Parameter optimization method and device for fusion sensor, electronic equipment and storage medium

Abstract

The application provides a parameter optimization method and device of a fusion sensor, electronic equipment and a storage medium, wherein the method comprises the following steps: receiving a configuration item input by a user through an interaction terminal to obtain a to-be-optimized structure parameter set; sampling and selecting in a parameter space to obtain a sample structure parameter point set; the parameter space is composed of multiple to-be-optimized structure parameter sets, the parameter values of the to-be-optimized structure parameters in the to-be-optimized structure parameter set constituting the parameter space are randomly generated, and the sample structure parameter point set is composed of the to-be-optimized structure parameter sets selected from the parameter space; sample point performance parameters corresponding to the sample structure parameter points are calculated according to the sample structure parameter point set; and a target parameter is determined according to the sample structure parameter points and the sample point performance parameters. The application has the advantages of small calculation amount, small investment in computing resources, low cost, high optimization efficiency and high optimization accuracy.

Description

Technical Field

[0001] This invention relates to the field of fusion sensor technology, and in particular to a parameter optimization method, apparatus, electronic device, and storage medium for fusion sensors. Background Technology

[0002] Among the many partial discharge detection technologies, ultra-high frequency signal detection is widely used in gas-insulated substations due to its advantages of high sensitivity and strong anti-interference ability.

[0003] During actual operation, power equipment inevitably experiences various overvoltages from sources such as lightning surges, circuit breaker operations, and disconnector switches. Under the influence of overvoltages, normally operating power equipment may be excited, resulting in partial discharge. This discharge can then rapidly develop under the influence of power frequency voltage, leading to insulation breakdown and posing a serious threat to the safe and reliable operation of the power equipment.

[0004] Currently, the parameter scanning method is used for sensor parameter optimization (the parameter scanning method involves scanning all influencing structural parameters and then selecting the structural parameters with better performance). However, as the number of structural parameters involved in the sensor design increases, the computational load required for parameter scanning increases exponentially. Therefore, for ultra-high frequency-overvoltage fusion sensors with a high number of parameters, the existing parameter scanning optimization method requires a large amount of computation, necessitates a huge investment of computing resources, is costly, and suffers from low optimization efficiency and poor accuracy. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for optimizing parameters of a fusion sensor, in order to solve the problems of high computational load, huge investment of computing power, high cost, low optimization efficiency, and poor accuracy of existing parameter scanning optimization methods for ultra-high frequency-overvoltage fusion sensors with a large number of parameters.

[0006] To solve the above-mentioned technical problems, the present invention is implemented as follows:

[0007] In a first aspect, embodiments of the present invention provide a parameter optimization method for fused sensors, comprising:

[0008] Receiving steps: Receive configuration items input by the user through the interactive terminal to obtain a set of structural parameters to be optimized. The configuration items are used to indicate the structural parameters to be optimized in the sensor structural parameters.

[0009] Selection steps: Sampling is performed in the parameter space to obtain a sample structure parameter point set; the parameter space is composed of multiple sets of the structure parameters to be optimized, the parameter values ​​of the structure parameters to be optimized in the sets of the structure parameters to be optimized constituting the parameter space are randomly generated, the sample structure parameter point set is composed of the selected sets of the structure parameters to be optimized in the parameter space, and the sample structure parameter points in the sample structure parameter point set correspond one-to-one with the selected sets of the structure parameters to be optimized;

[0010] Calculation steps: Based on the set of sample structure parameter points, calculate the performance parameters of the sample points that correspond one-to-one with the sample structure parameter points;

[0011] Determination steps: Determine the target parameters based on the sample structure parameter points and the sample point performance parameters.

[0012] Optionally,

[0013] Prior to the receiving step, the following is included:

[0014] Acquisition steps: Acquire sensor installation information; calculate structural parameter thresholds corresponding one-to-one with the sensor structural parameters based on the sensor installation information; send the structural parameter thresholds to the interactive terminal, whereby the structural parameter thresholds are used to determine the set of structural parameters to be optimized.

[0015] Optionally,

[0016] Based on the set of sample structure parameter points, the performance parameters of the sample points corresponding one-to-one with the sample structure parameter points are calculated, including:

[0017] Based on the set of sample structure parameter points, the performance parameters of the sample points corresponding one-to-one with the sample structure parameter points are calculated using the finite element method.

[0018] Optionally,

[0019] The determining steps include:

[0020] Verification steps: Verify the correlation between each sample structural parameter point and the corresponding sample point performance parameter to obtain the correlation verification result;

[0021] First execution step: If the correlation verification result is high correlation, determine the currently verified sample structural parameter point as a target structural parameter point, and return to the verification step until all sample structural parameter points have been verified; if the correlation verification result is low correlation, return to the verification step until all sample structural parameter points have been verified.

[0022] Second execution step: Construct a new parameter space using the set of parameters to be optimized corresponding to the target structural parameter points, and execute the selection step and the calculation step again to obtain new sample structural parameter points and new sample point performance parameters that correspond one-to-one with the new sample structural parameter points.

[0023] The third execution step: Determine the target parameters based on the new sample structure parameter points and the new sample point performance parameters.

[0024] Optionally,

[0025] The second execution step involves re-executing the selection step and the calculation step, which also yields a new set of sample structure parameter points.

[0026] The third execution step includes:

[0027] Modeling steps: Based on the new sample structure parameter points and the new sample point performance parameters, establish a regression surrogate model;

[0028] The second calculation step is to substitute the new set of sample structure parameter points into the regression surrogate model to calculate the performance parameters of the target sample points.

[0029] Comparison steps: Compare the performance parameters of the target sample points with the new performance parameters of the sample points to obtain the comparison results;

[0030] Fourth execution step: If the comparison result shows that the difference between the performance parameters of the target sample point and the new performance parameters of the sample point is less than a preset difference threshold, then the regression surrogate model is determined to be the target surrogate model;

[0031] The second determination step is to optimize and solve the target proxy model based on the new set of sample structure parameter points to determine the target parameters.

[0032] Optionally,

[0033] The comparison step is followed by:

[0034] Fifth execution step: If the comparison result is that the difference between the performance parameter of the target sample point and the new performance parameter of the sample point is greater than or equal to the preset difference threshold, return to the second execution step until the comparison result is that the difference between the performance parameter of the target sample point and the new performance parameter of the sample point is less than the preset difference threshold.

[0035] Optionally,

[0036] The algorithm for optimizing the solution in the second determining step includes at least one of the following:

[0037] Genetic algorithm, particle swarm optimization algorithm, and annealing algorithm.

[0038] Secondly, embodiments of the present invention provide a parameter optimization device for fusion sensors, comprising:

[0039] The receiving module is used to receive the following steps: receiving configuration items input by the user through the interactive terminal to obtain a set of parameters to be optimized, wherein the configuration items are used to indicate the structural parameters to be optimized in the sensor structural parameters;

[0040] The selection module is used for the following steps: a random sampling algorithm is used to select samples in the parameter space to obtain a set of sample structure parameter points; the parameter space is composed of multiple sets of the structure parameters to be optimized, the parameter values ​​of the structure parameters to be optimized in the sets of the structure parameters to be optimized constituting the parameter space are randomly generated, the set of sample structure parameter points is composed of the selected sets of the structure parameters to be optimized in the parameter space, and the sample structure parameter points in the set of sample structure parameter points correspond one-to-one with the selected sets of the structure parameters to be optimized;

[0041] The calculation module is used to calculate the following steps: based on the set of sample structure parameter points, calculate the sample point performance parameters that correspond one-to-one with the sample structure parameter points;

[0042] The determination module is used to determine the following steps: determining the target parameters based on the sample structure parameter points and the sample point performance parameters.

[0043] Thirdly, embodiments of the present invention provide an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps in the parameter optimization method for a fusion sensor as described in any one of the first aspects.

[0044] Fourthly, embodiments of the present invention provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps in the parameter optimization method for a fused sensor as described in any one of the first aspects.

[0045] In this embodiment of the invention, by receiving configuration items input by the user through an interactive terminal, a set of structural parameters to be optimized is obtained. Sample structural parameter points are then selected by sampling in the parameter space. Based on the set of sample structural parameter points, performance parameters corresponding one-to-one with each sample structural parameter point are calculated. Based on the sample structural parameter points and the performance parameters, target parameters are determined. This allows each parameter to be optimized to be optimized in a unified manner as a set, avoiding the complex calculation process of optimizing each parameter separately and then integrating them, as required by existing parameter scanning methods. The optimization using this embodiment requires less computation, less computing power, and is less costly.

[0046] Furthermore, since all parameters to be optimized can be optimized in a coordinated manner in the form of a set, mutual interference between the parameters during the optimization process is avoided, thereby avoiding the time cost of correcting interference. The embodiments of the present invention have high optimization efficiency and high optimization accuracy. Attached Figure Description

[0047] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0048] Figure 1 This is one of the flowcharts illustrating the parameter optimization method for fused sensors according to an embodiment of the present invention;

[0049] Figure 2 A flowchart illustrating the parameter optimization method for fusion sensors applied in this embodiment of the invention;

[0050] Figure 3 This is a second schematic flowchart of the parameter optimization method for fused sensors according to an embodiment of the present invention;

[0051] Figure 4 This is the third flowchart illustrating the parameter optimization method for fused sensors according to an embodiment of the present invention;

[0052] Figure 5 This is a schematic diagram of the structure of an ultra-high frequency-overvoltage fusion sensor;

[0053] Figure 6 This is a schematic diagram of the structure of the ultra-high frequency-overvoltage fusion sensor optimized using the parameter optimization method of the fusion sensor according to an embodiment of the present invention;

[0054] Figure 7 This is a schematic block diagram of the parameter optimization device for fusion sensors according to an embodiment of the present invention;

[0055] Figure 8This is a schematic block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Partial discharge detection is crucial for assessing the insulation reliability and operational status of gas-insulated equipment and is widely used for condition monitoring in substations. Among the various partial discharge detection techniques, ultra-high frequency (UHF) signal detection is widely applied in gas-insulated substations due to its high sensitivity and strong anti-interference capabilities. UHF detection primarily detects frequency components above 300MHz generated by partial discharges, effectively avoiding environmental factors and corona interference, making it a relatively ideal detection method.

[0058] However, in actual operation, power equipment inevitably experiences various overvoltages from sources such as lightning surges, circuit breaker operations, and disconnector switches. Under the influence of overvoltages, normally operating power equipment may be excited, leading to partial discharges. These discharges can rapidly develop under the influence of power frequency voltage, resulting in insulation breakdown and posing a serious threat to the safe and reliable operation of the power equipment. Therefore, monitoring the insulation condition of power equipment cannot be achieved solely through partial discharge detection; accurate and timely measurement of the overvoltage signals experienced by the power equipment is of great significance for assessing its insulation condition.

[0059] For field gas-insulated equipment, the detection methods for built-in UHF and overvoltage signals have been well-established, but there are few design schemes and applications for UHF-overvoltage fusion sensors. While built-in UHF and overvoltage sensors have some structural similarities, their fusion process generates stray parameters that affect their individual measurement performance. Therefore, the design of a fusion sensor requires comprehensive consideration of multiple factors and thorough parameter optimization. In previous UHF sensor optimization processes, the large computational load required for finite element analysis typically necessitates parameter scanning of each influencing structural parameter to select the best-performing one. However, with the introduction of overvoltage divider structures, the composite sensor structure becomes more complex, significantly increasing the number of parameters requiring optimization. If parameter scanning is still used for optimization, the computational load increases significantly, and accuracy is difficult to guarantee. Therefore, a more scientific optimization design method is needed.

[0060] This invention provides a parameter optimization method for fusion sensors, see [link to relevant documentation]. Figure 1 As shown, Figure 1 This is one of the flowcharts illustrating the parameter optimization method for fused sensors according to an embodiment of the present invention, including:

[0061] Step 11: Receive the configuration items input by the user through the interactive terminal to obtain the set of structural parameters to be optimized. The configuration items are used to indicate the structural parameters to be optimized in the sensor structural parameters.

[0062] Step 12: Sampling is performed in the parameter space to obtain a set of sample structure parameter points; the parameter space consists of multiple sets of structure parameters to be optimized, and the parameter values ​​of the structure parameters to be optimized in the set of structure parameters to be optimized that constitute the parameter space are randomly generated. The set of sample structure parameter points consists of the set of structure parameters to be optimized selected in the parameter space, and the sample structure parameter points in the set of sample structure parameter points correspond one-to-one with the set of structure parameters to be optimized selected.

[0063] Calculation step 13: Based on the set of sample structure parameter points, calculate the performance parameters of the sample points that correspond one-to-one with the sample structure parameter points;

[0064] Step 14: Determine the target parameters based on the sample structure parameter points and sample point performance parameters.

[0065] In some embodiments of the present invention, the fusion sensor is optionally an ultra-high frequency-overvoltage fusion sensor, which can be used in gas-insulated equipment.

[0066] For example, the ultra-high frequency equivalent height H of the ultra-high frequency-overvoltage fusion sensor e Antenna parameters S 11 The three parameters of voltage divider capacitor were optimized, see [link to optimization]. Figure 2 As shown, Figure 2 A flowchart illustrating the parameter optimization method for fusion sensors according to embodiments of the present invention is provided, including:

[0067] 1) Based on the proposed sensor structure, the user selects i structural parameters S from the structural parameters that may affect the fusion sensor for optimization design. n = [a1, a2...a i ] T (Equivalent to the set of structural parameters to be optimized in the embodiments of the present invention), wherein: a i The geometric parameters of the sensor (equivalent to the structural parameters to be optimized in the embodiments of this invention) include, but are not limited to, the size of the UHF antenna, the outer diameter of the overvoltage divider arm, the thickness of the divider arm, and the height difference between the antenna and the electrode.

[0068] 2) Based on the selected structural parameters, randomly select a set of sample structural parameter points S = [S1, S2...S...] from the parameter space using a sampling algorithm. n (Equivalent to the sample structure parameter point set in the embodiments of the present invention), each parameter point S i S corresponds to 1) n n is the number of samples drawn, S n The included components are the structural parameters involved in the sensor optimization process. For example, a i Including the UHF antenna dimensions and the outer diameter of the overvoltage divider arm, each item S in the sample structural parameter point set S... n These all correspond to the dimensions of the UHF antenna and the outer diameter of the overvoltage divider arm.

[0069] 3) Calculate the UHF equivalent height H of the parameter points in the sample structure parameter point set in 2). e S 11 The parameters, such as voltage divider capacitor parameters, are fused sensor performance parameters (equivalent to the sample point performance parameters calculated in this embodiment that correspond one-to-one with the sample structure parameter points). The UHF equivalent height can be obtained by applying a normalized plane wave with its propagation direction parallel to the sensor surface and its electric field direction perpendicular to the antenna plate surface to simulate the propagation of TEM waves (Transverse Electromagnetic Waves) in the waveguide of a gas-insulated device, and by calculating the ratio of the sensor feed rod voltage to the surface electric field strength. Its equivalent height can be expressed as:

[0070]

[0071] Where U(f) is the output voltage of the feed section, and E(f) is the electric field strength on the sensor surface.

[0072] The antenna S can be obtained by calculating the ratio of the voltage incident and reflected signals at different input frequency bands of the feed port. 11 parameter:

[0073]

[0074] In the formula, U r and U i S represents the reflected voltage and input voltage of the UHF sensor feed rod interface, respectively. 11 The lower the parameter value, the better the sensor performance.

[0075] The voltage divider capacitor of the low-voltage arm can be directly solved using the electrostatic field.

[0076] The target parameters are determined based on the sample structure parameters and sample performance parameters.

[0077] In this embodiment of the invention, by receiving configuration items input by the user through an interactive terminal, a set of structural parameters to be optimized is obtained. Sample structural parameter points are then selected by sampling in the parameter space. Based on the set of sample structural parameter points, performance parameters corresponding one-to-one with each sample structural parameter point are calculated. Based on the sample structural parameter points and the performance parameters, target parameters are determined. This allows each parameter to be optimized to be optimized in a unified manner as a set, avoiding the complex calculation process of optimizing each parameter separately and then integrating them, as required by existing parameter scanning methods. The optimization using this embodiment requires less computation, less computing power, and is less costly.

[0078] Furthermore, since all parameters to be optimized can be optimized in a coordinated manner in the form of a set, mutual interference between the parameters during the optimization process is avoided, thereby avoiding the time cost of correcting interference. The embodiments of the present invention have high optimization efficiency and high optimization accuracy.

[0079] In some embodiments of the present invention, optionally,

[0080] Before receiving step 11, the following are included:

[0081] Acquisition steps: Acquire sensor installation information; calculate structural parameter thresholds corresponding one-to-one with the sensor structural parameters based on the sensor installation information; send the structural parameter thresholds to the interactive terminal, whereby the structural parameter thresholds are used to determine the set of structural parameters to be optimized.

[0082] For example, the ultra-high frequency equivalent height H of the ultra-high frequency-overvoltage fusion sensor e Antenna parameters S 11 The three parameters of voltage divider capacitor were optimized, see [link to optimization]. Figure 2 As shown, Figure 2 A flowchart illustrating the parameter optimization method for fusion sensors according to embodiments of the present invention is provided, including:

[0083] Define the sensor parameters required for the fusion sensor design to perform ultra-high frequency detection and overvoltage measurement, namely: ultra-high frequency equivalent height H. e Antenna parameters S 11 and voltage divider capacitors.

[0084] Depending on the voltage level of the gas-insulated equipment on site, the size of its mounting manhole is also limited. The depth and inner diameter requirements of the manhole restrict the overall height of the fusion sensor and the outer diameter of the outermost structure of the sensor. Therefore, before the design begins, the upper limit of the sensor's structural parameters (equivalent to the structural parameter threshold in the embodiments of this invention) should be planned based on the applicable platform of the sensor to be used.

[0085] 1) Based on the proposed sensor structure, the user selects i structural parameters S from the structural parameters that may affect the fusion sensor for optimization design. n = [a1, a2...a i ] T , where: a i The geometric parameters for designing the sensor include, but are not limited to, the size of the UHF antenna, the outer diameter of the overvoltage divider arm, the thickness of the divider arm, and the height difference between the antenna and the electrode.

[0086] 2) Based on the selected structural parameters, randomly select a set of sample structural parameter points S = [S1, S2...S...] from the parameter space using a sampling algorithm. n ], each parameter point S i S corresponds to 1) n n is the number of samples drawn, S n The included components are the structural parameters involved in the sensor optimization process. For example, a i Including the UHF antenna dimensions and the outer diameter of the overvoltage divider arm, each item S in the sample structural parameter point set S... n These all correspond to the dimensions of the UHF antenna and the outer diameter of the overvoltage divider arm.

[0087] 3) Calculate the UHF equivalent height H of the parameter points in the sample structure parameter point set in 2). e S 11 The parameters, including voltage divider capacitor parameters, are fused with sensor performance parameters. The UHF equivalent height can be obtained by applying a normalized plane wave with its propagation direction parallel to the sensor surface and its electric field direction perpendicular to the antenna plate surface to simulate the propagation of TEM (Transverse Electromagnetic Wave) waves in the waveguide of a gas-insulated device, and by calculating the ratio of the sensor feed rod voltage to the surface electric field strength. Its equivalent height can be expressed as:

[0088]

[0089] Where U(f) is the output voltage of the feed section, and E(f) is the electric field strength on the sensor surface.

[0090] The antenna S can be obtained by calculating the ratio of the voltage incident and reflected signals at different input frequency bands of the feed port. 11 parameter:

[0091]

[0092] In the formula, U r and U i S represents the reflected voltage and input voltage of the UHF sensor feed rod interface, respectively. 11 The lower the parameter value, the better the sensor performance.

[0093] The voltage divider capacitor of the low-voltage arm can be directly solved using the electrostatic field.

[0094] The target parameters are determined based on the sample structure parameters and sample performance parameters.

[0095] In some embodiments of the present invention, optionally,

[0096] Based on the set of sample structure parameter points, the performance parameters of the sample points corresponding one-to-one with the sample structure parameter points are calculated, including:

[0097] Based on the set of sample structure parameter points, the performance parameters of the sample points corresponding one-to-one with the sample structure parameter points are calculated using the finite element method.

[0098] In some embodiments of the present invention, see optionally, see Figure 3 As shown, Figure 3 This is a second schematic flowchart of the parameter optimization method for fused sensors according to an embodiment of the present invention. Step 14 includes:

[0099] Verification step 21: Verify the correlation between each sample structural parameter point and the corresponding sample point performance parameter to obtain the correlation verification result;

[0100] First execution step 22: If the correlation verification result is high correlation, determine the currently verified sample structural parameter point as a target structural parameter point, return to the verification step, until all sample structural parameter points have been verified; if the correlation verification result is low correlation, return to the verification step, until all sample structural parameter points have been verified.

[0101] Second execution step 23: Construct a new parameter space with the set of parameters to be optimized corresponding to the target structural parameter points, and execute the selection step and calculation step again to obtain new sample structural parameter points and new sample point performance parameters that correspond one-to-one with the new sample structural parameter points.

[0102] Third execution step 24: Determine the target parameters based on the new sample structure parameter points and the new sample point performance parameters.

[0103] For example, the ultra-high frequency equivalent height H of the ultra-high frequency-overvoltage fusion sensor e Antenna parameters S 11 The three parameters of voltage divider capacitor were optimized, see [link to optimization]. Figure 2 As shown, Figure 2 A flowchart illustrating the parameter optimization method for fusion sensors according to embodiments of the present invention is provided, including:

[0104] 1) Based on the proposed sensor structure, the user selects i structural parameters S from the structural parameters that may affect the fusion sensor for optimization design. n = [a1, a2...a i ] T , where: a i The geometric parameters for designing the sensor include, but are not limited to, the size of the UHF antenna, the outer diameter of the overvoltage divider arm, the thickness of the divider arm, and the height difference between the antenna and the electrode.

[0105] 2) Based on the selected structural parameters, randomly select a set of sample structural parameter points S = [S1, S2...S...] from the parameter space using a sampling algorithm. n ], each parameter point S i S corresponds to 1) n n is the number of samples drawn, S n The included components are the structural parameters involved in the sensor optimization process. For example, a i Including the UHF antenna dimensions and the outer diameter of the overvoltage divider arm, each item S in the sample structural parameter point set S... n These all correspond to the dimensions of the UHF antenna and the outer diameter of the overvoltage divider arm.

[0106] 3) The UHF equivalent height H of the parameter points in the sample structure parameter point set in 2) is calculated using the finite element method. e S 11 The parameters, including voltage divider capacitor parameters, are fused with sensor performance parameters. The UHF equivalent height can be obtained by applying a normalized plane wave with its propagation direction parallel to the sensor surface and its electric field direction perpendicular to the antenna plate surface to simulate the propagation of TEM (Transverse Electromagnetic Wave) waves in the waveguide of a gas-insulated device, and by calculating the ratio of the sensor feed rod voltage to the surface electric field strength. Its equivalent height can be expressed as:

[0107]

[0108] Where U(f) is the output voltage of the feed section, and E(f) is the electric field strength on the sensor surface.

[0109] The antenna S can be obtained by calculating the ratio of the voltage incident and reflected signals at different input frequency bands of the feed port. 11 parameter:

[0110]

[0111] In the formula, U r and U i S represents the reflected voltage and input voltage of the UHF sensor feed rod interface, respectively. 11The lower the parameter value, the better the sensor performance.

[0112] The voltage divider capacitor of the low-voltage arm can be directly solved using the electrostatic field.

[0113] 4) Based on the sensor structural parameters obtained in 2) and the sensor performance parameters in 3), conduct sensitivity analysis to investigate the correlation between the performance parameters of the composite sensor and the initially adopted optimized sensor parameters in 3). This can be expressed as:

[0114]

[0115] Where R is the i-th structural parameter a i The impact of sensor performance on sensitivity; y p The objective function for sensor optimization includes the sensor equivalent height, S... 11 The parameters and the overvoltage divider capacitor are three items; b p This represents the weight of each objective function in the sensitivity analysis process. Based on the sensitivity analysis results and factors such as sensor manufacturing process, parameters with low correlation or low sensitivity within the optimizable range are eliminated, thereby generating a new optimization space S. n = [a1, a2...a] j ] T , j≤i.

[0116] The evaluation criteria for the degree of correlation need to be comprehensively considered based on the calculation results. If there are parameters whose sensitivity is significantly lower than that of other structural parameters, they can be appropriately removed. If the influence of each parameter is comparable, or if the computing power is sufficient, the step of removing parameters can be omitted. Therefore, the new optimization space dimension is given as j≤i, rather than j<i.

[0117] Furthermore, removing parameters with low correlation or low sensitivity within the optimizable range involves eliminating redundant parameters. Sensitivity analysis considers a comprehensive range of parameters, which may include those with minimal impact on sensor performance; therefore, these can be selectively removed. For example, S can be a parameter set containing j parameters 'a', each 'a' representing a structural parameter. The j parameters in S can construct a sensor structure, which is used as a unit during optimization.

[0118] 5) New optimization space S n = [a1, a2...a] j ] T If j≤i, repeat steps 2) and 3) (equivalent to selection step 12 and calculation step 13 in this embodiment) to obtain a new set of sample structure parameter points S (equivalent to new sample structure parameter points in this embodiment) and a new H. e The new S11 The parameters and the new voltage dividing capacitor (equivalent to the new sample point performance parameters that correspond one-to-one with the new sample structure parameter points in the embodiments of this invention).

[0119] Based on the new sample structure parameter point set S and the new H e The new S 11 Determine the target parameters by considering the parameters and the new voltage divider capacitor.

[0120] In this embodiment of the invention, a new parameter space is constructed using all highly correlated sample structure parameter points obtained through verification. The selection and selection steps are executed again. Based on the obtained new sample structure parameter points and the performance parameters of the new sample points that correspond one-to-one with the new sample structure parameter points, the target parameters are determined. This helps to eliminate the interference of low-correlation sample structure parameter points on the target parameters, further improving the optimization accuracy of the parameter optimization method of the fusion sensor in this embodiment of the invention. Since low-correlation sample structure parameter points are eliminated, the need for multiple rounds of interference elimination due to the interference of low-correlation sample structure parameter points on the target parameters is avoided, further improving the optimization efficiency of the parameter optimization method of the fusion sensor in this embodiment of the invention, reducing the required computational load, reducing the required computing resources, and reducing costs.

[0121] In some embodiments of the present invention, optionally, the selection step 12 and the calculation step 13 are executed again in the second execution step 23 to obtain a new set of sample structure parameter points;

[0122] See Figure 4 As shown, Figure 4 This is a third flowchart illustrating the parameter optimization method for fused sensors according to an embodiment of the present invention. The third execution step 24 includes:

[0123] Modeling step 31: Establish a regression surrogate model based on the new sample structure parameter points and the new sample point performance parameters;

[0124] Second calculation step 32: Substitute the new set of sample structure parameter points into the regression surrogate model to calculate the performance parameters of the target sample points;

[0125] Comparison step 33: Compare the performance parameters of the target sample points with the performance parameters of the new sample points to obtain the comparison results;

[0126] Fourth execution step 34: If the comparison result shows that the difference between the performance parameters of the target sample point and the performance parameters of the new sample point is less than the preset difference threshold, the regression surrogate model is determined to be the target surrogate model;

[0127] The second step, step 35, involves optimizing the target surrogate model based on the new set of sample structure parameter points to determine the target parameters.

[0128] For example, the ultra-high frequency equivalent height H of the ultra-high frequency-overvoltage fusion sensor e Antenna parameters S 11 The three parameters of voltage divider capacitor were optimized, see [link to optimization]. Figure 2 As shown, Figure 2 A flowchart illustrating the parameter optimization method for fusion sensors according to embodiments of the present invention is provided, including:

[0129] 1) Based on the proposed sensor structure, the user selects i structural parameters S from the structural parameters that may affect the fusion sensor for optimization design. n = [a1, a2...a i ] T , where: a i The geometric parameters for designing the sensor include, but are not limited to, the size of the UHF antenna, the outer diameter of the overvoltage divider arm, the thickness of the divider arm, and the height difference between the antenna and the electrode.

[0130] 2) Based on the selected structural parameters, randomly select a set of sample structural parameter points S = [S1, S2...S...] from the parameter space using a sampling algorithm. n ], each parameter point S i S corresponds to 1) n n is the number of samples drawn, S n The included components are the structural parameters involved in the sensor optimization process. For example, a i Including the UHF antenna dimensions and the outer diameter of the overvoltage divider arm, each item S in the sample structural parameter point set S... n These all correspond to the dimensions of the UHF antenna and the outer diameter of the overvoltage divider arm.

[0131] 3) The UHF equivalent height H of the parameter points in the sample structure parameter point set in 2) is calculated using the finite element method. e S 11 The parameters, including voltage divider capacitor parameters, are fused with sensor performance parameters. The UHF equivalent height can be obtained by applying a normalized plane wave with its propagation direction parallel to the sensor surface and its electric field direction perpendicular to the antenna plate surface to simulate the propagation of TEM (Transverse Electromagnetic Wave) waves in the waveguide of a gas-insulated device, and by calculating the ratio of the sensor feed rod voltage to the surface electric field strength. Its equivalent height can be expressed as:

[0132]

[0133] Where U(f) is the output voltage of the feed section, and E(f) is the electric field strength on the sensor surface.

[0134] The antenna S can be obtained by calculating the ratio of the voltage incident and reflected signals at different input frequency bands of the feed port. 11 parameter:

[0135]

[0136] In the formula, U r and U i S represents the reflected voltage and input voltage of the UHF sensor feed rod interface, respectively. 11 The lower the parameter value, the better the sensor performance.

[0137] The voltage divider capacitor of the low-voltage arm can be directly solved using the electrostatic field.

[0138] 4) Based on the sensor structural parameters obtained in 2) and the sensor performance parameters in 3), conduct sensitivity analysis to investigate the correlation between the performance parameters of the composite sensor and the initially adopted optimized sensor parameters in 3). This can be expressed as:

[0139]

[0140] Where R is the i-th structural parameter a i The impact of sensor performance on sensitivity; y p The objective function for sensor optimization includes the sensor equivalent height, S... 11 The parameters and the overvoltage divider capacitor are three items; b p This represents the weight of each objective function in the sensitivity analysis process. Based on the sensitivity analysis results and factors such as sensor manufacturing process, parameters with low correlation or low sensitivity within the optimizable range are eliminated, thereby generating a new optimization space S. n = [a1, a2...a] j ] T , j≤i.

[0141] The evaluation criteria for the degree of correlation need to be comprehensively considered based on the calculation results. If there are parameters whose sensitivity is significantly lower than that of other structural parameters, they can be appropriately removed. If the influence of each parameter is comparable, or if the computing power is sufficient, the step of removing parameters can be omitted. Therefore, the new optimization space dimension is given as j≤i, rather than j<i.

[0142] Furthermore, removing parameters with low correlation or low sensitivity within the optimizable range involves eliminating redundant parameters. Sensitivity analysis considers a comprehensive range of parameters, which may include those with minimal impact on sensor performance; therefore, these can be selectively removed. For example, S can be a parameter set containing j parameters 'a', each 'a' representing a structural parameter. The j parameters in S can construct a sensor structure, which is used as a unit during optimization.

[0143] 5) New optimization space S n = [a1, a2...a] j ] T If j≤i, repeat steps 2) and 3) (equivalent to selection step 12 and calculation step 13 in this embodiment) to obtain a new set of sample structure parameter points S (equivalent to new sample structure parameter points in this embodiment) and a new H. e The new S 11 The parameters and the new voltage dividing capacitor (equivalent to the new sample point performance parameters that correspond one-to-one with the new sample structure parameter points in the embodiments of this invention).

[0144] 6) Based on the structural parameters and calculated performance parameters in 5) (i.e., the new sample structural parameter point set S, the new H) e and the new S 11 (Parameters) to establish a regression proxy model.

[0145] Taking the Kriging regression model as an example, its linear regression model can be expressed as:

[0146]

[0147] in ω is the predicted value of the function; ω is the regression coefficient, which is related to the sample points sampled in 5) and their corresponding sensor performance parameters; y s The sensor performance parameters corresponding to the sample points calculated in step 5) are used to replace the finite element method in subsequent optimization processes to calculate the sensor performance corresponding to different structural parameters.

[0148] 7) In the new optimization space described in 4), random sample points are generated and finite element calculations are performed. The sample parameters are then input into the surrogate model for calculation. The finite element calculation results are compared with the sensor performance parameter calculation results of the surrogate model to determine whether the deviation between the surrogate model calculation results and the finite element sensor performance results meets the design requirements (equivalent to comparing the performance parameters of the target sample points with the performance parameters of the new sample points in this embodiment of the invention to obtain the comparison results).

[0149] If the calculation result of the surrogate model of the sample point matches the finite element result (equivalent to if the comparison result in this embodiment is that the difference between the performance parameters of the target sample point and the performance parameters of the new sample point is less than the preset difference threshold), the regression surrogate model is determined to be the target surrogate model.

[0150] Based on the new set of sample structure parameter points, the target surrogate model is optimized and the target parameters are determined.

[0151] In this embodiment of the invention, by comparing whether the difference between the performance parameters of the target sample points and the performance parameters of the new sample points is less than a preset difference threshold, if it is less, the regression surrogate model is determined as the target surrogate model. Based on the new set of sample structure parameter points, the target surrogate model is optimized and solved to determine the target parameters. In the calculation process of large-scale parameter optimization, the surrogate model is simpler than the existing finite element method, and can replace the time-consuming finite element calculation with a simpler set of linear equations, facilitating subsequent optimization of the sensor structure. This further improves the optimization efficiency of the parameter optimization method for fused sensors in this embodiment of the invention, reduces the required computational load, reduces the computational resources required, and lowers costs.

[0152] In some embodiments of the present invention, see optionally, see Figure 4 As shown, the comparison after step 33 includes:

[0153] Fifth execution step 36: If the comparison result shows that the difference between the performance parameters of the target sample point and the performance parameters of the new sample point is greater than or equal to the preset difference threshold, return to the second execution step until the comparison result shows that the difference between the performance parameters of the target sample point and the performance parameters of the new sample point is less than the preset difference threshold.

[0154] For example, the ultra-high frequency equivalent height H of the ultra-high frequency-overvoltage fusion sensor e Antenna parameters S 11 The three parameters of voltage divider capacitor were optimized, see [link to optimization]. Figure 2 As shown, Figure 2 This is a flowchart illustrating the parameter optimization method for fusion sensors according to an embodiment of the present invention, wherein 7):

[0155] If the surrogate model calculation result of the sample point does not match the finite element result (equivalent to if the comparison result in this embodiment is that the difference between the performance parameters of the target sample point and the performance parameters of the new sample point is greater than or equal to the preset difference threshold), then it is used as a sample point in the surrogate model establishment process, the surrogate model is recalculated and improved, and steps 5) to 7) are repeated until the model accuracy meets the requirements (equivalent to if the comparison result in this embodiment is that the difference between the performance parameters of the target sample point and the performance parameters of the new sample point is less than the preset difference threshold).

[0156] In some embodiments of the present invention, optionally,

[0157] The algorithm for optimization in the second determination step 35 includes at least one of the following:

[0158] Genetic algorithm, particle swarm optimization algorithm, and annealing algorithm.

[0159] Genetic Algorithms (GAs) were first proposed by John Holland in the 1970s. These algorithms are designed based on the laws of biological evolution in nature. They are computational models that simulate the biological evolutionary process, based on Darwin's theory of evolutionary natural selection and genetic mechanisms. GAs are a method for searching for optimal solutions by simulating natural evolution. Through mathematical methods and computer simulation, the algorithm transforms the problem-solving process into processes similar to the crossover and mutation of chromosomes and genes in biological evolution. When solving complex combinatorial optimization problems, GAs typically achieve better optimization results faster than some conventional optimization algorithms. Genetic algorithms have been widely applied in fields such as combinatorial optimization, machine learning, signal processing, adaptive control, and artificial life.

[0160] Particle Swarm Optimization (PSO), also known as particle swarm optimization algorithm, is a stochastic search algorithm based on group cooperation, developed by simulating the foraging behavior of flocks of birds. It is generally considered a type of swarm intelligence (SI). It can be incorporated into Multiagent Optimization Systems (MAOS). PSO was invented by Dr. Eberhart and Dr. Kennedy.

[0161] Simulated Annealing (SAA) is a general probabilistic algorithm used to find the optimal solution to a problem within a large search space. It was invented by S. Kirkpatrick, C.D. Gelatt, and M.V. C.E.C. in 1983. (The last sentence appears to be incomplete and possibly refers to a different algorithm or concept.) He also independently invented this algorithm in 1985. Simulated annealing is one of the effective methods for solving the TSP problem.

[0162] The principle of simulated annealing is similar to that of metal annealing: applying thermodynamics to statistics, each point in the search space is imagined as a molecule in the air; the energy of a molecule is its kinetic energy; and each point in the search space, like an air molecule, carries "energy" to represent its suitability for the proposition. The algorithm starts with an arbitrary point in the search space: at each step, a "neighbor" is selected, and then the probability of reaching the "neighbor" from the current position is calculated.

[0163] In some embodiments of the present invention, see, for example, [examples to be provided]. Figure 5 As shown, Figure 5This is a schematic diagram of the structure of an ultra-high frequency (UHF)-overvoltage fusion sensor, where: 1. UHF antenna plate; 2. Sealing ring; 3. UHF dielectric layer; 4. Overvoltage divider arm; 5. Overvoltage dielectric layer; 6. Flange.

[0164] See Figure 6 As shown, Figure 6 This is a schematic diagram of the structure of the ultra-high frequency-overvoltage fusion sensor optimized by the parameter optimization method of the fusion sensor according to the embodiment of the present invention. The numbers represent the target parameters (size data) and the unit is mm.

[0165] This invention provides a parameter optimization device for fused sensors, see [link to relevant documentation]. Figure 7 As shown, Figure 7 This is a schematic block diagram of the parameter optimization device for fusion sensors according to an embodiment of the present invention. The parameter optimization device 70 for fusion sensors includes:

[0166] The receiving module 71 is used to receive the following steps: receiving configuration items input by the user through the interactive terminal to obtain a set of parameters to be optimized, wherein the configuration items are used to indicate the structural parameters to be optimized in the sensor structural parameters;

[0167] The selection module 72 is used for the following steps: a random sampling algorithm is used to select samples in the parameter space to obtain a set of sample structure parameter points; the parameter space is composed of multiple sets of the structure parameters to be optimized, the parameter values ​​of the structure parameters to be optimized in the sets of the structure parameters to be optimized constituting the parameter space are randomly generated, the set of sample structure parameter points is composed of the selected sets of the structure parameters to be optimized in the parameter space, and the sample structure parameter points in the set of sample structure parameter points correspond one-to-one with the selected sets of the structure parameters to be optimized;

[0168] Calculation module 73 is used to calculate the following steps: based on the set of sample structure parameter points, calculate the sample point performance parameters that correspond one-to-one with the sample structure parameter points;

[0169] The determination module 74 is used to determine the following steps: determining the target parameters based on the sample structure parameter points and the sample point performance parameters.

[0170] In some embodiments of the present invention, optionally,

[0171] The receiving module 71 is further configured to acquire the following steps: acquiring sensor installation information; calculating structural parameter thresholds corresponding one-to-one with the sensor structural parameters based on the sensor installation information; and sending the structural parameter thresholds to the interactive terminal, wherein the structural parameter thresholds are used to determine the set of structural parameters to be optimized.

[0172] In some embodiments of the present invention, optionally,

[0173] The calculation module 73 is also used to calculate the sample point performance parameters corresponding one-to-one with the sample structure parameter points using the finite element method based on the sample structure parameter point set.

[0174] In some embodiments of the present invention, optionally,

[0175] The determining module 74 is also used for the verification step: verifying the correlation between the sample structure parameter points and the corresponding sample point performance parameters one by one to obtain the correlation verification result;

[0176] The determining module 74 is further configured to perform the first execution step: if the correlation verification result is high correlation, determine the currently verified sample structural parameter point as a target structural parameter point, and return to the verification step until all sample structural parameter points have been verified; if the correlation verification result is low correlation, return to the verification step until all sample structural parameter points have been verified.

[0177] The determining module 74 is also used in the second execution step: to construct a new parameter space with the set of parameters to be optimized corresponding to the target structural parameter points, and to execute the selection step and the calculation step again to obtain new sample structural parameter points and new sample point performance parameters that correspond one-to-one with the new sample structural parameter points;

[0178] The determining module 74 is also used in the third execution step: determining the target parameter based on the new sample structure parameter points and the new sample point performance parameters.

[0179] In some embodiments of the present invention, optionally,

[0180] The determining module 74 is also used in the modeling step: establishing a regression surrogate model based on the new sample structure parameter points and the new sample point performance parameters;

[0181] The determining module 74 is also used in the second calculation step: substituting the new set of sample structure parameter points into the regression surrogate model to calculate the performance parameters of the target sample points;

[0182] The determining module 74 is also used for the comparison step: comparing the performance parameters of the target sample point with the new performance parameters of the sample point to obtain a comparison result;

[0183] The determining module 74 is also used in the fourth execution step: if the comparison result is that the difference between the performance parameter of the target sample point and the new performance parameter of the sample point is less than a preset difference threshold, the regression surrogate model is determined to be the target surrogate model;

[0184] The determining module 74 is also used in the second determining step: optimizing the target proxy model based on the new set of sample structure parameter points to determine the target parameters.

[0185] In some embodiments of the present invention, optionally,

[0186] The determining module 74 is further configured to perform a fifth execution step: if the comparison result is that the difference between the performance parameter of the target sample point and the new performance parameter of the sample point is greater than or equal to the preset difference threshold, return to the second execution step until the comparison result is that the difference between the performance parameter of the target sample point and the new performance parameter of the sample point is less than the preset difference threshold.

[0187] The parameter optimization device for fusion sensors provided in this application embodiment can achieve... Figures 1 to 6 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0188] This invention provides an electronic device 80, see [link to relevant documentation]. Figure 8 As shown, Figure 8 This is a schematic block diagram of an electronic device 80 according to an embodiment of the present invention, including a processor 81, a memory 82, and a program or instructions stored in the memory 82 and executable on the processor 81. When the program or instructions are executed by the processor, they implement the steps in any of the parameter optimization methods of the fusion sensor of the present invention.

[0189] This invention provides a readable storage medium on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements the various processes of the embodiment of the parameter optimization method for fused sensors as described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0190] The readable storage medium mentioned above includes, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0191] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. A method of parameter optimization for a fusion sensor, characterized by, The method comprises the following steps: a receiving step: receiving configuration items input by a user through an interactive terminal to obtain a set of to-be-optimized structure parameters, wherein the configuration items are used to indicate to-be-optimized structure parameters in sensor structure parameters; a selecting step: sampling and selecting in a parameter space to obtain a set of sample structure parameter points, wherein the parameter space is composed of multiple sets of the set of to-be-optimized structure parameters, the parameter values of the to-be-optimized structure parameters in the set of to-be-optimized structure parameters that constitute the parameter space are randomly generated, the set of sample structure parameter points is composed of the set of to-be-optimized structure parameters selected from the parameter space, and each sample structure parameter point in the set of sample structure parameter points corresponds to the set of to-be-optimized structure parameters selected from the parameter space; a calculating step: calculating sample point performance parameters corresponding to the set of sample structure parameter points according to the set of sample structure parameter points; a determining step: determining a target parameter according to the set of sample structure parameter points and the sample point performance parameters; the determining step comprises the following steps: a checking step: checking the correlation between the set of sample structure parameter points and the sample point performance parameters corresponding to the set of sample structure parameter points one by one to obtain a correlation checking result; a first execution step: if the correlation checking result is high correlation, determining that the sample structure parameter point currently checked is a target structure parameter point, returning to the checking step until all the sample structure parameter points are checked; if the correlation checking result is low correlation, returning to the checking step until all the sample structure parameter points are checked; a second execution step: constructing a new parameter space with the set of to-be-optimized parameters corresponding to the target structure parameter point, executing the selecting step and the calculating step again to obtain new sample structure parameter points and new sample point performance parameters corresponding to the new sample structure parameter points; a third execution step: determining the target parameter according to the new sample structure parameter points and the new sample point performance parameters; the expression of the correlation is as follows: ； Wherein, R is the i th structure parameter a i Sensitivity, representing the influence on sensor performance y p Objective function for sensor optimization, including sensor VHF equivalent height H e , antenna parameters S 11 and overvoltage dividing capacitor b p Represent the weight of each objective function.

2. The parameter optimization method of the fusion sensor according to claim 1, wherein: the receiving step comprises the following step: an obtaining step: obtaining installation information of the sensor; calculating structure parameter thresholds corresponding to the sensor structure parameters according to the installation information of the sensor; and sending the structure parameter thresholds to the interactive terminal, wherein the structure parameter thresholds are used to determine the set of to-be-optimized structure parameters.

3. The parameter optimization method of the fusion sensor according to claim 1, wherein: calculating sample point performance parameters corresponding to the set of sample structure parameter points according to the set of sample structure parameter points comprises the following step: calculating sample point performance parameters corresponding to the set of sample structure parameter points according to the set of sample structure parameter points by using a finite element calculation method.

4. The parameter optimization method of the fusion sensor according to claim 1, wherein: the re-execution of the selecting step and the calculating step in the second execution step further obtains a new set of sample structure parameter points; the third execution step comprises the following steps: The modeling step: according to the new sample structure parameter point and the new sample point performance parameter, a regression proxy model is established; The second calculation step: the new sample structure parameter point set is substituted into the regression proxy model, and the target sample point performance parameter is calculated; The comparison step: the target sample point performance parameter and the new sample point performance parameter are compared to obtain a comparison result; The fourth execution step: if the comparison result is that the difference between the target sample point performance parameter and the new sample point performance parameter is less than a preset difference threshold, the regression proxy model is determined as a target proxy model; The second determination step: according to the new sample structure parameter point set, the target proxy model is optimized and solved to determine the target parameter.

5. The parameter optimization method of the fusion sensor according to claim 4, characterized in that: The comparison step includes: The fifth execution step: if the comparison result is that the difference between the target sample point performance parameter and the new sample point performance parameter is greater than or equal to the preset difference threshold, the second execution step is returned until the comparison result is that the difference between the target sample point performance parameter and the new sample point performance parameter is less than the preset difference threshold.

6. The parameter optimization method of the fusion sensor according to claim 4, characterized in that: The optimization and solving algorithm in the second determination step includes at least one of the following: Genetic algorithm, particle swarm algorithm and annealing algorithm.

7. A parameter optimization device for fused sensors, characterized in that, Including: The receiving module is configured to receive the configuration item input by the user through the interactive terminal to obtain the to-be-optimized parameter set, and the configuration item is used to indicate the to-be-optimized structure parameter in the sensor structure parameter; The selection module is configured to select the sample structure parameter point set by using a random sampling algorithm in a parameter space, wherein the parameter space is composed of multiple sets of the to-be-optimized structure parameter set, the parameter values of the to-be-optimized structure parameters in the to-be-optimized structure parameter set constituting the parameter space are randomly generated, the sample structure parameter point set is composed of the selected to-be-optimized structure parameter set in the parameter space, and each sample structure parameter point in the sample structure parameter point set corresponds to the selected to-be-optimized structure parameter set; The calculation module is configured to calculate the sample point performance parameter corresponding to the sample structure parameter point according to the sample structure parameter point set; The determination module is configured to determine the target parameter according to the sample structure parameter point and the sample point performance parameter; The determination step includes: The verification step: the correlation between the sample structure parameter point and the sample point performance parameter corresponding to the sample structure parameter point is verified one by one to obtain a correlation verification result; The first execution step: if the correlation check result is high correlation, determining the sample structure parameter point currently checked as a target structure parameter point, returning to the checking step until all the sample structure parameter points complete the checking; if the correlation check result is low correlation, returning to the checking step until all the sample structure parameter points complete the checking; The second execution step: constructing a new parameter space with the set of to-be-optimized parameters corresponding to the target structure parameter point, executing the selecting step and the calculating step again to obtain new sample structure parameter points and new sample point performance parameters corresponding to the new sample structure parameter points one by one; The third execution step: determining the target parameter according to the new sample structure parameter points and the new sample point performance parameters; The expression of the correlation is: ； Wherein, R is the i th structure parameter a i The sensitivity of the impact on the sensor performance, representing the correlation; y p The objective function of the sensor optimization, including the sensor VHF equivalent height H e , antenna parameters S 11 And the overvoltage voltage dividing capacitor three; b p Represent the weight of each objective function.

8. An electronic device, comprising: The processor, the memory and the program or the instructions stored on the memory and executable on the processor are included, and the program or the instructions are executed by the processor to realize the steps in the parameter optimization method of the fusion sensor.

9. A readable storage medium characterized by: The program or the instructions are stored on the readable storage medium, and the program or the instructions are executed by the processor to realize the steps in the parameter optimization method of the fusion sensor.

Images