Method, device and equipment for predicting and optimizing commutation failure of embedded LCC-HVDC system and medium

Abstract

The present application relates to the technical field of conventional high-voltage direct current transmission LCC-HVDC, and particularly relates to a commutation failure prediction optimization method, device and equipment for embedded LCC-HVDC system and a medium, the method comprising: collecting electrical signal parameters of high-voltage side, medium-voltage side and low-voltage side, and constructing a criterion according to the three-side electrical signal parameters to determine whether the commutation failure prediction strategy needs to be started; if it is determined that the commutation failure prediction strategy needs to be started, the collected electrical signal parameters are converted into a fuzzy set, fuzzy reasoning is performed by using a pre-fuzzy rule base to generate a fuzzy control value of an increased turn-off angle; based on the fuzzy control value, a large amount of increased turn-off angle is obtained by a defuzzification method, and the control strategy of the direct current system is adjusted; and based on the adjusted state of the direct current system, the fuzzy rule base is dynamically optimized. In the present application, the traditional commutation failure prediction strategy and the advanced fuzzy control algorithm are combined, the commutation failure problem caused by the fault of the medium-voltage side and the low-voltage side is effectively coped with, and the system stability is significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of high-voltage direct current transmission LCC-HVDC, and particularly relates to a commutation failure prediction optimization method, device, equipment and medium for an embedded LCC-HVDC system. BACKGROUND

[0002] With the rapid growth of power supply capacity and electricity demand, the increasing tension of resources and energy, and the urgent requirement of environmental protection, it is necessary to greatly improve the power transmission capacity of key sections of the power grid by building a large number of power transmission lines or transforming existing power transmission lines. However, due to the difficulties in developing key channels, it is an economic and feasible solution to transform the "embedded" high-voltage direct current transmission system LCC-HVDC by fully utilizing the internal key power transmission channels of the existing regional power grid.

[0003] Unlike conventional ultra-high voltage or super-high voltage direct current transmission systems, no additional main transformer is usually equipped in the station, so there is no voltage drop of the DC system connected to the AC bus caused by the fault of each voltage level side of the main transformer. However, for the DC system in the regional power grid embedded with 220kV (high voltage side of the main transformer) voltage level, the main transformer is usually equipped in the converter station, and connected to the medium voltage side (110kV) and low voltage side (35kV, 10kV) power grid. In order to quickly respond to the fault of the medium and low voltage side of the main transformer and reduce the risk of commutation failure, it is urgent to develop a new commutation failure prediction strategy suitable for the "embedded" direct current transmission system.

[0004] The information disclosed in this BACKGROUND section is only for the purpose of enhancing the understanding of the background of the present application and should not be taken as an acknowledgment or any form of suggestion that this information forms prior art in the field. SUMMARY

[0005] The present application provides an embedded LCC-HVDC system commutation failure prediction optimization method, device, equipment and medium, thereby effectively solving the problems in the background art.

[0006] In order to achieve the above purpose, the technical solution adopted by the present application is as follows: an embedded LCC-HVDC system commutation failure prediction optimization method, comprising the following steps:

[0007] Collecting electrical signal parameters of the high voltage side, the medium voltage side and the low voltage side, and constructing a criterion according to the three-side electrical signal parameters to determine whether the commutation failure prediction strategy needs to be started;

[0008] If it is judged that the commutation failure prediction strategy needs to be started, the collected electrical signal parameters are converted into fuzzy sets, fuzzy reasoning is performed by using a pre-fuzzy rule base, and a fuzzy control value of the increased turn-off angle is generated;

[0009] Based on the fuzzy control value, the amount of the increased turn-off angle is obtained by a defuzzification method, and the control strategy of the DC system is adjusted;

[0010] Based on the adjusted state of the DC system, the fuzzy rule base is dynamically optimized.

[0011] Further, the electrical signal parameters are voltage amplitudes, and the voltage drop amplitude is calculated based on the voltage amplitudes.

[0012] Further, the conversion of the collected electrical signal parameters into fuzzy sets comprises:

[0013] The electrical signal parameters of the high-voltage side, the medium-voltage side and the low-voltage side are taken as input variables, and membership functions are used to describe the fuzzy degrees of different input variables.

[0014] The membership functions include triangular, trapezoidal and Gaussian membership functions.

[0015] Further, the construction of the criterion according to the electrical signal parameters of the three sides to judge whether the commutation failure prediction strategy needs to be started comprises:

[0016] The first set value and the second set value are set, and it is judged whether the bus voltages of the high-voltage side, the medium-voltage side and the low-voltage side satisfy the set criterion.

[0017] If the criterion is satisfied, the commutation failure prediction strategy needs to be started.

[0018] Further, the criterion comprises:

[0019]

[0020] In the formula, U ac高压侧 , U ac中压侧 , U ac低压侧 are the bus voltages of the high-voltage side, the medium-voltage side and the low-voltage side respectively, and U set1 , U set2 are the first set value and the second set value respectively.

[0021] Further, the criterion comprises:

[0022]

[0023] In the formula, U ac高压侧 , U ac中压侧 , U ac低压侧 are the bus voltages of the high-voltage side, the medium-voltage side and the low-voltage side respectively, and U set1 , Uset2 respectively, are first and second set values; ΔU T11 represents the maximum drop level of the high-voltage side bus voltage when a three-phase fault occurs on the medium-voltage side; ΔU set1 represents the voltage drop of the high-voltage side of the main transformer to the medium-voltage side when the maximum drop level of the high-voltage side bus voltage is U T12 represents the maximum drop level of the high-voltage side bus voltage when a three-phase fault occurs on the low-voltage side; ΔU set2 represents the voltage drop of the high-voltage side of the main transformer to the low-voltage side when the maximum drop level of the high-voltage side bus voltage is U T2 represents the maximum drop level of the high-voltage side bus voltage when a three-phase fault occurs on the low-voltage side; ΔU set2 represents the voltage drop of the high-voltage side of the main transformer to the low-voltage side when the maximum drop level of the high-voltage side bus voltage is U

[0024] Further, the defuzzification method includes a centroid method or a maximum membership degree method, and converts the result of the fuzzy reasoning into an actual value.

[0025] The application also includes an embedded LCC-HVDC system commutation failure prediction optimization device using the above method, and the device includes:

[0026] A criterion construction unit is configured to collect electrical signal parameters of the high-voltage side, the medium-voltage side and the low-voltage side, and construct a criterion based on the three-side electrical signal parameters to determine whether to start a commutation failure prediction strategy;

[0027] A fuzzy reasoning unit is configured to convert the collected electrical signal parameters into a fuzzy set if it is determined to start the commutation failure prediction strategy, and perform fuzzy reasoning by using a pre-fuzzy rule base to generate a fuzzy control value of an increased extinction angle;

[0028] A defuzzification unit is configured to obtain the increased extinction angle amount by using a defuzzification method based on the fuzzy control value, and adjust the control strategy of the DC system;

[0029] A learning unit is configured to dynamically optimize the fuzzy rule base based on the adjusted state of the DC system.

[0030] The application also includes a computer device including a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the above method when executing the computer program.

[0031] The application also includes a storage medium having a computer program stored thereon, and the computer program is executable on the processor to implement the above method.

[0032] The beneficial effects of the present application are: by combining the fuzzy control algorithm, the system can flexibly and dynamically adjust the turn-off angle according to different factors, and accurately control the commutation failure prediction. This method not only improves the adaptability of the system to various fault conditions, but also reduces the probability of commutation failure when facing complex and uncertain power system faults, thereby improving the stability and reliability of the "embedded" LCC-HVDC system. And combined with the traditional commutation failure prediction strategy and the advanced fuzzy control algorithm, through the fuzzification process and rule reasoning, more accurate turn-off angle adjustment is provided, which can effectively deal with the commutation failure problem caused by the fault of the medium voltage side and the low voltage side, and optimize the system stability. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0034] Figure 1 The flow chart of the method of the present application;

[0035] Figure 2 The main circuit topology diagram of the embedded HVDC project;

[0036] Figure 3 The three-phase short-circuit fault waveform diagram of the 110kV side of the main transformer;

[0037] Figure 4 The three-phase short-circuit fault waveform diagram of the 35kV side of the main transformer;

[0038] Figure 5 The first turn-off angle control strategy;

[0039] Figure 6 The second turn-off angle control strategy;

[0040] Figure 7 The structural schematic diagram of the device of the present application;

[0041] Figure 8 The structural schematic diagram of the computer equipment of the present application. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments.

[0043] As Figure 1The method comprises the following steps:

[0044] Collecting electrical signal parameters of high-voltage side, medium-voltage side and low-voltage side, and constructing a criterion according to the three-side electrical signal parameters to determine whether the commutation failure prediction strategy needs to be started;

[0045] If it is determined that the commutation failure prediction strategy needs to be started, the collected electrical signal parameters are converted into a fuzzy set, fuzzy reasoning is performed by using a pre-fuzzy rule base, and a fuzzy control value of the increased turn-off angle is generated;

[0046] Based on the fuzzy control value, the amount of the increased turn-off angle is obtained by a defuzzification method, and the control strategy of the DC system is adjusted;

[0047] Based on the adjusted state of the DC system, the fuzzy rule base is dynamically optimized.

[0048] By combining the fuzzy control algorithm, the system can flexibly and dynamically adjust the turn-off angle according to different factors, and accurately control the commutation failure prediction. This method not only improves the adaptability of the system to various fault conditions, but also reduces the probability of commutation failure when facing complex and uncertain power system faults, thereby improving the stability and reliability of the "embedded" LCC-HVDC system. Combined with the traditional commutation failure prediction strategy and the advanced fuzzy control algorithm, more accurate turn-off angle adjustment is provided through the fuzzification process and rule reasoning, which can effectively deal with the commutation failure problem caused by medium-voltage side and low-voltage side faults, optimize the system stability, and significantly improve the system stability.

[0049] Commutation failure prediction control (CFPRED) is used to prevent commutation failure caused by AC faults. Three-phase faults are detected based on AC voltage α / β conversion. The detection principle is as follows:

[0050] αβ transformed voltage criterion;

[0051] The αβ transformed voltage criterion is mainly for the disturbance condition of the inverter side AC system. αβ transformation is a transformation from time phasor to space vector. The AC voltage is transformed by abc-αβ to obtain two components on the α and β axes of the space stationary coordinate system. After transformation, the three-phase symmetrical components obtain a vector rotating at an angular velocity in the α-β plane.

[0052]

[0053] When a three-phase ground fault occurs in the inverter-side AC system, if the α / β transformation voltage is less than the α / β transformation voltage under steady-state conditions and the change exceeds the set value, the commutation failure prediction control function will be activated.

[0054] ΔU αβ =U αβ (t)(1-e -t / 2 )-U αβ ;

[0055] Its action conditions are:

[0056] ΔU αβ >AB_SET_VAL;

[0057] Among them, each voltage quantity is taken as a per-unit value, and AB_SET_VAL is the zero-sequence voltage starting value, which is generally taken as 0.15 for ultra-high voltage projects.

[0058] The maximum value of the zero-sequence voltage criterion and the α / β transformation voltage criterion is multiplied by the gain coefficient (0.075) to obtain the angle output AMIN_CFPREV, which is applied to the AMAX controller to increase the turn-off angle and help avoid commutation failure.

[0059] like Figure 2 As shown, embedded high-voltage direct current projects typically involve the construction of converter stations and substations in the same location. The main transformers within the station may have different voltage levels on the high, medium, and low voltage sides. When AC faults occur on the medium and low voltage sides, the transmission delay of the main transformer may increase the risk of commutation failure of the inverter-side converter valve.

[0060] In this embodiment, the acquired electrical signal parameters are converted into fuzzy sets, including:

[0061] The electrical signal parameters of the high-voltage side, medium-voltage side, and low-voltage side are used as input variables, and membership functions are used to describe the fuzziness of different input variables.

[0062] Membership functions include triangular, trapezoidal, and Gaussian membership functions.

[0063] The electrical signal parameter is the voltage amplitude, and the voltage drop amplitude is calculated based on the voltage amplitude.

[0064] The input variables are transformed into fuzzy sets using a fuzzification function. Voltage amplitude and voltage drop can be represented using Gaussian membership functions.

[0065] Fuzzy inference is the process of deriving an output fuzzy set from an input fuzzy set and a fuzzy rule base. The Mamdani inference method is used to derive the output from the fuzzy rule base.

[0066] Based on the voltage amplitude and the voltage drop amplitude, the fuzzy rule can combine these conditions to infer the degree of the turn-off angle increase (Δγ). The inference result will get a fuzzy output according to the inference result in the rule base.

[0067] As the preferred embodiment of the above embodiment, the criterion is constructed according to the three-side electrical signal parameters to determine whether the commutation failure prediction strategy needs to be started, including:

[0068] The first setting value and the second setting value are set to determine whether the bus voltages of the high-voltage side, the medium-voltage side and the low-voltage side meet the set criterion;

[0069] If the criterion is met, the commutation failure prediction strategy needs to be started.

[0070] As shown in Figures 3 to 5 , in order to make the DC control system respond faster when the main transformer is in medium-voltage and low-voltage side fault, and reduce the risk of commutation failure, the auxiliary prediction criterion of commutation failure is constructed. Compared with the conventional commutation failure prediction strategy, the auxiliary criterion increases the turn-off angle after detecting that the medium-voltage and low-voltage side voltages are lower than a certain level. That is, the bus voltages of the high-voltage side (220 kV), the medium-voltage side (110 kV) and the low-voltage side (35 kV) are collected at the same time. Among them, when the high-voltage side (220 kV) bus voltage is lower than the set value U set1 (0.85 p.u. in engineering), and the medium-voltage side (110 kV) and the low-voltage side (35 kV, 10 kV) bus voltages are lower than U set2 (0.8 p.u. in engineering), the γ angle of the inverter will increase.

[0071] Among them, the criterion includes:

[0072]

[0073] In the formula, U ac高压侧 , U ac中压侧 , and U ac低压侧 are the bus voltages of the high-voltage side, the medium-voltage side and the low-voltage side, respectively, and U set1 , U set2 are the first setting value and the second setting value, respectively.

[0074] When the high-voltage side is less than the first setting value, and the medium-voltage side and the low-voltage side are less than the second setting value, the criterion is met, and the commutation failure prediction strategy needs to be started. After fuzzy inference, the turn-off angle is increased by 15°-25° according to the drop degree of the voltage level.

[0075] However, as Figure 3 and 4The simulation fault waveform in the simulation experiment shows that in actual engineering, when three-phase ground fault occurs in the medium voltage side (110 kV) bus, the maximum voltage drop level of the high voltage side (220 kV) is 84.5%. When three-phase ground fault occurs in the low voltage side (35 kV) bus, the voltage drop level of the medium voltage side (110 kV) is 64.3%, and the voltage drop level of the high voltage side (220 kV) is 96%. It can be seen that the low voltage side (35 kV) and the medium voltage side (110 kV) have little effect on the voltage of the 220 kV side.

[0076] Or as shown in Figure 6 To prevent serious voltage drop fault in 220 kV and 35 kV, the DC system adjusts the turn-off angle, affecting the stability of the system. The commutation failure criterion is adjusted to the following strategy:

[0077] The criterion includes:

[0078]

[0079] In the formula, U ac高压侧 , U ac中压侧 , U ac低压侧 are the bus voltages of the high voltage side, the medium voltage side and the low voltage side, respectively, U set1 , U set2 are the first and second set values, respectively; ΔU T11 represents the voltage drop of the high voltage side to the medium voltage side when the maximum voltage drop level of the high voltage side is U set1 when three-phase fault occurs in the medium voltage side; ΔU T12 represents the voltage drop of the high voltage side to the medium voltage side when the maximum voltage drop level of the high voltage side is U set2 when three-phase fault occurs in the medium voltage side; ΔU T2 represents the voltage drop of the high voltage side to the low voltage side when the maximum voltage drop level of the high voltage side is U set2 when three-phase fault occurs in the low voltage side;

[0080] If the high voltage side is less than the first set value, if the medium voltage side satisfies U set1 - ΔU T11 , if the medium voltage side satisfies U set1 - ΔU T12 <U ac中压侧 <U set2 - ΔU T12 , if the low voltage side satisfies U set1 - ΔU T2 , the criterion is satisfied, the commutation failure prediction strategy needs to be started, and after fuzzy reasoning, the turn-off angle is increased by at least 5°.

[0081] Based on the fuzzy control value obtained by fuzzy reasoning, a specific numerical value of the turn-off angle increase is obtained by a defuzzification method.

[0082] According to the simulation test, it is known that the three-phase fault of the medium-voltage side and the low-voltage side has a relatively small influence on the voltage drop of the high-voltage side bus, and only when the three-phase short-circuit fault of the medium-voltage side and the low-voltage side is relatively serious, the voltage of the high-voltage side bus will be obviously dropped. Therefore, the commutation failure setting value of the medium-voltage side and the low-voltage side should be determined by the voltage drop level of the high-voltage side bus and the voltage drop on the main transformer.

[0083] The influence of the low-voltage side bus fault on the voltage of the high-voltage side bus is lower than that of the medium-voltage side bus fault, wherein the serious fault of the medium-voltage side may cause the voltage of the high-voltage side bus to drop to U set1 ; the serious fault of the low-voltage side will not cause the voltage of the high-voltage side bus to drop to U set1 (0.85p.u.), but can cause the voltage of the high-voltage side bus to drop to U set2 (0.95p.u.). Therefore, different criteria are set for the medium-voltage side and the low-voltage side. When the low-voltage side fault criterion is started, the turn-off angle increase value is at least 5°

[0084] When the medium-voltage side fault causes the voltage of the high-voltage side bus to drop to U set1 (0.85p.u.) or below, the turn-off angle increase value (at least 15°) is determined according to the drop degree, but since the medium-voltage side fault will not cause the high-voltage side bus to be 0, the turn-off angle increase value will not reach 25°. If the medium-voltage side fault causes the voltage of the high-voltage side bus to drop to U set1 (0.85p.u.) to U set2 (0.95p.u.), the commutation failure prediction criterion can also be started, but the turn-off angle increase value is at least 5°.

[0085] As a preferred embodiment of the above embodiment, the defuzzification method includes the centroid method or the maximum membership degree method, which converts the result of fuzzy reasoning into an actual value.

[0086] As shown in Figure 7 , the embodiment also includes an embedded LCC-HVDC system commutation failure prediction optimization device, which uses the method as described above, and the device includes:

[0087] A criterion construction unit is configured to collect electrical signal parameters of the high-voltage side, the medium-voltage side and the low-voltage side, and construct a criterion according to the three-side electrical signal parameters to determine whether the commutation failure prediction strategy needs to be started;

[0088] A fuzzy reasoning unit is configured to convert the collected electrical signal parameters into a fuzzy set if it is determined that the commutation failure prediction strategy needs to be started, and perform fuzzy reasoning by using a pre-fuzzy rule base to generate a fuzzy control value of the turn-off angle increase;

[0089] The deblurring unit is configured to obtain the increase in the off angle by a deblurring method based on the fuzzy control value, and adjust the control strategy of the DC system.

[0090] The learning unit is configured to dynamically optimize the fuzzy rule base based on the adjusted state of the DC system.

[0091] Please refer to Figure 8 The computer device 400 provided by the embodiment of the present application includes a processor 410 and a memory 420, the memory 420 stores a computer program executable by the processor 410, and the computer program is executed by the processor 410 to perform the method as above.

[0092] The embodiment of the present application further provides a storage medium 430, and the storage medium 430 stores a computer program, and the computer program is executed by the processor 410 to perform the method as above.

[0093] The storage medium 430 can be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk.

[0094] In the description of the present application, the terms "first", "second" are only used for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. The meaning of "plurality" is two or more, unless otherwise specifically limited.

[0095] In the present application, unless specifically defined otherwise and limited in the specification, the terms "mount", "connect", "connection", "contact", and the like are to be construed in their broadest possible sense, such as to include fixed connections, detachable connections, or integral connections; mechanical connections, electrical connections, or connections made by means of intermediate medium; direct connections, or indirect connections via intermediate medium; internal connections between elements, or interaction between elements. The specific meaning of the above terms in the present application can be understood by those skilled in the art according to the specific circumstances.

[0096] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present application, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the skilled person can combine and combine the different embodiments or examples described in the present application and the features of the different embodiments or examples without contradiction.

[0097] Any process or method descriptions or descriptions of the flow diagrams in the present application can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for performing specific logic functions or steps in the process, and the preferred embodiments of the present application include additional implementations in which the order of steps can be changed, including use of the same step more than once, use of the same step in different orders, use of the same step in different ways, use of different steps in the same order, use of different steps in different orders, use of different steps in different ways, and so on, as will be appreciated by those skilled in the art.

[0098] The logic and / or steps represented in flow diagrams or otherwise described herein, for example, can be considered as a sequence of instructions to implement logic functions, and can be realized in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, processor- containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In the context of this specification, a "computer-readable medium" can be any means that can contain, store, communicate, propagate or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include an electronic connection (an electronic device), a portable computer diskette (a magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). Further, the computer-readable medium can even be paper or other suitable medium upon which the program is printed, as the program can be electronically captured, for example, by optically scanning the paper or other suitable medium, then electronically converted into a form that is suitable for use by the instruction execution system, apparatus, or device, and then stored in computer memory.

[0099] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, the various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, known in the art, or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0100] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiment method can be completed by a program instructing the relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0101] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application. Those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. An embedded LCC-HVDC system commutation failure prediction optimization method, characterized in that, The method comprises the following steps: collecting electrical signal parameters of high-voltage side, medium-voltage side and low-voltage side, and constructing a criterion based on the electrical signal parameters of the three sides to determine whether the commutation failure prediction strategy needs to be started; if it is determined that the commutation failure prediction strategy needs to be started, converting the collected electrical signal parameters into a fuzzy set, using a pre-fuzzy rule base to perform fuzzy reasoning, and generating a fuzzy control value of an increased turn-off angle; based on the fuzzy control value, obtaining the amount of increased turn-off angle by a defuzzification method, and adjusting the control strategy of the DC system; based on the adjusted state of the DC system, dynamically optimizing the fuzzy rule base; the electrical signal parameter is a voltage amplitude, and the voltage drop amplitude is calculated based on the voltage amplitude; the conversion of the collected electrical signal parameters into a fuzzy set comprises: using membership functions to describe the fuzzy degree of different input variables by taking the electrical signal parameters of the high-voltage side, medium-voltage side and low-voltage side as input variables; the membership functions include triangular, trapezoidal and Gaussian membership functions; the criterion based on the electrical signal parameters of the three sides to determine whether the commutation failure prediction strategy needs to be started comprises: setting a first set value and a second set value to determine whether the bus voltages of the high-voltage side, medium-voltage side and low-voltage side meet the set criterion; if the criterion is met, the commutation failure prediction strategy needs to be started.

2. The method for commutation failure prediction criterion optimization of embedded LCC-HVDC system according to claim 1, characterized in that, the criterion comprises: ； In the formula, U ac高压侧 , U ac中压侧 , U ac低压侧 are bus voltages of high-voltage side, medium-voltage side and low-voltage side, respectively, and U set1 , U set2 are first and second set values, respectively.

3. The commutation failure prediction optimization method for embedded LCC-HVDC systems of claim 1, wherein, the criterion comprises: ； In the formula, U ac高压侧 , U ac中压侧 , U ac低压侧 are bus voltages of high-voltage side, medium-voltage side and low-voltage side respectively, U set1 , U set2 are first and second set values respectively; ΔU T11 represents voltage drop of high-voltage side to medium-voltage side of main transformer when maximum drop level of high-voltage side bus voltage is just ΔU U set1 when three-phase fault occurs in medium-voltage side; ΔU T12 represents voltage drop of high-voltage side to medium-voltage side of main transformer when maximum drop level of high-voltage side bus voltage is just ΔU U set2 when three-phase fault occurs in medium-voltage side; ΔU T2 represents voltage drop of high-voltage side to low-voltage side of main transformer when maximum drop level of high-voltage side bus voltage is just ΔU U set2 when three-phase fault occurs in low-voltage side.

4. The commutation failure prediction optimization method for embedded LCC-HVDC systems of claim 1, wherein, the defuzzification method includes a centroid method or a maximum membership degree method, which converts the result of fuzzy reasoning into an actual value.

5. An apparatus for commutation failure prediction optimization in an embedded LCC-HVDC system, characterized by, The device comprises: a criterion construction unit configured to collect electrical signal parameters of high-voltage side, medium-voltage side and low-voltage side, and construct a criterion based on the electrical signal parameters of the three sides to determine whether the commutation failure prediction strategy needs to be started; a fuzzy reasoning unit configured to, if it is determined that the commutation failure prediction strategy needs to be started, convert the collected electrical signal parameters into a fuzzy set, use a pre-fuzzy rule base to perform fuzzy reasoning, and generate a fuzzy control value of an increased turn-off angle; a defuzzification unit configured to, based on the fuzzy control value, obtain the amount of increased turn-off angle by a defuzzification method, and adjust the control strategy of the DC system; a learning unit configured to, based on the adjusted state of the DC system, dynamically optimize the fuzzy rule base.

6. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1-4.

7. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the method of any one of claims 1-4.

Images