Preventive inspection and maintenance method for special vehicle and unpowered support equipment

Abstract

The invention belongs to the technical field of object flaw detection, particularly relates to a preventive inspection and maintenance method for a special vehicle and unpowered guarantee equipment, and aims to solve the problem that fault detection and prevention of the equipment cannot be guaranteed. The method comprises the steps that parameters of detection equipment are debugged based on the type of a to-be-detected object, and the outer surface of the to-be-detected object is comprehensively scanned through a probe; acquiring a signal received by the probe in the scanning process as damage data; inputting the damage data into the damage detection model for identification, positioning and prediction to obtain a damage area and prediction data, and analyzing the area of the damage area to obtain damage condition data; marking the to-be-detected object with corresponding abnormal information based on the damage condition data; and maintaining the to-be-detected object according to a maintenance plan which is pre-stored in the data storage equipment and corresponds to the abnormal information. According to the invention, automation and intelligentization of equipment detection are realized, the detection efficiency and precision are improved, the maintenance plan is optimized, and manual intervention is reduced.

Description

Background Art

[0002] Special vehicles and non-powered support equipment are devices that need to be used in special occasions. Due to their special application environment and operating conditions, strict requirements are placed on the structure and performance of the equipment. In airports, in order to allow the airport to operate normally, a large number of special vehicles and non-powered support equipment are needed. In large airports, the number of times lift trucks, baggage transfer trucks and ladder trucks are docked and unloaded exceeds a thousand times a day. During this high-frequency operation and support process, if there are any safety incidents involving special vehicles, such as aging of the lift truck door switch, internal cracking causing the large door to pop out, it may lead to unsafe incidents such as collisions with aircraft. In order to avoid affecting the safety of apron operations, preventive inspections and maintenance of special vehicles and non-powered support equipment can be carried out to reduce various risks such as aircraft collisions caused by special vehicle failures, thereby avoiding major economic losses to the company. Existing inspections and maintenance mainly include manual visual inspections, conventional instrument inspections, etc. These methods are difficult to detect tiny cracks and damage inside the equipment in some cases, and cannot guarantee early fault detection and prevention of the equipment.

[0003] Based on this, the present invention proposes a preventive inspection and maintenance method for special vehicles and non-powered support equipment. Summary of the invention

[0004] In order to solve the above-mentioned problems in the prior art, that is, the prior art is difficult to find tiny cracks and damages inside the equipment, and cannot ensure the early fault detection and prevention of the equipment, the present invention provides a preventive inspection and maintenance method for special vehicles and non-powered support equipment, the method comprising:

[0005] Debug the parameters of the testing equipment based on the type of the object to be tested, and use the probe to fully scan the outer surface of the object to be tested; obtain the signal received by the probe during the scanning process as damage data;

[0006] The damage data is input into a damage detection model for identification, location and prediction, to obtain a damaged area and prediction data, and the area of ​​the damaged area is analyzed to obtain damage condition data;

[0007] Based on the damage condition data, marking the object to be detected with corresponding abnormal information;

[0008] The object to be inspected is repaired according to a maintenance plan corresponding to the abnormal information pre-stored in the data storage device.

[0009] In some preferred embodiments, the detection equipment includes eddy current flaw detection equipment and ultrasonic guided wave equipment.

[0010] In some preferred embodiments, the injury condition data includes mild injury, moderate injury and severe injury.

[0011] In some preferred embodiments, the probe is used to perform a comprehensive scan on the outer surface of the object to be detected, and the method is as follows:

[0012] Take the probe of the eddy current flaw detection equipment, place the probe of the eddy current flaw detection equipment on the surface of the object to be detected, and make the probe of the eddy current flaw detection equipment close to the surface of the object to be detected, and pull the probe of the eddy current flaw detection equipment to make the probe move in close contact with the surface of the equipment;

[0013] Take the probe of the ultrasonic guided wave device, place the probe of the ultrasonic guided wave device on the surface of the object to be detected, and make the probe of the ultrasonic guided wave device close to the surface of the object to be detected, and pull the probe of the ultrasonic guided wave device to make the probe move in close contact with the device surface.

[0014] In some preferred embodiments, the area of ​​the damaged region is analyzed to obtain damage data, and the method is as follows:

[0015] Determine the percentage of the damaged area to the corresponding part surface area;

[0016] If the percentage is less than or equal to 5%, the injury data is mild injury; if the percentage is greater than 5% and less than 10%, the injury data is moderate injury; if the percentage is greater than 10%, the injury data is severe injury.

[0017] In some preferred embodiments, based on the damage condition data, the object to be detected is marked with corresponding abnormal information, and the method is as follows:

[0018] If the damage to the object to be detected is slight, the damaged area of ​​the object to be detected is marked as a repairable abnormality. If the damage to the object to be detected is moderate or severe, the damaged area of ​​the object to be detected is marked as an unrepairable abnormality.

[0019] In some preferred embodiments, the object to be inspected is repaired according to a maintenance plan corresponding to the abnormal information pre-stored in the data storage device, and the method is:

[0020] If the abnormal information is a repairable abnormality, the object in the damaged area is repaired; if the abnormal information is an unrepairable abnormality, the object in the damaged area is directly replaced.

[0021] In some preferred embodiments, the damage data is input into a damage detection model for identification, location and prediction to obtain a damaged area and prediction data, and the method is as follows:

[0022] Preprocessing the collected damage data, wherein the preprocessing at least includes data cleaning, denoising and standardization;

[0023] Extracting characteristic data related to potential problems of the object to be detected from the preprocessed damage data, wherein the characteristic data includes the size, shape, material properties, and damage condition of the object to be detected;

[0024] Train the damage detection model using known labeled data;

[0025] Inputting the test data into the trained damage detection model to perform performance evaluation, and adjusting the model parameters of the damage detection model based on the evaluation results to obtain the damage detection model to be used;

[0026] The characteristic data are input into the damage detection model to be used to obtain the damaged area and prediction data.

[0027] In some preferred embodiments, the damage detection model is a classifier constructed by support vector machine, logistic regression or decision tree.

[0028] In some preferred embodiments, the marking data includes normal state data and abnormal state data.

[0029] Beneficial effects of the present invention:

[0030] The present invention improves the efficiency and accuracy of detection by adopting eddy current flaw detection and ultrasonic guided wave technology, can comprehensively detect the outer surface and internal structure of the equipment, and can be trained according to historical data and known tags through algorithms such as SVM, Logistic Regression and Decision Tree, and automatically predict and classify new data, which makes the preventive inspection and maintenance method more automated and intelligent, reduces manual intervention and errors, and has high classification accuracy and reliability. They can classify and predict according to various parameters of the equipment (such as size, shape, material properties, damage conditions, etc.), so as to accurately identify potential problems and abnormal conditions. By applying these algorithms to real-time monitoring data, abnormal conditions can be identified in real time and early warnings can be issued. Various parameters of the equipment can be analyzed, and future trends can be predicted based on historical data, which helps to optimize maintenance plans, reduce manual intervention and inspection time, and improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0032] Figure 1 It is a flow chart of a preventive inspection and maintenance method for a special vehicle and non-powered support equipment of the present invention;

[0033] Figure 2It is a structural diagram of a computer system of a server for implementing the method, system, and device embodiments of the present application. DETAILED DESCRIPTION

[0034] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0035] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0036] The first embodiment of the present invention provides a preventive inspection and maintenance method for special vehicles and non-powered support equipment, the method comprising:

[0037] Step S1, debugging the parameters of the detection equipment based on the type of the object to be detected, and using the probe to perform a comprehensive scan on the outer surface of the object to be detected; obtaining the signal received by the probe during the scanning process as damage data;

[0038] Step S2, inputting the damage data into a damage detection model for identification, location and prediction, obtaining a damaged area and prediction data, and analyzing the area of ​​the damaged area to obtain damage condition data;

[0039] Step S3, based on the damage condition data, marking the object to be detected with corresponding abnormal information;

[0040] Step S4, repairing the object to be inspected according to the maintenance plan corresponding to the abnormal information pre-stored in the data storage device.

[0041] In order to more clearly explain the preventive inspection and maintenance method of a special vehicle and a non-powered support equipment of the present invention, the following is combined with Figure 1 Each step in the embodiment of the present invention is described in detail, and each step is described in detail as follows:

[0042] Step S1, debugging the parameters of the detection equipment based on the type of the object to be detected, and using the probe to perform a comprehensive scan on the outer surface of the object to be detected; obtaining the signal received by the probe during the scanning process as damage data;

[0043] The detection equipment used in the present invention includes eddy current flaw detection equipment and ultrasonic guided wave equipment, and the damage condition data includes mild damage, moderate damage and severe damage.

[0044] The probe is used to fully scan the outer surface of the object to be detected, and the method is as follows:

[0045] Take the probe of the eddy current flaw detection equipment, place the probe of the eddy current flaw detection equipment on the surface of the object to be detected, and make the probe of the eddy current flaw detection equipment close to the surface of the object to be detected, and pull the probe of the eddy current flaw detection equipment to make the probe move in close contact with the surface of the equipment;

[0046] Take the probe of the ultrasonic guided wave device, place the probe of the ultrasonic guided wave device on the surface of the object to be detected, and make the probe of the ultrasonic guided wave device close to the surface of the object to be detected, and pull the probe of the ultrasonic guided wave device to make the probe move in close contact with the device surface.

[0047] The present invention adjusts the parameters of the eddy current flaw detection equipment and the ultrasonic guided wave equipment before using them. By adjusting parameters such as frequency, gain, etc., the probe can be better adapted to the characteristics of the material being tested, thereby improving the sensitivity and accuracy of the test. Parameter setting can help eliminate interference signals, ensure the reliability and repeatability of the test results, and reduce unnecessary false alarms or missed detections. Different test objects may have different materials, thicknesses or other physical properties. Adjusting parameters can help the equipment adapt to these changes to ensure that the best results are achieved each time the test is performed.

[0048] Step S2, inputting the damage data into a damage detection model for identification, location and prediction, obtaining a damaged area and prediction data, and analyzing the area of ​​the damaged area to obtain damage condition data;

[0049] In the present invention, the damage data is input into a damage detection model for identification, location and prediction to obtain a damaged area and prediction data, and the method is as follows:

[0050] Preprocessing the collected damage data, wherein the preprocessing at least includes data cleaning, denoising and standardization;

[0051] Extracting characteristic data related to potential problems of the object to be detected from the preprocessed damage data, wherein the characteristic data includes the size, shape, material properties, and damage condition of the object to be detected;

[0052] The damage detection model is trained using known labeled data; the damage detection model is a classifier constructed by support vector machine, logistic regression or decision tree. The labeled data includes normal state data and abnormal state data, so as to classify new data into normal state or abnormal state.

[0053] Inputting the test data into the trained damage detection model to perform performance evaluation, and adjusting the model parameters of the damage detection model based on the evaluation results to obtain the damage detection model to be used;

[0054] The characteristic data are input into the damage detection model to be used to obtain the damaged area and prediction data.

[0055] The prediction data in this embodiment may be:

[0056] Probability of damage extension: predicts the likelihood that damage will continue to exist at a certain point in the future.

[0057] Damage Growth Rate: Predicts how fast the damaged area grows, which is critical for assessing how quickly the damage develops.

[0058] Critical value time point: The time point when the damage is predicted to reach a critical state. This critical value is the maintenance threshold or the safety limit.

[0059] Damage type evolution: Predict the changing trend of damage type, such as the evolution from small cracks to large cracks or other types of damage.

[0060] After obtaining the predicted data, use charts or graphs to intuitively display the predicted results, such as time-damage area graphs, damage extension rate curves, etc. Visualization tools can help users better understand the development trend of damage.

[0061] Plan appropriate maintenance cycles and inspection frequencies based on the prediction of damage development trends.

[0062] Decide whether immediate action is needed to repair the damage or if intervention can be performed at some point in the future. Specifically, based on the likelihood of the damage developing, take preventive measures to reduce the probability of the damage occurring or mitigate its impact, which may be enhanced monitoring, changes in work processes or environmental conditions, use of more durable materials, etc.

[0063] Based on the prediction data combined with the damage data, maintenance resources can be rationally allocated, with priority given to high-risk areas or emergency situations.

[0064] The present invention can also feed back the actual maintenance results to the model for subsequent model optimization and improvement. The effectiveness of the maintenance strategy can be reviewed regularly and the strategy can be adjusted according to the actual situation.

[0065] When the damage detection model is a classifier constructed by a support vector machine, the specific steps are as follows: The goal of SVM is to find a hyperplane that can maximize the separation of data of different categories. Its basic formula is:

[0066] f(x) = w·x+b;

[0067] Among them, f(x) is the hyperplane function, w is the weight vector, and b is the bias term. By optimizing the weight vector w and the bias term b, f(x) can maximize the separation of data of different categories;

[0068] Introducing an innovative SMO (Sequential Minimal Optimization) algorithm improvement for support vector machine (SVM), which is an SMO algorithm based on adaptive learning rate and dynamic sub-problem selection. Its innovations are as follows:

[0069] Adaptive learning rate: Introduce an adaptive learning rate mechanism to dynamically adjust the update step size of each Lagrange multiplier to improve optimization efficiency and convergence speed.

[0070] Dynamic sub-problem selection: Improve the sub-problem selection strategy of traditional SMO by introducing a dynamic adjustment mechanism to make the selected sub-problems more flexible and efficient in each iteration process.

[0071] Detailed description:

[0072] Adaptive learning rate:

[0073] The traditional SMO algorithm uses a fixed step size when updating the Lagrange multiplier. In order to improve efficiency, an adaptive learning rate can be introduced so that the learning rate is dynamically adjusted according to the current optimization state at each iteration. The learning rate is defined as η i , at each iteration, adjust the learning rate according to the error size:

[0074]

[0075] Among them, E i Indicates the error of the current sample, and k is the adjustment parameter. In this way, a larger learning rate can be used when the error is large to converge quickly; a smaller learning rate can be used when the error is small to make fine adjustments.

[0076] Dynamic subproblem selection

[0077] The traditional SMO algorithm optimizes two Lagrange multipliers a each time i and a j , usually a heuristic strategy is used to select these two variables. A dynamic sub-problem selection mechanism can be introduced to make the selection process more efficient.

[0078] Define the scoring function for subproblem selection:

[0079] S(i, j)=|E i -E j |;

[0080] E i and E j is the error between sample i and sample j. At each iteration, the two variables with the largest score function value are selected for optimization:

[0081] (i * , j *) = argmax i, jS ( i, j );

[0082] By dynamically selecting the subproblem with the largest score function value, the Lagrange multiplier can be optimized more effectively and the convergence speed of the algorithm can be improved.

[0083] Algorithm steps:

[0084] Step A1, initialization: Randomly initialize the Lagrange multiplier a and the bias term b.

[0085] Step A2, outer loop: traverse all Lagrange multipliers and find a that violates the KKT condition i .

[0086] Step A3, inner loop:

[0087] Step A31, select two variables (i * , j * )

[0088] Step A32, calculate the adaptive learning rate η i

[0089] Step A33, update a i* and a j*

[0090] a i* =a i* +η i* Δa i* ;

[0091] a j* =a j* +η i* Δa j* ;

[0092] Step A34, update the weight vector w and the bias term b.

[0093] Step A4, check convergence: determine whether all a satisfy the KKT condition, if so, stop iteration, otherwise return to step A2.

[0094] The advantage of adding the SMO innovative optimization algorithm is that the convergence speed of the SMO algorithm can be significantly improved through adaptive learning rate and dynamic sub-problem selection mechanism. Dynamic selection of sub-problems makes each iteration more effective and avoids invalid update steps.

[0095] At the same time, in order to map data to a high-dimensional space and make nonlinearly separable data linearly separable in a high-dimensional space, the SVM algorithm introduces a polynomial kernel function. The multi-layer kernel function structure draws on the idea of ​​hierarchical feature extraction in deep learning. It constructs multiple kernel functions by extracting features layer by layer and combines these kernel functions. Each layer uses a different kernel function and is optimized layer by layer to capture the high-level features of the data. The hierarchical structure is as follows:

[0096] Assume there are L layers of kernel functions, and define the kernel function of each layer as K (l) (x i , x j ), the final kernel function is the combination of kernel functions of each layer:

[0097]

[0098] β l is the weight of the kernel function of each layer, which is dynamically optimized through training.

[0099] Algorithm steps:

[0100] Step B1, initial layer (l=1):

[0101] The initial layer uses basic kernel functions such as RBF kernel and polynomial kernel. Assume that the kernel function of the initial layer is:

[0102] K (l) (x i , x j ) = exp(-γ||x i -x j || 2 );

[0103] γ is the parameter of the RBF kernel.

[0104] Step B2, extract features layer by layer:

[0105] Each layer extracts features from the data and uses these features to construct high-level kernel functions. Define the feature extraction function for layer l for:

[0106]

[0107] W (l) is the weight matrix of the lth layer, b (l) is the bias and σ is the activation function (ReLU).

[0108] Step B3, high-level kernel function:

[0109] Construct high-level kernel functions using the extracted features.

[0110]

[0111] Represents the feature extraction result of the lth layer.

[0112] Step B4, final kernel function:

[0113] Combine the kernel functions of each layer to get the final kernel function.

[0114] Through the above innovative multi-layer kernel function structure, the performance and generalization ability of SVM can be significantly improved, especially when processing high-dimensional and nonlinearly separable data.

[0115] When the damage detection model is a classifier constructed by logistic regression or decision tree, specifically:

[0116] P(y=1|x)=exp(w·x+b) / (1+exp(w·x+b));

[0117] Among them, P(y=1|x) represents the probability that sample y belongs to category 1 under the condition of given sample x; w is the weight vector, b is the bias term, and by optimizing the weight vector w and the bias term b, P(y=1|x) can accurately predict the category of sample y;

[0118] When the damage detection model is a classifier constructed by a decision tree, specifically:

[0119] Decision Tree is a classification algorithm based on a tree structure. Its basic steps are to divide nodes according to different values ​​of features and recursively divide nodes until the stopping condition is met. Its basic formula is:

[0120] f(x)=argmax{P(y=1|x)};

[0121] Among them, f(x) is the decision function used to predict the category of sample y, P(y=1|x) represents the probability that sample y belongs to category 1 given sample x. By recursively dividing the nodes and calculating the probabilities, f(x) can accurately predict the category of sample y.

[0122] In the present invention, the area of ​​the damaged area is analyzed to obtain damage data, and the method is as follows:

[0123] Determine the percentage of the damaged area to the corresponding part surface area;

[0124] If the percentage is less than or equal to 5%, the injury data is mild injury; if the percentage is greater than 5% and less than 10%, the injury data is moderate injury; if the percentage is greater than 10%, the injury data is severe injury.

[0125] Step S3, based on the damage condition data, marking the object to be detected with corresponding abnormal information;

[0126] In the present invention, based on the damage condition data, the object to be detected is marked with corresponding abnormal information, and the method is as follows:

[0127] If the damage to the object to be detected is slight, the damaged area of ​​the object to be detected is marked as a repairable abnormality. If the damage to the object to be detected is moderate or severe, the damaged area of ​​the object to be detected is marked as an unrepairable abnormality.

[0128] Step S4, repairing the object to be inspected according to the maintenance plan corresponding to the abnormal information pre-stored in the data storage device.

[0129] In the present invention, if the abnormal information is a repairable abnormality, the object in the damaged area is repaired; if the abnormal information is an unrepairable abnormality, the object in the damaged area is directly replaced.

[0130] The maintenance plan includes original parts maintenance and replacement parts maintenance.

[0131] The data storage device includes but is not limited to a smart phone, a laptop or a tablet computer.

[0132] Step S4 of the present invention may also be:

[0133] Step S4, repairing the object to be inspected according to the maintenance plan corresponding to the abnormal information pre-stored in the data storage device and in combination with the predicted data, specifically:

[0134] For damaged areas with "repairable anomalies"

[0135] Analyze and predict data

[0136] Damage Extension Probability: If the probability of damage extension is high, it means that there is a high probability that the damage will further expand in the near future. This requires us to take immediate action to prevent the failure.

[0137] Damage growth rate: If the damage growth rate is very fast, even if the growth probability is not high, it means that the damage will deteriorate rapidly. In this case, repairs should be carried out as soon as possible.

[0138] Critical time point: This is the time when the damage is expected to reach an irreparable state. If this time point is close to the current time, then repair measures should be taken immediately.

[0139] Damage type evolution: Different types of damage may have different evolution paths. For example, fatigue cracks may grow rapidly, while corrosion may be a gradual process. Understanding the type of damage evolution helps to select the most appropriate repair plan.

[0140] Develop a maintenance plan

[0141] If any of the above prediction data indicates an emergency situation (i.e., high expansion probability, fast expansion rate, close to the critical value time point), maintenance should be arranged as soon as possible.

[0142] Repair measures: Depending on the specific circumstances of the damage, measures such as repair (such as welding, bonding), partial replacement of damaged parts or reinforcement of damaged parts can be taken.

[0143] Repair time: If the risk of damage extension is low, a suitable time window can be arranged for repair without affecting overall performance.

[0144] Planned replacement: If the probability of damage extension is low, the extension rate is slow, and the critical value time point is far away, you can plan to replace it during the next routine maintenance. This can better arrange resources and reduce the impact on the normal operation of the equipment.

[0145] For damaged areas with "unrepairable abnormalities"

[0146] Develop a replacement plan

[0147] Replace immediately: If the probability of damage extension is high, the extension rate is fast, or the critical time point is very close to the current time, the damaged area should be replaced immediately to avoid potential safety risks.

[0148] Monitoring and Evaluation: Even if replacement is planned, the condition of the damaged area should be continuously monitored and the progression of damage should be assessed regularly to ensure there is no sudden deterioration.

[0149] The present invention further comprises step S5 after step S4:

[0150] Step S5, repeating the above steps S1-S4 until no damage is detected in the object to be inspected after repair.

[0151] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0152] The second embodiment of the present invention provides a preventive inspection and maintenance system for special vehicles and non-powered support equipment, based on a preventive inspection and maintenance method for special vehicles and non-powered support equipment of the first embodiment, the system includes:

[0153] A damage data acquisition module is configured to adjust the parameters of the detection equipment based on the type of the object to be detected, and use the probe to perform a comprehensive scan on the outer surface of the object to be detected; and obtain the signal received by the probe during the scanning process as damage data;

[0154] An analysis module is configured to input the damage data into a damage detection model for identification, location and prediction, obtain a damaged area and prediction data, and analyze the area of ​​the damaged area to obtain damage condition data;

[0155] A marking module, configured to mark the object to be detected with corresponding abnormal information based on the damage condition data;

[0156] The plan generation module is configured to repair the object to be inspected according to the maintenance plan corresponding to the abnormal information pre-stored in the data storage device.

[0157] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0158] It should be noted that the preventive inspection and maintenance system for special vehicles and non-powered support equipment provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0159] An electronic device according to a third embodiment of the present invention includes:

[0160] at least one processor; and

[0161] a memory communicatively connected to at least one of the processors; wherein,

[0162] The memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned preventive inspection and maintenance method for special vehicles and non-powered support equipment.

[0163] A computer-readable storage medium according to a fourth embodiment of the present invention stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned preventive inspection and maintenance method for special vehicles and non-powered support equipment.

[0164] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the storage device and processing device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0165] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0166] Reference below Figure 2 , which shows a schematic diagram of the structure of a computer system of a server for implementing the method, system, and device embodiments of the present application. Figure 2 The server shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0167] like Figure 2 As shown, the computer system includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 202 or the program loaded from the storage part 208 to the random access memory (RAM) 203. Various programs and data required for system operation are also stored in the RAM 203. The CPU 201, ROM 202 and RAM 203 are connected to each other through a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0168] The following components are connected to the I / O interface 205: an input section 206 including a keyboard, a mouse, etc.; an output section 207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 208 including a hard disk, etc.; and a communication section 209 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to the I / O interface 205 as needed. A removable medium 211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 210 as needed so that a computer program read therefrom is installed into the storage section 208 as needed.

[0169] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 209, and / or installed from the removable medium 211. When the computer program is executed by the central processing unit (CPU) 201, the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, - but not limited to - a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0170] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0171] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0172] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.

[0173] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0174] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A preventive inspection and maintenance method for special vehicles and non-powered support equipment, characterized in that: The method includes: Debug the parameters of the testing equipment based on the type of the object to be tested, and use the probe to fully scan the outer surface of the object to be tested; obtain the signal received by the probe during the scanning process as damage data; The damage data is input into a damage detection model for identification, location and prediction, to obtain a damaged area and prediction data, and the area of ​​the damaged area is analyzed to obtain damage condition data; Based on the damage condition data, marking the object to be detected with corresponding abnormal information; The object to be inspected is repaired according to a maintenance plan corresponding to the abnormal information pre-stored in the data storage device.

2. A preventive inspection and maintenance method for special vehicles and non-powered support equipment according to claim 1, characterized in that: The detection equipment includes eddy current flaw detection equipment and ultrasonic guided wave equipment.

3. A preventive inspection and maintenance method for special vehicles and non-powered support equipment according to claim 1, characterized in that: The injury condition data includes mild injury, moderate injury and severe injury.

4. A preventive inspection and maintenance method for special vehicles and non-powered support equipment according to claim 2, characterized in that: The probe is used to fully scan the outer surface of the object to be detected, and the method is as follows: Take the probe of the eddy current flaw detection equipment, place the probe of the eddy current flaw detection equipment on the surface of the object to be detected, and make the probe of the eddy current flaw detection equipment close to the surface of the object to be detected, and pull the probe of the eddy current flaw detection equipment to make the probe move in close contact with the surface of the equipment; Take the probe of the ultrasonic guided wave device, place the probe of the ultrasonic guided wave device on the surface of the object to be detected, and make the probe of the ultrasonic guided wave device close to the surface of the object to be detected, and pull the probe of the ultrasonic guided wave device to make the probe move in close contact with the device surface.

5. A preventive inspection and maintenance method for special vehicles and non-powered support equipment according to claim 3, characterized in that: The area of ​​the damaged area is analyzed to obtain damage data, and the method is as follows: Determine the percentage of the damaged area to the corresponding part surface area; If the percentage is less than or equal to 5%, the injury data is mild injury; if the percentage is greater than 5% and less than 10%, the injury data is moderate injury; if the percentage is greater than 10%, the injury data is severe injury.

6. A preventive inspection and maintenance method for special vehicles and non-powered support equipment according to claim 1, characterized in that: Based on the damage data, the object to be detected is marked with corresponding abnormal information, and the method is as follows: If the damage to the object to be detected is slight, the damaged area of ​​the object to be detected is marked as a repairable abnormality. If the damage to the object to be detected is moderate or severe, the damaged area of ​​the object to be detected is marked as an unrepairable abnormality.

7. A preventive inspection and maintenance method for special vehicles and non-powered support equipment according to claim 6, characterized in that: The object to be inspected is repaired according to the maintenance plan corresponding to the abnormal information pre-stored in the data storage device, and the method is as follows: If the abnormal information is a repairable abnormality, the object in the damaged area is repaired; if the abnormal information is an unrepairable abnormality, the object in the damaged area is directly replaced.

8. The preventive inspection and maintenance method for special vehicles and non-powered support equipment according to claim 1 is characterized in that: The damage data is input into the damage detection model for identification, location and prediction to obtain the damaged area and prediction data, and the method is as follows: Preprocessing the collected damage data, wherein the preprocessing at least includes data cleaning, denoising and standardization; Extracting characteristic data related to potential problems of the object to be detected from the preprocessed damage data, wherein the characteristic data includes the size, shape, material properties, and damage condition of the object to be detected; Train the damage detection model using known labeled data; Inputting the test data into the trained damage detection model to perform performance evaluation, and adjusting the model parameters of the damage detection model based on the evaluation results to obtain the damage detection model to be used; The characteristic data are input into the damage detection model to be used to obtain the damaged area and prediction data.

9. A preventive inspection and maintenance method for special vehicles and non-powered support equipment according to claim 8, characterized in that: The damage detection model is a classifier constructed by support vector machine, logistic regression or decision tree.

10. A preventive inspection and maintenance method for special vehicles and non-powered support equipment according to claim 8, characterized in that: The marking data includes normal state data and abnormal state data.

Images