Icing detection device and method, computer equipment, storage medium and program product
By combining complex impedance measurement units and temperature information, the icing detection method utilizes multiple sets of electrodes to collect data and performs cascaded machine learning. This solves the applicability and accuracy problems of existing icing detection technologies in scenarios with high requirements for surface contours, achieving higher icing detection accuracy and stability.
Patent Information
- Application Number
- CN202411088083.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-08-08
AI Technical Summary
Existing icing detection methods have poor applicability and low accuracy in scenarios with high requirements for surface contours.
A complex impedance measurement unit and a data processing unit are used to collect complex impedance data using multiple sets of electrodes. Ice accretion is detected by combining the data with temperature information, and ice type and thickness are determined by a cascaded machine learning model.
It improves the accuracy and stability of icing detection, reduces the complexity of ice thickness measurement, and enhances the robustness of data calculation.
Smart Images

Figure CN118913073A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of ice detection, and in particular to an ice detection device, method, computer equipment, storage medium and program product. Background Art
[0002] Icing is a common natural phenomenon, and icing can cause serious harm to normal production and life. Icing can cause wind turbines to be unable to generate electricity normally, icing on power transmission and transformation equipment can cause the power grid to be unable to operate safely and stably, and icing on wings can cause aircraft to be unable to fly safely.
[0003] At present, the main means of ice detection include mechanical method / weighing method, image method, fiber optic sensing method, etc. The mechanical method / weighing method calculates the ice thickness by measuring the strain or weight change of the object after ice coating. The image method obtains the ice image through a camera or drone, and uses image recognition technology to calculate the ice thickness. The fiber optic sensing method obtains the stress change of the object under test through a grating sensor or distributed Brillouin scattering fiber optic sensor to calculate the ice thickness.
[0004] For some scenes such as wind turbine blades and aircraft wings, very high requirements are placed on the surface contour. Currently, ice monitoring sensors are difficult to deploy, resulting in poor applicability and low accuracy. Summary of the invention
[0005] In view of this, the present invention provides an ice detection device, method and related devices to solve the problems of poor applicability and low accuracy.
[0006] In a first aspect, the present invention provides an ice coverage detection device, which includes a complex impedance measurement unit and a data processing unit, wherein the complex impedance measurement unit is connected to the data processing unit, wherein the complex impedance measurement unit includes a plurality of electrodes of preset shapes, the electrodes are arranged according to preset rules, and at least two electrodes are selected as a group of electrode pairs, and the complex impedance measurement unit is used to collect complex impedance data of multiple frequency bands at the position to be detected using the plurality of groups of electrode pairs; the data processing unit is used to process the complex impedance data and determine the ice coverage detection information at the position to be detected based on the complex impedance data.
[0007] In this implementation, the ice detection device of the present invention has a complex impedance measurement unit with multiple groups of electrode pairs, which uses multiple groups of electrode pairs to collect multiple groups of complex impedance data, and then determines ice detection information based on the data processing unit. Compared with dual-electrode solutions, the present invention expands the data source through the number of electrodes and electrode layout design, improves the measurement effect, and improves the accuracy of ice detection.
[0008] In an optional embodiment, the ice detection device also includes a temperature measurement unit, wherein the temperature measurement unit is used to collect temperature information at the position to be detected; the data processing unit is used to use the complex impedance data and the temperature information as input data of the ice detection model, process the complex impedance data and the temperature information, and output the ice detection information at the position to be detected, and the ice detection model is a cascade machine learning model.
[0009] In an optional embodiment, the electrodes include excitation electrodes and measuring electrodes, each electrode pair includes at least one excitation electrode and at least one measuring electrode, and the electrode pairs have different characteristic parameters, including inter-electrode distance, electrode width and electrode area.
[0010] In a second aspect, the present invention provides an ice detection method, which is applied to the above-mentioned ice detection device. The ice detection method includes: using multiple groups of electrode pairs to collect complex impedance data of multiple frequency bands at the position to be detected, and performing feature processing on the complex impedance data of each frequency band to obtain a complex impedance characteristic value; using a temperature measurement unit to collect temperature information at the position to be detected; using the temperature information to perform temperature compensation on the complex impedance characteristic value, detecting the ice condition at the position to be detected, and obtaining ice detection information.
[0011] In this implementation, the ice detection method of the present invention, based on the ice detection device, utilizes a complex impedance measurement unit of multiple groups of electrode pairs to collect multiple groups of complex impedance data, and then collects temperature information to perform ice detection to obtain ice detection information. The present invention expands the data source through the number of electrodes and electrode layout design, and the temperature information supplements the complex impedance characteristic value, thereby improving the measurement effect and the accuracy of ice detection.
[0012] In an optional embodiment, temperature information is used to perform temperature compensation on the complex impedance characteristic value, and the ice coverage at the detection position is detected to obtain ice coverage detection information, including: inputting the complex impedance characteristic value and temperature information into an ice coverage detection model, detecting the ice coverage at the detection position, and outputting ice coverage detection information; and / or using the complex impedance characteristic value and a preset capacitance ice thickness fitting curve to calculate the ice coverage detection information at the detection position.
[0013] In an optional embodiment, the ice detection model includes an ice type classifier, which uses temperature information to perform temperature compensation on the complex impedance eigenvalue, detects the ice condition of the detection position, and obtains ice detection information including: inputting the complex impedance eigenvalue and temperature information into the ice type classifier; calculating the probability that the ice type of the detection position is a preset ice type, and outputting the preset ice type with the highest probability as the ice type of the detection position; wherein the preset ice types include clear ice, frost ice, mixed ice, water, pollutants and dryness.
[0014] In an optional embodiment, the ice detection model also includes an ice thickness regressor, which outputs the preset ice type with the highest probability as the ice type of the location to be detected and further includes: obtaining an ice thickness regressor corresponding to the ice type; inputting the complex impedance eigenvalue and temperature information into the ice thickness regressor, fusing the ice thickness results of different machine learning algorithms, and calculating the ice thickness value of the location to be detected.
[0015] In this implementation, the present invention applies a cascade machine learning algorithm to judge the ice cover state, and uses an ice type classifier and an ice thickness regressor to judge the ice type and ice thickness respectively. By designing and applying the algorithm in ice cover measurement, the ice cover measurement has the robustness, stability and accuracy of data calculation.
[0016] In an optional embodiment, characteristic processing is performed on the complex impedance data of each frequency band to obtain a complex impedance characteristic value, including: using an RC parallel model to perform characteristic processing on the complex impedance data to calculate a first complex impedance characteristic value, the first complex impedance characteristic value including an equivalent capacitance value and a loss tangent value; based on the first complex impedance characteristic value, a second complex impedance characteristic value is calculated, the second complex impedance characteristic value including a low-frequency capacitance value, a high-frequency capacitance value, a relaxation time, a difference between high and low frequency capacitance, a ratio of high and low frequency capacitance, the number of loss peaks, a first loss peak-to-peak value, a second loss peak-to-peak value, and a loss peak-to-peak value ratio.
[0017] In an optional embodiment, the complex impedance characteristic value includes a capacitance value, and using the complex impedance characteristic value and a preset capacitance ice thickness fitting curve to calculate the ice cover detection information of the position to be detected includes: constructing multiple capacitance ice thickness fitting curves, where the multiple capacitance ice thickness fitting curves are pre-established ice thickness detection curves of multiple electrode pairs; using the equivalent capacitance value and the capacitance ice thickness fitting curve to determine the ice cover thickness value of the position to be detected.
[0018] In an optional embodiment, the equivalent capacitance value and the capacitance ice thickness fitting curve are used to determine the ice thickness value of the to-be-detected position, including: sorting the electrode pairs from small to large according to the electrode spacing, and determining the corresponding thickness information in sequence using the electrode pairs and the capacitance ice thickness fitting curve of the electrode pairs; judging whether the thickness information is less than a preset threshold of the electrode pair, and when the thickness information is less than the preset threshold of the electrode pair, using the thickness information as the ice thickness value of the to-be-detected position; otherwise, using the next electrode pair to calculate the thickness information until the ice thickness value of the to-be-detected position is obtained.
[0019] In this implementation, the present invention adopts a multi-level capacitance-ice thickness fitting curve query method, which further reduces the complexity of ice thickness measurement and ensures the signal-to-noise ratio of ice thickness measurement.
[0020] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the ice detection method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.
[0021] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the ice detection method of the first aspect or any corresponding embodiment thereof.
[0022] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the ice detection method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0024] Figure 1 is a schematic diagram of an ice detection system according to an embodiment of the present invention;
[0025] Figure 2 is a schematic diagram of an electrode pair combination of a complex impedance measurement unit according to an embodiment of the present invention;
[0026] Figure 3 is a schematic diagram of a specific complex impedance measurement unit according to an embodiment of the present invention;
[0027] Figure 4 is a flow chart of an ice detection method according to an embodiment of the present invention;
[0028] Figure 5 is a flow chart of another ice detection method according to an embodiment of the present invention;
[0029] Figure 6 is a schematic diagram of an ice detection model according to an embodiment of the present invention;
[0030] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0032] At present, the ice thickness measurement method that measures the vibration frequency or impedance change of the ice-covered object has low measurement accuracy for ice thickness, poor applicability and low accuracy for scenes with high requirements for surface contours. Therefore, according to an embodiment of the present invention, an ice detection system is provided, which can improve the accuracy of ice detection. Figure 1 As shown, Figure 1 is a schematic diagram of an ice detection system according to an embodiment of the present invention. In actual use, the ice detection system is placed on a device to be detected, such as Figure 1 As shown, the ice coating detection system includes a substrate 1, an ice coating detection device 2, a data transmission component 3 and a power supply component 4.
[0033] Among them, the substrate 1 is equipped with an ice detection device 2, a data transmission component 3 and a power supply component 4. The ice detection device 2 is used to detect the ice condition at the position to be detected and send the detection data to the data transmission component 3. The data transmission component 3 sends the detection data to the monitoring center to realize ice monitoring and alarm. The power supply component 4 is used to power the ice detection system.
[0034] In one implementation, the substrate may be selected to be a flexible substrate, so that the device can perfectly fit the shape of an irregular curved surface, and the design has a higher degree of fit.
[0035] In one implementation, the ice detection device includes a complex impedance measurement unit and a data processing unit, and the complex impedance measurement unit is connected to the data processing unit.
[0036] In one implementation, the electrode of the ice detection device is made of copper, which can perfectly fit the shape of an irregular curved surface. This design has a higher degree of fit.
[0037] Among them, the complex impedance measurement unit includes multiple electrodes of preset shapes, the electrodes are arranged according to preset rules, and at least two electrodes are selected as a group of electrode pairs. The complex impedance measurement unit is used to use multiple groups of electrode pairs to collect complex impedance data of multiple frequency bands at the positions to be detected.
[0038] Specifically, see Figure 2 , Figure 2 FIG. 1 is a schematic diagram of an electrode pair combination of a complex impedance measurement unit according to an embodiment of the present invention. Figure 2As shown, the complex impedance measurement unit has multiple electrodes distributed on a substrate, and electrodes of multiple shapes are arranged according to multiple preset rules. Relays are used to switch different independent electrodes for combination to obtain electrode pairs.
[0039] Exemplarily, E135 is three excitation electrodes and E24 is two measurement electrodes, or E135 is a measurement electrode and E24 is an excitation electrode.
[0040] The electrodes are array electrodes. When combining electrode pairs, the array electrodes follow the principle of detection penetration depth range coverage, that is, in all combinations, the spacing between the excitation electrode and the measuring electrode should include the possible maximum and minimum values.
[0041] In one implementation, the electrode pair has at least one different characteristic parameter and has different response characteristics to the ice layer, and the characteristic parameter includes the distance between electrodes, electrode width, electrode area, etc.
[0042] Specifically, the electrodes include excitation electrodes and measurement electrodes, each electrode has different lengths and widths, and the distances between adjacent electrodes are different. Each electrode pair includes at least one excitation electrode and at least one measurement electrode. Each electrode pair has a different detection depth. When the ice thickness changes, the complex impedance data measured by each electrode pair at different frequency points changes accordingly.
[0043] In a specific implementation, each independent electrode in the array electrode has the same length and shares an excitation electrode on the left. The width and spacing of the four measuring electrodes increase sequentially, and the specific parameters can be determined based on simulation optimization.
[0044] For example, see Figure 3 , Figure 3 FIG. 1 is a schematic diagram of a specific complex impedance measurement unit according to an embodiment of the present invention. Figure 3 As shown, the five independent electrodes have the same length, the leftmost electrode is the excitation electrode, and the other four electrodes are the measuring electrodes. The four measuring electrodes share one excitation electrode. Among them, the width and spacing of the four measuring electrodes increase in sequence, and their specific parameters can be determined according to simulation optimization. In this specific implementation, the width ratio of the four measuring electrodes is 1:2:3:4, the spacing ratio between the five electrodes is 2:3:4:5, and the width of the excitation electrode is the average of the widths of all measuring electrodes.
[0045] The data processing unit is used to process the complex impedance data and determine ice detection information at the position to be detected based on the complex impedance data.
[0046] In one implementation, the ice coating detection device further includes a temperature measurement unit.
[0047] The temperature measurement unit is used to collect temperature information at the position to be detected.
[0048] The data processing unit is used to process the complex impedance data and determine ice detection information at the position to be detected based on the complex impedance data.
[0049] Among them, the ice detection model is a cascade machine learning model.
[0050] In one implementation, the complex impedance data is processed using a pre-trained ice detection model.
[0051] Specifically, the data processing unit is used to use the complex impedance data and the temperature information as input data of the ice detection model, process the complex impedance data and the temperature information, and output the ice detection information at the position to be detected. The ice detection model is a cascade machine learning model.
[0052] In this implementation, the ice detection device of the present invention has a complex impedance measurement unit with multiple groups of electrode pairs, which uses multiple groups of electrode pairs to collect multiple groups of complex impedance data, and then determines ice detection information based on the data processing unit. Compared with dual-electrode solutions, the present invention expands the data source through the number of electrodes and electrode layout design, improves the measurement effect, and improves the accuracy of ice detection.
[0053] According to an embodiment of the present invention, an embodiment of an ice coating detection method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0054] In this embodiment, a method for detecting ice coating is provided, which can be used in the above-mentioned ice coating detection device. Figure 4 is a flow chart of an ice detection method according to an embodiment of the present invention. It should be noted that if there are substantially the same results, this embodiment does not necessarily use Figure 4 The process sequence shown is limited. Figure 4 As shown, the process includes the following steps:
[0055] Step S401 : using multiple groups of electrode pairs to collect complex impedance data of multiple frequency bands at positions to be detected, and performing feature processing on the complex impedance data of each frequency band to obtain complex impedance feature values.
[0056] The complex impedance data at the position to be detected is collected by using the complex impedance measurement unit on the ice detection device.
[0057] Specifically, an electrode pair of the complex impedance measurement unit is selected to switch multiple frequencies, and complex impedance data of multiple frequency bands is collected at the position to be detected. The frequency can be a preset frequency. The electrode pair is switched, and multiple frequencies are switched using the next electrode pair, and complex impedance data of multiple frequency bands is collected again at the position to be detected. By analogy, multi-band complex impedance data of each electrode pair is obtained.
[0058] Furthermore, data processing is performed on the multi-band complex impedance data of each electrode pair, such as data cleaning, data conversion and other methods.
[0059] In one implementation, a network model is used to perform data conversion on complex impedance data to facilitate subsequent detection accuracy.
[0060] Step S402: using a temperature measurement unit to collect temperature information at a position to be detected.
[0061] Step S403, temperature compensation is performed on the complex impedance characteristic value using the temperature information, and the ice coverage at the position to be detected is detected to obtain ice coverage detection information.
[0062] The complex impedance characteristic value is used as the original data measured by each group of electrode pairs, and the temperature information of the collected ice layer is used to perform temperature compensation on the complex impedance characteristic value measured by each group of electrode pairs. When the complex impedance information and temperature information at the position to be detected are determined, they are compared with the complex impedance information and temperature information of multiple preset ice cover types to determine the ice cover detection information at the position to be detected.
[0063] The ice detection information includes ice types, including clear ice, frost ice, mixed ice, water, pollutants, and dryness.
[0064] The ice detection method provided in the present embodiment, based on the ice detection device, uses a complex impedance measurement unit of multiple groups of electrode pairs to collect multiple groups of complex impedance data, and then collects temperature information to perform ice detection to obtain ice detection information. The present invention expands the data source through the number of electrodes and electrode layout design, and the temperature information supplements the complex impedance characteristic value, thereby improving the measurement effect and the accuracy of ice detection.
[0065] The ice detection method of the present application can be applied to ice monitoring scenarios such as wind turbines, photovoltaic panels, aircraft, roads, bridges, etc., and has a broad application prospect. In this embodiment, an ice detection method is provided, which can be used for the above-mentioned ice detection device. Figure 5 is a flow chart of another ice detection method according to an embodiment of the present invention. It should be noted that if there are substantially the same results, this embodiment does not use Figure 5 The process sequence shown is limited. Figure 5 As shown, the process includes the following steps:
[0066] Step S501 : using multiple groups of electrode pairs to collect complex impedance data of multiple frequency bands at positions to be detected, and performing feature processing on the complex impedance data of each frequency band to obtain complex impedance feature values.
[0067] Specifically, the above step S501 includes:
[0068] Step S5011, using multiple groups of electrode pairs to collect complex impedance data of multiple frequency bands at the positions to be detected.
[0069] The complex impedance data at the position to be detected is collected by using the complex impedance measurement unit on the ice detection device.
[0070] Specifically, an electrode pair of the complex impedance measurement unit is selected to switch multiple frequencies, and complex impedance data of multiple frequency bands is collected at the position to be detected. The frequency can be a preset frequency. The electrode pair is switched, and multiple frequencies are switched using the next electrode pair, and complex impedance data of multiple frequency bands is collected again at the position to be detected. By analogy, multi-band complex impedance data of each electrode pair is obtained.
[0071] Step S5012: perform characteristic processing on the complex impedance data using the RC parallel model to calculate and obtain a first complex impedance characteristic value.
[0072] The first complex impedance characteristic value includes an equivalent capacitance value and a loss tangent value.
[0073] Specifically, the RC parallel model is used to perform feature processing on the complex impedance data to obtain the equivalent capacitance C P And the loss tangent tanδ.
[0074] Step S5013: Calculate a second complex impedance characteristic value based on the first complex impedance characteristic value.
[0075] Among them, the second complex impedance characteristic value includes low-frequency capacitance value, high-frequency capacitance value, relaxation time, high-frequency and low-frequency capacitance difference, high-frequency and low-frequency capacitance ratio, number of loss peaks, first loss peak-to-peak value, second loss peak-to-peak value and loss peak-to-peak value ratio.
[0076] Specifically, calculating the second complex impedance characteristic value based on the first complex impedance characteristic value includes:
[0077] Among them, the relaxation time τ is calculated as:
[0078]
[0079] Among them, calculate the low frequency capacitance value C low for:
[0080] C 1ow =C f ,f=1kHz.
[0081] Among them, calculate the high frequency capacitance value C high for:
[0082] C high =C f ,f=100kHz.
[0083] Among them, calculate the difference between high and low frequency capacitance ΔC P for:
[0084] ΔC P =C low -C high .
[0085] Among them, calculate the high-frequency and low-frequency capacitance ratio R C for:
[0086]
[0087] The peak-finding algorithm is used to detect the loss peaks and determine the number of loss peaks N. The corresponding first loss peak value P is obtained. 1 , the second loss peak value P 2 If the number of loss peaks in the measurement frequency band is 1, then let P 2 =0, if the number of loss peaks in the measurement frequency band is greater than 2, it is judged to be a pollutant interference state.
[0088] Among them, the calculated loss peak-to-peak ratio R P for:
[0089]
[0090] Step S502: using a temperature measurement unit to collect temperature information at a position to be detected.
[0091] Step S503: Based on the complex impedance characteristic value and the temperature information, the ice coverage at the detection location is detected to obtain ice coverage detection information.
[0092] In one implementation, the complex impedance characteristic value and temperature information are input into an ice detection model, the ice condition of the detection position is detected, and ice detection information is output.
[0093] The ice detection model consists of an ice type classifier and an ice thickness regressor. Figure 6 , Figure 6 Schematic diagram of an ice detection model according to an embodiment of the present invention. First, the surface state is identified and the ice type is classified by temperature, complex impedance spectrum characteristic value and ice type classifier to obtain the ice type. In the icing state, the ice thickness range or ice thickness is calculated by ice type, temperature, complex impedance spectrum characteristic value measured by each group of electrodes and ice thickness regressor.
[0094] In one implementation, the ice detection model is a cascade machine learning model.
[0095] Specifically, the above step S504 includes:
[0096] Step S5041: using an ice type classifier to obtain the ice type of the position to be detected.
[0097] The complex impedance characteristic value and temperature information are input into the ice type classifier, the probability that the ice type of the position to be detected is the preset ice type is calculated, and the preset ice type with the highest probability is output as the ice type of the position to be detected.
[0098] Among them, the ice type classifier algorithm for ice type and state identification can be selected according to computing resources and indicator requirements.
[0099] In one implementation, in order to achieve a lightweight design of the ice thickness measurement model, the ice type classifier is a random forest model, the input feature data is the temperature and the characteristic values of the complex impedance spectrum measured by each group of electrodes, and the output is different ice types and surface states such as clear ice, frost ice, mixed ice, water, pollutants, and dryness.
[0100] Step S5042: using an ice thickness regressor to obtain the ice thickness value of the position to be detected.
[0101] One or more ice thickness regressors based on different machine learning algorithms are configured for each ice type. The ice thickness regressor corresponding to the ice type is obtained, the complex impedance eigenvalue and temperature information are input into the ice thickness regressor, the ice thickness results of different machine learning algorithms are integrated, and the ice thickness value of the location to be detected is calculated.
[0102] Among them, the ice thickness regressor algorithm for ice thickness measurement can be selected according to computing resources and index requirements.
[0103] In one implementation, in order to achieve a lightweight design of the ice thickness measurement model, the ice thickness regressor is a decision tree model, whose input feature data are temperature and characteristic values of the complex impedance spectrum measured by each group of electrodes, and whose output is the calculated ice thickness value range.
[0104] Exemplarily, the ice thickness ranges are divided into: less than 1 mm, 1-5 mm, 5-10 mm, 10-20 mm, and greater than 20 mm.
[0105] In one implementation, the ice thickness results of different machine learning algorithms are weighted averaged to calculate the ice thickness value of the location to be detected.
[0106] In another implementation, the complex impedance characteristic value and temperature information are input into an ice detection model, the ice condition at the detection position is detected, and ice detection information is output; and the complex impedance characteristic value and a preset capacitance ice thickness fitting curve are used to calculate the ice detection information at the detection position.
[0107] Specifically, the above step S504 includes:
[0108] Step S5041: using an ice type classifier to obtain the ice type of the position to be detected.
[0109] The ice cover detection model is an ice type classifier. The ice cover type of the position to be detected is obtained by using the ice type classifier using the method of step S5041. No further details will be given here.
[0110] Step S5042,
[0111] The ice thickness value of the position to be detected is obtained by using an ice thickness regressor, or the ice thickness value of the position to be detected is calculated by using the complex impedance characteristic value and a preset capacitance ice thickness fitting curve.
[0112] Specifically, the above step S5042 includes:
[0113] Step a1, constructing multiple capacitance ice thickness fitting curves.
[0114] The multiple capacitance ice thickness fitting curves are pre-established ice thickness detection curves of multiple electrode pairs, that is, a capacitance ice thickness fitting curve is determined for each electrode pair.
[0115] Step a2, using the equivalent capacitance value and the capacitance ice thickness fitting curve to determine the ice thickness value at the position to be detected.
[0116] Each electrode pair has a corresponding thickness detection threshold. The method of the present application is used to determine the electrode pair suitable for current ice surface thickness detection, and the ice thickness value is obtained based on the corresponding capacitance ice thickness fitting curve.
[0117] The capacitance value at a certain high signal-to-noise ratio frequency measured by the electrode pair with the closest electrode spacing is preferentially used for thickness calculation. The electrode pairs are sorted from small to large according to the electrode spacing, and the corresponding thickness information is determined by the electrode pairs and the capacitance ice thickness fitting curve of the electrode pairs in turn, and it is judged whether the thickness information is less than the preset threshold of the electrode pair. When the thickness information is less than the preset threshold of the electrode pair, the thickness information is used as the ice thickness value of the position to be detected, otherwise, the thickness information is calculated using the next electrode pair until the ice thickness value of the position to be detected is obtained.
[0118] Specifically, obtain the first equivalent capacitance value corresponding to the complex impedance data collected by the first electrode pair with the smallest electrode spacing, obtain the first capacitance ice thickness fitting curve of the first electrode pair, and calculate the first thickness information corresponding to the first equivalent capacitance value in the first capacitance ice thickness fitting curve. When the first thickness information is less than the first preset threshold value of the first electrode pair, it means that the current electrode pair is suitable for detecting the ice surface, and the first thickness information is used as the ice thickness value of the position to be detected. Otherwise, obtain the second equivalent capacitance value corresponding to the complex impedance data collected by the second electrode pair, obtain the second capacitance ice thickness fitting curve of the second electrode pair, and calculate the second thickness information corresponding to the second equivalent capacitance value in the second capacitance ice thickness fitting curve. No further details will be given below.
[0119] Based on the ice detection device, the present application uses a complex impedance measurement unit with multiple groups of electrode pairs to collect multiple groups of complex impedance data, and then collects temperature information to perform ice detection and obtain ice detection information. The present invention expands the data source by designing the number of electrodes and the electrode layout, and the temperature information supplements the complex impedance characteristic value, thereby improving the measurement effect and the accuracy of ice detection. Specifically, the present invention applies a cascade machine learning algorithm to judge the ice state, and uses an ice type classifier and an ice thickness regressor to judge the ice type and ice thickness respectively. The design and application of the algorithm in ice measurement makes the ice measurement have the robustness, stability and accuracy of data calculation. The multi-level capacitance-ice thickness fitting curve query method is adopted to further reduce the complexity of ice thickness measurement, while ensuring the signal-to-noise ratio of ice thickness measurement.
[0120] The embodiment of the present invention also provides a computer device. Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.
[0121] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.
[0122] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.
[0123] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0124] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.
[0125] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.
[0126] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.
[0127] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.
[0128] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.
[0129] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. An ice detection device, It is characterized in that The ice detection device comprises a complex impedance measurement unit and a data processing unit, wherein the complex impedance measurement unit is connected to the data processing unit, wherein: The complex impedance measurement unit includes a plurality of electrodes of preset shapes, the electrodes are arranged according to a preset rule, at least two of the electrodes are selected as a group of electrode pairs, and the complex impedance measurement unit is used to collect complex impedance data of multiple frequency bands at the positions to be detected using the plurality of groups of electrode pairs; The data processing unit is used to process the complex impedance data and determine ice coverage detection information at the position to be detected based on the complex impedance data.
2. The ice detection device according to claim 1, It is characterized in that The ice detection device further includes a temperature measurement unit, wherein: The temperature measuring unit is used to collect temperature information at the position to be detected; The data processing unit is used to use the complex impedance data and the temperature information as input data of an ice detection model, process the complex impedance data and the temperature information, and output the ice detection information at the position to be detected. The ice detection model is a cascade machine learning model.
3. The ice detection device according to claim 1, It is characterized in that The electrodes include excitation electrodes and measurement electrodes, each group of the electrode pairs includes at least one of the excitation electrodes and at least one of the measurement electrodes, and the electrode pairs have different characteristic parameters, including the distance between electrodes, electrode width and electrode area.
4. An ice detection method, applied to the ice detection device according to claim 2, It is characterized in that The method comprises: Using multiple groups of electrode pairs to collect complex impedance data of multiple frequency bands at the positions to be detected, and performing characteristic processing on the complex impedance data of each frequency band to obtain complex impedance characteristic values; Using a temperature measurement unit to collect temperature information at the position to be detected; The temperature information is used to perform temperature compensation on the complex impedance characteristic value, and the ice coverage at the position to be detected is detected to obtain ice coverage detection information.
5. The ice detection method according to claim 4, It is characterized in that The using the temperature information to perform temperature compensation on the complex impedance characteristic value, detecting the ice coverage condition of the position to be detected, and obtaining the ice coverage detection information includes: The complex impedance characteristic value and the temperature information are input into the ice detection model, the ice condition of the position to be detected is detected, and ice detection information is output; and / or the complex impedance characteristic value and a preset capacitance ice thickness fitting curve are used to calculate the ice detection information of the position to be detected.
6. The ice detection method according to claim 5, It is characterized in that The ice detection model includes an ice type classifier, and the temperature information is used to perform temperature compensation on the complex impedance characteristic value, and the ice condition of the position to be detected is detected, and the ice detection information obtained includes: inputting the complex impedance characteristic value and the temperature information into the ice type classifier; Calculating the probability that the ice covering type of the position to be detected is a preset ice covering type, and outputting the preset ice covering type with the highest probability as the ice covering type of the position to be detected; The preset ice types include clear ice, frost ice, mixed ice, water, pollutants and dry.
7. The ice detection method according to claim 6, It is characterized in that The ice cover detection model further includes an ice thickness regressor, and after the preset ice cover type with the highest output probability is used as the ice cover type of the position to be detected, the following further includes: Obtain the ice thickness regressor corresponding to the ice cover type; The complex impedance characteristic value and the temperature information are input into the ice thickness regressor, and the ice thickness results of different machine learning algorithms are integrated to calculate the ice thickness value of the position to be detected.
8. The ice detection method according to claim 5, It is characterized in that The performing characteristic processing on the complex impedance data of each frequency band to obtain a complex impedance characteristic value comprises: Performing feature processing on the complex impedance data using an RC parallel model to calculate a first complex impedance feature value, where the first complex impedance feature value includes an equivalent capacitance value and a loss tangent value; A second complex impedance characteristic value is calculated based on the first complex impedance characteristic value, wherein the second complex impedance characteristic value includes a low-frequency capacitance value, a high-frequency capacitance value, a relaxation time, a high- and low-frequency capacitance difference, a high- and low-frequency capacitance ratio, a number of loss peaks, a first loss peak-to-peak value, a second loss peak-to-peak value, and a loss peak-to-peak value ratio.
9. The ice detection method according to claim 8, It is characterized in that The complex impedance characteristic value includes a capacitance value, and the calculation of ice detection information of the to-be-detected position by using the complex impedance characteristic value and a preset capacitance ice thickness fitting curve includes: Constructing a plurality of capacitive ice thickness fitting curves, wherein the plurality of capacitive ice thickness fitting curves are pre-established ice thickness detection curves of a plurality of electrode pairs; The ice thickness value of the position to be detected is determined by using the equivalent capacitance value and the capacitance ice thickness fitting curve.
10. The ice detection method according to claim 9, It is characterized in that The step of determining the ice thickness value of the position to be detected by using the equivalent capacitance value and the capacitance ice thickness fitting curve comprises: The electrode pairs are sorted according to the electrode spacing from small to large, and the corresponding thickness information is determined by using the electrode pairs and the capacitance ice thickness fitting curves of the electrode pairs in turn; Determine whether the thickness information is less than a preset threshold value of the electrode pair, and when the thickness information is less than the preset threshold value of the electrode pair, use the thickness information as the ice thickness value of the position to be detected; Otherwise, the thickness information is calculated using the next electrode pair until the ice thickness value of the position to be detected is obtained.
11. The ice detection method according to claim 10, It is characterized in that The determining corresponding thickness information by sequentially using the electrode pair and the capacitance ice thickness fitting curve of the electrode pair comprises: Obtaining a first equivalent capacitance value corresponding to the complex impedance data collected by a first electrode pair having the smallest electrode spacing; Obtaining a first capacitance ice thickness fitting curve of the first electrode pair; The first thickness information corresponding to the first equivalent capacitance value is calculated in the first capacitance ice thickness fitting curve.
12. A computer device, It is characterized in that include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the ice detection method according to any one of claims 4 to 11 by executing the computer instructions.
13. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the ice detection method according to any one of claims 4 to 11.
14. A computer program product, It is characterized in that The method comprises computer instructions, wherein the computer instructions are used to enable a computer to execute the ice coating detection method according to any one of claims 4 to 11.
Citation Information
Patent Citations
Supercooled large water drop icing probe and detector
CN112550723A
Composite aircraft icing detector and icing thickness measuring method
CN112697055A
Ice detection and removal device and method
CN113286391A
Wind turbine blade deicing system based on low-resistance metal material, blade deicing control method, blade and wind generating set
CN115614233A
Array type icing detector
CN116022340A
Cited By
Electrode dislocation detection method and system based on dual-magnetic-pole Hall effect sensor
CN120368837A
Mountain area power distribution network voltage dynamic regulation and energy-saving operation method
CN121461364A
Icing detection method and system
CN122486454A
Ice detection method and system
CN122486454B
