An RFID-based aircraft maintenance process management method

Abstract

The present application relates to the technical field of aircraft maintenance management, and particularly relates to an aircraft maintenance process management method based on RFID, comprising: obtaining a surface image of a to-be-identified part label; determining whether an occlusion area exists on the surface of the to-be-identified part label based on a gray scale variance characteristic parameter; determining whether the occlusion area is oil dirt based on an oil dirt comprehensive discrimination index; identifying the to-be-identified part label by using an RFID reader-writer, determining whether the identification process of the to-be-identified part label is affected by oil dirt based on an oil dirt impedance index, and adjusting the transmission power of the reader-writer according to the difference; determining the relationship between the oil dirt of the to-be-identified part label and the oil dirt of an adjacent part label based on an oil dirt diffusion form characteristic value; determining whether the cleaning degree of the to-be-identified part label meets the standard based on the oil dirt residual gradient value of the to-be-identified part label after cleaning, and adjusting the preset cleaning parameters according to the ratio. The present application improves the accuracy of RFID identification in the aircraft maintenance process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of aircraft maintenance management, and particularly relates to an aircraft maintenance process management method based on RFID. BACKGROUND

[0002] In the aircraft maintenance process, RFID technology is widely used in the identification and information tracing of aircraft parts due to its non-contact identification and batch reading advantages. However, the RFID tags on the surface of aircraft parts are easily blocked by oil stains and other pollutants in the long-term complex operating environment, which leads to identification failure or reduced identification accuracy of the RFID reader, seriously affecting the real-time acquisition and management of part information in the maintenance process. There is a lack of quantitative evaluation of the impact of oil stains on RFID identification, and the adjustment of the transmission power of the reader is mostly dependent on experience, which may lead to energy waste or interference with other devices due to excessive power, or still cannot identify due to insufficient power. The diffusion characteristics of oil stains are not considered, and cross-contamination often occurs during the cleaning process due to the unclear diffusion direction of oil stains, which reduces the cleaning efficiency and affects the accuracy of maintenance records.

[0003] Chinese Patent Application Publication No. CN101614829A discloses an airborne laser fluorescence marine oil pollution detection device, which includes a laser, a telescope, and a spectrometer. The region of the divergent light of each divergence angle generated by the light emitted by the laser irradiating the surface of the detected object can overlap with the field of view of the telescope. When the laser emits laser light to irradiate the surface of the detected object, the telescope receives the fluorescence emitted after excitation, and the amplified fluorescence is transmitted to the spectrometer through the light receiving end of the spectrometer via the observation end. The laser is used to emit ultraviolet light of a certain wavelength to irradiate the surface of the detected object. The fluorescence emitted after excitation of the surface of the detected object is amplified by the telescope and received by the spectrometer. The spectrometer analyzes the spectral characteristics of the received fluorescence to analyze the type of the detected object. The installation of a movable window and a sliding rail type support on the aircraft can facilitate the operation of the entire device.

[0004] However, the prior art has the following problems: the RFID electronic tag may be blocked due to contamination, and the impact of the contamination on the RFID signal transmission is not handled, which leads to low accuracy of RFID identification in the aircraft maintenance process. SUMMARY

[0005] Therefore, the present application provides an aircraft maintenance process management method based on RFID to overcome the problem of low accuracy of RFID identification in the aircraft maintenance process due to the lack of handling of the RFID electronic tag being blocked due to contamination and the impact of the contamination on the RFID signal transmission in the prior art.

[0006] To achieve the above-mentioned purpose, the present application provides an aircraft maintenance process management method based on RFID, which comprises:

[0007] acquiring a surface image of the part label to be identified;

[0008] extracting a gray scale feature of the surface image to determine a gray scale variance characteristic parameter and determine whether there is an occluded area on the surface of the part label to be identified;

[0009] extracting a visible light image of the occluded area to determine an oil stain comprehensive discrimination index and determine whether the occluded area is an oil stain;

[0010] identifying the part label to be identified by using an RFID reader-writer, determining whether the oil stain has an impact on the identification process of the part label to be identified based on an oil stain impedance index of the part label to be identified, and determining the adjustment of the transmission power of the reader-writer according to the difference between the oil stain impedance index and a preset oil stain impedance index;

[0011] determining the degree of oil stain adhesion based on the surface image to determine whether the oil stain of the part label to be identified is solidified, and determining whether to analyze the relationship between the oil stain of the part label to be identified and the adjacent part label according to the relative difference between the oil stain adhesion degree and a preset oil stain adhesion degree;

[0012] extracting the oil stain diffusion characteristics of a plurality of adjacent part labels to determine the relationship between the oil stain of the part label to be identified and the oil stain of the adjacent part label based on the obtained oil stain diffusion form characteristic value;

[0013] cleaning the part label to be identified with a preset cleaning parameter, determining whether the cleaning degree of the part label to be identified meets the standard based on the oil stain residual gradient value of the part label to be identified after cleaning, and determining the adjustment of the preset cleaning parameter according to the ratio of the preset oil stain residual gradient value to the oil stain residual gradient value.

[0014] Further, the existence of the occluded area of the part label to be identified is determined based on the comparison result that the gray scale variance characteristic parameter is greater than a preset gray scale variance characteristic parameter.

[0015] The gray scale variance characteristic parameter is the gray scale value variance of all pixels in the gray scale image converted from the surface image.

[0016] Further, the occluded area is an oil stain occluded area, which is determined based on the comparison result that the oil stain comprehensive discrimination index is greater than a preset oil stain comprehensive discrimination index.

[0017] The determination process of the oil stain comprehensive discrimination index includes,

[0018] calculating the average gray scale value of the gray scale image of the occluded area and the average gray scale value of the clean area, and calculating the average contrast value of the occluded area and the average contrast value of the clean area;

[0019] The difference between the average gray value of the occlusion area gray image and the average gray value of the clean area is taken as an absolute value, and then divided by the difference between the maximum gray value of the occlusion area gray image and the minimum gray value of the occlusion area gray image, and then multiplied by the difference between the average contrast of the occlusion area gray image and the average contrast of the clean area, which is taken as an absolute value, and then divided by the difference between the maximum contrast of the occlusion area gray image and the minimum contrast of the occlusion area gray image.

[0020] Further, the oil stain has an impact on the identification process of the to-be-identified part label, and the identification process is determined based on the comparison result that the oil stain resistance index is greater than a preset oil stain resistance index.

[0021] The oil stain resistance index is the product of the difference between the reference maximum reading distance normalized value and the maximum reading distance normalized value, which is taken as an absolute value, and the reference maximum reading distance normalized value, multiplied by the product of the number of reading failures and the number of repeated readings.

[0022] Further, the process of adjusting the transmission power of the reader-writer includes:

[0023] Calculate the difference between the oil stain resistance index and the preset oil stain resistance index;

[0024] Based on the comparison result that the difference is less than or equal to a preset difference, the transmission power is increased by a first preset power adjustment coefficient;

[0025] Based on the comparison result that the difference is greater than the preset difference, the transmission power is increased by a second preset power adjustment coefficient;

[0026] Wherein, the adjusted transmission power is the product of the transmission power and the preset power adjustment coefficient, and the preset power adjustment coefficient includes the first preset power adjustment coefficient and the second preset power adjustment coefficient.

[0027] Further, the oil stain of the to-be-identified part label has solidified based on the comparison result that the oil stain adhesion degree is greater than a preset oil stain adhesion degree.

[0028] The oil stain adhesion degree is the ratio of the average contrast of the oil stain area to the average contrast of the clean area, and the average contrast is determined based on the gray level co-occurrence matrix, wherein

[0029] The determination process of the average contrast is to calculate the contrast using the Haralick feature standard formula, and calculate the arithmetic mean of the contrast in different directions, which is the average contrast.

[0030] Further, in the condition that it is determined that the oil stain of the part label to be identified has been solidified, the process of determining whether to analyze the oil stain of the part label to be identified and the adjacent part label according to a comparison result of a relative difference of the oil stain adhesion degree and a preset relative difference and the preset relative difference comprises:

[0031] determining to analyze the relationship between the oil stain of the part label to be identified and the adjacent part label based on the comparison result that the relative difference is greater than the preset relative difference, wherein

[0032] the process of analyzing the relationship between the oil stain of the part label to be identified and the adjacent part label comprises: finding a plurality of adjacent part labels of the part label to be identified according to the aircraft maintenance manual, and capturing local images of the adjacent part labels by using an industrial camera, and extracting oil stain diffusion characteristics of the adjacent part labels.

[0033] Further, the oil stain diffusion from the part label to be identified to the adjacent part label is determined based on a comparison result that the oil stain diffusion form characteristic value is greater than a preset oil stain diffusion form characteristic value, wherein

[0034] the oil stain diffusion form characteristic value is a product of an average value of the oil stain area of the part label to be identified and the oil stain area of the adjacent part label and a ratio of a total area of the part label to be identified to a total area of the adjacent part label.

[0035] Further, the cleaning degree of the part label to be identified is determined to be substandard based on a comparison result that the oil stain residual gradient value is greater than a preset oil stain residual gradient value, wherein

[0036] the oil stain residual gradient value is a product of a ratio of an absolute value of a difference between an average gray value of a central region and an average gray value of an edge region of a surface of the part label to be identified after cleaning to the average gray value of the central region and a ratio of a gray standard deviation of the edge region to a gray standard deviation of the central region.

[0037] Further, the process of adjusting the preset cleaning parameter comprises:

[0038] calculating a ratio of the preset oil stain residual gradient value to the oil stain residual gradient value;

[0039] based on a comparison result that the ratio is less than or equal to a preset ratio, determining to increase the cleaning time to a corresponding value by a preset cleaning time adjustment coefficient;

[0040] based on a comparison result that the ratio is greater than the preset ratio, determining to increase the cleaning temperature to a corresponding value by a preset cleaning temperature adjustment coefficient;

[0041] wherein the increased cleaning time is a product of the cleaning time and the preset cleaning time adjustment coefficient, and the increased cleaning temperature is a product of the cleaning temperature and the preset cleaning temperature adjustment coefficient.

[0042] Compared with the prior art, the present application has the beneficial effects that the present application determines whether there is an occlusion area on the surface of the part label to be identified by the gray scale variance characteristic parameter of the surface image, reduces the occlusion false detection rate, determines whether the occlusion area is oil stain according to the oil stain comprehensive discrimination index, determines whether the oil stain affects the identification process of the part label to be identified based on the oil stain impedance index, adjusts the read-write device transmission power when the oil stain affects the identification process, compensates for the signal attenuation caused by the oil stain, determines the relationship between the oil stain of the part label to be identified and the oil stain of the adjacent part label according to the oil stain diffusion form characteristic value, determines whether the cleaning degree of the part label to be identified meets the standard according to the oil stain residual gradient value, and adjusts the preset cleaning parameter according to the ratio of the preset oil stain residual gradient value and the oil stain residual gradient value when the cleaning degree does not meet the standard, so that the RFID power dynamic compensation mechanism improves the identification success rate of the oil stain covered label, guarantees the integrity of the maintenance data, and thus improves the accuracy of RFID identification in the aircraft maintenance process.

[0043] Further, the present application converts the part label surface image into a gray scale image, calculates the pixel gray scale value variance and compares it with the preset threshold value, determines that there is an occlusion if the variance is out of limit, extracts the visible light image features for the occlusion area, calculates the oil stain comprehensive discrimination index combining the gray scale difference and the texture contrast, and confirms that it is oil stain pollution if the index is out of limit, so that the occlusion detection time is reduced, the oil stain discrimination index fuses multi-dimensional features, reduces the misjudgment rate, improves the oil stain identification confidence, improves the aircraft maintenance quality, and thus improves the accuracy of RFID identification in the aircraft maintenance process.

[0044] Further, the present application determines the influence of the oil stain on the RFID identification by comparing the oil stain impedance index in the oil stain state, selects the power adjustment coefficient according to the out-of-limit amplitude of the impedance index, compensates for the signal attenuation, improves the identification reliability, improves the identification success rate in the oil stain scene, reduces the repeated scanning frequency, eliminates the misjudgment caused by occasional interference, reduces the false alarm rate, limits the power adjustment amplitude to prevent electromagnetic interference from spreading, guarantees the RFID system compatibility of adjacent equipment, avoids communication conflicts, and improves the identification coverage rate in complex cabin environments, thereby improving the accuracy of RFID identification in the aircraft maintenance process.

[0045] Further, the present application determines whether the oil stain is solidified by the oil stain adhesion degree, determines whether to start the pollution diffusion analysis of the adjacent part label if it is determined that the oil stain is solidified, directly cleans the current label if the analysis is not needed, uses the determination result of the physical state of the oil stain as the direct input of whether to start the subsequent diffusion correlation analysis, filters out the slight solidified pollution, and only performs complex diffusion analysis on the significantly solidified oil stain, thereby avoiding unnecessary consumption of computing resources, ensuring the accuracy of the pollution traceability analysis, and improving the efficiency of the cleaning decision.

[0046] Further, the present application determines the pollution spread direction through the diffusion form characterization value, preferentially cleans the pollution source label or synchronously cleans the associated label according to the diffusion direction, reduces the invalid cleaning caused by misjudgment, reduces the cross-contamination risk through the contact edge reinforced cleaning design, reduces the failure rate of key components, realizes the accurate allocation of maintenance resources while reducing the environmental load, and improves the accuracy of RFID identification in the aircraft maintenance process.

[0047] Further, the present application determines the pollution spread direction through the diffusion form characterization value, preferentially cleans the pollution source label or synchronously cleans the associated label according to the diffusion direction, reduces the invalid cleaning caused by misjudgment, reduces the cross-contamination risk through the contact edge reinforced cleaning design, reduces the failure rate of key components, realizes the accurate allocation of maintenance resources while reducing the environmental load, and improves the accuracy of RFID identification in the aircraft maintenance process. BRIEF DESCRIPTION OF DRAWINGS

[0048] Figure 1 The flowchart of the embodiment of the present application is shown in the figure.

[0049] Figure 2 The flowchart of the embodiment of the present application is shown in the figure.

[0050] Figure 3 The flowchart of the embodiment of the present application is shown in the figure.

[0051] Figure 4 The flowchart of the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0052] In order to make the purpose and advantages of the present application clearer and more apparent, the present application will be further described below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application.

[0053] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application.

[0054] It should be noted that the data in the embodiment are obtained by comprehensive analysis and evaluation of historical detection data and corresponding historical detection results in the three months before the detection. Those skilled in the art can understand that the determination method of the present application for a single parameter can be to select the value with the highest proportion as the preset standard parameter according to the data distribution, to use weighted summation to obtain the value as the preset standard parameter, to substitute each historical data into a specific formula and to obtain the value by using the formula as the preset standard parameter, or other selection methods, as long as the present application can clearly define different specific situations in the single determination process by the obtained value.

[0055] Referring to Figure 1 Fig. 1 is a flowchart of an RFID-based aircraft maintenance process management method according to an embodiment of the present application.

[0056] The RFID-based aircraft maintenance process management method according to an embodiment of the present application comprises the following steps.

[0057] Step S1, obtaining a surface image of a part tag to be identified;

[0058] Step S2, extracting a gray-scale feature of the surface image to determine a gray-scale variance characteristic parameter and determining whether there is an occlusion area on the surface of the part tag to be identified;

[0059] Step S3, extracting a visible light image of the occlusion area to determine an oil stain comprehensive discrimination index and determining whether the occlusion area is an oil stain;

[0060] Step S4, identifying the part tag to be identified by using an RFID reader-writer, determining whether the identification process of the part tag to be identified is affected by the oil stain based on an oil stain impedance index of the part tag to be identified, and determining the adjustment of the transmission power of the reader-writer according to the difference between the oil stain impedance index and a preset oil stain impedance index;

[0061] Step S5, determining the oil stain adhesion degree based on the surface image to determine whether the oil stain of the part tag to be identified is solidified, and determining whether to analyze the relationship between the oil stain of the part tag to be identified and the adjacent part tag according to the relative difference between the oil stain adhesion degree and a preset oil stain adhesion degree;

[0062] Step S6, extracting oil stain diffusion features of a plurality of adjacent part tags to determine the relationship between the oil stain of the part tag to be identified and the oil stain of the adjacent part tags based on the obtained oil stain diffusion mode characteristic value;

[0063] In step S7, the to-be-identified part label is cleaned with preset cleaning parameters, and whether the cleaning degree of the to-be-identified part label meets the standard is determined based on the oil stain residual gradient value of the to-be-identified part label after cleaning, so as to determine the adjustment of the preset cleaning parameters according to the ratio of the preset oil stain residual gradient value to the oil stain residual gradient value.

[0064] Specifically, the present application determines whether the surface of the to-be-identified part label has a shielding area by the gray variance characterization parameter of the surface image, reduces the shielding false detection rate, determines whether the shielding area is oil stain according to the oil stain comprehensive discrimination index, determines whether the identification process of the to-be-identified part label is affected by the oil stain based on the oil stain impedance index, adjusts the transmission power of the reader when the identification process is affected, compensates for the attenuation of the signal caused by the oil stain, determines the relationship between the oil stain of the to-be-identified part label and the oil stain of the adjacent part label according to the oil stain diffusion form characterization value, determines whether the cleaning degree of the to-be-identified part label meets the standard according to the oil stain residual gradient value, and adjusts the preset cleaning parameters according to the ratio of the preset oil stain residual gradient value to the oil stain residual gradient value when the cleaning degree does not meet the standard. The RFID power dynamic compensation mechanism improves the identification success rate of the oil stain covered label, ensures the integrity of the maintenance data, and thus improves the accuracy of RFID identification in the process of aircraft maintenance.

[0065] Please refer to Figure 2 As shown in the flow chart of determining whether the surface of the to-be-identified part label has a shielding area in the embodiment of the present application.

[0066] Specifically, the present application determines whether the surface of the to-be-identified part label has a shielding area according to the comparison result of the gray variance characterization parameter obtained from the surface image and the preset gray variance characterization parameter.

[0067] When the gray variance characterization parameter is less than or equal to the preset gray variance characterization parameter, it is determined that the surface of the to-be-identified part label does not have a shielding area.

[0068] When the gray variance characterization parameter is greater than the preset gray variance characterization parameter, it is determined that the surface of the to-be-identified part label has a shielding area.

[0069] In the embodiment of the present application, the value range of the preset gray variance characterization parameter is [70, 100], and the preferred value is 85, but the above value is not limited thereto, and the value can be adjusted according to actual needs by those skilled in the art.

[0070] In the embodiment of the present application, the process of obtaining the gray variance characterization parameter is to convert the surface image into an 8-bit gray image, calculate the gray value variance of all pixels in the gray image, that is, the sum of the square of the difference between the gray value of all pixels and the average gray value divided by the number of pixels.

[0071] Specifically, the embodiment of the present application extracts a visible light image of the occluded area under the condition that the surface of the part label to be identified is determined to have an occluded area, and determines whether the occluded area is oil dirt according to the comparison result of the comprehensive oil dirt discrimination index obtained from the visible light image features and the preset comprehensive oil dirt discrimination index.

[0072] When the comprehensive oil dirt discrimination index is less than or equal to the preset comprehensive oil dirt discrimination index, it is determined that the occluded area is non-oil dirt occlusion.

[0073] When the comprehensive oil dirt discrimination index is greater than the preset comprehensive oil dirt discrimination index, it is determined that the occluded area is oil dirt occlusion.

[0074] In the embodiment of the present application, the preset comprehensive oil dirt discrimination index has a value range of [0.3, 0.5], preferably 0.4, but the above value is not limited thereto, and the skilled person in the art can also adjust the value according to actual needs.

[0075] In the embodiment of the present application, the process of obtaining the comprehensive oil dirt discrimination index is to calculate the average gray value of the occluded area gray image and the average gray value of the clean area; calculate the average contrast of the occluded area and the average contrast of the clean area using the gray level co-occurrence matrix; subtract the average gray value of the occluded area gray image from the average gray value of the clean area, take the absolute value, divide the difference between the maximum gray value of the occluded area gray image and the minimum gray value of the occluded area gray image, multiply the average contrast of the occluded area gray image and the average contrast of the clean area, take the absolute value, divide the difference between the maximum contrast of the occluded area gray image and the minimum contrast of the occluded area gray image.

[0076] Specifically, the present application converts the part label surface image into a gray image, calculates the pixel gray value variance and compares it with the preset threshold value, and if the variance is out of limit, it is determined that there is an occlusion. Visible light image features are extracted for the occluded area, and the comprehensive oil dirt discrimination index is calculated by combining the gray difference and the texture contrast. If it is out of limit, it is confirmed as oil dirt pollution. The time-consuming of occlusion detection is reduced, the oil dirt discrimination index integrates multi-dimensional features, the misjudgment rate is reduced, the identification confidence of oil dirt is improved, the quality of aircraft maintenance is improved, and the accuracy of RFID identification in the process of aircraft maintenance is improved.

[0077] Please refer to Figure 3 shown, which is a flow chart of the process of determining whether the oil dirt affects the identification of the part label to be identified according to the embodiment of the present application.

[0078] Specifically, in the condition that the shielding area is determined as oil stain, the RFID reader is used to identify the part label to be identified, and the influence of the oil stain on the identification process of the part label to be identified is determined according to the comparison result of the oil stain impedance index obtained according to the identification feature and the preset oil stain impedance index.

[0079] When the oil stain impedance index is less than or equal to the preset oil stain impedance index, it is determined that the oil stain has no influence on the identification process of the part label to be identified.

[0080] When the oil stain impedance index is greater than the preset oil stain impedance index, it is determined that the oil stain has influence on the identification process of the part label to be identified.

[0081] In the embodiment of the present application, the preset oil stain impedance index is in the range of [0.2, 0.4], preferably 0.3, but the above value is not limited thereto, and the skilled person in the art can also adjust the value according to the actual needs.

[0082] In the embodiment of the present application, the process of obtaining the oil stain impedance index is as follows: in the oil stain area detection state, the maximum reading distance of the reader to the label is recorded, in the clean state, the reference maximum reading distance of the same reader to the same label is recorded, the reading is repeated several times in the oil stain area, the number of reading failures is counted, and the oil stain impedance index is the result of the absolute value of the difference between the reference maximum reading distance normalized value and the maximum reading distance normalized value divided by the reference maximum reading distance normalized value multiplied by the product of the number of reading failures and the number of repeated readings.

[0083] Specifically, in the condition that the oil stain has influence on the identification process of the part label to be identified, the difference between the oil stain impedance index and the preset oil stain impedance index is compared with the preset difference value to determine the adjustment of the transmission power of the reader.

[0084] When the difference is less than or equal to the preset difference value, it is determined that the transmission power of the reader is increased to a corresponding value by a first preset power adjustment coefficient 1.10.

[0085] When the difference is greater than the preset difference value, it is determined that the transmission power of the reader is increased to a corresponding value by a second preset power adjustment coefficient 1.20.

[0086] The difference is the difference between the oil stain impedance index and the preset oil stain impedance index.

[0087] In the embodiment of the present application, the preset difference value is in the range of [0.15, 0.25], preferably 0.2, but the above value is not limited thereto, and the skilled person in the art can also adjust the value according to the actual needs.

[0088] In the embodiment of the present application, the adjusted transmission power is the product of the transmission power and the preset power adjustment coefficient, the preset power adjustment coefficient includes a first preset power adjustment coefficient with a value of 1.10 and a second preset power adjustment coefficient with a value of 1.20, in order to ensure that the adjusted transmission power meets the actual demand, the adjustment range should not be too large, so the adjustment coefficient is set to control the adjustment range.

[0089] In the embodiment of the present application, the first preset power adjustment coefficient and the second preset power adjustment coefficient are both determined based on historical RFID identification processes. 500 groups of RFID identification success rate data under different oil stain impedance index difference intervals in the historical maintenance process are selected, the power adjustment coefficient used in each difference interval is evaluated for effect, and the coefficient with the largest identification success rate improvement is selected as the preset value; through weighted average method or cluster analysis, the coefficient with the highest identification success rate and the optimal energy consumption control is set as the first and second adjustment coefficients respectively.

[0090] Specifically, the present application determines the influence of oil stains on RFID identification by comparing the oil stain impedance index under oil stains, selects a power adjustment coefficient according to the impedance index overrun amplitude, compensates for signal attenuation, improves identification reliability, improves identification success rate in oil stain scenarios, reduces repeated scanning frequency, eliminates occasional interference misjudgment, reduces false alarm rate, limits power adjustment amplitude to prevent electromagnetic interference from spreading, ensures compatibility of RFID systems of adjacent equipment, avoids communication conflicts, and improves identification coverage rate in complex engine compartment environments, thereby improving the accuracy of RFID identification in the process of aircraft maintenance.

[0091] Specifically, in the embodiment of the present application, under the condition of adjusting the transmission power of the reader-writer, whether the oil stain of the part label to be identified has solidified is determined according to the comparison result of the oil stain adhesion degree of the oil stain and the preset oil stain adhesion degree.

[0092] When the oil stain adhesion degree is less than or equal to the preset oil stain adhesion degree, it is determined that the oil stain of the part label to be identified has not solidified.

[0093] When the oil stain adhesion degree is greater than the preset oil stain adhesion degree, it is determined that the oil stain of the part label to be identified has solidified.

[0094] In the embodiment of the present application, the preset oil stain adhesion degree has a value range of [0.35, 0.45], preferably 0.4, but the above value is not limited thereto, and a person skilled in the art can also adjust the value according to actual needs.

[0095] In the embodiment of the present application, the process of obtaining the oil adhesion degree is as follows: calculating the gray level co-occurrence matrix of the oil area and the gray level co-occurrence matrix of the clean area; calculating the average contrast of the oil area according to the gray level co-occurrence matrix of the oil area; calculating the average contrast of the clean area according to the gray level co-occurrence matrix of the clean area; and the oil adhesion degree is the ratio of the average contrast of the oil area to the average contrast of the clean area.

[0096] In the embodiment of the present application, the process of calculating the average contrast is as follows: calculating the contrast of the oil area by using the Haralick feature standard formula, calculating the contrast of the oil area in different directions, and then taking the arithmetic average as the average contrast of the oil area. The above process of calculating the contrast is a conventional process and will not be described here.

[0097] Specifically, in the condition of determining that the oil of the to-be-identified part label has solidified, whether to analyze the oil of the to-be-identified part label and the adjacent part label is determined according to the comparison result of the relative difference between the oil adhesion degree and the preset oil adhesion degree and the preset relative difference.

[0098] When the relative difference is less than or equal to the preset relative difference, it is determined not to analyze the oil of the to-be-identified part label and the adjacent part label.

[0099] When the relative difference is greater than the preset relative difference, it is determined to analyze the relationship between the oil of the to-be-identified part label and the adjacent part label.

[0100] The relative difference is the relative difference between the oil adhesion degree and the preset oil adhesion degree.

[0101] In the embodiment of the present application, the preset relative difference is in the range of [0.25, 0.35], and is preferably 0.3. However, the above value is not limited thereto, and a person skilled in the art can adjust the value according to actual needs.

[0102] Specifically, in the condition of determining not to analyze the oil of the to-be-identified part label and the adjacent part label, the oil of the to-be-identified part label is cleaned.

[0103] Specifically, the present application determines whether the oil has solidified by using the oil adhesion degree. If it is determined that the oil has solidified, whether to start the pollution diffusion analysis of the adjacent part label is determined. If there is no need to analyze, the current label is directly cleaned. The determination result of the physical state of the oil is directly input as whether to start the subsequent diffusion correlation analysis, filters out the slightly solidified pollution, and only the significantly solidified oil is subjected to complex diffusion analysis, thereby avoiding unnecessary consumption of computing resources, ensuring the accuracy of the pollution traceability analysis, and improving the efficiency of the cleaning decision.

[0104] Specifically, the embodiment of the present application determines the condition of analyzing the oil stains of the to-be-identified part label and the adjacent part label, finds a plurality of adjacent part labels of the to-be-identified part label according to the aircraft maintenance manual, takes local images of the adjacent part labels by using an industrial camera, and extracts oil stain diffusion characteristics of the adjacent part labels.

[0105] Specifically, the embodiment of the present application determines the oil stain diffusion relationship between the to-be-identified part label and the adjacent part label according to the comparison result of the oil stain diffusion form characteristic value obtained according to the oil stain diffusion characteristics and the preset oil stain diffusion form characteristic value.

[0106] When the oil stain diffusion form characteristic value is less than or equal to the preset oil stain diffusion form characteristic value, it is determined that the oil stain diffuses from the adjacent part label to the to-be-identified part label.

[0107] When the oil stain diffusion form characteristic value is greater than the preset oil stain diffusion form characteristic value, it is determined that the oil stain diffuses from the to-be-identified part label to the adjacent part label.

[0108] In the embodiment of the present application, the preset oil stain diffusion form characteristic value is 1, but the above value is not limited thereto, and the skilled person in the art can also adjust the value according to actual needs.

[0109] In the embodiment of the present application, the process of obtaining the oil stain diffusion form characteristic value is to extract the oil stain area of the local image by using an image segmentation algorithm, calculate the area proportion of the oil stain area, and the oil stain diffusion form characteristic value is the product of the average value of the oil stain area of the to-be-identified part label and the oil stain area of the adjacent part label and the ratio of the total area of the to-be-identified part label to the total area of the adjacent part label.

[0110] Specifically, when it is determined that the oil stain diffuses from the adjacent part label, the adjacent part label is preferentially cleaned, the contact edge area between the adjacent part label and the to-be-identified part label is mainly cleaned, and the risk of cross contamination is reduced; when it is determined that the oil stain diffuses from the to-be-identified part label to the adjacent part label, the to-be-identified part label and the adjacent part label need to be cleaned synchronously to avoid the expansion of the pollution range.

[0111] Specifically, the to-be-identified part label is cleaned with preset cleaning parameters in the embodiment of the present application, wherein the preset cleaning parameters include a cleaning temperature range of 50℃-60℃, preferably 55℃, and a cleaning time of 55s-65s, preferably 60s.

[0112] Specifically, the application determines the pollution transmission direction through the diffusion mode characterization value, preferentially cleans the pollution source label or synchronously cleans the associated label according to the diffusion direction, reduces the invalid cleaning caused by misjudgment, reduces the cross-contamination risk through the contact edge reinforced cleaning design, reduces the failure rate of key components, realizes the accurate allocation of maintenance resources while reducing the environmental load, and improves the accuracy of RFID identification in the aircraft maintenance process.

[0113] Referring to Figure 4 As shown in the figure, it is a flow chart for determining whether the cleaning degree of the to-be-identified part label meets the standard in the embodiment of the application.

[0114] Specifically, the application determines whether the cleaning degree of the to-be-identified part label meets the standard according to the comparison result of the oil stain residual gradient value of the to-be-identified part label after cleaning and the preset oil stain residual gradient value;

[0115] When the oil stain residual gradient value is less than or equal to the preset oil stain residual gradient value, it is determined that the cleaning degree of the to-be-identified part label meets the standard;

[0116] When the oil stain residual gradient value is greater than the preset oil stain residual gradient value, it is determined that the cleaning degree of the to-be-identified part label does not meet the standard.

[0117] In the embodiment of the application, the preset oil stain residual gradient value is in the range of [0.15, 0.20], preferably 0.17, but the above value is not limited thereto, and the skilled person in the art can also adjust the value according to actual needs.

[0118] In the embodiment of the application, the process of obtaining the oil stain residual gradient value is to divide the surface image of the to-be-identified part label after cleaning into a 3x3 grid, calculate the average gray difference ratio of the center area (grid 5) and the edge area (grids 2, 4, 6, 8), and the oil stain residual gradient value is the absolute value of the difference between the average gray value of the center area and the average gray value of the edge area, multiplied by the ratio of the edge area gray standard deviation to the center area gray standard deviation.

[0119] Specifically, under the condition that the cleaning degree of the to-be-identified part label does not meet the standard, the embodiment of the application determines to adjust the preset cleaning parameter according to the ratio of the preset oil stain residual gradient value to the oil stain residual gradient value and the preset ratio;

[0120] When the ratio is less than or equal to the preset ratio, it is determined to increase the cleaning time to the corresponding value by a preset cleaning time adjustment coefficient 1.5;

[0121] When the ratio is greater than the preset ratio, it is determined to increase the cleaning temperature to the corresponding value by a preset cleaning temperature adjustment coefficient 1.3;

[0122] The ratio is a ratio of a preset oil stain residual gradient value to an oil stain residual gradient value.

[0123] In the embodiment of the present application, the preset ratio value range is [0.72, 0.85], preferably 0.78, but the above-mentioned value is not limited thereto, and the person skilled in the art can also adjust the value according to actual needs.

[0124] In the embodiment of the present application, the increased cleaning time is the product of the cleaning time and the preset cleaning time adjustment coefficient, and the preset cleaning time adjustment coefficient is valued at 1.5; the increased cleaning temperature is the product of the cleaning temperature and the preset cleaning temperature adjustment coefficient, and the preset cleaning temperature adjustment coefficient is valued at 1.3; in order to ensure that the adjusted cleaning time and cleaning temperature meet the actual needs, the adjustment range should not be too large, so the adjustment coefficient is set to control the adjustment range.

[0125] In the embodiment of the present application, the determination of the preset cleaning temperature adjustment coefficient and the preset cleaning time adjustment coefficient is based on historical cleaning effect data and a thermodynamic-time coupling model, the cleaning time and temperature combination corresponding to different oil stain residual gradient values in the historical cleaning record are analyzed; a regression model of oil stain residual gradient and time, temperature is established to determine the optimal adjustment range; through experimental verification, under the premise of controlling the cleaning medium unchanged, the cleaning effect of different time and temperature combinations on residual oil stain is tested; the coefficient that maximizes the cleaning efficiency and does not damage the label surface is selected, and is set as the preset cleaning temperature adjustment coefficient and the preset cleaning time adjustment coefficient, respectively.

[0126] Specifically, in the embodiment of the present application, under the condition that the cleaning degree of the to-be-identified part label meets the standard, the current part label image is re-shot, the cleaning reference features of the to-be-identified part label are extracted, the matching degree of the current part label image and the cleaning reference is calculated using an image registration algorithm, if the matching degree is greater than or equal to a preset matching degree, it means that the pollution is caused by diffusion, and the information can be recovered; if the matching degree is less than the preset matching degree, it means that the original component oil stain has penetrated into the chip packaging layer, and the label needs to be replaced and the maintenance record needs to be updated.

[0127] In the embodiment of the present application, the preset matching degree value range is [80%, 90%], preferably 85%, but the above-mentioned value is not limited thereto, and the person skilled in the art can also adjust the value according to actual needs.

[0128] In the embodiment of the present application, the matching degree is the ratio of the cleaning features of the current part label image to the cleaning reference features of the to-be-identified part label, and the cleaning reference features of the to-be-identified part label are the label outline and text in the oil-free state stored in advance.

[0129] Specifically, the application determines the cleaning compliance rate through the oil stain residual gradient value, adjusts the cleaning time or temperature according to the residual gradient overrun amplitude, verifies whether the pollution is caused by chip penetration through image matching degree, improves the residual detection precision, avoids the risk of visual cleaning but microscopic pollution, prolongs the service life of the label, reduces the equipment overload risk caused by repeated operation, automatically distinguishes the surface pollution and chip penetration failure, improves the diffusion pollution tracing function to make the cross contamination responsibility judgment accuracy rate, and thus improves the accuracy of RFID identification in the aircraft maintenance process.

[0130] So far, the technical solutions of the application have been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the application, and the technical solutions after the changes or replacements will fall within the protection scope of the application.

Claims

1. An RFID-based aircraft maintenance process management method, characterized in that, include: Acquire a surface image of the label on the part to be identified; Extract the grayscale features of the surface image to determine the grayscale variance characterization parameter, and determine whether there is an occlusion area on the surface of the label of the part to be identified; Extract the visible light image of the obscured area to determine the comprehensive oil stain discrimination index, and determine whether the obscured area is oil stain; The RFID reader is used to identify the tag of the part to be identified. Based on the oil resistance index of the tag, it is determined whether the oil affects the identification process of the tag. The reader transmission power is adjusted according to the difference between the oil resistance index and the preset oil resistance index. The oil adhesion degree is determined based on the surface image to determine whether the oil on the label of the part to be identified has solidified, and the relationship between the oil on the label of the part to be identified and adjacent part labels is analyzed based on the relative difference between the oil adhesion degree and the preset oil adhesion degree. Extract the oil stain diffusion characteristics of several adjacent part labels to determine the relationship between the oil stains on the part label to be identified and the oil stains on adjacent part labels based on the obtained oil stain diffusion morphology characterization value; The label of the part to be identified is cleaned with preset cleaning parameters. The degree of cleaning of the label is determined based on the oil residue gradient value of the label after cleaning. The preset cleaning parameters are adjusted according to the ratio of the preset oil residue gradient value to the preset oil residue gradient value.

2. The RFID-based aircraft maintenance process management method according to claim 1, characterized in that, The occlusion area of ​​the label on the part to be identified is determined based on the comparison result of the gray-level variance characterization parameter being greater than a preset gray-level variance characterization parameter. The grayscale variance characterization parameter is the variance of grayscale values ​​of all pixels in the grayscale image converted from the surface image.

3. The RFID-based aircraft maintenance process management method according to claim 2, characterized in that, The area to be covered by oil stains is determined based on a comparison result where the comprehensive oil stain discrimination index is greater than a preset comprehensive oil stain discrimination index. The process of determining the comprehensive oil pollution discrimination index includes, Calculate the average gray value of the grayscale image in the occluded area and the average gray value in the clean area, and calculate the average contrast of the occluded area and the average contrast of the clean area. The absolute value of the difference between the average gray value of the occluded area and the average gray value of the clean area is divided by the difference between the maximum and minimum gray values ​​of the occluded area. This result is then multiplied by the absolute value of the difference between the average contrast of the occluded area and the average contrast of the clean area, and then divided by the difference between the maximum and minimum contrast of the occluded area.

4. The RFID-based aircraft maintenance process management method according to claim 3, characterized in that, The impact of oil contamination on the identification process of the part label is determined based on the comparison results where the oil contamination impedance index is greater than a preset oil contamination impedance index. The oil resistance index is calculated by taking the absolute value of the difference between the baseline maximum reading distance normalized value and the maximum reading distance normalized value, dividing it by the baseline maximum reading distance normalized value, and multiplying the result by the product of the number of reading failures and the number of repeated readings.

5. The RFID-based aircraft maintenance process management method according to claim 4, characterized in that, The process of adjusting the reader's transmission power includes: Calculate the difference between the oil resistance index and the preset oil resistance index; Based on the comparison results where the difference is less than or equal to a preset difference, the transmission power is increased by a first preset power adjustment coefficient. Based on the comparison result where the difference is greater than the preset difference, the transmission power is increased by a second preset power adjustment coefficient. The adjusted transmit power is the product of the transmit power and the preset power adjustment coefficient, which includes the first preset power adjustment coefficient and the second preset power adjustment coefficient.

6. The RFID-based aircraft maintenance process management method according to claim 5, characterized in that, The determination that the oil stains on the label of the part to be identified have solidified is based on a comparison result where the oil stain adhesion is greater than a preset oil stain adhesion. The oil stain adhesion degree is the ratio of the average contrast of the oil-stained area to the average contrast of the clean area. The average contrast is determined based on the gray-level co-occurrence matrix. The process of determining the average contrast ratio is as follows: the contrast ratio is calculated using the Haralick characteristic standard formula, and the arithmetic mean of the contrast ratio in different directions is calculated. The arithmetic mean is the average contrast ratio.

7. The RFID-based aircraft maintenance process management method according to claim 6, characterized in that, Under the condition that the oil stains on the label of the part to be identified have solidified, the process of determining whether to analyze the oil stains on the label of the part to be identified and adjacent label of the part, based on the comparison between the relative difference of the oil stain adhesion degree and the preset relative difference, includes: Based on the comparison results where the relative difference is greater than the preset relative difference, the relationship between the oil stains on the label of the part to be identified and adjacent part labels is analyzed, wherein... The process of analyzing the relationship between the oil stains on the label of the part to be identified and adjacent part labels is as follows: according to the aircraft maintenance manual, several adjacent part labels of the label of the part to be identified are found, local images of these adjacent part labels are taken with an industrial camera, and the oil stain diffusion characteristics of the adjacent part labels are extracted.

8. The RFID-based aircraft maintenance process management method according to claim 7, characterized in that, The spread of oil contamination from the label of the part to be identified to adjacent labels is determined based on a comparison of the oil contamination diffusion morphology characterization value, which is greater than a preset oil contamination diffusion morphology characterization value. The oil contamination morphology characterization value is the ratio of the oil contamination area of ​​the label of the part to be identified to the average oil contamination area of ​​the labels of adjacent parts, multiplied by the total area of ​​the label of the part to be identified to the total area of ​​the labels of adjacent parts.

9. The RFID-based aircraft maintenance process management method according to claim 8, characterized in that, The determination that the cleaning level of the label on the part to be identified is substandard is based on a comparison result where the oil residue gradient value is greater than a preset oil residue gradient value. The oil residue gradient value is the ratio of the absolute value of the difference between the average gray value of the central area and the average gray value of the edge area on the surface of the label of the part to be identified after cleaning to the average gray value of the central area, multiplied by the ratio of the standard deviation of gray value of the edge area to the standard deviation of gray value of the central area.

10. The RFID-based aircraft maintenance process management method according to claim 9, characterized in that, The process of adjusting the preset cleaning parameters includes: Calculate the ratio of the preset oil residue gradient value to the oil residue gradient value; Based on the comparison results where the ratio is less than or equal to a preset ratio, the cleaning time is increased to the corresponding value using a preset cleaning time adjustment coefficient. Based on the comparison results where the ratio is greater than the preset ratio, the cleaning temperature is increased to the corresponding value using a preset cleaning temperature adjustment coefficient. The increased cleaning time is the product of the cleaning time and the preset cleaning time adjustment coefficient, and the increased cleaning temperature is the product of the cleaning temperature and the preset cleaning temperature adjustment coefficient.

Images