Cover identification method based on multi-frequency excitation and detection device

Abstract

The invention discloses a covering identification method and detection device based on multi-frequency excitation, and belongs to the technical field of electronics and sensors, the covering identification method comprises the following steps: constructing an equivalent circuit of a sensitive capacitor, the equivalent circuit comprising an equivalent resistor, an equivalent inductor and an equivalent capacitor which are connected in series; at different temperatures, exciting the sensitive capacitor through excitation signals with different frequencies, and obtaining the resistance value of the equivalent resistor, the capacitance value of the equivalent capacitor and the category of the covering on the sensitive capacitor; taking the temperature value, the frequency value, the resistance value and the capacitance value of the same group as sample data, taking the corresponding covering category as a real label, and constructing a sample set; constructing a covering identification model based on a neural network, and training the covering identification model through the sample set; and realizing covering identification through the trained covering identification model. According to the invention, the covering can be identified accurately and reliably.

Description

Technical Field

[0001] The present invention relates to the field of electronic technology and sensor technology, and in particular to a covering object recognition method and a detection device based on multi-frequency excitation. Background Art

[0002] In the field of road surface cover detection, traditional detection methods mainly distinguish different types of road surface covers, such as ice, water, snow, and dry road surfaces, by the capacitance value reflected by the charge and discharge waveform of the sensitive capacitor. However, although the charge and discharge waveform of the sensitive capacitor is widely used to distinguish different road surface covers, in some cases, such as when there are similarities between snow and dry road surfaces, it may face the problem of reduced distinction accuracy. In some cases between ice and snow and dry road surfaces, the similarity of the charge and discharge waveform of the sensitive capacitor may cause detection errors. This error may be caused by certain specific weather or road surface conditions, making it impossible for the charge and discharge waveform to clearly distinguish between the two road surface covers. This may lead to uncertainty and unreliability in road surface cover detection, thereby affecting road safety and the reliability of vehicle driving. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method and a detection device for identifying a covering object based on multi-frequency excitation, so as to improve the accuracy and reliability of the detection of road covering objects.

[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0005] In a first aspect, the present invention provides a method for identifying a covering based on multi-frequency excitation, comprising:

[0006] Constructing an equivalent circuit of the sensitive capacitor, wherein the equivalent circuit includes an equivalent resistance, an equivalent inductance, and an equivalent capacitance connected in series;

[0007] At different temperatures, the sensitive capacitor is stimulated by excitation signals of different frequencies, and the resistance value of the equivalent resistor, the capacitance value of the equivalent capacitor, and the type of the covering on the sensitive capacitor are obtained;

[0008] The temperature values, frequency values, resistance values, and capacitance values ​​of the same group are used as sample data, and the corresponding covering categories are used as true labels to construct a sample set;

[0009] Constructing a covering recognition model based on a neural network, and training the covering recognition model through the sample set;

[0010] Covering recognition is achieved through the trained covering recognition model.

[0011] Optionally, the cover recognition model includes a first convolutional layer, a second convolutional layer, a flattening layer, a first fully connected layer, and a second fully connected layer connected in sequence;

[0012] The first convolution layer uses a convolution kernel of size 2, the number of input channels is 1, the number of output channels is 8, the stride is 1, and the padding is 0; the first convolution layer is used to process the input data and extract local features;

[0013] The second convolution layer uses a convolution kernel of size 2, the number of input channels is 8, the number of output channels is 16, the stride is 1, and the padding is 0; the second convolution layer is used to process the local features and extract global features;

[0014] The flattening layer flattens the multi-dimensional global features into a one-dimensional vector;

[0015] The first fully connected layer has an input feature number of 16 and an output feature number of 16; the first fully connected layer is used to perform high-level feature representation on the one-dimensional vector;

[0016] The second fully connected layer has an input feature number of 16 and an output feature number of 4; the second fully connected layer performs classification prediction based on the high-level feature representation;

[0017] The first convolutional layer, the second convolutional layer and the first fully connected layer are respectively provided with ReLU activation functions, and the ReLU activation functions are used to ensure that the features are effectively nonlinearized.

[0018] Optionally, during the training process of the cover recognition model, the loss between the prediction result and the true label is calculated by a cross entropy loss function, and the model parameters are updated by an Adam optimizer.

[0019] In a second aspect, the present invention provides a detection device applicable to the above-mentioned method for identifying a covered object based on multi-frequency excitation, wherein the detection device is configured to excite the sensitive capacitor by excitation signals of different frequencies at different temperatures, and obtain the resistance value of the equivalent resistor and the capacitance value of the equivalent capacitor; the detection device comprises:

[0020] Temperature sensor, used to collect temperature values;

[0021] A capacitor excitation circuit, connected to one end of the sensitive capacitor, for exciting the sensitive capacitor through excitation signals of different frequencies;

[0022] An impedance matching circuit, connected to the other end of the sensitive capacitor, for matching the impedance of the sensitive capacitor;

[0023] A phase difference detection circuit is used to obtain the voltage when the impedance matching circuit reaches a balanced state. With the voltage The phase difference between , the voltage With the voltage The phase difference between , the voltage is the voltage across the sensitive capacitor, is the voltage across the impedance matching circuit, the voltage is the voltage between the two ends of the sensitive capacitor and the impedance matching circuit after being connected;

[0024] A microprocessor is used to and the phase difference Calculate the resistance value of the equivalent resistor and the capacitance value of the equivalent capacitor.

[0025] Optionally, the capacitor excitation circuit includes a DAC module, a high-pass filter circuit and a first voltage follower connected in sequence, the DAC generates a sinusoidal wave signal, and the sinusoidal wave signal is filtered by the high-pass filter circuit and enhanced by the first voltage follower.

[0026] Optionally, the impedance matching circuit includes a plurality of parallel branches, each of which includes a switch and a weighted resistor connected in series, and the total resistance value of the impedance matching circuit is changed by controlling the on and off of the switch on each branch. , the total resistance Should be less than and as close as possible to , is the impedance of the equivalent capacitor, is the resistance value of the equivalent resistor, Is an imaginary unit.

[0027] Optionally, the phase difference detection circuit includes a second voltage follower, three voltage detection circuits, three square wave conversion circuits and a phase difference detection chip; the input end and the output end of the second voltage follower are respectively connected to the two ends of the impedance matching circuit, and the input ends of the three voltage detection circuits are respectively connected to the two ends of the sensitive capacitor, the two ends of the impedance matching circuit, and the two ends after the sensitive capacitor and the impedance matching circuit are connected, for measuring the voltage ,Voltage And voltage The input ends of the three square wave conversion circuits are respectively connected to the output ends of the three voltage detection circuits, and the input ends of the phase difference detection chip are respectively connected to the output ends of the three square wave conversion circuits, for obtaining the phase difference and phase difference ;

[0028]

[0029]

[0030] In the formula, Voltage ,Voltage And voltage signal, Phase difference and phase difference signal.

[0031] Optionally, the voltage detection circuit adopts a differential amplifier circuit, the phase conversion circuit adopts a voltage comparator, and the phase difference detection chip adopts a NOR gate logic chip.

[0032] Optionally, the voltage The output end of the voltage detection circuit is also connected to a full-wave rectifier and filter circuit for Sampling is performed to determine the total resistance value .

[0033] Optionally, the calculation formula of the resistance value of the equivalent resistor and the capacitance value of the equivalent capacitor is:

[0034]

[0035]

[0036]

[0037] In the formula, For voltage and The phase difference between For voltage and The phase difference between is the impedance of the equivalent capacitor, is the frequency of the excitation signal, is the resistance value of the equivalent resistor, is the capacitance value of the equivalent capacitor, is the total resistance of the impedance matching circuit.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The embodiment of the present invention provides a method and detection device for identifying a covering based on multi-frequency excitation. The detection device utilizes a combination of multi-frequency sensitive capacitor excitation and an impedance matching circuit. By exciting the capacitor to be tested at multiple frequency points, the impedance response at different frequencies is obtained, ensuring that when a certain frequency point cannot be distinguished, it can be supplemented and confirmed by the response data of other frequency points, so that the system can more comprehensively obtain the characteristics of the capacitor to be tested, thereby improving the accuracy of identifying the covering. Compared with the traditional method of detecting a single data source of charging and discharging waveforms and detecting the peak value and phase difference of sensitive capacitors, the condition of the detection surface can be more comprehensively and accurately understood, and the accuracy of identifying different coverings can be improved. After comprehensively obtaining the characteristics of the capacitor to be tested, these features can be quickly and real-time analyzed through the covering identification method, thereby achieving rapid response and monitoring of the condition of the detection surface. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flow chart of a method for identifying a covered object based on multi-frequency excitation provided by an embodiment of the present invention;

[0041] Figure 2 It is a topological schematic diagram of an equivalent circuit of a sensitive capacitor provided by the prior art;

[0042] Figure 3 It is a graph of the equivalent capacitance and equivalent resistance at 20℃ and -20℃ versus frequency provided by the prior art;

[0043] Figure 4 It is a test schematic diagram of the equivalent capacitance and equivalent resistance of dryness and water accumulation provided by an embodiment of the present invention;

[0044] Figure 5 1 is a test schematic diagram of equivalent capacitance and equivalent resistance of dryness, ice and snow provided by an embodiment of the present invention;

[0045] Figure 6 is a schematic diagram of the structure of a covering recognition model based on a neural network provided in an embodiment of the present invention;

[0046] Figure 7 is a test result diagram of a covering recognition model based on a neural network provided by an embodiment of the present invention;

[0047] Figure 8 is a hardware block diagram of a detection device provided by an embodiment of the present invention;

[0048] Fig. 9 is a topological schematic diagram of a capacitor excitation circuit provided by an embodiment of the present invention;

[0049] Fig.10 is a topological schematic diagram of an impedance matching circuit provided by an embodiment of the present invention;

[0050] Fig.11 is a detection principle diagram of a phase difference detection circuit provided by an embodiment of the present invention;

[0051] Fig.12 is a schematic diagram of vector method analysis provided by an embodiment of the present invention;

[0052] Fig.13 is the phase difference provided by the embodiment of the present invention and phase difference Schematic diagram of

[0053] Fig.14 The embodiment of the present invention provides Schematic diagram of vector method analysis with negative processing;

[0054] Fig.15 1 is a topological schematic diagram of a square wave conversion circuit provided in an embodiment of the present invention;

[0055] Fig.16 It is a schematic diagram of the phase difference extraction process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0057] Embodiment 1:

[0058] like Figure 1 As shown, an embodiment of the present invention provides a method for identifying a covered object based on multi-frequency excitation, comprising the following steps:

[0059] Step S1, constructing an equivalent circuit of a sensitive capacitor.

[0060] Due to the manufacturing process, actual sensitive capacitors have certain parasitic resistance and inductance. The existence of internal resistance causes energy loss during the charging and discharging process of the capacitor at the detection frequency, and introduces additional thermal effects. The internal inductance causes the impedance of the capacitor to increase in the high-frequency range. In high-frequency applications, the equivalent inductance of the capacitor will have a significant impact on the impedance of the capacitor, thereby limiting the performance of the capacitor.

[0061] In order to more accurately describe the actual sensitive capacitor, an equivalent circuit of the sensitive capacitor is constructed. Figure 2 As shown, the equivalent circuit includes equivalent resistances in series , equivalent inductance And the equivalent capacitance , its impedance for:

[0062]

[0063] When the formula satisfies: When , the capacitor behaves as capacitive.

[0064] When the formula satisfies: At high frequencies, capacitors behave like inductors.

[0065] When the formula satisfies: When the capacitive reactance vector is equal to the inductive reactance vector, the total impedance of the capacitor is the smallest, showing a pure resistance characteristic. It is called the self-resonant frequency of the capacitor.

[0066] In the embodiment of the present invention, the signal frequency is at a low frequency, and the internal inductance of the capacitor can be ignored. According to the polarization phenomenon of the dielectric and the existing dielectric loss and Debye relaxation effect, different detection frequencies and covers will affect the equivalent capacitance and equivalent resistance of the capacitor, such as Figure 3 As shown. At 20℃, the equivalent capacitance in the case of water accumulation is larger than that in the case of dryness, but the equivalent resistance is smaller; at -20℃, the equivalent capacitance and equivalent resistance of ice change greatly with frequency. The equivalent capacitance and equivalent resistance in the case of dryness and snow accumulation are relatively close and are less affected by frequency.

[0067] Therefore, it is very important to select a suitable detection frequency. When the detection frequency is constant, the equivalent capacitance and equivalent resistance of the capacitor only change with the different covering materials. In the embodiment of the present invention, an excitation signal of 10KHz to 100KHz is selected for multi-frequency excitation to perform design analysis.

[0068] like Figure 4 , Figure 5 As shown, different road covering conditions were tested at -30℃~60℃ and 10KHz~100KHz.

[0069] The covers are classified and judged according to the average values ​​of equivalent capacitance Cs and equivalent resistance Rs. When the temperature is greater than or equal to 0°C, the average values ​​of equivalent resistance Rs and equivalent capacitance Cs in dry and waterlogged conditions are as follows: Figure 4 When the temperature is less than 0℃, the average values ​​of the equivalent resistance Rs and equivalent capacitance Cs of dry, icy and snowy conditions are as follows: Figure 5As shown. According to the average value data of Cs and Rs under different covers, the ideal threshold is set, and the judgment is made according to the threshold. When the temperature is greater than or equal to 0℃, only the two situations of dryness and water accumulation are considered, and the equivalent capacitance value Cs can be directly distinguished. The equivalent capacitance value Cs when water accumulates is generally nf level, and the equivalent capacitance value Cs when dry is generally pf level. The equivalent capacitance value Cs when water accumulates is one order of magnitude larger than that of dryness. Therefore, when it is above zero, the distinction between dryness and ice can be completed by detecting the equivalent capacitance value Cs at any frequency. When the temperature is less than 0℃, it is necessary to consider three situations: dryness, ice and snow accumulation. The equivalent capacitance values ​​Cs in the three situations are relatively close and have intersections, so it is impossible to make a direct judgment by the Cs value. According to the above test of the equivalent resistance of dryness, snow accumulation and ice, it can be found that the equivalent resistance value Rs of the three has a distinguishing degree, but the data will cross at multiple temperature points at low frequency, and the data will cross at -10℃ to 0℃ at medium frequency, while the data will cross less at high frequency, and the higher the frequency, the more stable the data. Therefore, it can be seen that, combined with the temperature data, the equivalent capacitance value can be used to distinguish between dryness and water accumulation in above-zero conditions, and the equivalent resistance value can be used to distinguish between dryness, ice and snow accumulation in below-zero conditions.

[0070] Step S2: at different temperatures, the sensitive capacitor is stimulated by using excitation signals of different frequencies, and the resistance value of the equivalent resistor, the capacitance value of the equivalent capacitor, and the type of the covering on the sensitive capacitor are obtained.

[0071] Based on the above analysis, in this embodiment, the covering categories include dry, water accumulation, ice and snow accumulation.

[0072] Step S3: Taking the temperature values, frequency values, resistance values, and capacitance values ​​of the same group as sample data and the corresponding covering categories as true labels, a sample set is constructed.

[0073] Step S4: construct a covering object recognition model based on a neural network, and train the covering object recognition model using a sample set.

[0074] like Figure 6 As shown, specifically in this embodiment, the cover recognition model includes a first convolutional layer, a second convolutional layer, a flattening layer, a first fully connected layer and a second fully connected layer which are connected in sequence.

[0075] The first convolutional layer uses a convolution kernel of size 2, an input channel of 1, an output channel of 8, a stride of 1, and a padding of 0; the parameters of this layer are calculated as follows: the convolution kernel parameter is 2*1*8, and the bias parameter is 8. Choosing a smaller convolution kernel size helps capture local features, reduce the amount of calculation, and speed up the training process.

[0076] The second convolutional layer uses a convolution kernel of size 2, 8 input channels, 16 output channels, a stride of 1, and a padding of 0; the parameter calculation of this layer is: the convolution kernel parameter is 2*8*16, and the bias parameter is 16. The increase in the number of output channels in the second layer helps to extract richer features.

[0077] The flattening layer flattens the multi-dimensional global features into a one-dimensional vector, which facilitates subsequent fully connected layer processing.

[0078] The input feature number of the first fully connected layer is 16, and the output feature number is 16; the parameter calculation of this layer is: the weight parameter is 16*16, and the bias parameter is 16. The fully connected layer is used to integrate the features extracted by the convolutional layer for high-level feature representation.

[0079] The second fully connected layer has 16 input features and 4 output features. The parameter calculation of this layer is as follows: the weight parameter is 16*4, the bias parameter is 4, and the second fully connected layer performs classification prediction based on high-level feature representation and outputs a four-dimensional probability vector. Each value in the vector corresponds to the prediction probability of a category. The highest category is selected as the final prediction result based on the prediction probability of each category.

[0080] The model designed in the embodiment of the present invention extracts local features of input data through the convolution layer, converts it into a one-dimensional vector through the flattening layer, and performs classification prediction through the fully connected layer. The model has relatively few parameters and is suitable for processing data classification tasks with four input features.

[0081] ReLU activation functions are set after the first convolutional layer, the second convolutional layer, and the first fully connected layer. The ReLU activation function is simple and efficient to calculate, and has a constant gradient in the positive range, which helps to alleviate the problem of gradient vanishing. The ReLU activation function ensures that the features are effectively nonlinearized, thereby improving the expressiveness of the model.

[0082] The cover recognition model is trained through the sample set, including:

[0083] (1) Construct sample data: Test every 10℃ in the range of -30℃ to 60℃. The surface of the sensitive capacitor is covered with air, water, ice and snow, and the temperature, frequency, equivalent series capacitance value Cs and equivalent series resistance value Rs at different frequencies are tested.

[0084] (2) Data loading and preprocessing: Use DataLoader to load training and test data.

[0085] (3) Model definition: Define the neural network model structure according to actual needs, including the type and parameters of each layer.

[0086] (4) Definition of loss function and optimizer: Select a suitable loss function, such as cross entropy loss. At the same time, define an optimizer, such as the Adam optimizer.

[0087] (5) Training cycle: In each training round, the training data set is traversed to perform forward propagation, loss calculation, back propagation, and parameter update. After each training round, the loss value of the current round is output.

[0088] (6) Prediction: Use the trained model to predict new data. Pass the test data to the trained neural network model to obtain the final prediction result.

[0089] (7) Model evaluation: After training is completed, use the test dataset to evaluate the performance of the model, such as calculating accuracy and other indicators.

[0090] like Figure 7 As shown in the figure, after actual testing, through the classification prediction of temperature, frequency, equivalent series capacitance value and equivalent series resistance value, when the temperature is above zero, the accuracy of dryness and water accumulation is higher; when the temperature is below zero, the accuracy of dryness, snow accumulation and ice is higher. It meets the requirements.

[0091] Step S5: Implement covering object recognition through the trained covering object recognition model.

[0092] The method for identifying covered objects based on multi-frequency excitation provided by the embodiment of the present invention utilizes the deeper features in the output data of the sensitive capacitor and establishes a complex pattern recognition and classification model to achieve accurate identification of road covering objects. This method can overcome the difficulty in identifying the similarity of charge and discharge waveforms in traditional methods and improve the accuracy of covering detection. In addition, the intelligent classification prediction algorithm also has the advantage of adapting to different road conditions and environmental changes, providing more reliable support for road safety and vehicle driving stability.

[0093] Embodiment 2: like Figure 8 As shown, an embodiment of the present invention provides a detection device suitable for a cover identification method based on multi-frequency excitation as in Embodiment 1, wherein the detection device is configured to excite a sensitive capacitor by excitation signals of different frequencies at different temperatures, and obtain the resistance value of an equivalent resistor and the capacitance value of an equivalent capacitor; the detection device comprises: a temperature sensor, a capacitor excitation circuit, an impedance matching circuit, a phase difference detection circuit and a microprocessor, wherein the temperature sensor is used to collect a temperature value; the capacitor excitation circuit is connected to one end of the sensitive capacitor, and is used to excite the sensitive capacitor by excitation signals of different frequencies; the impedance matching circuit is connected to the other end of the sensitive capacitor, and is used to match the impedance of the sensitive capacitor; the phase difference detection circuit is used to obtain a voltage when the impedance matching circuit reaches a balanced state. With voltage The phase difference between ,Voltage With voltage The phase difference between ,Voltage is the voltage across the sensitive capacitor, is the voltage across the impedance matching circuit, It is the voltage between the two ends of the sensitive capacitor and the impedance matching circuit. The microprocessor is used to calculate the phase difference. and phase difference Calculate the resistance value of the equivalent resistor and the capacitance value of the equivalent capacitor.

[0094] The embodiment of the present invention excites the sensitive capacitor to be measured at multiple frequency points to obtain the impedance response at different frequencies, ensuring that when a certain frequency point cannot be distinguished, it can be supplemented and confirmed by the response data of other frequency points, so that the system can more comprehensively obtain the characteristics of the capacitor to be measured, thereby improving the recognition accuracy of the covering. By combining the capacitor excitation circuit with the impedance matching circuit, the impedance response of the sensitive capacitor is changed, and the impedance of the impedance matching circuit is adjusted to achieve a balanced state, thereby reducing the measurement error, and then the phase difference detection circuit is used to measure and calculate the impedance characteristics of the sensitive capacitor by measuring and calculating the signal phase difference angle between each other, thereby reflecting the influence of the covering and the detection frequency on the equivalent capacitance and equivalent resistance.

[0095] like Fig. 9 As shown, the capacitor excitation circuit includes a DAC module, a high-pass filter circuit and a first voltage follower U7 connected in sequence. The DAC generates a sine wave signal (10KHz 100KHz). The sine wave signal is filtered by the high-pass filter circuit and the first voltage follower enhances the driving ability to excite the sensitive capacitor. The high-pass filter circuit consists of a resistor and a capacitor. The circuit has important applications in signal processing, especially in the process of removing low-frequency noise and preventing low-frequency interference, which can ensure that the high-frequency components of the signal are transmitted. The first voltage follower U7 after the high-pass filter circuit mainly provides high input impedance and low output impedance, thereby realizing buffered transmission of the signal. The input signal and output signal of the circuit are equal, but it can effectively isolate the front-stage signal source from the rear-stage load to prevent the load from affecting the signal source. In this design, a voltage follower is formed by an operational amplifier and a resistor and capacitor. The output end of the operational amplifier is connected in series to the inverting input end through a resistor R17, and a capacitor C21 is connected in parallel. The function of the resistor R17 is to make the positive and negative input biases symmetrical. For actual op amps, there is a small input capacitance (distributed parameter) between the op amp input and the ground. This input capacitance forms a low-pass filter with the resistor R17 from the op amp output to the reverse end, affecting the response at high frequencies. The capacitor C21 connected in parallel with the resistor R17 is used to cancel this effect and improve the high-frequency response.

[0096] The impedance matching circuit includes multiple parallel branches, each branch includes a switch and a weighted resistor connected in series. By controlling the on and off of the switch on each branch, the total resistance value of the impedance matching circuit is changed. , total resistance Should be less than and as close as possible to , is the impedance of the equivalent capacitor, is the resistance value of the equivalent resistor, Is an imaginary unit.

[0097] like Fig.10 As shown, specifically in this embodiment, the impedance matching circuit is mainly composed of four analog switch chips (U9, U12, U15, U18), which contain two independently optional single-pole double-throw switches with ultra-low capacitance and charge injection characteristics, and are particularly suitable for data acquisition and sample-and-hold applications. It can provide an ideal solution in situations where low interference and fast stability are required. Each switch can be equally conductive in both directions when it is on, and its input signal range extends to the power supply voltage. The present invention designs an 8-way weighted resistor, so 4 analog switch chips are used. For measuring impedance elements of different sizes, switches are used to switch different ranges.

[0098] The phase difference detection circuit includes a second voltage follower, three voltage detection circuits, three square wave conversion circuits and a phase difference detection chip; the input end and the output end of the second voltage follower are respectively connected to the two ends of the impedance matching circuit, and the input ends of the three voltage detection circuits are respectively connected to the two ends of the sensitive capacitor, the two ends of the impedance matching circuit, and the two ends after the sensitive capacitor and the impedance matching circuit are connected, for measuring the voltage ,Voltage And voltage The input ends of the three square wave conversion circuits are connected to the output ends of the three voltage detection circuits, and the input ends of the phase difference detection chip are connected to the output ends of the three square wave conversion circuits to obtain the phase difference. and phase difference .

[0099] Specifically, in this embodiment, the voltage detection circuit adopts a differential amplifier circuit, and the input ends of the three voltage detection circuits are respectively connected to the two ends of the sensitive capacitor, the two ends of the impedance matching circuit, and the two ends of the sensitive capacitor and the impedance matching circuit are connected to measure the voltage. ,Voltage And voltage ,like Fig.11 As shown, A1 corresponds to the second voltage follower, and A2, A3, and A4 correspond to three voltage detection circuits respectively.

[0100] Voltage ,Voltage And voltage And the input and output voltage signals of the total circuit and , the three voltage signals are analyzed using the vector method in circuit analysis. The vector method analysis diagram is shown in Fig.12 As shown, take a reference direction, which is the direction of the current. The relationships between several voltage signals are:

[0101]

[0102]

[0103]

[0104] No matter how Cs and Rs change, It should be based on is a circle with a radius of , and its modulus should be a constant. for and The phase difference angle between for and The phase difference between and The schematic diagram is as follows Fig.13 As shown, if these two angles are measured, the tangent angle formula can be combined with the total parallel resistance value R of the half-bridge circuit and the circuit excitation frequency f to establish a set of two-variable linear equations to calculate the equivalent series resistance value Rs and the equivalent series capacitance value Cs of the sensitive capacitor element. The calculation formula is as follows:

[0105]

[0106]

[0107]

[0108] In the formula, For voltage and The phase difference between For voltage and The phase difference between is the impedance of the equivalent capacitor, is the frequency of the excitation signal, is the resistance value of the equivalent resistor, is the capacitance value of the equivalent capacitor, is the total resistance of the impedance matching circuit.

[0109] However, the above method will cause a problem in practical application, that is, when Rs and After an hour, and It is difficult to measure, so the reverse differential amplifier can be used to Negative processing, that is ,like Fig.14 Negative processing The vector method analysis diagram after that, at this time, even if Rs and becomes smaller, the measured and It will also be huge.

[0110] The total parallel resistance value R of the impedance matching circuit needs to meet certain requirements, which can be divided into three situations:

[0111] 1. ,but , which will cause waveform distortion;

[0112] 2. , at this time the measurement accuracy is the best, and ;

[0113] 3. , the measurement accuracy deteriorates, Too small, resulting in The angle is too small.

[0114] therefore, The value should be less than and as close as possible to , but not through Is it greater than and close to To judge, because in When the time is very small, it is difficult to accurately judge. Is it less than and close to To judge, we should As large as possible without distortion, and gradually reduce during measurement , so that At first less than Time is good.

[0115] By measuring Right now ,Voltage The output end of the voltage detection circuit is also connected to a full-wave rectifier and filter circuit for voltage Sampling is performed to determine the total resistance value . The operational amplifier can be used to perform full-wave rectification on the AC signal, convert the input bipolar AC signal into a unipolar signal, and amplify the signal. Although the output voltage of the rectifier circuit is unidirectional, it contains a large AC component. Therefore, in the present invention, a capacitor is connected in parallel to the output end of the rectifier circuit to form a capacitor filter circuit. The larger the capacity of the filter capacitor, the smaller the low-frequency cutoff frequency, and the better the filtering effect.

[0116] The R value should meet the following requirements in circuit design: Fig.10 , a total of 8 channels, 256 combinations of R value range should be as large as possible under all selected frequencies, the impedance range of the sensitive capacitor. In each test, the algorithm is used to find the R value that best suits the current frequency and the current cover.

[0117] The amplification factor of the differential amplifier circuit is designed to be 1, and the resistors are metal film resistors. After passing through the differential amplifier circuit, three signals are obtained. , , In order to obtain the phase difference between them, the conversion circuit uses a voltage comparator, such as Fig.15 and Fig.16 As shown, voltage comparators U10, U13, and U19 are used to , , They are converted into square waves respectively and then input into the phase difference detection chip, which is a NOR gate logic chip with 4 2-input NOR gates. and and The relationship is a two-or-no relationship, and and The relationship is also a two-way or non-relationship, and the final output is through the logic chip and The two square wave signals are input into the single chip microcomputer, and the single chip microcomputer timer is used to detect the duty cycle by high level duration.

[0118] A square wave is a periodic signal consisting of alternating high and low levels. Its characteristic is that it is easy to compare phase differences. After the signal passes through the voltage comparator, it will become a square wave signal with the threshold as the boundary according to the threshold setting. When the voltage of the input signal is higher than the threshold, the comparator outputs a high level; conversely, it outputs a low level when it is lower than the threshold. By comparing the phases of the converted square wave signals, the phase difference between the calculated signals can be measured. Logical symbols are assigned to the square waves converted from the three groups of signals. , , Assign logical symbols A, B, C, and two phases respectively. and The corresponding signals are assigned to Y1 and Y2 respectively. The three groups of square waves are compared and analyzed respectively to establish a truth table. When A=1 and B=0, Y1=1, and in other cases, Y1=0; similarly, when C=1 and B=0, Y2=1, and in other cases, Y2=0.

[0119]

[0120]

[0121] In the formula, Voltage ,Voltage And voltage signal, Phase difference and phase difference signal.

[0122] Specifically in this embodiment, the temperature sensor uses a PT100 platinum resistor, and the measurement range of the PT100 platinum resistor is usually between -200°C and 850°C, which can cover a wide temperature range. Platinum metal has high chemical stability, and the temperature measurement of the PT100 platinum resistor has good long-term stability. The resistance of PT100 changes with temperature in a roughly linear relationship, so it is easy to establish an accurate corresponding relationship with the temperature. The temperature is obtained by measuring the resistance value of the PT100 platinum resistor.

[0123] The detection device also includes a power supply circuit, which consists of two parts: an analog circuit and a digital circuit. Due to the high requirements for measurement accuracy, the power supply circuit part needs to be reliable and stable. By isolating the analog power supply and the digital power supply, the electromagnetic coupling between them can be reduced and the possibility of mutual interference can be reduced. Since there may be stray interference in the ground return, it is necessary to separate the digital ground and the analog ground, and finally connect them to the common ground of the power input to reduce the adverse effects of the ground return on the analog circuit.

[0124] The detection device provided by the embodiment of the present invention obtains the impedance response at different frequencies, ensures that when a certain frequency point cannot be distinguished, it can be supplemented and confirmed by the response data of other frequency points, so that the system can more comprehensively obtain the characteristics of the capacitor to be measured, thereby improving the recognition accuracy of the cover. At different frequency points, the equivalent series capacitance value Cs of the sensitive capacitor element will change, so that the impedance value Xc of the equivalent series capacitance will also change, and then the impedance value R of the corresponding best matching half-bridge circuit will also change. Under some covers, the equivalent series capacitance value Cs and the equivalent series resistance value Rs of the sensitive capacitor element will decay, and under some covers, it will hardly change. By changing different excitation frequencies, it is judged whether the equivalent series capacitance value Cs and the equivalent series resistance value Rs of the sensitive capacitor element will decay or not change, thereby increasing the criterion, ensuring that when a certain frequency point cannot be distinguished, it can be supplemented and confirmed by the response data of other frequency points, so that the system can more comprehensively obtain the characteristics of the capacitor to be measured, thereby improving the recognition accuracy of the cover.

[0125] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0127] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0129] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for identifying covered objects based on multi-frequency excitation, characterized in that: include: Constructing an equivalent circuit of the sensitive capacitor, wherein the equivalent circuit includes an equivalent resistance, an equivalent inductance, and an equivalent capacitance connected in series; At different temperatures, the sensitive capacitor is stimulated by excitation signals of different frequencies, and the resistance value of the equivalent resistor, the capacitance value of the equivalent capacitor, and the type of the covering on the sensitive capacitor are obtained; The temperature values, frequency values, resistance values, and capacitance values ​​of the same group are used as sample data, and the corresponding covering categories are used as true labels to construct a sample set; Constructing a covering recognition model based on a neural network, and training the covering recognition model through the sample set; Covering recognition is achieved through the trained covering recognition model.

2. The method for identifying covered objects based on multi-frequency excitation according to claim 1, characterized in that: The cover recognition model includes a first convolutional layer, a second convolutional layer, a flattening layer, a first fully connected layer and a second fully connected layer connected in sequence; The first convolution layer uses a convolution kernel of size 2, the number of input channels is 1, the number of output channels is 8, the stride is 1, and the padding is 0; the first convolution layer is used to process the input data and extract local features; The second convolution layer uses a convolution kernel of size 2, the number of input channels is 8, the number of output channels is 16, the stride is 1, and the padding is 0; the second convolution layer is used to process the local features and extract global features; The flattening layer flattens the multi-dimensional global features into a one-dimensional vector; The first fully connected layer has an input feature number of 16 and an output feature number of 16; the first fully connected layer is used to perform high-level feature representation on the one-dimensional vector; The second fully connected layer has an input feature number of 16 and an output feature number of 4; The second fully connected layer performs classification prediction based on the high-level feature representation; The first convolutional layer, the second convolutional layer and the first fully connected layer are respectively provided with ReLU activation functions, and the ReLU activation functions are used to ensure that the features are effectively nonlinearized.

3. The method for identifying covered objects based on multi-frequency excitation according to claim 2, characterized in that: During the training process of the cover recognition model, the loss between the predicted result and the true label is calculated by the cross entropy loss function, and the model parameters are updated by the Adam optimizer.

4. A detection device applicable to the method for identifying covered objects based on multi-frequency excitation as claimed in any one of claims 1 to 3, characterized in that: The detection device is configured to excite the sensitive capacitor by excitation signals of different frequencies at different temperatures, and obtain the resistance value of the equivalent resistor and the capacitance value of the equivalent capacitor; The detection device comprises: Temperature sensor, used to collect temperature values; A capacitor excitation circuit, connected to one end of the sensitive capacitor, for exciting the sensitive capacitor through excitation signals of different frequencies; An impedance matching circuit, connected to the other end of the sensitive capacitor, for matching the impedance of the sensitive capacitor; A phase difference detection circuit is used to obtain a voltage when the impedance matching circuit reaches a balanced state. With voltage The phase difference between ,Voltage With voltage The phase difference between , the voltage is the voltage across the sensitive capacitor, is the voltage across the impedance matching circuit, the voltage is the voltage between the two ends of the sensitive capacitor and the impedance matching circuit after being connected; A microprocessor is used to and the phase difference Calculate the resistance value of the equivalent resistor and the capacitance value of the equivalent capacitor.

5. The detection device according to claim 4, characterized in that: The capacitor excitation circuit includes a DAC module, a high-pass filter circuit and a first voltage follower connected in sequence. The DAC generates a sine wave signal, and the sine wave signal is filtered by the high-pass filter circuit and enhanced by the first voltage follower.

6. The detection device according to claim 4, characterized in that: The impedance matching circuit includes a plurality of parallel branches, each of which includes a switch and a weighted resistor connected in series. By controlling the on and off of the switch on each branch, the total resistance value of the impedance matching circuit is changed. , the total resistance Should be less than and as close as possible to , is the impedance of the equivalent capacitor, is the resistance value of the equivalent resistor, Is an imaginary unit.

7. The detection device according to claim 4, characterized in that: The phase difference detection circuit includes a second voltage follower, three voltage detection circuits, three square wave conversion circuits and a phase difference detection chip; the input end and the output end of the second voltage follower are respectively connected to the two ends of the impedance matching circuit, and the input ends of the three voltage detection circuits are respectively connected to the two ends of the sensitive capacitor, the two ends of the impedance matching circuit, and the two ends after the sensitive capacitor and the impedance matching circuit are connected, for measuring the voltage ,Voltage And voltage The input ends of the three square wave conversion circuits are respectively connected to the output ends of the three voltage detection circuits, and the input ends of the phase difference detection chip are respectively connected to the output ends of the three square wave conversion circuits, for obtaining the phase difference and phase difference ; ； ； In the formula, Voltage ,Voltage And voltage signal, Phase difference and phase difference signal.

8. The detection device according to claim 7, characterized in that: The voltage detection circuit adopts a differential amplifier circuit, the phase conversion circuit adopts a voltage comparator, and the phase difference detection chip adopts a NOR gate logic chip.

9. The detection device according to claim 7, characterized in that: The voltage The output end of the voltage detection circuit is also connected to a full-wave rectifier and filter circuit for Sampling is performed to determine the total resistance value .

10. The detection device according to claim 4, characterized in that: The calculation formula of the resistance value of the equivalent resistor and the capacitance value of the equivalent capacitor is: ； ； ； In the formula, For voltage and The phase difference between For voltage and The phase difference between is the impedance of the equivalent capacitor, is the frequency of the excitation signal, is the resistance value of the equivalent resistor, is the capacitance value of the equivalent capacitor, is the total resistance of the impedance matching circuit.

Images