A port lifting equipment health monitoring method and system

Abstract

The present invention discloses a port lifting equipment health monitoring method and system, which specifically relates to the technical field of port lifting equipment, including a drone inspection module, a lifting equipment appearance monitoring module, a lifting equipment data acquisition module, a lifting equipment health status feature processing module, a lifting equipment health fusion analysis module, a lifting equipment anomaly detection module, and a digital twin modeling module. The present invention calculates the comprehensive evaluation index of lifting equipment appearance defects, load fluctuation, height control error change rate and wire rope bending health evaluation characteristics through drone inspection and sensor data, establishes a health status feature early warning, and further obtains the health assessment coefficient of the lifting equipment, realizing comprehensive monitoring of the equipment appearance and operating status, improving the coverage of data collection, and quantitative evaluation and comparison methods, making the equipment health status judgment more objective, and making analysis and judgment based on data, making the formulation of maintenance plans more scientific and reasonable.

Description

Technical Field

[0001] The present invention relates to the technical field of port lifting equipment, and more particularly, to a health monitoring method and system for port lifting equipment. Background Art

[0002] With the continuous expansion of global trade and the popularization of containerized transportation mode, the number and frequency of use of port lifting equipment continue to increase, which puts higher requirements on the reliability and health of the equipment. As the core equipment in the modern port logistics system, port lifting equipment undertakes key tasks such as cargo loading and unloading, handling and storage. Its operating efficiency and safety directly affect the overall operating capacity of the port and the timeliness of cargo transportation.

[0003] In recent years, with the development of sensor technology, data acquisition and transmission technology, and intelligent analysis algorithms, health management based on equipment status monitoring has gradually become a research hotspot. Through the real-time collection of vibration, temperature, pressure, current and other parameter information by various sensors installed on the equipment, and combined with big data analysis methods to evaluate the operating status of the equipment, early fault warning and accurate maintenance decisions can be achieved.

[0004] However, in actual use, it still has some shortcomings. For example, the special working environment of port crane equipment also brings a variety of external interferences to health monitoring. Existing port crane equipment health monitoring methods still have deficiencies in data collection and lack of autonomous learning ability, making it difficult to achieve early detection accuracy and response speed for potential faults.

[0005] In actual applications, due to the long-term high-intensity and high-load working environment, traditional lifting equipment monitoring methods rely on regular maintenance, which often requires the suspension of equipment operation, directly affecting the port's production efficiency. In addition, it is impossible to accurately assess the wear of key components of the equipment and achieve early fault warning, which may lead to safety accidents. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a method and system for monitoring the health of port crane equipment, which are used to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solutions: a port crane equipment health monitoring system, comprising:

[0008] Drone inspection module: Demarcates a drone inspection area at the port, uses adaptive flight path planning technology and adjusts the shooting angle and distance according to the equipment structure to collect equipment appearance images every t time periods.

[0009] Lifting equipment appearance monitoring module: obtains all defect information in the lifting equipment appearance image collected in the i-th time period, calculates the comprehensive evaluation index of the lifting equipment appearance defects in the i-th time period based on the defect area, and processes it.

[0010] Lifting equipment data acquisition module: collects equipment operating parameters of each operation cycle of the lifting equipment through sensors. The operation cycle is a single lifting as one cycle. The equipment operating parameters include lifting weight, lifting height, and wire rope micro-bend.

[0011] Lifting equipment health status feature processing module: used to obtain the equipment operating parameters of each operation cycle of the lifting equipment, calculate the load fluctuation of the lifting equipment, the height control error change rate and the wire rope bending health assessment characteristics, and establish health status feature early warning.

[0012] Lifting equipment health fusion analysis module: used to obtain the comprehensive evaluation index of lifting equipment appearance defects, load fluctuation, height control error change rate and wire rope bending health assessment of the lifting equipment, and obtain the health assessment coefficient of the lifting equipment based on the equipment health assessment model.

[0013] Lifting equipment anomaly detection module: obtains the health assessment coefficient of the lifting equipment, compares it with the preset health assessment coefficient, and classifies the lifting equipment status level according to the health assessment coefficient deviation of the lifting equipment.

[0014] Digital twin modeling module: Builds a virtual model based on the actual physical structure and operating parameters of the lifting equipment, and updates the equipment's operating status and health by receiving real-time equipment appearance images and equipment operating parameter data.

[0015] Preferably, the steps for implementing the drone inspection module are as follows:

[0016] S21: Designate drone inspection areas at the port, design inspection routes for each crane using adaptive flight path planning technology, and set take-off points, inspection routes, and return points.

[0017] S22: Equip the drone with a high-resolution camera to capture images of the crane's exterior every t time periods. Simultaneously, a light sensor in the drone's environmental perception unit monitors ambient light intensity. According to a preset light intensity-light source adjustment strategy, the angle and intensity of the light source are flexibly adjusted. Each time period is sequentially numbered 1, 2, ..., i, ..., n.

[0018] S23: Establish a normal state image database and a defect state image database, match the collected equipment appearance image with the normal state image database and the defect state image database, traverse all defect information in the lifting equipment appearance image, and perform defect data annotation.

[0019] Preferably, the adaptive flight path planning technology is based on the distribution of key monitoring points of the equipment structure and combined with the navigation function of the three-dimensional geographic information system to plan the drone inspection flight route to ensure comprehensive and efficient inspection coverage.

[0020] Preferably, the lifting equipment appearance monitoring module is implemented in the following steps:

[0021] S41: Obtain all defect information in the lifting equipment appearance image collected in the i-th time period, and extract the area of ​​each defect in the image and the lifting equipment position;

[0022] S42: calculating the comprehensive evaluation index of the lifting equipment appearance defects in the i-th time period based on the set appearance defect evaluation model according to the area of ​​each defect in the lifting equipment appearance image in the i-th time period;

[0023] S43: Obtain the comprehensive evaluation index of the lifting equipment appearance defects in the i-th time period, and compare it with the preset comprehensive evaluation index of the lifting equipment appearance defects. If the comprehensive evaluation index of the lifting equipment appearance defects at this moment is greater than the preset comprehensive evaluation index of the lifting equipment appearance defects, it indicates that the appearance defects of the lifting equipment at this moment are serious. Extract the lifting equipment position corresponding to the lifting equipment appearance image at this moment, and send the lifting equipment appearance image to the maintenance personnel, who perform maintenance operations. Otherwise, it indicates that the appearance monitoring of the lifting equipment at this moment is better.

[0024] Preferably, the lifting equipment data acquisition module is specifically:

[0025] By installing a strain gauge weighing sensor on the lifting equipment, the lifting weight borne by the equipment during operation is collected every t time periods according to the operation cycle; by installing a position sensor on the lifting equipment, the vertical displacement of the equipment during operation is collected every t time periods according to the operation cycle to obtain the lifting height; by installing a laser sensor for detecting micro-bending of the wire rope on the lifting equipment, the micro-bending of the wire rope during operation is collected every t time periods according to the operation cycle.

[0026] Preferably, the steps for implementing the lifting equipment health status feature processing module are specifically as follows:

[0027] S61: Load Fluctuation Characteristics: By calculating the mean and standard deviation of the lifting weight of each operation cycle of the lifting equipment, and based on the ratio of the standard deviation of the lifting weight to the mean, the load fluctuation of each operation cycle of the lifting equipment is calculated. By obtaining the load fluctuation of each operation cycle of the lifting equipment, it is compared with the preset load fluctuation. If the load fluctuation of a certain operation cycle is greater than the preset load fluctuation, it indicates that the load of the lifting equipment fluctuates abnormally, and the management personnel should be notified to check the equipment. Otherwise, it indicates that the load of the lifting equipment is normal.

[0028] S62: Height control error change rate feature: Calculate the height control error change rate of each operation cycle of the lifting equipment based on the lifting height and the target height. The height control error change rate of each operation cycle of the lifting equipment is obtained and compared with a preset height control error change rate. If the height control error change rate of a certain operation cycle is greater than the preset height control error change rate, it indicates that the lifting equipment control system is faulty and the management personnel should be notified to check the equipment. Otherwise, it indicates that there is no abnormality in the lifting equipment control system.

[0029] S63: Wire rope bending health assessment features: According to the operation cycle, the micro-bending of the wire rope during the equipment operation process is collected every t time periods. The bending health assessment of the wire rope of the lifting equipment is calculated based on the micro-bending and critical bending of the wire rope of the lifting equipment. The obtained wire rope bending health assessment of the lifting equipment is compared with the preset wire rope bending health assessment. If the wire rope bending health assessment of a certain time period is less than the preset wire rope bending health assessment and is greater than or equal to 0, it indicates that the wire rope of the lifting equipment is damaged and the management personnel should be notified to check the equipment. If the wire rope bending health assessment of a certain time period is less than 0, it indicates that the bending health of the wire rope of the lifting equipment exceeds the safety limit and an emergency shutdown is immediately performed. Otherwise, it indicates that there is no abnormality in the bending health assessment of the wire rope of the lifting equipment.

[0030] Preferably, the steps for implementing the lifting equipment health fusion analysis module are as follows:

[0031] S71: Obtain the comprehensive evaluation index of the appearance defects of the lifting equipment in each time period, the load fluctuation of each operation cycle, the height control error change rate of each operation cycle, and the wire rope bending health evaluation in each operation cycle time period, and perform parameter normalization processing;

[0032] S72: Obtain the normalized comprehensive evaluation index of appearance defects of the lifting equipment, load fluctuation, height control error change rate, and wire rope bending health assessment, and obtain the health assessment coefficient of the lifting equipment based on the set equipment health assessment model.

[0033] Preferably, the lifting equipment abnormality detection module is specifically:

[0034] Obtain the health assessment coefficient of the lifting equipment, compare it with the preset health assessment coefficient, and obtain the health assessment coefficient deviation of the lifting equipment. Match the health assessment coefficient deviation value with the lifting equipment status level classification standard, and divide the lifting equipment into four equipment status levels: healthy, warning, abnormal, and faulty. Push the equipment status level of the lifting equipment to relevant personnel to maintain the lifting equipment.

[0035] Preferably, a method for monitoring the health of port lifting equipment comprises the following steps:

[0036] Step S01: Demarcate the drone inspection area at the port, use adaptive flight path planning technology and adjust the shooting angle and distance according to the equipment structure to collect equipment appearance images every t time period;

[0037] Step S02: Obtain all defect information in the lifting equipment appearance image collected in the i-th time period, calculate the lifting equipment appearance defect comprehensive evaluation index in the i-th time period based on the defect area, and process the information;

[0038] Step S03: collecting equipment operating parameters of each operation cycle of the lifting equipment through sensors, wherein a single lifting cycle is one cycle, and the equipment operating parameters include lifting weight, lifting height, and wire rope microbend;

[0039] Step S04: obtaining the equipment operating parameters of each operation cycle of the lifting equipment, calculating the load fluctuation, height control error change rate and wire rope bending health assessment characteristics of the lifting equipment, and establishing a health status characteristic early warning;

[0040] Step S05: obtaining a comprehensive evaluation index of appearance defects of the lifting equipment, load fluctuation, height control error change rate, and wire rope bending health evaluation of the lifting equipment, and obtaining a health evaluation coefficient of the lifting equipment according to an equipment health evaluation model;

[0041] Step S06: Obtaining a health assessment coefficient of the lifting equipment, comparing it with a preset health assessment coefficient, and classifying the state of the lifting equipment according to the health assessment coefficient deviation of the lifting equipment;

[0042] Step S07: Build a virtual model based on the actual physical structure and operating parameters of the lifting equipment, and update the operating status and health of the equipment by receiving the equipment appearance image and equipment operating parameter data in real time.

[0043] Technical effects and advantages of the present invention:

[0044] 1. The present invention provides a method and system for monitoring the health of port lifting equipment. The method defines a drone inspection area in the port, uses adaptive flight path planning technology and adjusts the shooting angle and distance according to the equipment structure, collects equipment appearance images every t time periods, calculates the comprehensive evaluation index of the lifting equipment appearance defects in the i-th time period based on all defect information in the lifting equipment appearance image and the defect area, and compares it with the preset comprehensive evaluation index of the lifting equipment appearance defects. If the comprehensive evaluation index of the lifting equipment appearance defects at that moment is greater than the preset comprehensive evaluation index of the lifting equipment appearance defects, it indicates that the lifting equipment appearance defects at that moment are serious, and the defects at that time are extracted. The crane position corresponding to the appearance image of the crane is engraved and sent to the maintenance personnel for maintenance operations. Conversely, the better the appearance monitoring of the crane at that moment, the better. The equipment operating parameters of each operation cycle of the crane are collected through sensors, and the load fluctuation, height control error change rate and wire rope bending health assessment characteristics of the crane are calculated. The health status characteristic early warning is established. Through the fusion of drone inspection and sensor data, the comprehensive monitoring of the equipment appearance and operation status is realized, the accuracy and coverage of data collection are improved, and the analysis and judgment based on the data make the formulation of maintenance plans more scientific and reasonable.

[0045] 2. The present invention provides a port crane equipment health monitoring method and system, which obtains the comprehensive evaluation index of the crane equipment appearance defects, load fluctuation, height control error change rate and wire rope bending health evaluation of the crane equipment, performs parameter normalization processing, and further obtains the health assessment coefficient of the crane equipment based on the set equipment health assessment model, obtains the health assessment coefficient of the crane equipment, compares it with the preset health assessment coefficient, and obtains the health assessment coefficient deviation of the crane equipment. The health assessment coefficient deviation value is matched with the crane equipment status level classification standard, and the crane equipment is divided into four equipment status levels: healthy, warning, abnormal, and fault. The equipment status level of the crane equipment is pushed to relevant personnel, and the crane equipment is maintained. A virtual model is constructed, and equipment appearance images and equipment operating parameter data are received in real time to update the equipment's operating status and health status, realizing a multi-dimensional comprehensive evaluation of the crane equipment. The health assessment coefficient is obtained based on the equipment health assessment model. The quantitative evaluation and comparison method makes the equipment health status judgment more objective and intuitive, and can accurately locate the degree to which the equipment deviates from the normal state, thereby realizing precise maintenance. The introduction of digital twin technology can map the equipment operating status in real time, providing accurate support for fault warning and maintenance decision-making; BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a structural schematic diagram of a port crane equipment health monitoring system according to the present invention.

[0047] Figure 2The figure is a flow chart of a method for monitoring the health of port crane equipment according to the present invention. DETAILED DESCRIPTION

[0048] 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.

[0049] See also Figure 1 As shown, the present invention provides a port lifting equipment health monitoring system, including a drone inspection module, a lifting equipment appearance monitoring module, a lifting equipment data acquisition module, a lifting equipment health status feature processing module, a lifting equipment health fusion analysis module, a lifting equipment anomaly detection module, and a digital twin modeling module.

[0050] The drone inspection module is connected to the lifting equipment appearance monitoring module, the lifting equipment data acquisition module is connected to the lifting equipment health status feature processing module, the lifting equipment appearance monitoring module and the lifting equipment health status feature processing module are connected to the lifting equipment health fusion analysis module, the lifting equipment health fusion analysis module is connected to the lifting equipment anomaly detection module, and the lifting equipment anomaly detection module is connected to the digital twin modeling module.

[0051] The drone inspection module defines a drone inspection area in the port, uses adaptive flight path planning technology and adjusts the shooting angle and distance according to the equipment structure to collect equipment appearance images every t time periods.

[0052] In one possible design, the drone inspection module implements the following steps:

[0053] S01: Define a drone inspection area at the port, design an inspection route for each crane using adaptive flight path planning technology, and set the take-off point, inspection path, and return point;

[0054] S02: Equip the drone with a high-resolution camera to capture images of the crane's exterior every t time periods. Simultaneously, the drone's environmental perception unit uses a light sensor to monitor ambient light intensity. Based on a preset light intensity-light source adjustment strategy, the drone flexibly adjusts the light source angle and intensity. Each time period is numbered 1, 2, ..., i, ..., n.

[0055] S03: Establish a normal state image database and a defect state image database, match the collected equipment appearance image with the normal state image database and the defect state image database, traverse all defect information in the lifting equipment appearance image, and perform defect data annotation.

[0056] In one possible design, the adaptive flight path planning technology plans the drone inspection flight route based on the distribution of key monitoring points of the equipment structure and combines the navigation function of the three-dimensional geographic information system to ensure comprehensive and efficient inspection coverage.

[0057] The lifting equipment appearance monitoring module obtains all defect information in the lifting equipment appearance image collected in the i-th time period, calculates the comprehensive evaluation index of the lifting equipment appearance defects in the i-th time period based on the defect area, and processes it.

[0058] In one possible design, the steps for implementing the lifting equipment appearance monitoring module are as follows:

[0059] S01: Obtain all defect information in the lifting equipment appearance image collected in the i-th time period, and extract the area of ​​each defect in the image and the lifting equipment position;

[0060] S02: calculating the comprehensive evaluation index of the appearance defects of the lifting equipment in the i-th time period based on the set appearance defect evaluation model according to the area of ​​each defect in the appearance image of the lifting equipment in the i-th time period;

[0061] S03: Obtain the comprehensive evaluation index of the appearance defects of the lifting equipment in the i-th time period, and compare it with the preset comprehensive evaluation index of the appearance defects of the lifting equipment. If the comprehensive evaluation index of the appearance defects of the lifting equipment at this moment is greater than the preset comprehensive evaluation index of the appearance defects of the lifting equipment, it indicates that the appearance defects of the lifting equipment at this moment are serious. Extract the lifting equipment position corresponding to the appearance image of the lifting equipment at this moment, and send the appearance image of the lifting equipment to the maintenance personnel, who perform the maintenance operation. Otherwise, it indicates that the appearance monitoring of the lifting equipment at this moment is better.

[0062] In this embodiment, it should be specifically explained that the calculation formula of the comprehensive evaluation index of the lifting equipment appearance defects is:

[0063] ,in, It is expressed as the comprehensive evaluation index of appearance defects of lifting equipment in the i-th time period, Expressed as the area of ​​the qth defect in the i-th time period, is the weight factor of the qth defect, and m is the total number of defects.

[0064] The lifting equipment data acquisition module collects equipment operating parameters of each operation cycle of the lifting equipment through sensors. The operation cycle is a single lifting as one cycle. The equipment operating parameters include lifting weight, lifting height, and wire rope micro-bend.

[0065] In one possible design, the lifting equipment data acquisition module is specifically:

[0066] By installing a strain gauge weighing sensor on the lifting equipment, the lifting weight borne by the equipment during operation is collected every t time periods according to the operation cycle; by installing a position sensor on the lifting equipment, the vertical displacement of the equipment during operation is collected every t time periods according to the operation cycle to obtain the lifting height; by installing a laser sensor for detecting micro-bending of the wire rope on the lifting equipment, the micro-bending of the wire rope during operation is collected every t time periods according to the operation cycle.

[0067] The lifting equipment health status feature processing module is used to obtain the equipment operating parameters of each operation cycle of the lifting equipment, calculate the load fluctuation, height control error change rate and wire rope bending health assessment characteristics of the lifting equipment, and establish a health status feature early warning.

[0068] In one possible design, the steps for implementing the lifting equipment health status feature processing module are specifically as follows:

[0069] S01: Load Fluctuation Characteristics: By calculating the mean and standard deviation of the lifting capacity of each operation cycle of the lifting equipment, and based on the ratio of the standard deviation of the lifting capacity to the mean, the load fluctuation of each operation cycle of the lifting equipment is calculated. By obtaining the load fluctuation of each operation cycle of the lifting equipment, it is compared with the preset load fluctuation. If the load fluctuation of a certain operation cycle is greater than the preset load fluctuation, it indicates that the load fluctuation of the lifting equipment is abnormal, and the management personnel should be notified to check the equipment. Otherwise, it indicates that the load of the lifting equipment is normal;

[0070] S02: Height Control Error Change Rate Characteristics: Calculate the height control error change rate of each operation cycle of the lifting equipment based on the lifting height and target height. Compare the obtained height control error change rate of each operation cycle of the lifting equipment with the preset height control error change rate. If the height control error change rate of a certain operation cycle is greater than the preset height control error change rate, it indicates that the lifting equipment control system is faulty and the management personnel should be notified to check the equipment. Otherwise, it indicates that there is no abnormality in the lifting equipment control system.

[0071] S03: Wire rope bending health assessment features: According to the operation cycle, the micro-bending of the wire rope during the equipment operation process is collected every t time periods. The bending health assessment of the wire rope of the lifting equipment is calculated based on the micro-bending and critical bending of the wire rope of the lifting equipment. The obtained bending health assessment of the wire rope of the lifting equipment is compared with the preset bending health assessment of the wire rope. If the bending health assessment of the wire rope in a certain time period is less than the preset bending health assessment and is greater than or equal to 0, it indicates that the wire rope of the lifting equipment is damaged and the management personnel should be notified to check the equipment. If the bending health assessment of the wire rope in a certain time period is less than 0, it indicates that the bending health of the wire rope of the lifting equipment exceeds the safety limit and an emergency shutdown is immediately performed. Otherwise, it indicates that there is no abnormality in the bending health assessment of the wire rope of the lifting equipment.

[0072] In this embodiment, it should be specifically explained that the lifting equipment health status feature processing module further includes:

[0073] The load fluctuation characteristics are as follows: by calculating the mean and standard deviation of the lifting weight of each operation cycle of the lifting equipment, and according to the ratio of the standard deviation to the mean of the lifting weight, the load fluctuation of each operation cycle of the lifting equipment is calculated, specifically:

[0074] ,in, Expressed as the mean lifting weight of the j-th operation cycle, It is expressed as the lifting capacity of the jth operation cycle in the i-th time period, and n is the number of time periods;

[0075] ,in, Expressed as the standard deviation of the lifting weight in the jth operation cycle;

[0076] The calculation formula for the load fluctuation is:

[0077] ,in, It is expressed as the load fluctuation of the j-th operation cycle, reflecting the dynamic change of the load during the lifting process. Larger values ​​indicate more unstable loading.

[0078] The height control error change rate characteristic is as follows: the height control error change rate of each operation cycle of the lifting equipment is calculated by comparing the lifting height and the target height of each operation cycle of the lifting equipment, specifically:

[0079] ,in, Expressed as the rate of change of the height control error in the j-th operation cycle, It is expressed as the lifting height of the jth operation cycle in the i-th time period, Expressed as the target height in the i-th time period, It is expressed as the allowable error between the lifting height and the target height, reflecting the position control accuracy of the lifting process.

[0080] The wire rope bending health assessment features: According to the operation cycle, the wire rope micro-bend during the equipment operation is collected every t time periods. The wire rope bending health assessment of the lifting equipment is calculated based on the micro-bend and critical bending of the wire rope of the lifting equipment. Specifically,

[0081] ,in, It is expressed as the bending health assessment of the wire rope in the jth operating cycle in the i-th time period, It is expressed as the wire rope microbend of the j-th operation cycle in the i-th time period, It is expressed as critical bending, reflecting the health status of the wire rope at the current moment of the lifting process.

[0082] The lifting equipment health fusion analysis module is used to obtain the comprehensive evaluation index of the lifting equipment appearance defects, load fluctuation, height control error change rate and wire rope bending health evaluation of the lifting equipment, and obtain the health assessment coefficient of the lifting equipment according to the equipment health assessment model.

[0083] In one possible design, the steps for implementing the lifting equipment health fusion analysis module are as follows:

[0084] S01: Obtain the comprehensive evaluation index of the appearance defects of the lifting equipment in each time period, the load fluctuation of each operation cycle, the height control error change rate of each operation cycle, and the wire rope bending health evaluation in each operation cycle time period, and perform parameter normalization processing.

[0085] S02: Obtain the normalized comprehensive evaluation index of appearance defects of the lifting equipment, load fluctuation, height control error change rate, and wire rope bending health assessment, and obtain the health assessment coefficient of the lifting equipment based on the set equipment health assessment model.

[0086] In this embodiment, it should be specifically noted that the lifting equipment health fusion analysis module further includes:

[0087] S01: Parameter normalization processing, specifically:

[0088]

[0089] in, It is expressed as the normalized value of the comprehensive evaluation index of the appearance defects of lifting equipment. It is expressed as the comprehensive evaluation index of appearance defects of lifting equipment in the i-th time period, It is expressed as the maximum value of the comprehensive evaluation index of the appearance defects of lifting equipment. It is expressed as the minimum value of the comprehensive evaluation index of lifting equipment appearance defects;

[0090]

[0091] in, Expressed as the normalized value of load fluctuation, Expressed as the load fluctuation of the j-th operating cycle, Expressed as the minimum value of load fluctuation, Expressed as the maximum value of load fluctuation;

[0092]

[0093] in, Expressed as the normalized value of the rate of change of height control error, Expressed as the rate of change of the height control error in the j-th operation cycle, Expressed as the minimum value of the rate of change of altitude control error, Expressed as the maximum value of the rate of change of altitude control error.

[0094] ,in, Expressed as the normalized value of wire rope bending health assessment, It is expressed as the bending health assessment of the wire rope in the jth operating cycle in the i-th time period, It is expressed as the minimum value of the wire rope bending health assessment, Expressed as the maximum value for the wire rope bending health assessment.

[0095] S02: The calculation formula of the health assessment coefficient is:

[0096]

[0097] in, Expressed as the health assessment coefficient, 、 、 、 are respectively expressed as weight factors of each normalized value, and + + + =1.

[0098] The lifting equipment abnormality detection module obtains the health assessment coefficient of the lifting equipment, compares it with the preset health assessment coefficient, and classifies the lifting equipment status according to the health assessment coefficient deviation of the lifting equipment.

[0099] In one possible design, the lifting equipment abnormality detection module is specifically:

[0100] Obtain the health assessment coefficient of the lifting equipment, compare it with the preset health assessment coefficient, and obtain the health assessment coefficient deviation of the lifting equipment. Match the health assessment coefficient deviation value with the lifting equipment status level classification standard, and divide the lifting equipment into four equipment status levels: healthy, warning, abnormal, and faulty. Push the equipment status level of the lifting equipment to relevant personnel to maintain the lifting equipment.

[0101] The digital twin modeling module builds a virtual model based on the actual physical structure and operating parameters of the lifting equipment, and updates the operating status and health of the equipment by receiving real-time equipment appearance images and equipment operating parameter data.

[0102] See also Figure 2 As shown, a method for monitoring the health of port lifting equipment includes the following steps:

[0103] Step S01: Demarcate the drone inspection area at the port, use adaptive flight path planning technology and adjust the shooting angle and distance according to the equipment structure to collect equipment appearance images every t time period;

[0104] Step S02: Obtain all defect information in the lifting equipment appearance image collected in the i-th time period, calculate the lifting equipment appearance defect comprehensive evaluation index in the i-th time period based on the defect area, and process the information;

[0105] Step S03: collecting equipment operating parameters of each operation cycle of the lifting equipment through sensors, wherein a single lifting cycle is one cycle, and the equipment operating parameters include lifting weight, lifting height, and wire rope microbend;

[0106] Step S04: obtaining the equipment operating parameters of each operation cycle of the lifting equipment, calculating the load fluctuation, height control error change rate and wire rope bending health assessment characteristics of the lifting equipment, and establishing a health status characteristic early warning;

[0107] Step S05: obtaining a comprehensive evaluation index of appearance defects of the lifting equipment, load fluctuation, height control error change rate, and wire rope bending health evaluation of the lifting equipment, and obtaining a health evaluation coefficient of the lifting equipment according to an equipment health evaluation model;

[0108] Step S06: Obtaining a health assessment coefficient of the lifting equipment, comparing it with a preset health assessment coefficient, and classifying the state of the lifting equipment according to the health assessment coefficient deviation of the lifting equipment;

[0109] Step S07: Build a virtual model based on the actual physical structure and operating parameters of the lifting equipment, and update the operating status and health of the equipment by receiving the equipment appearance image and equipment operating parameter data in real time.

[0110] In this embodiment, it should be specifically explained that the present invention demarcates the drone inspection area in the port, uses adaptive flight path planning technology and adjusts the shooting angle and distance according to the equipment structure, collects equipment appearance images every t time periods, and calculates the comprehensive evaluation index of the lifting equipment appearance defects in the i-th time period through all defect information in the lifting equipment appearance image and the defect area, and compares it with the preset comprehensive evaluation index of the lifting equipment appearance defects. If the comprehensive evaluation index of the lifting equipment appearance defects at this moment is greater than the preset comprehensive evaluation index of the lifting equipment appearance defects, it indicates that the appearance defects of the lifting equipment at this moment are serious, and the lifting equipment at this moment is extracted. The equipment appearance image corresponds to the position of the lifting equipment, and the lifting equipment appearance image is sent to the maintenance personnel for maintenance operations. Conversely, the better the appearance monitoring of the lifting equipment at that moment, the better. The equipment operating parameters of each operation cycle of the lifting equipment are collected through sensors, and the load fluctuation, height control error change rate and wire rope bending health assessment characteristics of the lifting equipment are calculated. The health status feature early warning is established. Through the fusion of drone inspection and sensor data, comprehensive monitoring of the equipment appearance and operating status is achieved, the accuracy and coverage of data collection are improved, and analysis and judgment based on data make the formulation of maintenance plans more scientific and reasonable.

[0111] The present invention obtains a comprehensive evaluation index of appearance defects of the lifting equipment, load fluctuation, height control error change rate and wire rope bending health evaluation of the lifting equipment, performs parameter normalization processing, and further obtains a health assessment coefficient of the lifting equipment based on a set equipment health assessment model, obtains the health assessment coefficient of the lifting equipment, compares it with the preset health assessment coefficient, and obtains the health assessment coefficient deviation of the lifting equipment. According to the health assessment coefficient deviation value and the lifting equipment status level classification standard, the lifting equipment is divided into four equipment status levels of health, warning, abnormality and failure, and the equipment status level of the lifting equipment is pushed to relevant personnel. The lifting equipment is maintained, a virtual model is constructed, and equipment appearance images and equipment operating parameter data are received in real time to update the equipment's operating status and health status, realizing a multi-dimensional comprehensive evaluation of the lifting equipment. The health assessment coefficient is obtained based on the equipment health assessment model. The quantitative evaluation and comparison method makes the equipment health status judgment more objective and intuitive, and can accurately locate the degree to which the equipment deviates from the normal state, thereby realizing precise maintenance. The introduction of digital twin technology can map the equipment operating status in real time, providing precise support for fault warning and maintenance decision-making.

[0112] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A port crane equipment health monitoring system, characterized in that: include: Drone inspection module: This module defines a drone inspection area within the port, uses adaptive flight path planning technology and adjusts the shooting angle and distance based on the equipment structure to capture images of the equipment's appearance at intervals of t. Lifting equipment appearance monitoring module: obtains all defect information in the lifting equipment appearance image collected in the i-th time period, calculates the comprehensive evaluation index of the lifting equipment appearance defects in the i-th time period based on the defect area, and processes it; The specific steps for implementing the lifting equipment appearance monitoring module are as follows: S41: Obtain all defect information in the lifting equipment appearance image collected in the i-th time period, and extract the area of ​​each defect in the image and the lifting equipment position; S42: calculating the comprehensive evaluation index of the lifting equipment appearance defects in the i-th time period based on the set appearance defect evaluation model according to the area of ​​each defect in the lifting equipment appearance image in the i-th time period; S43: Obtaining a comprehensive evaluation index of appearance defects of the lifting equipment in the i-th time period, and comparing it with a preset comprehensive evaluation index of appearance defects of the lifting equipment. If the comprehensive evaluation index of appearance defects of the lifting equipment in the i-th time period is greater than the preset comprehensive evaluation index of appearance defects of the lifting equipment, it indicates that the appearance defects of the lifting equipment in the time period are serious. The lifting equipment position corresponding to the appearance image of the lifting equipment in the time period is extracted, and the appearance image of the lifting equipment is sent to the maintenance personnel, who perform maintenance operations. Otherwise, it indicates that the appearance monitoring of the lifting equipment in the time period is better. The calculation formula for the comprehensive evaluation index of the lifting equipment appearance defects is: ,in, It is expressed as the comprehensive evaluation index of appearance defects of lifting equipment in the i-th time period, Expressed as the area of ​​the qth defect in the i-th time period, It is represented as the weight factor of the qth defect, and m is the total number of defects; Lifting equipment data acquisition module: collects equipment operating parameters of each operation cycle of the lifting equipment through sensors. The operation cycle is a single lifting cycle. The equipment operating parameters include lifting weight, lifting height, and wire rope microbend; Lifting equipment health status feature processing module: used to obtain equipment operating parameters for each operation cycle of the lifting equipment, calculate the load fluctuation of the lifting equipment, the rate of change of height control error and the wire rope bending health assessment characteristics, and establish health status feature early warning; Lifting equipment health fusion analysis module: used to obtain the comprehensive evaluation index of lifting equipment appearance defects, load fluctuation, height control error change rate and wire rope bending health assessment of the lifting equipment, and obtain the lifting equipment health assessment coefficient based on the equipment health assessment model; Lifting equipment anomaly detection module: obtains the health assessment coefficient of the lifting equipment, compares it with the preset health assessment coefficient, and classifies the lifting equipment status according to the deviation of the health assessment coefficient of the lifting equipment; Digital twin modeling module: Builds a virtual model based on the actual physical structure and operating parameters of the lifting equipment, and updates the equipment's operating status and health by receiving real-time equipment appearance images and equipment operating parameter data.

2. A port crane equipment health monitoring system according to claim 1, characterized in that: The specific steps for implementing the drone inspection module are as follows: S21: Designate drone inspection areas at the port, design inspection routes for each crane using adaptive flight path planning technology, and set take-off points, inspection routes, and return points. S22: Equip the drone with a high-resolution camera to capture images of the crane's exterior every t time periods. Simultaneously, a light sensor in the drone's environmental perception unit monitors ambient light intensity. According to a preset light intensity-light source adjustment strategy, the angle and intensity of the light source are flexibly adjusted. Each time period is sequentially numbered 1, 2, ..., i, ..., n. S23: Establish a normal state image database and a defect state image database, match the collected equipment appearance image with the normal state image database and the defect state image database, traverse all defect information in the lifting equipment appearance image, and perform defect data annotation.

3. The port crane equipment health monitoring system according to claim 1, characterized in that: The adaptive flight path planning technology is based on the distribution of key monitoring points of the equipment structure and combines the navigation function of the three-dimensional geographic information system to plan the drone inspection flight route to ensure comprehensive and efficient inspection coverage.

4. The port crane equipment health monitoring system according to claim 1, characterized in that: The lifting equipment data acquisition module is specifically: The strain gauge load cell installed on the lifting equipment collects the lifting weight during operation at intervals of t according to the operation cycle. The position sensor installed on the lifting equipment collects the vertical displacement of the equipment during operation at intervals of t according to the operation cycle to obtain the lifting height. The laser sensor for detecting micro-bend of the wire rope is installed on the lifting equipment. The micro-bend of the wire rope during the operation of the equipment is collected every t time periods according to the operation cycle.

5. The port crane equipment health monitoring system according to claim 1, characterized in that: The specific steps for implementing the lifting equipment health status feature processing module are as follows: S51: Load Fluctuation Characteristics: By calculating the mean and standard deviation of the lifting weight of each operation cycle of the lifting equipment, and based on the ratio of the standard deviation of the lifting weight to the mean, the load fluctuation of each operation cycle of the lifting equipment is calculated. By obtaining the load fluctuation of each operation cycle of the lifting equipment, it is compared with the preset load fluctuation. If the load fluctuation of a certain operation cycle is greater than the preset load fluctuation, it indicates that the load fluctuation of the lifting equipment is abnormal, and the management personnel should be notified to check the equipment. Otherwise, it indicates that the load of the lifting equipment is normal. S52: Height control error change rate feature: Calculate the height control error change rate of each operation cycle of the lifting equipment based on the lifting height and the target height. The height control error change rate of each operation cycle of the lifting equipment is obtained and compared with a preset height control error change rate. If the height control error change rate of a certain operation cycle is greater than the preset height control error change rate, it indicates that the lifting equipment control system is faulty and the management personnel should be notified to check the equipment. Otherwise, it indicates that there is no abnormality in the lifting equipment control system. S53: Wire rope bending health assessment features: According to the operation cycle, the micro-bending of the wire rope during the equipment operation process is collected every t time periods. The bending health assessment of the wire rope of the lifting equipment is calculated based on the micro-bending and critical bending of the wire rope of the lifting equipment. The obtained bending health assessment of the wire rope of the lifting equipment is compared with the preset bending health assessment of the wire rope. If the bending health assessment of the wire rope in a certain time period is less than the preset bending health assessment and is greater than or equal to 0, it indicates that the wire rope of the lifting equipment is damaged and the management personnel should be notified to check the equipment. If the bending health assessment of the wire rope in a certain time period is less than 0, it indicates that the bending health of the wire rope of the lifting equipment exceeds the safety limit and an emergency shutdown is immediately performed. Otherwise, it indicates that there is no abnormality in the bending health assessment of the wire rope of the lifting equipment.

6. The port crane equipment health monitoring system according to claim 1, characterized in that: The specific steps for implementing the lifting equipment health fusion analysis module are as follows: S61: Obtain the comprehensive evaluation index of the appearance defects of the lifting equipment in each time period, the load fluctuation of each operation cycle, the height control error change rate of each operation cycle, and the wire rope bending health evaluation in each operation cycle time period, and perform parameter normalization processing; S62: Obtain the normalized comprehensive evaluation index of appearance defects of the lifting equipment, load fluctuation, height control error change rate, and wire rope bending health assessment, and obtain the health assessment coefficient of the lifting equipment based on the set equipment health assessment model.

7. The port crane equipment health monitoring system according to claim 1, characterized in that: The lifting equipment abnormality detection module is specifically: Obtain the health assessment coefficient of the lifting equipment, compare it with the preset health assessment coefficient, and obtain the health assessment coefficient deviation of the lifting equipment. Match the health assessment coefficient deviation value with the lifting equipment status level classification standard, and divide the lifting equipment into four equipment status levels: healthy, warning, abnormal, and faulty. Push the equipment status level of the lifting equipment to relevant personnel to maintain the lifting equipment.

8. A method for monitoring the health of port crane equipment, using a port crane equipment health monitoring system according to any one of claims 1 to 7, characterized in that: The following steps are involved: Step S01: Demarcate the drone inspection area at the port, use adaptive flight path planning technology and adjust the shooting angle and distance according to the equipment structure to collect equipment appearance images every t time period; Step S02: Obtain all defect information in the lifting equipment appearance image collected in the i-th time period, calculate the lifting equipment appearance defect comprehensive evaluation index in the i-th time period based on the defect area, and process the information; Step S03: collecting equipment operating parameters of each operation cycle of the lifting equipment through sensors, wherein a single lifting cycle is one cycle, and the equipment operating parameters include lifting weight, lifting height, and wire rope microbend; Step S04: obtaining the equipment operating parameters of each operation cycle of the lifting equipment, calculating the load fluctuation, height control error change rate and wire rope bending health assessment characteristics of the lifting equipment, and establishing a health status characteristic early warning; Step S05: obtaining a comprehensive evaluation index of appearance defects of the lifting equipment, load fluctuation, height control error change rate, and wire rope bending health evaluation of the lifting equipment, and obtaining a health evaluation coefficient of the lifting equipment according to an equipment health evaluation model; Step S06: Obtaining a health assessment coefficient of the lifting equipment, comparing it with a preset health assessment coefficient, and classifying the state of the lifting equipment according to the health assessment coefficient deviation of the lifting equipment; Step S07: Build a virtual model based on the actual physical structure and operating parameters of the lifting equipment, and update the operating status and health of the equipment by receiving the equipment appearance image and equipment operating parameter data in real time.

Images