corresponding to the state variables, and obtain the power difference prediction of the current generator set under the set state parameters; A controller is connected to the power prediction model, optimizes and corrects the AGC instructions according to the power difference of the generator set according to the particle swarm algorithm, and dynamically allocates the AGC generator set corresponding to the active power gap of the regional power grid in combination with the AGC regulation rate, response time, regulation accuracy and grid regulation rate of the generator set; The monitoring module monitors the dynamic deployment results of the AGC generator sets in real time, obtains the corresponding frequency and peak regulation data, and evaluates the stability of the regional power grid within the set time period based on the frequency and peak regulation data.

2. The frequency modulation and peak regulation parameter online monitoring and evaluation system according to claim 1 is characterized in that: The input configurations include: The difference data between the actual output of the power plant in the same period of history and the value issued by the dispatcher is used as the first variable and configured into the first matrix unit of the input matrix according to the set first configuration channel; The preset scheduling value is used as a second variable and configured into a second matrix unit of the input matrix according to a set second configuration channel; The state data of the historical operation of the power grid is used as the third variable and configured into the third matrix unit of the input matrix according to the set third configuration channel.

3. The frequency modulation and peak regulation parameter online monitoring and evaluation system according to claim 1 is characterized in that: The grid structure characteristic parameters include: power line parameters, reactor parameters, transformer parameters, generator parameters, load parameters, and system inertia time constant.

4. The frequency modulation and peak regulation parameter online monitoring and evaluation system according to claim 1 is characterized in that: The control coefficients of the AGC system include: a frequency regulation coefficient, a voltage regulation coefficient and a load distribution coefficient of the generator set.

5. The frequency modulation and peak regulation parameter online monitoring and evaluation system according to claim 1 is characterized in that: The configuration module includes: The logic controller calls the structure script of the input matrix to obtain the matrix structure of the input matrix and encodes the matrix structure of the input matrix; The configuration manager is connected to the logic controller. Under the control of the logic controller, the input matrix is ​​used as a configuration management object. Several configuration channels are configured according to the matrix structure of the input matrix to configure the multivariate variables into the matrix units set by the input matrix according to the matching configuration channels.

6. The frequency modulation and peak regulation parameter online monitoring and evaluation system according to claim 5 is characterized in that: The logic controller associates the matrix units set by the input matrix with a plurality of configuration channels according to the coding correspondence of the matrix structure.

7. The frequency modulation and peak regulation parameter online monitoring and evaluation system according to claim 2 is characterized in that: The difference data between the actual output of the power plant and the dispatched value in the same period of history and the status data of the historical operation of the power grid are obtained in the following way; Constructing a historical database, dividing the historical database into a first data storage block and a second data storage block, and configuring the first data storage block and the second data storage block to perform synchronous caching processing according to a set collection rule; The data cached in the first data storage block and the second data storage block are pre-processed by a set cleaning module to remove data with inconsistent data formats. The cleaned data is identified by using the K-Medoids algorithm for the data stored in the first data storage block and the second data storage block, and the identification results are extracted to obtain the corresponding data features; The data features are divided according to the segmentation points in the same way as the collection rules. The segmentation points are stored in the first data storage block and the second data storage block as storage nodes.

8. The frequency modulation and peak regulation parameter online monitoring and evaluation system according to claim 7 is characterized in that: The collection rule is to use the collection time set when the actual output of the power plant and the dispatched value are collected as the synchronous collection time of the status data of the historical operation of the power grid; At the same time, an independent channel is established based on the data source collected during power grid operation to collect data and perform data format conversion processing, and different formats of data from different collection sources have been converted into the same format data.

9. The frequency modulation and peak regulation parameter online monitoring and evaluation system according to claim 8 is characterized in that: The cleaning module screens the data according to the set data format and clears the data in an unrecognizable data format.

10. The frequency modulation and peak regulation parameter online monitoring and evaluation system according to claim 8, characterized in that: The K-Medoids algorithm is used to divide the acquisition data transmitted by the same acquisition channel into segmentation points according to the acquisition time setting.

Images