Intelligent optimization method for debugging communication power supply of super-high voltage transformer substation

Abstract

The application discloses a kind of intelligent optimization ultrahigh voltage substation communication power supply debugging method, the method includes the following steps: S1, constructs the digital twin of ultrahigh voltage substation communication power supply, and the operating state of communication power supply is mapped in real time by the digital twin;S2, the key debugging parameter and corresponding double-band signal difference value of communication power supply under preset standard working condition are synchronously collected;S3, mapping model of double-band signal difference value and debugging parameter deviation is constructed based on deep learning network, the present application relates to electric power system technical field.The ultrahigh voltage substation communication power supply debugging method of a kind of intelligent optimization, reaches by constructing the digital twin of ultrahigh voltage substation communication power supply, so that the debugging process can realize intelligent, automation management, with the real-time operating state mapping of digital twin, debugging personnel can more intuitively, real-time master power supply operating state and debugging parameter, to optimize debugging decision.

Description

Technical Field

[0001] This invention relates to the field of power systems, and more specifically, to a method for intelligently optimizing the commissioning of communication power supplies in ultra-high voltage substations. Background Technology

[0002] With the intelligent development of modern power systems, substations, as core facilities for power transmission, undertake important functions of power distribution and monitoring. The communication power supply system within a substation, as a key component ensuring communication stability and power system security, typically involves complex parameter configuration and manual operation during its commissioning process.

[0003] Traditional debugging methods typically require technicians to rely on experience and manual measurement to adjust key power supply parameters, such as the threshold of the power supply regulator module, the capacitance of the filter capacitor, and the trigger current of the protection circuit. This method is inefficient and prone to errors, leading to inaccurate or unstable results that affect the normal operation of the system.

[0004] Furthermore, with increasing demands for efficiency, stability, and accuracy in communication power supplies, traditional commissioning methods are no longer sufficient to meet the precise adjustment requirements of modern substations. To improve commissioning efficiency and accuracy, the introduction of digital twin technology and deep learning models has become a trend. By mapping the power supply's operating status in real time and combining it with automated adjustments, the commissioning process can be effectively optimized, reducing the impact of human factors. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent and optimized commissioning method for communication power supply in ultra-high voltage substations. This method solves the problem that traditional commissioning methods often require technicians to rely on experience and manual measurement to adjust key power supply parameters, resulting in low commissioning efficiency and a high risk of errors, leading to inaccurate or unstable results that affect the normal operation of the system.

[0006] This invention achieves the above objective through the following technical solution: a method for intelligently optimizing the commissioning of communication power supply in ultra-high voltage substations, the method comprising the following steps:

[0007] S1. Construct a digital twin of the communication power supply of the ultra-high voltage substation, and map the operating status of the communication power supply in real time through the digital twin;

[0008] S2. Synchronously acquire the key debugging parameters of the communication power supply under preset standard operating conditions and the corresponding dual-band signal difference. ;

[0009] S3. Construct a mapping model between the difference between dual-band signals and the deviation of debugging parameters based on a deep learning network;

[0010] S4. Obtain the real-time dual-band signal difference during the communication power supply debugging process. The corresponding debugging parameter deviation is obtained by inputting it into the mapping model;

[0011] S5. Automatically correct the key debugging parameters of the communication power supply according to the deviation of the debugging parameters, and complete the debugging of the substation communication power supply.

[0012] Furthermore, step S1 involves constructing a digital twin and achieving real-time mapping of its operational status, specifically including the following steps:

[0013] Obtain the physical structure parameters, electrical performance parameters, and historical operation data of the communication power supply in ultra-high voltage substations, and establish a digital twin framework that matches the physical power supply;

[0014] A real-time data acquisition interface is embedded in the digital twin to collect the operating status parameters of the physical power supply through sensing devices;

[0015] The collected operating status parameters are transmitted to the digital twin in real time, realizing the synchronous mapping between the digital twin and the physical power supply operating status.

[0016] Furthermore, the operating status parameters include at least the input voltage, output current, and internal temperature.

[0017] Furthermore, in step S2, the key debugging parameters and the difference between the dual-band signals are collected synchronously. Specifically, it includes the following steps:

[0018] Set the standard operating conditions for the substation's communication power supply;

[0019] Determine key debugging parameters;

[0020] A dual-band signal acquisition device is used to simultaneously acquire the high-frequency and low-frequency signals of the communication power supply under standard operating conditions, and calculate the voltage difference between the two signals, which is denoted as the dual-band signal difference ΔU.

[0021] Establish a parameter-signal database to store key debugging parameters acquired synchronously and their corresponding dual-band signal differences. .

[0022] Furthermore, the standard operating conditions include: input voltage stability range, output current rated range, and ambient temperature range; the key debugging parameters include: power supply regulator module threshold, filter capacitor value, and protection circuit trigger current.

[0023] Furthermore, the frequency range of the high-frequency band signal is 1MHz-10MHz, and the frequency range of the low-frequency band signal is 50Hz-500Hz; the sample size of the parameter-signal database is not less than 1000 groups.

[0024] Furthermore, step S3 involves constructing a mapping model based on a deep learning network, specifically including:

[0025] Dual-band signal difference in parameter-signal database Perform normalization processing;

[0026] The deviation of the debugging parameters is defined as the difference between the actual debugging parameters and the standard debugging parameters;

[0027] Construct a deep learning network architecture, which includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer;

[0028] The parameter-signal database is divided into a training set and a test set. The deep learning network model is trained using the training set, and the model parameters are optimized through error until the prediction error of the model on the test set meets the preset requirements.

[0029] Furthermore, the calculation formula for the normalization process is as follows:

[0030] ,

[0031] in, For the database The minimum value, For the database The maximum value;

[0032] The formula for calculating the deviation of the debugging parameters is:

[0033] ,

[0034] in These are the actual debugging parameters. These are the standard debugging parameters.

[0035] Furthermore, in step S4, the real-time dual-band signal difference is obtained and the debugging parameter deviation is calculated, specifically including...

[0036] During the debugging of the communication power supply, the dual-band signal acquisition device is activated to collect the high-frequency and low-frequency signals of the current power supply in real time and calculate the real-time dual-band signal difference. ;

[0037] right After normalization, we get ;

[0038] Will The input is given to the trained mapping model, and the model outputs the current corresponding deviation of the debugging parameters. .

[0039] Furthermore, step S5 automatically corrects key debugging parameters, specifically including:

[0040] According to the deviation of the debugging parameters Calculate the key debugging parameters after correction. The calculation formula is:

[0041] ,

[0042] in, Standard debugging parameters;

[0043] Through the control interface of the digital twin, the corrected key debugging parameters are sent to the control module of the physical communication power supply to realize automatic parameter adjustment;

[0044] After adjustment, the real-time dual-band signal difference of the power supply was collected again. Input the mapping model to verify whether the deviation meets the preset standard. If it does, the debugging is complete. If it does not, repeat the parameter correction steps until the deviation meets the standard.

[0045] The beneficial effects of this invention are as follows:

[0046] 1. This invention constructs a digital twin of the communication power supply in ultra-high voltage substations, enabling intelligent and automated management of the commissioning process. With the help of the real-time operation status mapping of the digital twin, commissioning personnel can more intuitively and in real time grasp the operating status and commissioning parameters of the power supply, thereby optimizing commissioning decisions.

[0047] 2. By applying deep learning models, a precise mapping model between parameters and signals can be established based on a large amount of collected data. This allows for real-time prediction and correction of debugging parameter deviations, thereby improving the accuracy and efficiency of debugging, greatly reducing manual intervention and experience errors, and enhancing the level of automation in debugging.

[0048] 3. This invention achieves precise control of power supply debugging by acquiring the difference between dual-band signals in real time and mapping it to the deviation of debugging parameters, which significantly reduces debugging errors, improves the stability of substation communication power supply, and avoids power supply failures or communication interruptions caused by parameter errors.

[0049] 4. By establishing a database containing dual-band signal difference and debugging parameter data, this invention provides rich data support for the debugging process, which can provide a basis for future maintenance and optimization. The deep learning-based model continuously learns and optimizes, which can continuously improve the accuracy and intelligence level of the debugging process.

[0050] 5. Since the calibration process of the debugging parameters is based on digital twins and deep learning models, the entire debugging process has high repeatability and high reliability, which can ensure the stability and consistency of the debugging results each time and avoid deviations caused by human factors. Attached Figure Description

[0051] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0052] Figure 1 This is a flowchart of the method of the present invention;

[0053] Figure 2 This is a flowchart illustrating the construction process of the digital twin of this invention.

[0054] Figure 3 This is the process for constructing the mapping model based on a convolutional neural network in this invention;

[0055] Figure 4 This is a flowchart illustrating the application of the mapping model of this invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described 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 are within the scope of protection of the present invention.

[0057] Example 1:

[0058] Please see Figure 1-4 This invention provides a technical solution: a method for intelligently optimizing the commissioning of communication power supply in ultra-high voltage substations, the method comprising:

[0059] S1. Construct a digital twin of the communication power supply in the ultra-high voltage substation, and map the operating status of the communication power supply in real time through the digital twin;

[0060] Among them, a digital twin is a virtual representation of a physical entity. It integrates information such as the physical entity's geometric structure, physical attributes, behavioral rules, and environmental interactions. Through the digital twin, the operating status of the physical entity can be simulated, monitored, analyzed, and optimized in real time. Real-time mapping refers to the fact that the digital twin can receive and reflect the operating status data of the physical entity in real time, such as voltage, current, and temperature, to ensure that the state between the digital twin and the physical entity is synchronized.

[0061] S2. Synchronously acquire the key debugging parameters of the communication power supply under standard operating conditions and the corresponding dual-band signal difference. ;

[0062] Among them, standard operating conditions refer to the environmental conditions and operating parameter ranges that the communication power supply should meet when it is working normally, such as the stable range of input voltage, the rated range of output current, and the range of ambient temperature; key debugging parameters refer to the key parameters that affect the performance of the communication power supply, such as the threshold of the power supply voltage regulator module, the capacitance of the filter capacitor, and the trigger current of the protection circuit; dual-band signal difference refers to the voltage difference between the high-frequency band signal and the low-frequency band signal of the communication power supply acquired at the same time. The high-frequency band signal is usually used to reflect the dynamic response characteristics of the power supply, while the low-frequency band signal is used to reflect the steady-state characteristics of the power supply.

[0063] S3. Construct a mapping model between the difference between dual-band signals and the deviation of debugging parameters based on a convolutional neural network;

[0064] Among them, convolutional neural networks are a type of deep learning model that is particularly suitable for processing data with a grid structure; the mapping model refers to a mathematical model obtained through training that can describe the relationship between the difference between the input dual-band signals and the deviation of the output tuning parameters; the tuning parameter deviation refers to the difference between the actual tuning parameters and the standard tuning parameters, which is used to measure the amount of parameter adjustment during the tuning process;

[0065] S4. Obtain the real-time dual-band signal difference during the communication power supply debugging process. The corresponding debugging parameter deviation is obtained by inputting it into the mapping model;

[0066] Among them, the real-time dual-band signal difference is the voltage difference between the high-frequency band signal and the low-frequency band signal that is collected in real time during the communication power supply debugging process;

[0067] S5. Automatically correct the key debugging parameters of the communication power supply according to the deviation of the debugging parameters, and complete the debugging of the communication power supply of the ultra-high voltage substation.

[0068] Automatic calibration refers to automatically adjusting the key debugging parameters of the communication power supply based on the deviation of the debugging parameters output by the mapping model, so as to achieve the preset performance indicators.

[0069] It should be noted that during operation, the digital twin maps the communication power supply's operating status in real time, avoiding frequent shutdowns for testing and shortening the debugging cycle. A convolutional neural network is used to construct a mapping model between the difference between the two frequency band signals and the deviation of debugging parameters, reducing human error and improving the accuracy of parameter correction. By collecting the difference between the two frequency band signals in real time and automatically inputting it into the mapping model, automatic calculation of debugging parameter deviations and automatic correction of key debugging parameters are achieved, reducing reliance on technical personnel. Precise debugging parameter correction helps optimize the communication power supply's performance, improve voltage regulation accuracy and filtering effect, thereby enhancing the stability of the entire power system.

[0070] In one embodiment, a digital twin of the communication power supply of an ultra-high voltage substation is constructed, and the operating status of the communication power supply is mapped in real time through the digital twin. Specifically, this includes the following steps:

[0071] Obtain the physical structure parameters, electrical performance parameters, and historical operation data of the communication power supply of ultra-high voltage substations, and establish a digital twin framework that matches the physical power supply in a 1:1 ratio;

[0072] A real-time data acquisition interface is embedded in the digital twin to collect the operating status parameters of the physical power supply through sensors. The operating status parameters include input voltage, output current, and internal temperature.

[0073] The collected operating status parameters are transmitted to the digital twin in real time, realizing synchronous mapping between the digital twin and the physical power supply operating status, with a mapping delay of no more than 50ms.

[0074] This design, by establishing a 1:1 matching digital twin framework and embedding a real-time data acquisition interface, enables the system to synchronize the operating status parameters of the physical power supply with a delay of no more than 50ms. This achieves real-time bidirectional interaction between the physical and virtual spaces, avoiding the frequent intervention of physical equipment in traditional debugging, and ensuring the dynamic response capability of the debugging process through high-precision data mapping, thus providing a reliable data foundation for subsequent parameter optimization.

[0075] In one embodiment, the key debugging parameters of the communication power supply under standard operating conditions and the corresponding dual-band signal difference are synchronously collected. Specifically, it includes:

[0076] The standard operating conditions for the communication power supply of the ultra-high voltage substation are set, including: input voltage stability range of 220V±5%, output current rated value, and ambient temperature of 25℃±2℃.

[0077] Determine the key debugging parameters, which include: the threshold of the power supply regulator module, the capacitance of the filter capacitor, and the trigger current of the protection circuit.

[0078] A dual-band signal acquisition device is used to simultaneously acquire high-frequency and low-frequency signals from the communication power supply under standard operating conditions. The high-frequency signal ranges from 1MHz to 10MHz, and the low-frequency signal ranges from 50Hz to 500Hz. The voltage difference between the two signals is calculated and recorded as the dual-band signal difference. ;

[0079] Establish a parameter-signal database to store key debugging parameters acquired synchronously and their corresponding dual-band signal differences. The database sample size is no less than 1000 groups.

[0080] This design allows for the simultaneous acquisition of signal differences between high-frequency (1MHz-10MHz) and low-frequency (50Hz-500Hz) bands under standard operating conditions (input voltage 220V±5%, output current rated value, ambient temperature 25℃±2℃). A parameter-signal database with ≥1000 samples is established. Through multi-band signal fusion analysis, the coupling relationship between the dynamic and steady-state characteristics of the power supply can be captured. Combined with a large sample database (≥1000 samples), the generalization ability of the model training can be improved, providing more comprehensive feature inputs for subsequent convolutional neural networks and enhancing the accuracy of parameter deviation prediction.

[0081] In one embodiment, constructing a mapping model between the difference in dual-band signals and the deviation of tuning parameters based on a convolutional neural network includes the following steps:

[0082] Dual-band signal difference in parameter-signal database Normalization is performed using the following formula:

[0083] ,

[0084] in, For the database The minimum value, For the database The maximum value;

[0085] The deviation of the debugging parameters is defined as the difference between the actual debugging parameters and the standard debugging parameters, that is:

[0086] ,

[0087] in These are the actual debugging parameters. Standard debugging parameters;

[0088] Construct a convolutional neural network architecture, which includes an input layer, two convolutional layers, one pooling layer, two fully connected layers, and an output layer;

[0089] The input layer is used to receive the normalized... The two convolutional layers have kernel sizes of 3×1 and 5×1, respectively, and use ReLU activation function; the pooling layer uses max pooling with a kernel size of 2×1; the two fully connected layers have 64 and 32 neurons, respectively; the output layer has output tuning parameter deviation. ;

[0090] The parameter-signal database was divided into training and test sets in a 7:3 ratio. The CNN model was trained using the training set, and the model parameters were optimized using mean squared error until the prediction error of the model on the test set was less than 5%.

[0091] This design uses convolutional layers with 3×1 and 5×1 kernels to extract the time-frequency features of the difference between the two frequency bands. It achieves feature dimensionality reduction and bias prediction through max pooling (2×1) and fully connected layers with 64 / 32 neurons. The prediction error of the model on the test set is <5%. It focuses on local signal features through small convolutional kernels (3×1 / 5×1) and enhances nonlinear expression by combining the ReLU activation function. Finally, the output layer is directly associated with the debugging parameter bias, realizing a high-precision mapping from signal difference to parameter bias with an error of <5%, which significantly improves the level of debugging automation.

[0092] In one embodiment, the real-time dual-band signal difference is acquired during the communication power supply debugging process. The input to the mapping model yields the corresponding debugging parameter deviation, specifically including the following steps:

[0093] During the debugging of the communication power supply, the dual-band signal acquisition device is activated to acquire the high-frequency and low-frequency signals of the current power supply in real time and calculate the real-time dual-band signal difference. ;

[0094] Will After processing according to the normalization formula, we obtain... ;

[0095] Will The input is fed into the trained convolutional neural network mapping model, and the model outputs the current corresponding tuning parameter deviation. .

[0096] This design allows for real-time acquisition of high-frequency and low-frequency signals during debugging. The difference is calculated, normalized, and then input into a pre-trained convolutional neural network. The model outputs the debugging parameter deviation in real time. Through real-time signal acquisition and normalization, the influence of dimensional differences on the model input is eliminated. Combined with the pre-trained convolutional neural network, deviation calculation with millisecond-level response can be achieved, providing an immediate basis for subsequent automatic parameter correction and significantly improving debugging efficiency.

[0097] In one embodiment, step S5 includes the following steps:

[0098] According to the deviation of the debugging parameters Calculate the key debugging parameters after correction. The formula is:

[0099] ,

[0100] in, Standard debugging parameters;

[0101] Through the control interface of the digital twin, the corrected key debugging parameters are... The control module of the physical communication power supply is sent to achieve automatic parameter adjustment;

[0102] After adjustment, the real-time dual-band signal difference of the power supply was collected again. Input the mapping model to verify if the deviation is less than 1%. If it is, the debugging is complete. If it is not, repeat the parameter correction steps until the deviation meets the standard.

[0103] This design calculates the corrected parameter values ​​based on the deviation of the debugging parameters, sends them to the physical power supply through the digital twin control interface, and cyclically verifies whether the deviation is less than 1%. The digital twin enables remote parameter sending and linkage with physical devices. Combined with the 1% deviation threshold, a closed-loop control is formed to ensure that the debugging results meet the high-precision requirements with a deviation of less than 1%. This avoids the lag and subjectivity of manual adjustments and significantly improves the reliability of debugging and the stability of power supply operation.

[0104] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] The above embodiments provide a detailed description of the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for intelligently optimizing the commissioning of communication power supply in ultra-high voltage substations, characterized in that, The method includes the following steps: S1. Construct a digital twin of the communication power supply of the ultra-high voltage substation, and map the operating status of the communication power supply in real time through the digital twin; S2. Synchronously acquire the key debugging parameters of the communication power supply under preset standard operating conditions and the corresponding dual-band signal difference. ; S3. Construct a mapping model between the difference between dual-band signals and the deviation of debugging parameters based on a deep learning network; S4. Obtain the real-time dual-band signal difference during the communication power supply debugging process. The corresponding debugging parameter deviation is obtained by inputting it into the mapping model; S5. Automatically correct the key debugging parameters of the communication power supply according to the deviation of the debugging parameters, and complete the debugging of the substation communication power supply.

2. The intelligent optimized ultra-high voltage substation communication power supply debugging method according to claim 1, characterized in that, Step S1 involves constructing a digital twin and achieving real-time mapping of its operational status, specifically including the following steps: Obtain the physical structure parameters, electrical performance parameters, and historical operation data of the communication power supply in ultra-high voltage substations, and establish a digital twin framework that matches the physical power supply; A real-time data acquisition interface is embedded in the digital twin to collect the operating status parameters of the physical power supply through sensing devices; The collected operating status parameters are transmitted to the digital twin in real time, realizing the synchronous mapping between the digital twin and the physical power supply operating status.

3. The intelligent optimized ultra-high voltage substation communication power supply commissioning method according to claim 2, characterized in that: The operating status parameters include at least the input voltage, output current, and internal temperature.

4. The intelligent optimized ultra-high voltage substation communication power supply commissioning method according to claim 1, characterized in that, In step S2, key debugging parameters and the difference between the dual-band signals are collected synchronously. Specifically, it includes the following steps: Set the standard operating conditions for the substation's communication power supply; Determine key debugging parameters; A dual-band signal acquisition device is used to simultaneously acquire the high-frequency and low-frequency signals of the communication power supply under standard operating conditions, and calculate the voltage difference between the two signals, which is denoted as the dual-band signal difference ΔU. Establish a parameter-signal database to store key debugging parameters acquired synchronously and the corresponding differences between the dual-band signals. .

5. The intelligent optimized ultra-high voltage substation communication power supply commissioning method according to claim 4, characterized in that: The standard operating conditions include: input voltage stability range, output current rated range, and ambient temperature range; the key debugging parameters include: power supply regulator module threshold, filter capacitor value, and protection circuit trigger current.

6. The intelligent optimized ultra-high voltage substation communication power supply debugging method according to claim 4, characterized in that, The frequency range of the high-frequency band signal is 1MHz-10MHz, and the frequency range of the low-frequency band signal is 50Hz-500Hz; the sample size of the parameter-signal database is not less than 1000 groups.

7. The intelligent optimized ultra-high voltage substation communication power supply commissioning method according to claim 1, characterized in that, Step S3 involves constructing a mapping model based on a deep learning network, specifically including: Dual-band signal difference in parameter-signal database Perform normalization processing; The deviation of the debugging parameters is defined as the difference between the actual debugging parameters and the standard debugging parameters; Construct a deep learning network architecture, which includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer; The parameter-signal database is divided into a training set and a test set. The deep learning network model is trained using the training set, and the model parameters are optimized through error until the prediction error of the model on the test set meets the preset requirements.

8. The intelligent optimized ultra-high voltage substation communication power supply debugging method according to claim 7, characterized in that, The calculation formula for the normalization process is as follows: ， in, For the database The minimum value, For the database The maximum value; The formula for calculating the deviation of the debugging parameters is: ， in These are the actual debugging parameters. These are the standard debugging parameters.

9. The intelligent optimized ultra-high voltage substation communication power supply debugging method according to claim 1, characterized in that, Step S4 involves acquiring the real-time dual-band signal difference and obtaining the debugging parameter deviation, specifically including... During the debugging of the communication power supply, the dual-band signal acquisition device is activated to acquire the high-frequency and low-frequency signals of the current power supply in real time and calculate the real-time dual-band signal difference. ; right After normalization, we get ; Will The input is given to the trained mapping model, and the model outputs the current corresponding deviation of the debugging parameters. .

10. The intelligent optimized ultra-high voltage substation communication power supply debugging method according to claim 1, characterized in that, Step S5 involves automatically correcting key debugging parameters, specifically including: According to the deviation of the debugging parameters Calculate the key debugging parameters after correction. The calculation formula is: ， in, Standard debugging parameters; Through the control interface of the digital twin, the corrected key debugging parameters are sent to the control module of the physical communication power supply to achieve automatic parameter adjustment; After adjustment, the real-time dual-band signal difference of the power supply was collected again. Input the mapping model to verify whether the deviation meets the preset standard. If it does, the debugging is complete. If it does not, repeat the parameter correction steps until the deviation meets the standard.

Images