Crane fault diagnosis method and system based on Internet of Things

Abstract

The invention relates to the technical field of cranes, and discloses a crane fault diagnosis method and system based on the Internet of Things, and the system comprises a hydraulic crane product identification module, a hydraulic crane boom bending fault diagnosis module, and a hydraulic crane boom leakage fault diagnosis and fault feedback module. According to real-time curvature information of a target hydraulic crane cargo boom and a bending overload curvature threshold value of the target hydraulic crane cargo boom, dynamic detection of the bending overload fault of the automobile hydraulic crane cargo boom is carried out, and the bending overload fault of the automobile hydraulic crane cargo boom is intelligently diagnosed in real time. Based on the hydraulic crane boom bending overload appearance image information, an image recognition algorithm and hydraulic crane boom hydraulic oil leakage standard image information are combined for intelligent recognition of boom hydraulic oil leakage faults in the automobile hydraulic crane boom bending overload state, and the safety of an automobile hydraulic crane hydraulic system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cranes, and in particular to a crane fault diagnosis method and system based on the Internet of Things. Background Art

[0002] A crane is a multi-action lifting machine capable of vertically lifting and horizontally transporting heavy objects within a certain range. The main features of a tire crane are: its driving cab and lifting control cabin are integrated into one, evolving from a crawler crane. The crawler tracks and running frames of the traveling mechanism have been transformed into a tire-covered chassis, overcoming the damage to the road surface caused by crawler plates of crawler cranes. It is a type of material handling machinery. A bridge crane is a type of lifting equipment used horizontally above workshops, warehouses, and material yards to lift materials. Because its ends rest on tall concrete columns or metal supports, its shape resembles a bridge. The bridge crane's girth runs longitudinally along tracks laid on elevated platforms on both sides, fully utilizing the space beneath the girth to lift materials without being obstructed by ground equipment. The working characteristic of some lifting equipment is intermittent movement, that is, the corresponding mechanisms of material picking, transportation, unloading and other actions work alternately in one working cycle. The development and use of cranes in the market are becoming more and more extensive; among them, automobile hydraulic cranes are the most widely used. During the lifting operation, the boom of automobile hydraulic cranes is subjected to overload lifting force, which leads to damage to the boom structure and leakage of boom hydraulic oil. The existing automobile hydraulic crane lifting operation process cannot realize intelligent detection of boom bending overload failure and boom bending overload hydraulic oil leakage, which reduces the safety and service life of the automobile hydraulic crane lifting operation.

[0003] A Chinese invention patent application with publication number CN118771197A and publication date 2024.10.15 discloses an electrical fault diagnosis system for crane equipment, including a data acquisition module, a client CMS system and a storage logic processing module; the data acquisition module is a professional power detection device that transmits real-time power quality data and is bound one-to-one with PLC fault points; the storage logic processing module stores points in a point-to-point manner, and the client CMS system is used to conveniently and quickly find the cause of the fault point; the electrical fault diagnosis system has real-time, high precision, flexibility and visualization functions; however, the above technical solution cannot accurately diagnose the boom bending overload and boom bending overload hydraulic oil leakage faults of the hydraulic crane. Summary of the Invention

[0004] (1) Technical problems solved

[0005] In order to solve the problem that the above-mentioned existing automobile hydraulic crane lifting operation process cannot realize intelligent detection of boom bending overload failure and boom bending overload hydraulic oil leakage, which reduces the safety and service life of the automobile hydraulic crane lifting operation, the above purposes are achieved: accurately identifying the product type of hydraulic crane, dynamically matching the bending overload curvature threshold of the hydraulic crane boom, dynamically measuring the real-time curvature of the hydraulic crane boom, intelligently diagnosing the bending overload failure of the hydraulic crane boom, real-time collection of the appearance image information of the bending overload of the hydraulic crane boom, and intelligently diagnosing the hydraulic oil leakage of the hydraulic crane boom.

[0006] (2) Technical solution

[0007] The present invention is implemented through the following technical solution: a crane fault diagnosis method based on the Internet of Things, the method comprising the following steps:

[0008] S1. Collecting appearance image data of the hydraulic crane;

[0009] S2. Perform product type recognition processing on the automobile hydraulic crane based on the hydraulic crane appearance image data and appearance image data of hydraulic cranes of different product types to generate target hydraulic crane product type data;

[0010] S3. performing a boom bending overload curvature threshold search process for a target truck hydraulic crane based on the target hydraulic crane product type data and boom bending overload curvature thresholds of hydraulic cranes of different product types, and generating a boom bending overload curvature threshold for the target hydraulic crane;

[0011] S4, collecting the hydraulic crane boom physical model data and performing the coordinate establishment and processing of the boom axis direction sampling points required for measuring the curvature radius of the automobile hydraulic crane boom, and generating the hydraulic crane boom curvature radius measurement coordinate data;

[0012] S5. Performing hydraulic crane boom curvature radius measurement processing based on the hydraulic crane boom curvature radius measurement coordinate data to generate target hydraulic crane boom curvature radius data and performing automobile hydraulic crane boom curvature numerical measurement processing to generate target hydraulic crane boom real-time curvature data;

[0013] S6, performing a bending overload fault detection process for the automobile hydraulic crane boom according to the real-time curvature data of the target hydraulic crane boom and the curvature overload threshold of the target hydraulic crane boom, generating target hydraulic crane boom bending overload fault detection data; if the target hydraulic crane boom is not overloaded, repeatedly executing S4, S5, and S6 until the automobile hydraulic crane boom bending overload fault detection result is overloaded;

[0014] S7. When overloaded, collect the appearance image data of the hydraulic crane boom bending overload and perform boom hydraulic oil leakage fault detection processing on the automobile hydraulic crane boom under the boom bending overload state with the standard image data of the hydraulic crane boom hydraulic oil leakage to generate target hydraulic crane boom hydraulic oil leakage detection data;

[0015] S8. Construct the fault diagnosis result data of the automobile hydraulic crane and perform the crane fault diagnosis feedback operation.

[0016] Preferably, the steps of collecting the appearance image data of the hydraulic crane are as follows:

[0017] S11. Collect overall appearance image information of a truck-mounted hydraulic crane performing a lifting operation online through a cloud camera mounted on a drone, and generate appearance image data of the hydraulic crane.

[0018] Preferably, the steps of performing product type recognition processing on the automobile hydraulic crane based on the hydraulic crane appearance image data and the appearance image data of hydraulic cranes of different product types to generate target hydraulic crane product type data are as follows:

[0019] S21. Establish appearance image data sets of different product types of hydraulic cranes where v c Represents the appearance image data of different product types of hydraulic cranes corresponding to the c-th type of automobile hydraulic crane product type, Indicates the maximum number of truck hydraulic crane types; the truck hydraulic crane product type indicates different models of truck hydraulic cranes produced by different truck hydraulic crane brands, and the appearance image data of hydraulic cranes of different product types indicates the appearance image information of standard truck hydraulic crane products set for different types of truck hydraulic crane products;

[0020] S22, using an ORB image recognition algorithm to compare the hydraulic crane appearance image data with the different product type hydraulic crane appearance image data v in the different product type hydraulic crane appearance image data set V. c Perform image feature matching to search for the hydraulic crane appearance image data of different product types that matches the hydraulic crane appearance image data v c The corresponding automobile hydraulic crane product type information is obtained, and the target hydraulic crane product type data is constructed.

[0021] Preferably, the boom bending overload curvature threshold value of the target truck hydraulic crane is searched based on the target hydraulic crane product type data and the boom bending overload curvature threshold values ​​of hydraulic cranes of different product types, and the operation steps for generating the boom bending overload curvature threshold value of the target hydraulic crane are as follows:

[0022] S31. Establish a set of overload curvature thresholds for the bending of hydraulic crane booms of different product types. where v′ c represents the overload curvature thresholds of the boom bending of different hydraulic cranes corresponding to the c-th type of truck hydraulic crane product. The overload curvature thresholds of the boom bending of different hydraulic cranes represent the maximum curvatures of the boom bending of different types of truck hydraulic cranes when the boom is in a critical overload state during a lifting operation. The greater the curvature of the boom bending, the greater the degree of the boom bending.

[0023] S32, using the Aho-Corasick search algorithm to compare the target hydraulic crane product type data with the different product types of hydraulic crane boom bending overload curvature thresholds v' in the different product types of hydraulic crane boom bending overload curvature threshold set V'. c Perform character matching on the automobile hydraulic crane product type to search for the different product types of hydraulic crane boom bending overload curvature threshold v' corresponding to the target hydraulic crane product type data c , and construct the target hydraulic crane boom bending overload curvature threshold v mubiao .

[0024] Preferably, the steps of collecting the hydraulic crane boom entity model data, establishing the coordinates of the sampling points in the boom axis direction required for measuring the curvature radius of the automobile hydraulic crane boom, and generating the coordinate data for measuring the curvature radius of the hydraulic crane boom are as follows:

[0025] S41. Using a laser scanner mounted on a drone, online collecting three-dimensional solid model information of the entire boom of a truck-mounted hydraulic crane performing a lifting operation, and generating solid model data of the hydraulic crane boom;

[0026] S42, importing the hydraulic crane boom entity model data into AutoCAD and running it, and using the AutoCAD coordinate measurement tool to respectively collect the spatial coordinates of the sampling points at the left and right ends of the boom axis of the automobile hydraulic crane and the spatial coordinate information of the sampling point in the middle of the boom axis, and generating the hydraulic crane boom curvature radius measurement coordinate data set O = (o zuo ,o zhong ,o you ), where ozuo 、o zhong and o you They respectively represent the left end coordinate data of the hydraulic crane boom curvature radius measurement, the middle coordinate data of the hydraulic crane boom curvature radius measurement, and the right end coordinate data of the hydraulic crane boom curvature radius measurement.

[0027] Preferably, the hydraulic crane boom curvature radius measurement process is performed based on the hydraulic crane boom curvature radius measurement coordinate data, target hydraulic crane boom curvature radius data is generated, and the automobile hydraulic crane boom curvature numerical measurement process is performed to generate the target hydraulic crane boom real-time curvature data in the following steps:

[0028] S51, importing the hydraulic crane boom curvature radius measurement coordinate data set O into AutoCAD, and measuring the left end coordinate data o based on the hydraulic crane boom curvature radius using the AutoCAD radius measurement tool. zuo , the intermediate coordinate data of the hydraulic crane boom curvature radius measurement o zhong and the right end coordinate data of the hydraulic crane boom curvature radius measurement o you The corresponding coordinate parameters are used to measure the curvature radius parameters of the boom axis of the automobile hydraulic crane, and generate the target hydraulic crane boom curvature radius data L;

[0029] S52, based on the target hydraulic crane boom curvature radius data L and combined with the curvature parameter of the automobile hydraulic crane boom axis bending through the curvature-curvature radius calculation formula, and generate the target hydraulic crane boom real-time curvature data J, wherein

[0030] Preferably, a vehicle hydraulic crane boom bending fault overload fault detection process is performed based on the target hydraulic crane boom real-time curvature data and the target hydraulic crane boom bending overload curvature threshold to generate target hydraulic crane boom bending overload fault detection data. When the target hydraulic crane boom is not overloaded, S4, S5, and S6 are repeatedly executed until the vehicle hydraulic crane boom bending overload fault detection result is overloaded. The following operating steps are performed:

[0031] S61, obtaining the target hydraulic crane boom bending overload curvature threshold value v mubiao and the target hydraulic crane boom real-time curvature data J;

[0032] S62, comparing the target hydraulic crane boom real-time curvature data J with the target hydraulic crane boom bending overload curvature threshold value v mubiao Performing curvature value comparison, and generating target hydraulic crane boom bending overload fault detection data based on the curvature value comparison result;

[0033] When J is not greater than v mubiao , indicating that the bending state of the automobile hydraulic crane boom has not reached the overload state, the target hydraulic crane boom bending overload fault detection data is output as not overloaded, and S4, S5, and S6 are repeatedly executed until the target hydraulic crane boom bending overload fault detection data is overloaded;

[0034] When J is greater than v mubiao , indicating that the bending state of the boom of the automobile hydraulic crane reaches an overload state, the target hydraulic crane boom bending overload fault detection data is output as overload.

[0035] Preferably, when overloaded, the hydraulic crane boom bending overload appearance image data is collected and compared with the hydraulic crane boom hydraulic oil leakage standard image data to perform boom hydraulic oil leakage fault detection processing under the boom bending overload state of the automobile hydraulic crane, and the operating steps for generating target hydraulic crane boom hydraulic oil leakage detection data are as follows:

[0036] S71. When the target hydraulic crane boom bending overload fault detection data indicates overload, online collecting appearance image information of the automobile hydraulic crane boom in an overload state by using a cloud camera mounted on an unmanned aerial vehicle, and generating hydraulic crane boom bending overload appearance image data;

[0037] S72, establish a hydraulic crane boom hydraulic oil leakage standard image data set M = (m1, ..., m a ,…,m γ ), a=1,2,3,…,γ; where m a represents the a-th type of hydraulic crane boom hydraulic oil leakage standard image data, γ represents the maximum number of hydraulic crane boom hydraulic oil leakage standard images; the hydraulic crane boom hydraulic oil leakage standard image data represents the set standard image information of the hydraulic crane boom hydraulic oil leakage state;

[0038] S73, using the ORB image recognition algorithm to compare the hydraulic crane boom bending overload appearance image data with the hydraulic crane boom hydraulic oil leakage standard image data m in the hydraulic crane boom hydraulic oil leakage standard image data set M. a Perform image feature matching and generate target hydraulic crane boom hydraulic oil leakage detection data based on the image feature matching results;

[0039] When the hydraulic crane boom bending overload appearance image data and the hydraulic crane boom hydraulic oil leakage standard image data m aWhen the image feature matching is successful, it indicates that there is a hydraulic oil leakage fault at the boom position of the automobile hydraulic crane currently photographed by the drone equipped with the cloud camera, and the hydraulic oil leakage detection data of the target hydraulic crane boom is output as leakage;

[0040] When the hydraulic crane boom bending overload appearance image data and the hydraulic crane boom hydraulic oil leakage standard image data m a When the image feature matching is unsuccessful, it indicates that there is a hydraulic oil leakage fault at the boom position of the automobile hydraulic crane photographed by the current drone equipped with the cloud camera, and the hydraulic oil leakage detection data of the target hydraulic crane boom is output as no leakage.

[0041] Preferably, the steps of constructing the truck hydraulic crane fault diagnosis result data and performing the crane fault diagnosis feedback operation are as follows:

[0042] S81, combining the generated target hydraulic crane boom bending overload fault detection data, the hydraulic crane boom bending overload appearance image data, and the target hydraulic crane boom hydraulic oil leakage detection data to construct automobile hydraulic crane fault diagnosis result data;

[0043] S82: Transmit the fault diagnosis result data of the truck hydraulic crane to the crane management center via the Internet of Things communication network to perform crane fault diagnosis feedback work.

[0044] An IoT-based crane fault diagnosis system is used to implement the IoT-based crane fault diagnosis method. The system includes a hydraulic crane product identification module, a hydraulic crane boom bending fault diagnosis module, and a hydraulic crane boom leakage fault diagnosis and fault feedback module.

[0045] The hydraulic crane product identification module includes a hydraulic crane appearance image acquisition unit, a hydraulic crane appearance image storage unit for different product types, and a hydraulic crane product type identification unit;

[0046] The hydraulic crane appearance image acquisition unit collects hydraulic crane appearance image data using a cloud camera mounted on a drone; the different product types hydraulic crane appearance image storage unit is used to store the appearance image data of hydraulic cranes of different product types; the hydraulic crane product type identification unit performs product type identification processing on the automobile hydraulic crane based on the hydraulic crane appearance image data and the appearance image data of hydraulic cranes of different product types, and generates target hydraulic crane product type data;

[0047] The hydraulic crane boom bending fault diagnosis module includes a hydraulic crane boom bending overload curvature threshold storage unit for different product types, a hydraulic crane boom bending overload curvature threshold search unit, a hydraulic crane boom entity model acquisition unit, a hydraulic crane boom curvature radius measurement sampling point establishment unit, a hydraulic crane boom curvature radius measurement unit, a hydraulic crane boom real-time curvature measurement unit, and a hydraulic crane boom bending overload fault detection unit;

[0048] The hydraulic crane boom bending overload curvature threshold storage unit for different product types is used to store the hydraulic crane boom bending overload curvature thresholds for different product types; the hydraulic crane boom bending overload curvature threshold search unit performs a boom bending overload curvature threshold search process for the target automobile hydraulic crane based on the target hydraulic crane product type data and the hydraulic crane boom bending overload curvature thresholds for different product types, and generates a target hydraulic crane boom bending overload curvature threshold; the hydraulic crane boom entity model acquisition unit acquires the hydraulic crane boom entity model data through a laser scanner mounted on an unmanned aerial vehicle; the hydraulic crane boom curvature radius measurement sampling point establishment unit performs a boom axis direction sampling point coordinate establishment process required for automobile hydraulic crane boom curvature radius measurement based on the hydraulic crane boom entity model data and in combination with AutoCAD, and generates the hydraulic crane boom curvature radius measurement coordinate data; the hydraulic crane boom curvature radius measurement unit performs hydraulic crane boom curvature radius measurement processing based on the hydraulic crane boom curvature radius measurement coordinate data and in combination with AutoCAD, and generates target hydraulic crane boom curvature radius data; the hydraulic crane boom real-time curvature measurement unit performs automobile hydraulic crane boom curvature numerical measurement processing based on the target hydraulic crane boom curvature radius data and in combination with numerical processing, and generates target hydraulic crane boom real-time curvature data; the hydraulic crane boom bending overload fault detection unit performs automobile hydraulic crane boom bending overload fault detection processing based on the target hydraulic crane boom real-time curvature data and the target hydraulic crane boom bending overload curvature threshold, and generates target hydraulic crane boom bending overload fault detection data;

[0049] The hydraulic crane boom leakage fault diagnosis and fault feedback module includes a hydraulic crane boom bending overload appearance image acquisition unit, a hydraulic crane boom hydraulic oil leakage standard image storage unit, a hydraulic crane boom hydraulic oil leakage monitoring unit, and a hydraulic crane boom fault feedback unit;

[0050] The hydraulic crane boom bending overload appearance image acquisition unit collects the hydraulic crane boom bending overload appearance image data through the cloud camera carried by the drone; the hydraulic crane boom hydraulic oil leakage standard image storage unit is used to store the hydraulic crane boom hydraulic oil leakage standard image data; the hydraulic crane boom hydraulic oil leakage monitoring unit performs boom hydraulic oil leakage fault detection and processing under the boom bending overload state of the automobile hydraulic crane based on the hydraulic crane boom bending overload appearance image data and the hydraulic crane boom hydraulic oil leakage standard image data, and generates target hydraulic crane boom hydraulic oil leakage detection data; the hydraulic crane boom fault feedback unit is used to construct the automobile hydraulic crane fault diagnosis result data and perform crane fault diagnosis feedback operations in conjunction with the crane management center.

[0051] (3) Beneficial effects

[0052] The present invention provides a crane fault diagnosis method and system based on the Internet of Things. It has the following beneficial effects:

[0053] 1. Dynamically collect image information of the hydraulic crane's appearance through a drone-mounted cloud camera to provide real data support for accurately identifying the product type of the truck hydraulic crane. Based on the hydraulic crane's appearance image information, combined with image recognition algorithms and appearance image data of hydraulic cranes of different product types, autonomous identification of the truck hydraulic crane product type is performed to achieve refined fault diagnosis based on the truck hydraulic crane product type, thereby improving the accuracy of truck hydraulic crane fault diagnosis.

[0054] 2. By combining the target hydraulic crane product type information with the intelligent search algorithm and the bending overload curvature threshold of the hydraulic crane boom of different product types, the target automobile hydraulic crane boom bending overload curvature threshold is accurately matched, so as to realize the accurate screening of the ultimate curvature parameters of the boom bending overload critical state based on the hydraulic crane product model; the automobile hydraulic crane boom solid model information is dynamically collected by the UAV equipped with a laser scanner, and the curvature radius information of the bending axis of the automobile hydraulic crane boom is accurately measured by AutoCAD, and the real-time curvature information of the automobile hydraulic crane boom is dynamically measured in combination with numerical calculation, so as to realize the accurate monitoring of the automobile hydraulic crane boom bending curvature information based on model numerical analysis; the automobile hydraulic crane boom bending fault overload fault dynamic detection is carried out according to the real-time curvature information of the target hydraulic crane boom and the target hydraulic crane boom bending overload curvature threshold, so as to realize the intelligent real-time diagnosis of the automobile hydraulic crane boom bending overload fault and improve the safety and stability of the automobile hydraulic crane operation.

[0055] 3. Dynamically collect appearance image information of the boom bending overload state of the automobile hydraulic crane through the cloud camera equipped by the drone, and provide real data support for the accurate monitoring of hydraulic oil leakage faults in the boom bending overload state of the automobile hydraulic crane; Based on the appearance image information of the hydraulic crane boom bending overload and combined with the image recognition algorithm and the standard image information of the hydraulic oil leakage of the hydraulic crane boom, intelligent identification of the hydraulic oil leakage fault of the boom bending overload state of the automobile hydraulic crane is performed to improve the safety of the hydraulic system of the automobile hydraulic crane; Based on the automobile hydraulic crane boom bending overload fault detection information, the automobile hydraulic crane boom bending overload appearance image information and the automobile hydraulic crane boom hydraulic oil leakage detection information combined with numerical analysis, the automobile hydraulic crane fault diagnosis result information is accurately constructed, and at the same time, combined with the crane management center to autonomously and efficiently execute the crane fault diagnosis feedback operation, the visual dynamic feedback of the boom bending overload fault of the automobile hydraulic crane and the hydraulic oil leakage fault in the boom bending overload state of the automobile hydraulic crane is realized, thereby improving the response speed of the fault diagnosis of the automobile hydraulic crane. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a module diagram of the crane fault diagnosis system based on the Internet of Things provided by the present invention;

[0057] Figure 2 This is a flow chart of the crane fault diagnosis method based on the Internet of Things provided by the present invention. DETAILED DESCRIPTION

[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0059] The embodiments of the crane fault diagnosis method and system based on the Internet of Things are as follows:

[0060] Example 1:

[0061] See also Figure 1-Figure 2 ,A crane fault diagnosis method based on the Internet of Things, the method includes the following steps:

[0062] S1. Collecting appearance image data of the hydraulic crane;

[0063] S2. Perform product type recognition processing on the automobile hydraulic crane based on the hydraulic crane appearance image data and the appearance image data of hydraulic cranes of different product types to generate target hydraulic crane product type data;

[0064] S3. performing a boom bending overload curvature threshold search process for a target truck hydraulic crane based on the target hydraulic crane product type data and boom bending overload curvature thresholds of hydraulic cranes of different product types, and generating a boom bending overload curvature threshold for the target hydraulic crane;

[0065] S4, collecting the hydraulic crane boom physical model data and performing the coordinate establishment and processing of the boom axis direction sampling points required for measuring the curvature radius of the automobile hydraulic crane boom, and generating the hydraulic crane boom curvature radius measurement coordinate data;

[0066] S5. Performing hydraulic crane boom curvature radius measurement processing based on the hydraulic crane boom curvature radius measurement coordinate data to generate target hydraulic crane boom curvature radius data and performing automobile hydraulic crane boom curvature numerical measurement processing to generate target hydraulic crane boom real-time curvature data;

[0067] S6. Performing an overload fault detection process for a truck hydraulic crane boom bending fault based on the target hydraulic crane boom real-time curvature data and the target hydraulic crane boom bending overload curvature threshold value to generate target hydraulic crane boom bending overload fault detection data. If the target hydraulic crane boom is not overloaded, repeatedly executing S4, S5, and S6 until the truck hydraulic crane boom bending overload fault detection result indicates an overload.

[0068] S7. When overloaded, collect the appearance image data of the hydraulic crane boom bending overload and perform boom hydraulic oil leakage fault detection processing on the automobile hydraulic crane boom under the boom bending overload state with the standard image data of the hydraulic crane boom hydraulic oil leakage to generate target hydraulic crane boom hydraulic oil leakage detection data;

[0069] S8. Construct the fault diagnosis result data of the automobile hydraulic crane and perform the crane fault diagnosis feedback operation.

[0070] For further information, see Figure 1-Figure 2 ,The steps for collecting the appearance image data of the hydraulic crane are as follows:

[0071] S11. Collect overall appearance image information of a truck-mounted hydraulic crane performing a lifting operation online through a cloud camera mounted on a drone, and generate appearance image data of the hydraulic crane.

[0072] The steps for identifying the product type of a truck hydraulic crane based on the appearance image data of the hydraulic crane and the appearance image data of hydraulic cranes of different product types and generating the target hydraulic crane product type data are as follows:

[0073] S21. Establish appearance image data sets of different product types of hydraulic cranes where v c Represents the appearance image data of different product types of hydraulic cranes corresponding to the c-th type of automobile hydraulic crane product type, Indicates the maximum number of truck hydraulic crane types; truck hydraulic crane product types indicate different models of truck hydraulic cranes produced by different truck hydraulic crane brands; and the appearance image data of hydraulic cranes of different product types indicate the appearance image information of standard truck hydraulic crane products set for different types of truck hydraulic crane products;

[0074] S22, using the ORB image recognition algorithm to compare the hydraulic crane appearance image data with the different product types of hydraulic crane appearance image data v in the different product types of hydraulic crane appearance image data set V. c Perform image feature matching to search for different product types of hydraulic crane appearance image data that match the hydraulic crane appearance image data v c The corresponding automobile hydraulic crane product type information is obtained, and the target hydraulic crane product type data is constructed.

[0075] Through the hydraulic crane appearance image acquisition unit, a drone equipped with a cloud camera is used to dynamically collect the appearance image information of the hydraulic crane, providing real data support for the accurate identification of the product type of the automobile hydraulic crane; the hydraulic crane product type identification unit independently identifies the automobile hydraulic crane product type based on the hydraulic crane appearance image information combined with the image recognition algorithm and the appearance image data of hydraulic cranes of different product types, realizing refined fault diagnosis based on the automobile hydraulic crane product type and improving the accuracy of automobile hydraulic crane fault diagnosis.

[0076] For further information, see Figure 1-Figure 2 , based on the target hydraulic crane product type data and the boom bending overload curvature thresholds of hydraulic cranes of different product types, the boom bending overload curvature threshold of the target truck hydraulic crane is searched and processed. The operation steps for generating the boom bending overload curvature threshold of the target hydraulic crane are as follows:

[0077] S31. Establish a set of overload curvature thresholds for the bending of hydraulic crane booms of different product types. where v′ c Indicates the overload curvature threshold value of the hydraulic crane boom bending for different product types corresponding to the c-th type of truck hydraulic crane product. The overload curvature threshold value of the hydraulic crane boom bending for different product types indicates the maximum curvature value of the boom bending when the boom of different types of truck hydraulic crane products is in a critical overload state during a lifting operation. The greater the curvature value of the truck hydraulic crane boom, the greater the degree of bending of the truck hydraulic crane boom.

[0078] S32, using the Aho-Corasick search algorithm to compare the target hydraulic crane product type data with the different product types of hydraulic crane boom bending overload curvature threshold value v' in the different product types of hydraulic crane boom bending overload curvature threshold value set V'. c Perform character matching on the automobile hydraulic crane product type and search for the different product types of hydraulic crane boom bending overload curvature threshold v′ corresponding to the target hydraulic crane product type data c , and construct the target hydraulic crane boom bending overload curvature threshold v mubiao .

[0079] The steps for collecting the hydraulic crane boom entity model data and establishing the coordinates of the sampling points in the boom axis direction required for measuring the curvature radius of the automobile hydraulic crane boom are as follows:

[0080] S41. Using a laser scanner mounted on a drone, online collecting three-dimensional solid model information of the entire boom of a truck-mounted hydraulic crane performing a lifting operation, and generating solid model data of the hydraulic crane boom;

[0081] S42, importing the hydraulic crane boom solid model data into AutoCAD and running it, and using the AutoCAD coordinate measurement tool to respectively collect the spatial coordinates of the sampling points at the left and right ends of the boom axis of the automobile hydraulic crane and the spatial coordinate information of the sampling point in the middle of the boom axis, and generating the hydraulic crane boom curvature radius measurement coordinate data set O = (o zuo ,o zhong ,o you ), where o zuo 、o zhong and o you They respectively represent the left end coordinate data of the hydraulic crane boom curvature radius measurement, the middle coordinate data of the hydraulic crane boom curvature radius measurement, and the right end coordinate data of the hydraulic crane boom curvature radius measurement.

[0082] The following steps are used to measure the curvature radius of the hydraulic crane boom based on the measured coordinate data of the curvature radius of the hydraulic crane boom, generate the curvature radius data of the target hydraulic crane boom, and perform numerical measurement of the curvature of the automobile hydraulic crane boom to generate the real-time curvature data of the target hydraulic crane boom:

[0083] S51, importing the hydraulic crane boom curvature radius measurement coordinate data set O into AutoCAD, and measuring the left end coordinate data o based on the hydraulic crane boom curvature radius using the AutoCAD radius measurement tool. zuo , hydraulic crane boom curvature radius measurement intermediate coordinate datazhong And the right end coordinate data of the hydraulic crane boom curvature radius measurement o you The corresponding coordinate parameters are used to measure the curvature radius parameters of the boom axis of the automobile hydraulic crane, and generate the target hydraulic crane boom curvature radius data L;

[0084] S52, based on the target hydraulic crane boom curvature radius data L and combined with the curvature parameter of the automobile hydraulic crane boom axis bending through the curvature-curvature radius calculation formula, and generate the target hydraulic crane boom real-time curvature data J, where

[0085] The vehicle hydraulic crane boom bending fault overload fault detection process is performed based on the target hydraulic crane boom real-time curvature data and the target hydraulic crane boom bending overload curvature threshold, and the target hydraulic crane boom bending overload fault detection data is generated. When it is not overloaded, S4, S5, and S6 are repeatedly executed until the vehicle hydraulic crane boom bending overload fault detection result is overloaded. The operation steps are as follows:

[0086] S61. Obtaining the target hydraulic crane boom bending overload curvature threshold value v mubiao and the target hydraulic crane boom real-time curvature data J;

[0087] S62, compare the target hydraulic crane boom real-time curvature data J with the target hydraulic crane boom bending overload curvature threshold v mubiao Performing curvature value comparison, and generating target hydraulic crane boom bending overload fault detection data based on the curvature value comparison result;

[0088] When J is not greater than v mubiao , indicating that the bending state of the automobile hydraulic crane boom has not reached the overload state, the target hydraulic crane boom bending overload fault detection data is output as not overloaded, and S4, S5, and S6 are repeatedly executed until the target hydraulic crane boom bending overload fault detection data is overloaded;

[0089] When J is greater than v mubiao , indicating that the bending state of the automobile hydraulic crane boom reaches the overload state, then the output target hydraulic crane boom bending overload fault detection data is overload.

[0090] Through the hydraulic crane boom bending overload curvature threshold search unit, the target automobile hydraulic crane boom bending overload curvature threshold is accurately matched according to the target hydraulic crane product type information combined with the intelligent search algorithm and the hydraulic crane boom bending overload curvature threshold of different product types, so as to realize the accurate screening of the ultimate curvature parameters of the boom bending overload critical state based on the hydraulic crane product model; the hydraulic crane boom entity model acquisition unit, the hydraulic crane boom curvature radius measurement sampling point establishment unit, the hydraulic crane boom curvature radius measurement unit cooperate with each other and the hydraulic crane boom real-time curvature measurement unit, and the automobile hydraulic crane boom dynamic collection is realized through the UAV equipped with a laser scanner. The crane boom entity model information is used, and AutoCAD is used to accurately measure the curvature radius information of the bending axis of the automobile hydraulic crane boom. The real-time curvature information of the automobile hydraulic crane boom is dynamically measured in combination with numerical calculation, so as to realize the precise monitoring of the bending curvature information of the automobile hydraulic crane boom based on the model numerical analysis; the hydraulic crane boom bending overload fault detection unit performs dynamic detection of the automobile hydraulic crane boom bending overload fault according to the target hydraulic crane boom real-time curvature information and the target hydraulic crane boom bending overload curvature threshold, so as to realize intelligent real-time diagnosis of the automobile hydraulic crane boom bending overload fault and improve the safety and stability of the automobile hydraulic crane operation.

[0091] For further information, see Figure 1-Figure 2 When overloaded, the hydraulic crane boom bending overload appearance image data is collected and compared with the hydraulic crane boom hydraulic oil leakage standard image data to perform boom hydraulic oil leakage fault detection processing under the boom bending overload state of the automobile hydraulic crane. The operation steps for generating the target hydraulic crane boom hydraulic oil leakage detection data are as follows:

[0092] S71. When the target hydraulic crane boom bending overload fault detection data indicates overload, online image information of the appearance of the automobile hydraulic crane boom in the overload state is collected using a cloud camera mounted on a drone, and hydraulic crane boom bending overload appearance image data is generated.

[0093] S72, establish a hydraulic crane boom hydraulic oil leakage standard image data set M = (m1, ..., m a ,…,m γ ), a=1,2,3,…,γ; where m a represents the a-th type of hydraulic crane boom hydraulic oil leakage standard image data, γ represents the maximum number of hydraulic crane boom hydraulic oil leakage standard images; the hydraulic crane boom hydraulic oil leakage standard image data represents the set standard image information of the hydraulic crane boom hydraulic oil leakage state;

[0094] S73, using the ORB image recognition algorithm to compare the hydraulic crane boom bending overload appearance image data with the hydraulic crane boom hydraulic oil leakage standard image data set M of the hydraulic crane boom hydraulic oil leakage standard image data m. a Perform image feature matching and generate target hydraulic crane boom hydraulic oil leakage detection data based on the image feature matching results;

[0095] When the hydraulic crane boom is bent and overloaded, the appearance image data and the hydraulic crane boom hydraulic oil leakage standard image data m a When the image feature matching is successful, it means that there is a hydraulic oil leakage fault at the boom position of the automobile hydraulic crane currently photographed by the drone equipped with the cloud camera, and the target hydraulic crane boom hydraulic oil leakage detection data is output as leakage;

[0096] When the hydraulic crane boom is bent and overloaded, the appearance image data and the hydraulic crane boom hydraulic oil leakage standard image data m a If the image feature matching fails, it means that there is a hydraulic oil leakage fault at the boom position of the automobile hydraulic crane currently photographed by the drone equipped with the cloud camera, and the output target hydraulic crane boom hydraulic oil leakage detection data is that there is no leakage.

[0097] The steps for constructing the fault diagnosis result data of the truck hydraulic crane and performing the crane fault diagnosis feedback operation are as follows:

[0098] S81, combining the generated target hydraulic crane boom bending overload fault detection data, the hydraulic crane boom bending overload appearance image data, and the target hydraulic crane boom hydraulic oil leakage detection data to construct automobile hydraulic crane fault diagnosis result data;

[0099] S82. Transmit the fault diagnosis result data of the truck hydraulic crane to the crane management center through the Internet of Things communication network to perform crane fault diagnosis feedback work.

[0100] The hydraulic crane boom bending overload appearance image acquisition unit uses a drone-mounted cloud camera to dynamically capture appearance image information of the boom bending overload state of a truck hydraulic crane, providing real-world data support for the precise monitoring of hydraulic oil leakage faults in this state. The hydraulic crane boom hydraulic oil leakage monitoring unit intelligently identifies hydraulic oil leakage faults in this state based on the appearance image information of the boom bending overload state, combined with image recognition algorithms and standard image information of hydraulic oil leakage in the boom bending overload state, thereby improving the safety of the hydraulic system of the truck hydraulic crane. The hydraulic crane boom fault feedback unit accurately constructs fault diagnosis results for the truck hydraulic crane based on the boom bending overload fault detection information, the boom bending overload appearance image information, and the boom hydraulic oil leakage detection information, combined with numerical analysis. At the same time, combined with the crane management center to autonomously and efficiently execute crane fault diagnosis feedback operations, it realizes visual dynamic feedback of boom bending overload faults and hydraulic oil leakage faults in this state of boom bending overload, thereby improving the response speed of truck hydraulic crane fault diagnosis.

[0101] Example 2:

[0102] See also Figure 1-Figure 2 The crane fault diagnosis system based on the Internet of Things is used to implement the crane fault diagnosis method based on the Internet of Things. The system includes a hydraulic crane product identification module, a hydraulic crane boom bending fault diagnosis module, and a hydraulic crane boom leakage fault diagnosis and fault feedback module;

[0103] The hydraulic crane product identification module includes a hydraulic crane appearance image acquisition unit, a hydraulic crane appearance image storage unit for different product types, and a hydraulic crane product type identification unit;

[0104] The hydraulic crane appearance image acquisition unit uses a drone-mounted cloud camera to collect hydraulic crane appearance image data; the different product types of hydraulic crane appearance image storage unit is used to store the appearance image data of hydraulic cranes of different product types; the hydraulic crane product type recognition unit performs product type recognition processing on the automobile hydraulic crane based on the hydraulic crane appearance image data and the appearance image data of hydraulic cranes of different product types, and generates the target hydraulic crane product type data;

[0105] The hydraulic crane boom bending fault diagnosis module includes a hydraulic crane boom bending overload curvature threshold storage unit for different product types, a hydraulic crane boom bending overload curvature threshold search unit, a hydraulic crane boom entity model acquisition unit, a hydraulic crane boom curvature radius measurement sampling point establishment unit, a hydraulic crane boom curvature radius measurement unit, a hydraulic crane boom real-time curvature measurement unit, and a hydraulic crane boom bending overload fault detection unit;

[0106] A storage unit for the bending overload curvature threshold value of hydraulic crane booms of different product types is used to store the bending overload curvature threshold values ​​of hydraulic crane booms of different product types; a search unit for the bending overload curvature threshold value of a hydraulic crane boom is used to search for the boom bending overload curvature threshold value of a target automobile hydraulic crane based on the target hydraulic crane product type data and the bending overload curvature threshold values ​​of hydraulic crane booms of different product types, and generate the bending overload curvature threshold value of the target hydraulic crane boom; a hydraulic crane boom entity model acquisition unit is used to acquire the entity model data of the hydraulic crane boom through a laser scanner mounted on a drone; a hydraulic crane boom curvature radius measurement sampling point establishment unit is used to establish the coordinates of the sampling points in the boom axis direction required for measuring the curvature radius of the automobile hydraulic crane boom based on the hydraulic crane boom entity model data and in combination with AutoCAD. , and generates the measurement coordinate data of the curvature radius of the hydraulic crane boom; the hydraulic crane boom curvature radius measurement unit, based on the hydraulic crane boom curvature radius measurement coordinate data and combined with AutoCAD, performs hydraulic crane boom curvature radius measurement processing, and generates the target hydraulic crane boom curvature radius data; the hydraulic crane boom real-time curvature measurement unit, based on the target hydraulic crane boom curvature radius data and combined with numerical processing, performs automobile hydraulic crane boom curvature numerical measurement processing, and generates the target hydraulic crane boom real-time curvature data; the hydraulic crane boom bending overload fault detection unit, performs automobile hydraulic crane boom bending overload fault detection processing according to the target hydraulic crane boom real-time curvature data and the target hydraulic crane boom bending overload curvature threshold, and generates the target hydraulic crane boom bending overload fault detection data;

[0107] The hydraulic crane boom leakage fault diagnosis and fault feedback module includes a hydraulic crane boom bending overload appearance image acquisition unit, a hydraulic crane boom hydraulic oil leakage standard image storage unit, a hydraulic crane boom hydraulic oil leakage monitoring unit, and a hydraulic crane boom fault feedback unit;

[0108] The hydraulic crane boom bending overload appearance image acquisition unit collects the hydraulic crane boom bending overload appearance image data through the drone-mounted cloud camera; the hydraulic crane boom hydraulic oil leakage standard image storage unit is used to store the hydraulic crane boom hydraulic oil leakage standard image data; the hydraulic crane boom hydraulic oil leakage monitoring unit performs boom hydraulic oil leakage fault detection and processing under the boom bending overload state of the automobile hydraulic crane based on the hydraulic crane boom bending overload appearance image data and the hydraulic crane boom hydraulic oil leakage standard image data, and generates the target hydraulic crane boom hydraulic oil leakage detection data; the hydraulic crane boom fault feedback unit is used to construct the automobile hydraulic crane fault diagnosis result data and perform crane fault diagnosis feedback operations in conjunction with the crane management center.

[0109] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A crane fault diagnosis method based on the Internet of Things, characterized in that: The method comprises the following steps: S1. Collecting appearance image data of the hydraulic crane; S2. Perform product type identification processing on the truck hydraulic crane to generate target hydraulic crane product type data; S3, performing a search process for a boom bending overload curvature threshold value of a target truck hydraulic crane to generate a boom bending overload curvature threshold value of the target hydraulic crane; S4, collecting the hydraulic crane boom physical model data and performing the coordinate establishment and processing of the boom axis direction sampling points required for measuring the curvature radius of the automobile hydraulic crane boom, and generating the hydraulic crane boom curvature radius measurement coordinate data; S5. Performing a hydraulic crane boom curvature radius measurement process to generate target hydraulic crane boom curvature radius data and performing a vehicle hydraulic crane boom curvature numerical measurement process to generate target hydraulic crane boom real-time curvature data; S6. Performing a detection process for a bending overload fault of a truck hydraulic crane boom to generate target hydraulic crane boom bending overload fault detection data. If the target hydraulic crane boom is not overloaded, repeatedly performing S4, S5, and S6 until the truck hydraulic crane boom bending overload fault detection result indicates an overload. S7. When overloaded, collect the appearance image data of the hydraulic crane boom bending overload and perform boom hydraulic oil leakage fault detection processing on the automobile hydraulic crane boom under the boom bending overload state with the standard image data of the hydraulic crane boom hydraulic oil leakage to generate target hydraulic crane boom hydraulic oil leakage detection data; S8. Construct the fault diagnosis result data of the automobile hydraulic crane and perform the crane fault diagnosis feedback operation.

2. The method for diagnosing crane faults based on the Internet of Things according to claim 1, characterized in that: Said S1 comprises the following steps: S11. Collect overall appearance image information of a truck-mounted hydraulic crane performing a lifting operation online through a cloud camera mounted on a drone, and generate appearance image data of the hydraulic crane.

3. The crane fault diagnosis method based on the Internet of Things according to claim 2 is characterized in that: The S2 comprises the following steps: S21, establish a data set V of appearance images of hydraulic cranes of different product types, wherein V includes v c , where v c Represents the appearance image data of different product types of hydraulic cranes corresponding to the c-th type of automobile hydraulic crane product; S22, using ORB image recognition algorithm to compare the hydraulic crane appearance image data with the v in the V c Perform image feature matching to search for the v that matches the hydraulic crane appearance image data. c The corresponding automobile hydraulic crane product type information is obtained, and the target hydraulic crane product type data is constructed.

4. The method for diagnosing crane faults based on the Internet of Things according to claim 3, characterized in that: The S3 includes the following steps: S31, establishing a set of curvature threshold values ​​V' of the boom bending overload of hydraulic cranes of different product types, wherein V' includes v' c , where v′ c It represents the overload curvature threshold of the hydraulic crane boom bending of different product types corresponding to the c-th type of automobile hydraulic crane product type; S32, using the Aho-Corasick search algorithm to compare the target hydraulic crane product type data with the v′ in the V′ c Carry out the character matching of automobile hydraulic crane product type and search for the v' corresponding to the target hydraulic crane product type data c , and construct the target hydraulic crane boom bending overload curvature threshold v mubiao .

5. The method for diagnosing crane faults based on the Internet of Things according to claim 4, characterized in that: The S4 comprises the following steps: S41. Using a laser scanner mounted on a drone, online collecting three-dimensional solid model information of the entire boom of a truck-mounted hydraulic crane performing a lifting operation, and generating solid model data of the hydraulic crane boom; S42, importing the hydraulic crane boom entity model data into AutoCAD and running it, and using the AutoCAD coordinate measurement tool to respectively collect the spatial coordinates of the sampling points at the left and right ends of the boom axis of the automobile hydraulic crane and the spatial coordinate information of the sampling point in the middle of the boom axis, and generating the hydraulic crane boom curvature radius measurement coordinate data set O = (o zuo ,o zhong ,o you ), where o zuo 、o zhong and o you They respectively represent the left end coordinate data of the hydraulic crane boom curvature radius measurement, the middle coordinate data of the hydraulic crane boom curvature radius measurement, and the right end coordinate data of the hydraulic crane boom curvature radius measurement.

6. The method for diagnosing crane faults based on the Internet of Things according to claim 5, characterized in that: The S5 comprises the following steps: S51, import the O into AutoCAD, and use the AutoCAD radius measurement tool to measure the radius based on the O zuo 、The above zhong and the o you The corresponding coordinate parameters are used to measure the curvature radius parameters of the boom axis of the automobile hydraulic crane, and generate the target hydraulic crane boom curvature radius data L; S52, based on the L and in combination with the curvature-curvature radius calculation formula, the curvature parameter of the boom axis of the automobile hydraulic crane is calculated, and the target hydraulic crane boom real-time curvature data J is generated, wherein 7. The method for diagnosing crane faults based on the Internet of Things according to claim 6, characterized in that: The S6 comprises the following steps: S61, obtain the v mubiao and said J; S62, the J and the v mubiao Performing curvature value comparison, and generating target hydraulic crane boom bending overload fault detection data based on the curvature value comparison result; When J is not greater than v mubiao , then outputting the target hydraulic crane boom bending overload fault detection data as not overloaded, and repeatedly executing S4, S5, and S6 until the target hydraulic crane boom bending overload fault detection data is overloaded; When J is greater than v mubiao , then the target hydraulic crane boom bending overload fault detection data is output as overload.

8. The method for diagnosing crane faults based on the Internet of Things according to claim 7, characterized in that: The S7 comprises the following steps: S71. When the target hydraulic crane boom bending overload fault detection data indicates overload, online collecting appearance image information of the automobile hydraulic crane boom in an overload state by using a cloud camera mounted on an unmanned aerial vehicle, and generating hydraulic crane boom bending overload appearance image data; S72, establish a hydraulic crane boom hydraulic oil leakage standard image data set M, wherein M includes m a ; where m a represents the standard image data of hydraulic oil leakage of the boom of the hydraulic crane of type a; S73, using ORB image recognition algorithm to compare the hydraulic crane boom bending overload appearance image data with the m in M a Perform image feature matching and generate target hydraulic crane boom hydraulic oil leakage detection data based on the image feature matching results; When the hydraulic crane boom is bent and overloaded, the appearance image data is combined with the m a When the image feature matching is successful, the target hydraulic crane boom hydraulic oil leakage detection data is output as leakage; When the hydraulic crane boom is bent and overloaded, the appearance image data is combined with the m a When the image feature matching is unsuccessful, the target hydraulic crane boom hydraulic oil leakage detection data is output as no leakage.

9. The method for diagnosing crane faults based on the Internet of Things according to claim 8, characterized in that: The S8 comprises the following steps: S81, combining the generated target hydraulic crane boom bending overload fault detection data, the hydraulic crane boom bending overload appearance image data, and the target hydraulic crane boom hydraulic oil leakage detection data to construct automobile hydraulic crane fault diagnosis result data; S82: Transmit the fault diagnosis result data of the truck hydraulic crane to the crane management center via the Internet of Things communication network to perform crane fault diagnosis feedback work.

10. A crane fault diagnosis system based on the Internet of Things, used to implement the crane fault diagnosis method based on the Internet of Things according to any one of claims 1 to 9, characterized in that: The system includes a hydraulic crane product identification module, a hydraulic crane boom bending fault diagnosis module, and a hydraulic crane boom leakage fault diagnosis and fault feedback module.

Images