Phase change detection method, storage medium and equipment

Abstract

The invention relates to the technical field of electric power, in particular to a commutation detection method, a storage medium and equipment, and the method comprises the steps: achieving the dynamic dual-feature extraction and precise quantitative characterization of an exit valve energy mismatch index and a conduction valve charge injection efficiency in a commutation process through the collaborative analysis of dual-valve current signals; according to the method, the geometric constraint characteristics of the preset hyperbola criterion equation are utilized, commutation state judgment is converted into judgment of the geometrical relationship between the criterion value and the threshold boundary, the problem of insufficient robustness of single electrical quantity monitoring is effectively solved, meanwhile, the detection delay defect of an actual measurement method and the misjudgment risk of a prediction method are eliminated, and the detection accuracy is improved. According to the method, the reliability and the anti-interference capability are remarkably improved while the detection rapidity is guaranteed, collaborative optimization of the rapidity, the reliability and the robustness of commutation detection is achieved, and an effective technical solution is provided for real-time accurate monitoring of the commutation process of the high-voltage direct-current power transmission system.

Description

Technical Field

[0001] This invention relates to the field of power technology, and in particular to a commutation detection method, storage medium, and device. Background Technology

[0002] In high-voltage direct current transmission systems based on grid-commutated converters, the commutation process of the six-pulse converter bridge is a key link in achieving a smooth transfer of DC current from the exit valve to the conduction valve, and its reliability directly affects the stability of system operation.

[0003] Existing commutation detection technologies mainly fall into three categories: 1) Measurement-based methods determine commutation failure by measuring the arc-extinguishing angle γ of the converter valve, but this requires measurement after the commutation window has ended, resulting in inherent detection delays and thus representing post-event diagnosis. 2) Predictive methods predict commutation failure by monitoring abnormal AC commutation voltage, but these are unreliable and prone to false alarms or missed alarms due to factors such as system operating conditions and voltage dip characteristics. 3) Characteristic methods based on single electrical quantities determine commutation failure by monitoring transient characteristics of single signals such as the rate of change of DC current or the waveform of a single valve current. While direct, these methods suffer from poor robustness, difficulty in threshold tuning, and susceptibility to measurement noise and transient disturbances. These methods struggle to balance detection speed, reliability, and robustness, leading to inherent problems in commutation monitoring, including lag, risk of misjudgment, and weak anti-interference capabilities. Consequently, they fail to meet the real-time and accurate monitoring requirements of high-voltage direct current transmission systems. Summary of the Invention

[0004] Based on this, it is necessary to propose a commutation detection method, storage medium, and device to address the above problems. This method effectively overcomes the insufficient robustness of single electrical quantity monitoring, eliminates the detection delay defects of measurement-based methods and the misjudgment risks of prediction-based methods, and significantly improves reliability and anti-interference ability while ensuring detection speed. It achieves synergistic optimization of commutation detection in terms of speed, reliability, and robustness, and provides an effective technical solution for real-time and accurate monitoring of the commutation process in high-voltage direct current transmission systems.

[0005] To achieve the above objectives, the present invention provides a commutation detection method in a first aspect, the method comprising: Acquire the exit valve current signal and the conduction valve current signal of the current commutation event under test, and acquire the steady-state value of the exit valve DC current before the occurrence of the current commutation event under test; Based on the exit valve current signal and the conduction valve current signal of the current commutation event under test, as well as the steady-state value of the exit valve DC current, determine the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test. Substitute the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test into the preset hyperbolic criterion equation to obtain the hyperbolic criterion value; Based on the hyperbolic criterion value, the commutation detection result of the current commutation event to be tested is determined.

[0006] Optionally, determining the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test based on the exit valve current signal and the conduction valve current signal of the current commutation event under test, and the steady-state value of the exit valve DC current, includes: Determine the minimum current value in the exit valve current signal of the current commutation event under test, and the rebound current value after a first preset time interval following the moment corresponding to the minimum current value. Based on the minimum current value and rebound current value in the exit valve current signal of the current commutation event under test, and the steady-state value of the DC current of the exit valve, determine the exit valve energy mismatch index of the current commutation event under test. The starting current value at the start of commutation in the current commutation event to be tested, and the blocked current value after a second preset time interval following the start of commutation are determined. Based on the starting current value and blocked current value in the current commutation event to be tested, and the steady-state value of the DC current of the exit valve, the charge injection efficiency of the current commutation event to be tested is determined.

[0007] Optionally, the exit valve energy mismatch index of the current commutation event under test can be determined using the following formula: ; in, The exit valve energy mismatch index is the current commutation event to be tested. This refers to the moment corresponding to the minimum current value in the exit valve current signal of the current commutation event under test. For the first preset duration, in hour, The minimum current value in the exit valve current signal of the current commutation event under test is... hour, The bounce current value is the value in the exit valve current signal of the current commutation event under test. This is the steady-state value of the DC current of the exit valve.

[0008] Optionally, the charge injection efficiency of the on-valve for the current commutation event under test can be determined using the following formula: ; in, The charge injection efficiency of the on-valve for the current commutation event under test. The commutation start time is [the time specified in the original text]. For the second preset duration, in hour, The starting current value in the conduction valve current signal of the current commutation event under test is... hour, This refers to the obstructed current value in the on-valve current signal of the current commutation event under test. This is the steady-state value of the DC current of the exit valve.

[0009] Optionally, the method further includes: Acquire the exit valve current signal, conduction valve current signal and tag of various historical commutation events, including various normal operating conditions and various commutation failure scenarios; Based on the exit valve current signal and the conduction valve current signal for each historical commutation event, determine the exit valve energy mismatch index and the conduction valve charge injection efficiency for each historical commutation event. The exit valve energy mismatch index, conduction valve charge injection efficiency, and labels of various historical commutation events are input into the initial classification prediction model for training, thus obtaining the target classification prediction model. Based on the model parameters of the target classification prediction model, determine the hyperbolic criterion parameters; Based on the hyperbola criterion parameters, the preset hyperbola criterion equation is constructed.

[0010] Optionally, the model parameters of the target classification prediction model include a support vector set, a label set corresponding to the support vector set, a dual coefficient set corresponding to the support vector set, and a bias term. The hyperbolic criterion parameters include the x-coordinate of the center of the hyperbola, the y-coordinate of the center, the coefficient of the quadratic term on the x-axis, the coefficient of the quadratic term on the y-axis, and the coefficient of the cross product term. Determining the hyperbolic criterion parameters based on the model parameters of the target classification prediction model includes: Substituting the support vector set, the label set corresponding to the support vector set, the dual coefficient set corresponding to the support vector set, and the bias term into the decision function of the target classification prediction model, a second-order polynomial equation is obtained. By finding the center and eliminating the first-order terms of the second-order polynomial equation, the hyperbolic equation is obtained. Based on the hyperbola equation, determine the abscissa of the center, ordinate of the center, coefficient of the quadratic term, coefficient of the quadratic term, and coefficient of the cross product term of the hyperbola.

[0011] Optionally, the preset hyperbolic criterion equation is: ; in, The x-coordinate of the center of the hyperbola in the hyperbola criterion parameters. The ordinate of the center of the hyperbola in the hyperbola criterion parameters is... The coefficient of the quadratic term of the hyperbola in the hyperbola criterion parameters is... The coefficient of the quadratic term of the hyperbola in the hyperbola criterion parameters is... The coefficient of the cross product term of the hyperbola in the hyperbola criterion parameters. The energy mismatch index for the exit valve. To improve the charge injection efficiency of the conduction valve, This is the hyperbolic criterion value.

[0012] Optionally, determining the commutation detection result of the current commutation event to be tested based on the hyperbolic criterion value includes: If the hyperbolic criterion value is greater than or equal to the criterion threshold, the commutation detection result of the current commutation event to be tested is determined to be a commutation failure. If the hyperbolic criterion value is less than the criterion threshold, the commutation detection result of the current commutation event to be tested is determined to be a successful commutation.

[0013] To achieve the above objectives, the present invention provides a commutation detection device in a second aspect, the device comprising: The acquisition module is used to acquire the exit valve current signal and the conduction valve current signal of the current commutation event to be tested, and to acquire the steady-state value of the exit valve DC current before the occurrence of the current commutation event to be tested. The quantization parameter determination module is used to determine the energy mismatch index of the exit valve and the charge injection efficiency of the conduction valve for the current commutation event under test based on the exit valve current signal and the conduction valve current signal of the current commutation event under test, as well as the steady-state value of the DC current of the exit valve. The calculation module is used to substitute the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test into the preset hyperbolic criterion equation to obtain the hyperbolic criterion value. The detection result determination module is used to determine the commutation detection result of the current commutation event to be tested based on the hyperbolic criterion value.

[0014] To achieve the above objectives, the present invention provides, in a third aspect, a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the commutation detection method as described in any one of the first aspects.

[0015] To achieve the above objectives, the present invention provides a computer device in a fourth aspect, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor causes the processor to perform the commutation detection method as described in any one of the first aspects.

[0016] The present invention provides the following advantages: The method acquires the exit valve current signal and the conduction valve current signal of the current commutation event under test, as well as the steady-state value of the exit valve DC current before the occurrence of the current commutation event. Then, based on the exit valve current signal and the conduction valve current signal of the current commutation event under test, and the steady-state value of the exit valve DC current, it determines the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test. Next, it substitutes the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test into a preset hyperbolic criterion equation to obtain the hyperbolic criterion value. Finally, based on the hyperbolic criterion value, it determines the commutation detection result of the current commutation event under test; that is: By collaboratively analyzing the current signals of two valves, dynamic dual-feature extraction and precise quantitative characterization of the energy mismatch index of the exit valve and the charge injection efficiency of the conduction valve during the commutation process are achieved. Utilizing the geometric constraint characteristics of the preset hyperbolic criterion equation, the commutation state judgment is transformed into a geometric relationship judgment between the criterion value and the threshold boundary. This effectively overcomes the insufficient robustness of single electrical quantity monitoring, while eliminating the detection delay defects of the measurement method and the misjudgment risk of the prediction method. While ensuring rapid detection, it significantly improves reliability and anti-interference capability, achieving synergistic optimization of commutation detection among speed, reliability, and robustness. This provides an effective technical solution for real-time and accurate monitoring of the commutation process in high-voltage direct current transmission systems. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] in: Figure 1 This is a schematic diagram of a commutation detection method according to an embodiment of this application; Figure 2 This is a schematic diagram of a commutation detection device according to an embodiment of this application; Figure 3 This is a diagram showing the internal structure of a computer device in some embodiments. Detailed Implementation

[0019] 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 some embodiments of the present invention, and not all embodiments. 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.

[0020] In high-voltage direct current transmission systems based on grid-commutated converters, the commutation process of the six-pulse converter bridge is a key link in achieving a smooth transfer of DC current from the exit valve to the conduction valve, and its reliability directly affects the stability of system operation.

[0021] Existing commutation detection technologies mainly fall into three categories: 1) Measurement-based methods determine commutation failure by measuring the arc-extinguishing angle γ of the converter valve, but this requires measurement after the commutation window has ended, resulting in inherent detection delays and thus representing post-event diagnosis. 2) Predictive methods predict commutation failure by monitoring abnormal AC commutation voltage, but these are unreliable and prone to false alarms or missed alarms due to factors such as system operating conditions and voltage dip characteristics. 3) Characteristic methods based on single electrical quantities determine commutation failure by monitoring transient characteristics of single signals such as the rate of change of DC current or the waveform of a single valve current. While direct, these methods suffer from poor robustness, difficulty in threshold tuning, and susceptibility to measurement noise and transient disturbances. These methods struggle to balance detection speed, reliability, and robustness, leading to inherent problems in commutation monitoring, including lag, risk of misjudgment, and weak anti-interference capabilities. Consequently, they fail to meet the real-time and accurate monitoring requirements of high-voltage direct current transmission systems.

[0022] To address the aforementioned issues, this application proposes a commutation detection method, storage medium, and device, which effectively overcomes the insufficient robustness of single electrical quantity monitoring. It also eliminates the detection delay defects of measurement-based methods and the misjudgment risks of prediction-based methods. While ensuring rapid detection, it significantly improves reliability and anti-interference capabilities, achieving synergistic optimization of commutation detection in terms of speed, reliability, and robustness. This provides an effective technical solution for real-time and accurate monitoring of the commutation process in high-voltage direct current transmission systems. The specific implementation principle will be described in detail in the following embodiments.

[0023] This application provides a commutation detection method in its first aspect.

[0024] Please see Figure 1 The diagram below illustrates a commutation detection method according to an embodiment of this application. The method includes: Step 110: Obtain the exit valve current signal and the conduction valve current signal of the current commutation event under test, and obtain the steady-state value of the exit valve DC current before the current commutation event under test occurs.

[0025] Among them, the current commutation event to be tested refers to the commutation event between the exit valve and the on valve that are currently undergoing commutation, and this commutation event needs to be detected as either a commutation failure or a success.

[0026] Regarding the acquisition method of valve current signal, in some embodiments, when a commutation event occurs, the current signals of the exit valve and the conduction valve corresponding to the commutation event can be collected simultaneously to obtain the exit valve current signal and the conduction valve current signal of the current commutation event to be tested.

[0027] Regarding the method of obtaining the steady-state value of the DC current of the exit valve, in some embodiments, the current signal of the exit valve corresponding to the commutation event can be collected before the commutation event occurs, so as to obtain the steady-state value of the DC current of the exit valve for the current commutation event to be tested; wherein the steady-state value of the DC current of the exit valve is generally a fixed value. Of course, in order to avoid the influence of slight fluctuations in the steady-state value of the DC current of the exit valve, it is generally obtained through real-time monitoring.

[0028] It should be noted that the occurrence of a commutation event is essentially an interaction between the exit valve and the on valve. Therefore, detecting whether the commutation has failed or succeeded is not an isolated behavior of the exit valve. When commutation fails, the current signal of both the exit valve and the on valve will leave a corresponding distortion mark. In this regard, this application performs commutation detection by synchronously acquiring the current signals of the exit valve and the on valve corresponding to the commutation event. Compared with existing commutation detection methods, this can improve the reliability and robustness of the detection.

[0029] It should be further noted that, since this application performs commutation detection by synchronously acquiring the current signals of the exit valve and the on valve corresponding to the commutation event, this joint analysis mechanism of dual valve current signals naturally has common-mode noise suppression capability and higher recognition. Therefore, even if one of the valve current signals is affected by noise or slight disturbance, the reliability and robustness of the detection can be ensured.

[0030] Step 120: Based on the exit valve current signal and conduction valve current signal of the current commutation event under test, as well as the steady-state value of the exit valve DC current, determine the exit valve energy mismatch index and conduction valve charge injection efficiency of the current commutation event under test.

[0031] It should be noted that for the exit valve, if the commutation fails when the exit valve exits, the exit valve current signal will rebound at the moment of exit. The rebounded current is equivalent to applying a reverse electromotive force in the commutation circuit, which will hinder the rise of the conduction valve current signal. Therefore, for the conduction valve, if the commutation fails when the conduction valve is turned on, the current of the conduction valve current signal will be hindered at the moment of conduction.

[0032] Based on the above principles, in some embodiments, the energy mismatch index of the exit valve of the current commutation event under test can be determined based on the current value of the exit valve current signal when exiting and the steady-state value of the exit valve DC current. The charge injection efficiency of the conduction valve of the current commutation event under test can be determined based on the current value of the conduction valve current signal when conducting and the steady-state value of the exit valve DC current.

[0033] Step 130: Substitute the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test into the preset hyperbolic criterion equation to obtain the hyperbolic criterion value.

[0034] The preset hyperbola criterion equation can be obtained and set in advance by the operator based on a large amount of experience, experiments or statistics. Of course, it can also be set in advance by the operator according to actual needs.

[0035] In some embodiments, the determination of the preset hyperbolic criterion equation can be achieved by acquiring the exit valve current signal and the conduction valve current signal of various historical commutation events, as well as the steady-state value of the historical exit valve DC current before the occurrence of various historical commutation events. Then, the exit valve current signal and the conduction valve current signal of each historical commutation event, as well as the steady-state value of the historical exit valve DC current, are used to determine the exit valve energy mismatch index and the conduction valve charge injection efficiency of each historical commutation event. Hyperbolic fitting analysis is then performed on the exit valve energy mismatch index and the conduction valve charge injection efficiency of various historical commutation events to obtain the fixed parameters of the hyperbola. Then, the fixed parameters of the hyperbola are substituted into the hyperbolic equation to obtain the preset hyperbolic criterion equation. The various historical commutation events include various normal operating conditions (i.e., non-commutation failure conditions) and various commutation failure scenarios (i.e., commutation failure scenarios). The fixed parameters include the central abscissa, central ordinate, quadratic coefficient of the abscissa, quadratic coefficient of the ordinate, and cross product coefficient of the hyperbola.

[0036] Step 140: Determine the commutation detection result of the current commutation event to be tested based on the hyperbolic criterion value.

[0037] It should be noted that since the preset hyperbolic criterion equation is determined in advance based on the exit valve current signal and the conduction valve current signal under various normal operating conditions and various commutation failure scenarios, the preset hyperbolic criterion equation is equivalent to using geometric constraints to define the boundary between all commutation detection results being commutation failure and all commutation detection results being commutation success. That is, the curve on one side of the boundary represents all commutation detection results being commutation failure, while the curve on the other side of the boundary represents all commutation detection results being commutation success. When the commutation detection result is commutation failure, the points corresponding to the exit valve energy mismatch index and the conduction valve charge injection efficiency should fall on the curve on one side of the boundary, while when the commutation detection result is commutation success, the points corresponding to the exit valve energy mismatch index and the conduction valve charge injection efficiency should fall on the curve on the other side of the boundary.

[0038] Based on the above principle, in some embodiments, the commutation detection result of the current commutation event to be tested can be determined by comparing the hyperbolic criterion value with the preset threshold. The preset threshold can be obtained and set in advance by the operator based on a large amount of experience, experiments or statistics. Of course, it can also be set in advance by the operator according to actual needs.

[0039] In this embodiment, through the collaborative analysis of dual-valve current signals, dynamic dual-feature extraction and precise quantitative characterization of the energy mismatch index of the exit valve and the charge injection efficiency of the conduction valve during the commutation process are achieved. By utilizing the geometric constraint characteristics of the preset hyperbolic criterion equation, the commutation state judgment is transformed into a geometric relationship judgment between the criterion value and the threshold boundary. This effectively overcomes the insufficient robustness of single electrical quantity monitoring, while eliminating the detection delay defects of the actual measurement method and the misjudgment risk of the predictive method. While ensuring the speed of detection, the reliability and anti-interference ability are significantly improved. This achieves the synergistic optimization of commutation detection in terms of speed, reliability and robustness, and provides an effective technical solution for real-time and accurate monitoring of the commutation process in high-voltage direct current transmission systems.

[0040] In addition to the advantages mentioned above, this commutation detection method also has the following beneficial effects: Adaptability to complex and changing operating conditions: In actual operation, high-voltage direct current transmission systems face various complex and changing operating conditions. The method proposed in this application, by comprehensively considering the current signals of the exit valve and the conduction valve, as well as the steady-state value of the DC current of the exit valve, can more comprehensively reflect the actual situation of the commutation process. This multi-parameter comprehensive analysis method enables the method to accurately judge the commutation state under different operating conditions, without being limited by a single operating condition factor, thus improving the system's adaptability to complex operating environments; Reduced over-reliance on the accuracy of measuring equipment: Traditional feature-based methods based on a single electrical quantity rely on only a single signal for judgment, requiring extremely high accuracy of the measuring equipment. Measurement noise and transient disturbances can easily lead to misjudgment. This application, however, uses joint analysis of dual-valve current signals and, through dynamic dual-feature extraction and precise quantification, combined with a preset hyperbolic criterion equation for judgment, even if the measuring equipment has a certain accuracy error, the synergistic effect of the two parameters and the geometric constraint characteristics of the criterion equation can still ensure the accuracy of the commutation detection results, reducing over-reliance on the accuracy of the measuring equipment and minimizing the impact on the system's performance. The method addresses the detection risks arising from equipment accuracy issues and facilitates early warning and prevention of faults. It not only accurately determines commutation success but also provides detailed information about the commutation process status through analysis of the energy mismatch index of the exit valve and the charge injection efficiency of the conduction valve. When an abnormal trend is detected in the commutation process but before reaching the criteria for commutation failure, an early warning signal can be issued. Maintenance personnel can then take timely measures to troubleshoot and prevent faults, avoiding more serious system failures caused by commutation failure, improving system reliability and stability, and reducing power outages and economic losses due to faults. Furthermore, the method promotes the intelligent development of high-voltage direct current (HVDC) transmission systems. By combining this method with advanced sensor technology, data communication technology, and intelligent algorithms, real-time online monitoring, automatic fault diagnosis, and intelligent decision-making control of the commutation process can be achieved. This helps promote the intelligent development of HVDC transmission systems, improve the system's automation level and operating efficiency, reduce the need for manual intervention, and enhance the overall intelligent management level of the power system.

[0041] In one feasible implementation, step 120 in the above embodiment, determining the exit valve energy mismatch index and conduction valve charge injection efficiency of the current commutation event under test based on the exit valve current signal and conduction valve current signal of the current commutation event under test, and the steady-state value of the exit valve DC current, includes: determining the minimum current value in the exit valve current signal of the current commutation event under test, and the rebound current value after a first preset time interval following the moment corresponding to the minimum current value; and determining the exit valve energy mismatch index of the current commutation event under test based on the minimum current value and rebound current value in the exit valve current signal of the current commutation event under test, and the steady-state value of the exit valve DC current; determining the starting current value in the conduction valve current signal of the current commutation event under test at the start of commutation, and the blocked current value after a second preset time interval following the start of commutation; and determining the conduction valve charge injection efficiency of the current commutation event under test based on the starting current value and blocked current value in the conduction valve current signal of the current commutation event under test, and the steady-state value of the exit valve DC current.

[0042] The first and second preset durations can both be preset by the operator based on extensive experience, experiments, or statistics. Alternatively, they can be preset by the operator according to actual needs.

[0043] Regarding the values ​​of the first preset duration and the second preset duration, in some embodiments, this application preferably sets both the first preset duration and the second preset duration to an extremely short time window, such as setting both the first preset duration and the second preset duration to 20 milliseconds.

[0044] In this embodiment, by accurately extracting the key features of the current signals of the exit valve and the conduction valve, as well as the steady-state value of the DC current of the exit valve, the energy mismatch index and charge injection efficiency are determined, which effectively improves the accuracy and reliability of commutation detection and enhances the system's accuracy in monitoring the commutation process.

[0045] Understandably, accurately extracting the characteristics of the exit valve current signal to determine the energy mismatch index involves identifying the minimum current value in the exit valve current signal of the current commutation event under test, and the rebound current value at a first preset time interval after the moment corresponding to the minimum current value. When commutation fails, the exit valve current signal will rebound at the exit moment. The rebound current in the commutation circuit is equivalent to applying a reverse electromotive force, hindering the rise of the conduction valve current signal. By obtaining the minimum current value and the rebound current value, and combining them with the steady-state value of the exit valve DC current, the exit valve energy mismatch index can be determined. This can more accurately reflect the energy change of the exit valve during commutation, avoiding misjudgments caused by noise or disturbances when relying solely on monitoring a single electrical quantity. This improves the accuracy of commutation state judgment; it accurately extracts the characteristics of the conduction valve current signal to determine the charge injection efficiency: it determines the starting current value of the conduction valve current signal at the start of commutation and the obstructed current value at a second preset time interval after the start of commutation. When commutation fails, the current of the conduction valve current signal at the time of conduction will be obstructed. Based on the starting current value, the obstructed current value, and the steady-state value of the DC current of the exit valve, the charge injection efficiency of the conduction valve is determined. This can more accurately measure the obstruction of the current change of the conduction valve during the commutation process, further enhancing the ability to judge the commutation state, making the commutation detection results more reliable, and effectively improving the accuracy of the system's monitoring of the commutation process.

[0046] In one feasible implementation, the exit valve energy mismatch index of the current commutation event under test is determined using the following formula: ; in, The expulsion valve energy mismatch index is the current commutation event to be tested. This refers to the moment corresponding to the minimum current value in the exit valve current signal of the current commutation event under test. For the first preset duration, in hour, The minimum current value in the exit valve current signal of the current commutation event under test is... hour, This is the bounce current value in the exit valve current signal of the current commutation event under test. This is the steady-state value of the DC current of the exit valve.

[0047] In this embodiment, the energy mismatch index of the exit valve is precisely quantified by a specific formula, which effectively improves the sensitivity and accuracy of commutation detection.

[0048] Understandably, this formula uses the integral of the equal part of the current value within the first preset time period and the first product (the product of the equal part of the steady-state value of the DC current of the exit valve and the first preset time period) as the energy mismatch index of the exit valve, based on the minimum current value and the rebound current value in the exit valve current signal. This quantification method can accurately reflect the energy change of the exit valve during the commutation process, avoiding misjudgments caused by noise or disturbances when relying solely on monitoring a single electrical quantity. This improves the sensitivity and accuracy of commutation status judgment and provides more reliable technical support for commutation detection.

[0049] In one feasible implementation, the charge injection efficiency of the on-valve for the current commutation event under test is determined using the following formula: ; in, The charge injection efficiency of the on-valve for the current commutation event under test. The moment of commutation start. For the second preset duration, in hour, The starting current value in the conduction valve current signal of the current commutation event under test is... hour, This represents the obstructed current value in the on-valve current signal of the current commutation event under test. This is the steady-state value of the DC current of the exit valve.

[0050] It should be noted that, based on the start current value and the blocked current value in the current signal of the conduction valve, the quotient of the integral of the current value within the second preset time period and the second product (the product between the steady-state value of the DC current of the exit valve and the second preset time period) is used as the charge injection efficiency of the conduction valve. This can effectively smooth the interference of high-frequency noise, enhance the stability of the charge injection efficiency of the conduction valve, and achieve ultra-fast and high-reliability detection.

[0051] In this embodiment, the charge injection efficiency of the conduction valve is precisely quantified by a specific formula, which effectively enhances the stability of the detection and achieves ultra-fast and highly reliable detection.

[0052] Understandably, this formula uses the integral of the current value within the second preset time period and the second product (the product between the steady-state value of the DC current of the exit valve and the second preset time period) in the current signal of the conducting valve as the charge injection efficiency of the conducting valve. This quantification method can effectively smooth the interference of high-frequency noise and avoid misjudgment caused by the influence of noise or disturbance on the current signal of the conducting valve, thereby enhancing the stability of the charge injection efficiency of the conducting valve and providing more reliable technical support for commutation detection, realizing ultra-fast and highly reliable detection.

[0053] In one feasible implementation, the method in the above embodiments further includes: acquiring the exit valve current signal, conduction valve current signal, and tags for various historical commutation events, wherein the various historical commutation events include various normal operating conditions and various commutation failure scenarios; determining the exit valve energy mismatch index and conduction valve charge injection efficiency for each historical commutation event based on the exit valve current signal and conduction valve current signal for each historical commutation event; inputting the exit valve energy mismatch index, conduction valve charge injection efficiency, and tags for each historical commutation event into an initial classification prediction model for training to obtain a target classification prediction model; determining hyperbolic criterion parameters based on the model parameters of the target classification prediction model; and constructing a preset hyperbolic criterion equation based on the hyperbolic criterion parameters.

[0054] Among them, various historical commutation events refer to various normal operating conditions (i.e., non-commutation failure conditions) and various commutation failure scenarios (i.e., commutation failure scenarios); the labels here are used to distinguish between normal operating conditions and commutation failure scenarios; the target classification prediction model here refers to a pre-trained model that can output commutation detection results based on the input exit valve energy mismatch index and conduction valve charge injection efficiency; the hyperbolic criterion parameters refer to the various fixed parameters of the hyperbola, such as the hyperbola's center x-coordinate, center y-coordinate, x-squared coefficient, y-squared coefficient, and cross-product coefficient.

[0055] Regarding the selection of the initial classification prediction model, in some embodiments, a Support Vector Machine (SVM) with a second-order multinomial kernel function can be used as the initial classification prediction model.

[0056] In some embodiments, the preset hyperbola criterion equation can be constructed by substituting each parameter in the hyperbola criterion parameters into the hyperbola equation.

[0057] In this embodiment, by using historical data-driven model training and hyperbolic criterion construction, the automatic tuning and dynamic optimization of commutation detection parameters are achieved, which significantly improves the adaptability of the criterion equation and the accuracy of the detection results, while reducing the reliance on human experience.

[0058] Understandably, automated parameter tuning involves collecting historical data covering both normal operation and commutation failure scenarios, calculating the energy mismatch index of the exit valve and the charge injection efficiency of the conduction valve, and inputting this data into an initial classification model (such as a support vector machine) for training. This automatically extracts hyperbolic criterion parameters (such as center coordinates and quadratic coefficients). This process eliminates the need for manual threshold adjustments, avoiding potential biases introduced by empirical settings and improving the scientific rigor and efficiency of parameter tuning. Dynamic adaptation to complex operating conditions is also crucial. Historical data covers diverse operating conditions of the HVDC transmission system (such as voltage fluctuations and load changes). The trained target classification model can capture the statistical patterns of commutation characteristics under different scenarios. Based on this, the constructed hyperbolic criterion equation can dynamically adapt to complex operating conditions in actual operation, ensuring that the criterion boundary can effectively distinguish successful commutation under different conditions. The method enhances robustness by mitigating failures and improves detection accuracy and stability. Model training optimizes the criterion parameters, making the geometric constraints of the hyperbolic equation more closely match the physical characteristics of the actual commutation process. For example, the coefficients of the horizontal / vertical quadratic terms reflect the coupling relationship between energy mismatch and charge injection efficiency, while the coefficients of the cross-product terms capture the interaction between the two parameters. This quantitative relationship makes the criterion value more accurately represent the commutation state, reducing the risk of misjudgment and minimizing the interference of measurement noise on the judgment of a single parameter. It also reduces the need for manual intervention: traditional methods rely on expert experience to set thresholds, while this method uses data-driven automatic generation of criterion parameters, reducing the workload of manual debugging. Maintenance personnel only need to periodically update the historical database to cover new operating conditions to maintain the timeliness of the criterion equation, promoting the development of commutation detection towards intelligence and reduced human intervention.

[0059] In one feasible implementation, the model parameters of the target classification prediction model in the above embodiments include a support vector set, a label set corresponding to the support vector set, a dual coefficient set corresponding to the support vector set, and a bias term. The hyperbolic criterion parameters include the central abscissa, central ordinate, abscissa quadratic coefficient, ordinate quadratic coefficient, and cross-product coefficient of the hyperbola.

[0060] In the above embodiments, determining the hyperbolic criterion parameters based on the model parameters of the target classification prediction model includes: substituting the support vector set, the label set corresponding to the support vector set, the dual coefficient set corresponding to the support vector set, and the bias term into the decision function of the target classification prediction model to obtain a second-order polynomial equation; performing centering and linear term elimination on the second-order polynomial equation to obtain a hyperbolic equation; and determining the abscissa, ordinate, quadratic coefficient, quadratic coefficient, and cross-product coefficient of the hyperbola based on the hyperbolic equation.

[0061] In some embodiments, the following decision function can be used to determine the second-order polynomial equation: ; in, Let be the decision function. For the nth dual coefficient in the set of dual coefficients, For the nth tag in the tag set, It is a second-order polynomial kernel function. For bias terms, The dot product symbol is a vector symbol. The first support vector in the support vector set. This is the second support vector in the support vector set.

[0062] It should be noted that, since the model in this application is a model with a second-order multinomial kernel function, the total number of its support vector set, label set, and dual coefficient set is 2, and the total number of elements in the support vector is also 2.

[0063] It should be further noted that, in the process of simplifying the above-mentioned determination of the second-order polynomial equation, we can first... Substitution In the middle, we get Then Substitution In the middle, and ordered , that is , and then and They are respectively and ,get ,Will And substitute the elements of the dual coefficients, labels, bias terms, and support vectors. And combine like terms to obtain and A second-order polynomial equation with variables; where, For the first element of the nth support vector in the support vector set, It is the second element of the nth support vector in the support vector set.

[0064] In this embodiment, the dynamic optimization and scientific tuning of the commutation detection criterion are realized through the automatic conversion of model parameters to hyperbolic criterion parameters, which significantly improves the adaptability of the criterion equation to complex working conditions and the accuracy of the detection results.

[0065] Understandably, automated parameter generation involves substituting the support vector set, label set, dual coefficient set, and bias term into the decision function to directly derive the second-order polynomial equation and reconstruct it into a hyperbolic equation. This avoids the subjective bias of manually setting thresholds based on experience, making the tuning of criterion parameters (such as center coordinates and quadratic coefficients) more scientific and efficient. Dynamic adaptation to complex operating conditions is also achieved: the hyperbolic criterion parameters are trained using historical data, and their geometric constraint characteristics (such as the horizontal / vertical quadratic coefficients reflecting the coupling relationship between energy and charge, and the cross-product coefficients capturing the interaction of parameters) allow the criterion boundary to dynamically conform to the actual physical process, ensuring effective differentiation between commutation success and failure under different operating conditions. This improves detection accuracy and stability. Qualitatively: The quantized hyperbolic equation optimizes the coupling relationship between the energy mismatch index and charge injection efficiency through geometric constraints, reducing the risk of misjudgment caused by noise interference of a single parameter. For example, the horizontal quadratic coefficient can smooth the influence of current fluctuations, and the vertical quadratic coefficient enhances the sensitivity to energy changes, thereby improving the accuracy of the criterion value in representing the commutation state. Reduced need for manual intervention: Traditional methods rely on experts to manually adjust the threshold, while this method achieves automatic parameter generation through data-driven methods. Only periodic updates to the historical database are needed to maintain the timeliness of the criterion. Maintenance personnel do not need to frequently debug, promoting the development of commutation detection towards intelligence and less human intervention, while improving the system's adaptability to complex environments.

[0066] In one feasible implementation, the preset hyperbolic criterion equation in the above embodiments is: ; in, The x-coordinate of the center of the hyperbola in the hyperbola criterion parameters. The ordinate of the center of the hyperbola in the hyperbola criterion parameters. Here are the coefficients of the quadratic term of the hyperbola in the hyperbola criterion parameters. Here, represents the coefficient of the quadratic term of the hyperbola in the hyperbola criterion parameters. The coefficients of the cross product term of the hyperbola in the hyperbola criterion parameters. The energy mismatch index for the exit valve. To improve the charge injection efficiency of the conduction valve, This is the hyperbolic criterion value.

[0067] In this embodiment, the geometric constraint characteristics of the hyperbolic criterion equation are used to achieve dynamic optimization of the commutation detection boundary, which significantly improves the adaptability and anti-interference ability of the detection results to complex working conditions, while reducing the subjective bias of manual parameter tuning.

[0068] Understandably, the hyperbolic criterion equation dynamically adapts to complex operating conditions: the parameters (such as the horizontal / vertical quadratic coefficients and cross-product coefficients) are trained using historical data. Its geometric constraints allow the criterion boundary to dynamically conform to the actual physical process. For example, the horizontal quadratic coefficient smooths the influence of current fluctuations, while the vertical quadratic coefficient enhances sensitivity to energy changes, thus ensuring effective differentiation between commutation success and failure under different operating conditions. It also improves detection accuracy and stability: the quantized hyperbolic equation optimizes the coupling relationship between the energy mismatch index and charge injection efficiency through geometric constraints, reducing the risk of misjudgment caused by noise interference with a single parameter. The cross-product coefficient captures the interaction between the two parameters, making the criterion more accurate and stable. The data provides a more accurate representation of the commutation state, for example, it can reliably distinguish between commutation failure and success even in noisy environments; it reduces the need for manual intervention: traditional methods rely on experts to manually adjust thresholds, while this method automatically generates criteria parameters through data-driven approaches, avoiding subjective biases that may be introduced by experience-based settings. Maintenance personnel only need to periodically update the historical database to maintain the timeliness of the criteria, promoting the development of commutation detection towards intelligence and reduced human intervention; it enhances anti-interference capabilities: the geometric constraint characteristics of the hyperbolic equation naturally possess common-mode noise suppression capabilities. Even if a valve current signal is interfered with by noise, the criteria value can still remain stable through the compensation effect of another parameter, thereby improving the system's adaptability to complex environments.

[0069] In one feasible implementation, step 140 in the above embodiment, which determines the commutation detection result of the current commutation event to be tested based on the hyperbolic criterion value, includes: if the hyperbolic criterion value is greater than or equal to the criterion threshold, determining that the commutation detection result of the current commutation event to be tested is a commutation failure; if the hyperbolic criterion value is less than the criterion threshold, determining that the commutation detection result of the current commutation event to be tested is a commutation success.

[0070] The criterion threshold can be obtained and preset by the operator based on a large amount of experience, experiments or statistics. Of course, it can also be preset by the operator according to actual needs.

[0071] Regarding the value of the criterion threshold, in some embodiments, this application preferably sets the criterion threshold to 1.

[0072] In this embodiment of the application, by setting a criterion threshold and comparing it with the hyperbolic criterion value, the commutation detection result is quickly and accurately determined, which effectively improves the detection efficiency and reliability.

[0073] Understandably, this method uses the hyperbolic criterion value as the core judgment basis. By directly comparing it with the preset criterion threshold, it can quickly determine the commutation state. When the criterion value is greater than or equal to the threshold, it is judged as a commutation failure; when it is less than the threshold, it is judged as a success. This binary judgment mechanism simplifies the decision-making process and avoids the delay caused by complex calculations. At the same time, since the hyperbolic criterion equation has been trained with historical data to integrate the coupling relationship between the energy mismatch index and the charge injection efficiency, its geometric constraint characteristics enable the criterion value to dynamically adapt to different operating conditions, ensuring the accuracy of the judgment results. Compared with traditional methods that rely on a single parameter or manual experience to set the threshold, this scheme significantly reduces the risk of misjudgment and improves the system's adaptability to complex operating environments through data-driven threshold comparison.

[0074] In a second aspect, this application provides a commutation detection device.

[0075] Please see Figure 2 This is a schematic diagram of a commutation detection device according to an embodiment of this application. The device 210 includes: The acquisition module 211 is used to acquire the exit valve current signal and the conduction valve current signal of the current commutation event to be tested, and to acquire the steady-state value of the exit valve DC current before the current commutation event to be tested occurs. The quantization parameter determination module 212 is used to determine the energy mismatch index of the exit valve and the charge injection efficiency of the conduction valve for the current commutation event under test based on the exit valve current signal and conduction valve current signal of the current commutation event under test, as well as the steady-state value of the exit valve DC current. Substitute the values ​​into the calculation module 213, which is used to substitute the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test into the preset hyperbola criterion equation to obtain the hyperbola criterion value. The detection result determination module is used to determine the commutation detection result of the current commutation event to be tested based on the hyperbolic criterion value.

[0076] In this embodiment of the application, the relevant contents of the above-mentioned acquisition module 211, quantization parameter determination module 212, substitution calculation module 213 and detection result determination module 214 can be found in the following references. Figure 1 The contents of the illustrated embodiments will not be repeated here.

[0077] It should be noted that the device 210 of this application also includes other modules. It can be understood that the method of this application and the device 210 have a one-to-one correspondence. Therefore, the other modules of the device 210 of this application are the contents corresponding to the method of this application in the above embodiments.

[0078] In this embodiment, through the collaborative analysis of dual-valve current signals, dynamic dual-feature extraction and precise quantitative characterization of the energy mismatch index of the exit valve and the charge injection efficiency of the conduction valve during the commutation process are achieved. By utilizing the geometric constraint characteristics of the preset hyperbolic criterion equation, the commutation state judgment is transformed into a geometric relationship judgment between the criterion value and the threshold boundary. This effectively overcomes the problem of insufficient robustness of single electrical quantity monitoring, while eliminating the detection delay defects of the actual measurement device and the misjudgment risk of the predictive device. While ensuring the speed of detection, the reliability and anti-interference ability are significantly improved. This achieves the synergistic optimization of commutation detection in terms of speed, reliability and robustness, and provides an effective technical solution for real-time and accurate monitoring of the commutation process in high-voltage direct current transmission systems.

[0079] In addition to the advantages mentioned above, this commutation detection device also has the following beneficial effects: Adaptability to complex and changing operating conditions: In actual operation, high-voltage direct current transmission systems face various complex and changing operating conditions. The device proposed in this application, by comprehensively considering the current signals of the exit valve and the conduction valve, as well as the steady-state value of the DC current of the exit valve, can more comprehensively reflect the actual situation of the commutation process. This multi-parameter comprehensive analysis method enables the device to accurately determine the commutation state under different operating conditions, without being limited by a single operating condition factor, thus improving the system's adaptability to complex operating environments; Reduced over-reliance on the accuracy of measuring equipment: Traditional characteristic devices based on a single electrical quantity rely solely on a single signal for judgment, requiring extremely high accuracy of the measuring equipment, resulting in high measurement noise and transient disturbances. This approach, which can easily lead to misjudgments, employs a dual-valve current signal joint analysis and dynamic dual-feature extraction and precise quantification characterization, combined with a preset hyperbolic criterion equation for judgment. Even if the measuring equipment has certain precision errors, the accuracy of the commutation detection results can still be guaranteed due to the synergistic effect of the two parameters and the geometric constraint characteristics of the criterion equation. This reduces excessive reliance on the precision of the measuring equipment and minimizes the detection risks caused by equipment precision issues. It also facilitates early warning and prevention of faults: the device can not only accurately determine whether commutation is successful, but also provide detailed information about the commutation process status through the analysis of the exit valve energy mismatch index and the charge injection efficiency of the conduction valve. When an abnormal trend is detected in the commutation process, but the judgment criteria for commutation failure have not yet been met, an early warning signal can be issued in advance. Maintenance personnel can take timely measures to troubleshoot and prevent faults based on these early warning information, avoiding more serious system failures caused by commutation failures, improving system reliability and stability, and reducing power outage losses and economic losses caused by faults; promoting the intelligent development of HVDC transmission systems: the commutation detection device of this application provides an important technical foundation for the intelligent monitoring and control of HVDC transmission systems. By combining this device with advanced sensor technology, data communication technology, and intelligent algorithms, real-time online monitoring, automatic fault diagnosis, and intelligent decision control of the commutation process can be realized. This helps to promote the intelligent development of HVDC transmission systems, improve the automation level and operating efficiency of the system, reduce the need for manual intervention, and enhance the intelligent management level of the entire power system.

[0080] In a third aspect, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform a commutation detection method as described in any of the first aspects.

[0081] This application provides a computer device in a fourth aspect, including a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform a commutation detection method as described in any of the first aspects.

[0082] Figure 3 The diagram illustrates the internal structure of a computer device in some embodiments. This computer device may specifically be a terminal, a server, or a gateway. Figure 3 As shown, the computer device includes a processor, memory, and network interface connected via a system bus.

[0083] The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When executed by a processor, this computer program causes the processor to perform the steps in the above method embodiments. The internal memory may also store a computer program, which, when executed by a processor, causes the processor to perform the steps in the above method embodiments. Those skilled in the art will understand that... Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0084] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods.

[0085] Any references to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0086] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A commutation detection method, characterized in that, The method includes: Acquire the exit valve current signal and the conduction valve current signal of the current commutation event under test, and acquire the steady-state value of the exit valve DC current before the occurrence of the current commutation event under test; Based on the exit valve current signal and the conduction valve current signal of the current commutation event under test, as well as the steady-state value of the exit valve DC current, determine the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test. Substitute the exit valve energy mismatch index and the conduction valve charge injection efficiency of the current commutation event under test into the preset hyperbolic criterion equation to obtain the hyperbolic criterion value; Based on the hyperbolic criterion value, the commutation detection result of the current commutation event to be tested is determined.

2. The commutation detection method according to claim 1, characterized in that, The step of determining the exit valve energy mismatch index and conduction valve charge injection efficiency of the current commutation event under test based on the exit valve current signal and conduction valve current signal of the current commutation event under test, and the steady-state value of the exit valve DC current, includes: Determine the minimum current value in the exit valve current signal of the current commutation event under test, and the rebound current value after a first preset time interval following the moment corresponding to the minimum current value. Based on the minimum current value and rebound current value in the exit valve current signal of the current commutation event under test, and the steady-state value of the DC current of the exit valve, determine the exit valve energy mismatch index of the current commutation event under test. The starting current value at the start of commutation in the current commutation event to be tested, and the blocked current value after a second preset time interval following the start of commutation are determined. Based on the starting current value and blocked current value in the current commutation event to be tested, and the steady-state value of the DC current of the exit valve, the charge injection efficiency of the current commutation event to be tested is determined.

3. The commutation detection method according to claim 2, characterized in that, The exit valve energy mismatch index of the current commutation event under test is determined using the following formula: ； in, The exit valve energy mismatch index is the current commutation event to be tested. This refers to the moment corresponding to the minimum current value in the exit valve current signal of the current commutation event under test. For the first preset duration, in hour, The minimum current value in the exit valve current signal of the current commutation event under test is... hour, The bounce current value is the value in the exit valve current signal of the current commutation event under test. This is the steady-state value of the DC current of the exit valve.

4. The commutation detection method according to claim 2, characterized in that, The charge injection efficiency of the on-valve for the current commutation event under test is determined using the following formula: ； in, The charge injection efficiency of the on-valve for the current commutation event under test. The commutation start time is [the time specified in the original text]. For the second preset duration, in hour, The starting current value in the conduction valve current signal of the current commutation event under test is... hour, This refers to the obstructed current value in the on-valve current signal of the current commutation event under test. This is the steady-state value of the DC current of the exit valve.

5. The commutation detection method according to claim 1, characterized in that, The method further includes: Acquire the exit valve current signal, conduction valve current signal and tag of various historical commutation events, including various normal operating conditions and various commutation failure scenarios; Based on the exit valve current signal and the conduction valve current signal for each historical commutation event, determine the exit valve energy mismatch index and the conduction valve charge injection efficiency for each historical commutation event. The exit valve energy mismatch index, conduction valve charge injection efficiency, and labels of various historical commutation events are input into the initial classification prediction model for training, thus obtaining the target classification prediction model. Based on the model parameters of the target classification prediction model, determine the hyperbolic criterion parameters; Based on the hyperbola criterion parameters, the preset hyperbola criterion equation is constructed.

6. The method according to claim 5, characterized in that, The model parameters of the target classification prediction model include a support vector set, a label set corresponding to the support vector set, a dual coefficient set corresponding to the support vector set, and a bias term. The hyperbolic criterion parameters include the x-coordinate of the center of the hyperbola, the y-coordinate of the center, the coefficient of the quadratic term on the x-axis, the coefficient of the quadratic term on the y-axis, and the coefficient of the cross product term. Determining the hyperbolic criterion parameters based on the model parameters of the target classification prediction model includes: Substituting the support vector set, the label set corresponding to the support vector set, the dual coefficient set corresponding to the support vector set, and the bias term into the decision function of the target classification prediction model, a second-order polynomial equation is obtained. By finding the center and eliminating the first-order terms of the second-order polynomial equation, the hyperbolic equation is obtained. Based on the hyperbola equation, determine the abscissa of the center, ordinate of the center, coefficient of the quadratic term, coefficient of the quadratic term, and coefficient of the cross product term of the hyperbola.

7. The commutation detection method according to claim 1, 5, or 6, characterized in that, The preset hyperbola criterion equation is: ; in, The x-coordinate of the center of the hyperbola in the hyperbola criterion parameters. The ordinate of the center of the hyperbola in the hyperbola criterion parameters is... The coefficient of the quadratic term of the hyperbola in the hyperbola criterion parameters is... The coefficient of the quadratic term of the hyperbola in the hyperbola criterion parameters is... The coefficients of the cross product term of the hyperbola in the hyperbola criterion parameters are... The energy mismatch index for the exit valve. To improve the charge injection efficiency of the conduction valve, This is the hyperbolic criterion value.

8. The commutation detection method according to claim 1, characterized in that, The step of determining the commutation detection result of the current commutation event to be tested based on the hyperbolic criterion value includes: If the hyperbolic criterion value is greater than or equal to the criterion threshold, the commutation detection result of the current commutation event to be tested is determined to be a commutation failure. If the hyperbolic criterion value is less than the criterion threshold, the commutation detection result of the current commutation event to be tested is determined to be a successful commutation.

9. A computer-readable storage medium, characterized in that, The device contains a computer program that, when executed by a processor, causes the processor to perform the commutation detection method as described in any one of claims 1 to 8.

10. A computer device, characterized in that, It includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the commutation detection method as described in any one of claims 1 to 8.

Images