Maintenance system for high-altitude operation machine and high-altitude operation machine

Abstract

The embodiment of the invention provides a maintenance system for a high-altitude operation machine and the high-altitude operation machine. The maintenance system comprises a data acquisition module used for acquiring operation data of the high-altitude operation machine in real time, the operation data at least comprising operation data, electrical data and hydraulic data of the high-altitude operation machine; the service life detection module is used for determining a real-time damage value corresponding to the operation data based on a fatigue damage library and determining the residual service life of the execution mechanism based on the real-time damage value, and the fatigue damage library comprises a plurality of corresponding relations between the operation data and the damage value of the execution mechanism, the corresponding relation is obtained by performing fatigue test training according to a plurality of historical operation data meeting a preset condition; and the monitoring module is used for analyzing and processing the electrical data and the hydraulic data to obtain the current operation state of the high-altitude operation machine, and determining the fault type of the high-altitude operation machine based on the electrical data and the hydraulic data under the condition that the high-altitude operation machine breaks down.

Description

Technical Field

[0001] The present application relates to the technical field of engineering machinery, and in particular to a maintenance system for aerial work machinery and the aerial work machinery. Background Art

[0002] Aerial work machinery is an important branch of the field of engineering machinery. It is a general term for mechanical equipment used to transport workers and equipment to a designated height for work. Aerial work machinery is a complex mechanical equipment with interrelated and simultaneous structural, electrical and hydraulic systems. The fatigue life of any structure or the state of the system are important factors affecting the safety of the entire machine. Real-time monitoring of aerial work machinery, issuing alarms when the structure life is insufficient or the system fails, and reminding users to perform maintenance in a timely manner can effectively protect the lives of aerial workers.

[0003] In the prior art, the finite element method is usually used to calculate the multi-channel and multi-posture unit force damage library and to arrange a pin sensor at each hinge point of the equipment to obtain the hinge force in real time to calculate the damage and life in real time. However, this method is only suitable for monitoring the fatigue life of a certain local structure of the equipment, and is not suitable for predicting the life of aerial work machinery with complex structures. Therefore, how to accurately predict the remaining life of aerial work machinery and monitor the operating status of aerial work machinery at the same time is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a maintenance system for aerial work machinery and an aerial work machinery, so as to solve the technical defect in the prior art that the operating status of the aerial work machinery and the fatigue life of each mechanism component cannot be accurately monitored in real time.

[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a maintenance system for an aerial work machine, the aerial work machine includes a plurality of actuators, and the maintenance system includes:

[0006] A data acquisition module is used to obtain the operation data of the aerial work machine in real time, and the operation data at least includes the operation data, electrical data and hydraulic data of the aerial work machine;

[0007] A life detection module, used to determine a real-time damage value corresponding to the operating data based on a fatigue damage library, and determine the remaining life of the actuator based on the real-time damage value, wherein the fatigue damage library includes a correspondence between a plurality of operating data and the damage value of the actuator, and the correspondence is obtained after fatigue test training based on a plurality of historical operating data that meet preset conditions;

[0008] The monitoring module is used to analyze and process the electrical data and the hydraulic data to obtain the current operating status of the aerial work machinery, which operating status includes any one of normal and faulty. When a fault occurs in the aerial work machinery, the fault type of the aerial work machinery is determined based on the electrical data and the hydraulic data.

[0009] In an embodiment of the present application, the maintenance system further includes: a fatigue damage library construction module, which is used to perform fatigue test training based on a plurality of historical operating data that meet preset conditions to construct a fatigue damage library.

[0010] In an embodiment of the present application, the fatigue damage library construction module is also used to: obtain multiple historical operation data of the aerial work machinery within a historical time period, the multiple historical operation data including multiple historical torques and multiple historical operation angles of the actuator; for multiple historical operation angles, determine the cumulative number of occurrences of each historical operation angle within the historical time period; eliminate historical operation angles whose cumulative number of occurrences is lower than a preset number threshold, and determine the remaining historical operation angles as target operation angles that meet preset conditions; analyze multiple historical torques, and screen out target torques that meet the preset conditions; generate fatigue test conditions based on the target operating angles and target torques; for any fatigue test condition, repeat fatigue test training for the fatigue test condition until fatigue cracks exist in the actuator under the fatigue test condition, and determine the number of training times for the fatigue test condition as the fatigue life of the actuator under the fatigue test condition; determine the damage value corresponding to each fatigue test condition based on the fatigue life of the actuator under each fatigue test condition, and construct a fatigue damage library based on the correspondence between each fatigue test condition and the damage value.

[0011] In an embodiment of the present application, analyzing multiple historical moments and screening out target moments that meet preset conditions includes: performing normal distribution analysis on multiple historical moments to obtain a normal distribution graph for multiple historical moments; based on the normal distribution graph, eliminating historical moments outside a preset interval, and determining the remaining historical moments as target moments that meet the preset conditions.

[0012] In an embodiment of the present application, generating fatigue test conditions based on target operating angles and target torques includes: for each target operating angle, combining the target operating angle with all other target operating angles except the target operating angle in turn to obtain multiple angle groups; sorting all target torques in ascending order to obtain torque intervals for all target torques; dividing the torque interval into multiple continuous sub-torque intervals based on a preset division ratio; combining each sub-torque interval with each angle group in turn to generate corresponding multiple fatigue test conditions.

[0013] In an embodiment of the present application, the fatigue damage library construction module is also used to: obtain multiple historical operation data of the aerial work machinery within a historical time period, the historical operation data including multiple historical load data of the actuator and multiple historical operation data of the actuator, wherein the multiple historical operation data include multiple historical operation heights and multiple historical operation ranges of the actuator; determine the area that the actuator can reach at multiple historical operation heights and multiple historical operation ranges, and divide the area into multiple operation areas, and define an area number for each operation area; for multiple historical operation data, determine the area number where each historical operation data is located, and determine the cumulative number of occurrences of each area number within the historical time period; eliminate the areas with a cumulative number of occurrences lower than a preset number. The historical area numbers of the threshold value are obtained, and the operation areas corresponding to the remaining historical area numbers are determined as the target operation areas that meet the preset conditions; multiple historical loads are analyzed, and the target loads that meet the preset conditions are screened out; fatigue test conditions are generated based on the target operation areas and the target loads; for any fatigue test condition, fatigue test training is repeated for the fatigue test condition until fatigue cracks exist in the actuator under the fatigue test condition, and the number of training times for the fatigue test condition is determined as the fatigue life of the actuator under the fatigue test condition; the damage value corresponding to each fatigue test condition is determined based on the fatigue life of the actuator under each fatigue test condition, and a fatigue damage library is constructed based on the correspondence between each fatigue test condition and the damage value.

[0014] In an embodiment of the present application, multiple historical loads are analyzed and target loads that meet preset conditions are screened out, including: performing normal distribution analysis on multiple historical loads to obtain a normal distribution graph for multiple historical loads; based on the normal distribution graph, historical loads outside a preset interval are eliminated, and the remaining historical loads are determined as target loads that meet the preset conditions.

[0015] In an embodiment of the present application, generating fatigue test conditions based on the target operating angle and the target torque includes: for each target operating area, combining the target operating area with all other target operating areas except the target operating area in turn to obtain multiple operating area groups; sorting all target loads in ascending order to obtain load intervals for all target loads; dividing the load interval into multiple continuous sub-load intervals based on a preset division ratio; combining each sub-load interval with each operating area group in turn to generate corresponding multiple fatigue test conditions.

[0016] In an embodiment of the present application, the maintenance system also includes: an alarm module, which is used to generate a corresponding alarm signal when the remaining life of any actuator is lower than a preset threshold or a failure of the aerial work machinery occurs; an operation and maintenance module, which is used to generate and push an operation and maintenance plan corresponding to the alarm signal when the alarm module generates an alarm signal.

[0017] In an embodiment of the present application, the monitoring module includes: a state detection module, which is used to analyze and process electrical data and hydraulic data to obtain the current operating state of the aerial work machinery, the electrical data at least includes the rotor position data, speed data and temperature data of the motor, and the hydraulic data at least includes the pressure data and flow data of the hydraulic pump. When any one of the electrical data and the hydraulic data is in an abnormal state, it is determined that the aerial work machinery has a fault, wherein the operating state includes any one of normal and faulty; a fault detection module, which is used to output corresponding data labels based on the electrical data and the hydraulic data when the aerial work machinery fails, and determine the fault type corresponding to the data label based on the data label library, wherein the data label library includes multiple labels and fault types corresponding to each label, and the fault type includes at least one of rotor bar broken fault, stator fault, bearing fault, cylinder wear, oil leakage and bearing wear.

[0018] The second aspect of the present application provides an aerial work machine, comprising:

[0019] The above-mentioned maintenance system for aerial work machinery;

[0020] Multiple actuators.

[0021] The above technical scheme provides a maintenance system for aerial work machinery, including a data acquisition module for acquiring the operation data of the aerial work machinery in real time, the operation data at least including the operating data, electrical data and hydraulic data of the aerial work machinery; a life detection module for determining the real-time damage value corresponding to the operating data based on a fatigue damage library, and determining the remaining life of the actuator based on the real-time damage value, the fatigue damage library including a correspondence between a plurality of operating data and the damage value of the actuator, wherein the correspondence is obtained after fatigue test training based on a plurality of historical operating data that meet preset conditions; a monitoring module for analyzing and processing the electrical data and the hydraulic data to obtain the current operating status of the aerial work machinery, and in the event of a failure of the aerial work machinery, determining the fault type of the aerial work machinery based on the electrical data and the hydraulic data, thereby realizing real-time and accurate monitoring of the operating status of the aerial work machinery and the fatigue life of each actuator component.

[0022] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0024] Figure 1 The schematic diagram of the structure of an aerial work machine according to an embodiment of the present application is shown;

[0025] Figure 2 The schematic diagram shows the structure of another aerial work machine according to an embodiment of the present application;

[0026] Figure 3 The schematic diagram of the structure of another aerial work machine according to an embodiment of the present application is shown;

[0027] Figure 4 The schematic diagram shows a structure of a maintenance system for aerial work machinery according to an embodiment of the present application;

[0028] Figure 5 The schematic diagram shows the structure of another maintenance system for aerial work machinery according to an embodiment of the present application;

[0029] Figure 6 A schematic diagram of a process for building a digital twin model according to an embodiment of the present application is schematically shown;

[0030] Figure 7 A schematic diagram of a normal distribution diagram according to an embodiment of the present application is schematically shown;

[0031] Figure 8 A schematic diagram of a torque interval according to an embodiment of the present application is schematically shown;

[0032] Fig. 9 A schematic diagram of dividing a work area according to an embodiment of the present application is schematically shown;

[0033] Fig.10 A schematic diagram of a load range according to an embodiment of the present application is schematically shown;

[0034] Fig.11 The system architecture diagram of a maintenance system according to an embodiment of the present application is schematically shown.

[0035] Description of Reference Numerals

[0036] 101 chassis 102 first scissor arm

[0037] 103 Second scissor arm 104 Angle sensor

[0038] 105 torque sensor 106 motor

[0039] 107 Hydraulic pump 108 Cylinder

[0040] 109 Work Platform

[0041] 201 chassis 202 arm

[0042] 203 Leg 204 Angle sensor

[0043] 205 torque sensor 206 motor

[0044] 207 Hydraulic pump 208 Subframe

[0045] 209 Turntable 210 Working Platform

[0046] 301 chassis 302 first boom

[0047] 303 second arm 304 equivalent position sensor

[0048] 305 weighing sensor 306 engine

[0049] 307 Hydraulic pump 308 Fork DETAILED DESCRIPTION

[0050] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0051] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0052] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0053] The maintenance system for aerial work machinery provided in this application can be applied to Figure 1 In the application environment shown in the figure, Figure 1 As shown, a schematic diagram of the structure of an aerial work machine is provided, and the aerial work machine includes:

[0054] Chassis 101 , first scissor arm 102 , second scissor arm 103 , angle sensor 104 , torque sensor 105 , motor 106 , hydraulic pump 107 , oil cylinder 108 , working platform 109 .

[0055] In this embodiment, it should be noted that the aerial work machinery may refer to a scissor-type aerial work platform, for example, it may include a single-stage single-cylinder scissor-type aerial work platform. Specifically, the single-stage single-cylinder scissor-type aerial work platform includes a first scissor arm 102 and a second scissor arm 103 that are cross-connected, and one end of the first scissor arm 102 and the second scissor arm 103 is fixed to the chassis 101, and the other end is fixed to the work platform 109. The connection positions of the first scissor arm 102 and the second scissor arm 103 and the work platform 109 are both installed with a torque sensor 105, and the torque sensor 105 can be used to collect the torque of the corresponding scissor arm in real time, wherein, since the torque sensor 105 collects the torque of the connection position between the scissor arm and the work platform 109, and the pressure on the connection position is applied by the load borne by the work platform 109, therefore, the torque of the scissor arm collected by the torque sensor 105 can be the load of the work platform 109. The angle sensor 104 is installed at any position on any scissor arm, and is used to collect the operating angle of the corresponding scissor arm in real time.

[0056] The oil cylinder 108 is installed between the first scissor arm 102 and the second scissor arm 103, and is used to provide energy consumption for lifting the first scissor arm 102 and the second scissor arm 103. The chassis 101 is installed with a motor 106 and a hydraulic pump 107, wherein the motor 106 is arranged with a plurality of sensors, which may include a position sensor, a speed sensor and a temperature sensor to collect electrical data of the motor 106 in real time, and the hydraulic pump 107 is arranged with a plurality of sensors, which may include a pressure sensor and a flow sensor to collect hydraulic data of the hydraulic pump 107 in real time.

[0057] The aerial work platform 109 can be used to carry workers and work equipment. The first scissor arm 102 and the second scissor arm 103 can drive the aerial work platform 109 to rise through a lifting action, so as to transport the workers and work equipment to a target height.

[0058] The maintenance system for aerial work machinery provided in this application can be applied to Figure 2 In the application environment shown in the figure, Figure 2 As shown, a structural schematic diagram of another aerial work machine is provided, and the aerial work machine includes:

[0059] Chassis 201 , boom 202 , multiple legs 203 , angle sensor 204 , torque sensor 205 , motor 206 , hydraulic pump 207 , subframe 208 , turntable 209 , and work platform 210 .

[0060] In this embodiment, it should be noted that the aerial work machine may refer to a telescopic boom aerial work vehicle. Specifically, the main structure of the telescopic boom aerial work vehicle includes, from bottom to top, a plurality of legs 203, a chassis 201, a subframe 208, a turntable 209, a boom 202, and a work platform 210. The boom 202 is a telescopic segmented boom, a first end of the boom 202 is fixed to the chassis through a state 209, and the other end is fixed to the work platform 210.

[0061] An angle sensor 204 is installed on the bottom plate of the turntable 209 to collect the operating angle of the boom 202 in real time. The turntable 209 has a built-in motor 206, wherein the motor 206 is arranged with multiple sensors, which may include a current sensor, a temperature sensor, and a speed sensor to collect the electrical data of the motor 206 in real time. A hydraulic pump 207 is installed in the chassis 201, wherein the hydraulic pump 207 is arranged with multiple sensors, which may include a pressure sensor and a flow sensor to collect the hydraulic data of the hydraulic pump 207 in real time.

[0062] The sub-frame 208 is connected to a plurality of legs 203 , and a torque sensor 205 is installed at the support position of the leg 203 to collect the torque of the leg 203 in real time, wherein the torque of the leg 203 may refer to the leg reaction force of the leg 203 .

[0063] The aerial work platform 210 can be used to carry a target object, and the boom 202 can drive the aerial work platform 210 to rise through a lifting action, so as to transport the target object to a target height.

[0064] The maintenance system for aerial work machinery provided in this application can be applied to Figure 3 In the application environment shown in the figure, Figure 3 As shown, a schematic diagram of the structure of another aerial work machine is provided, and the aerial work machine includes:

[0065] Chassis 301 , first arm 302 , second arm 303 , relative position sensor 304 , weighing sensor 305 , engine 306 , hydraulic pump 307 , fork 308 .

[0066] In this embodiment, it should be noted that the aerial work machinery may refer to a telescopic forklift as an aerial work vehicle, for example, a telescopic forklift. Specifically, the main structure of the telescopic forklift includes a chassis 301, a boom and a fork 308 from bottom to top. Among them, the boom is a telescopic segmented boom, including a first boom 302 and a second boom 303 embedded with the first boom 302, one end of the first boom 302 is fixed to the chassis 301, the second end is embedded with one end of the second boom 303, and the other end of the second boom 303 is connected to the fork 308. A relative position sensor 304 is arranged between the front end of the fork 308 and the front end of the frame on the chassis 301 to collect the working height and working range of the boom in real time, and a weighing sensor 305 is arranged at the connection position between the fork 308 and the second boom 303 to collect the load of the fork 308 in real time.

[0067] An engine 306 and a hydraulic pump 307 are installed in the chassis 301, wherein the engine 306 is provided with a plurality of sensors, which may include a speed sensor and a temperature sensor to collect electrical data of the engine 306 in real time, and the hydraulic pump 307 is provided with a plurality of sensors, which may include a pressure sensor and a flow sensor to collect hydraulic data of the hydraulic pump 307 in real time.

[0068] The fork 308 can be used to carry the target object, and the first arm 302 and the second arm 303 can drive the fork 308 to lift through a lifting action, so as to transport the target object to a target height.

[0069] Figure 4 The schematic diagram of the structure of a maintenance system for aerial work machinery according to an embodiment of the present application is shown schematically. Figure 4 As shown, the embodiment of the present application provides a maintenance system for aerial work machinery, which can be applied to Figure 1 , Figure 2 as well as Figure 3 For aerial work machinery, the maintenance system can include the following modules.

[0070] The data acquisition module 410 is used to obtain the operation data of the aerial work machine in real time, and the operation data at least includes the operation data, electrical data and hydraulic data of the aerial work machine;

[0071] The life detection module 420 is used to determine the real-time damage value corresponding to the operation data based on the fatigue damage library, and determine the remaining life of the actuator based on the real-time damage value, wherein the fatigue damage library includes a correspondence between a plurality of operation data and the damage value of the actuator, and the correspondence is obtained after fatigue test training based on a plurality of historical operation data that meet preset conditions;

[0072] The monitoring module 430 is used to analyze and process the electrical data and the hydraulic data to obtain the current operating status of the aerial work machinery, which operating status includes any one of normal and faulty. When a fault occurs in the aerial work machinery, the fault type of the aerial work machinery is determined based on the electrical data and the hydraulic data.

[0073] In this embodiment, it should be noted that the aerial work machine includes multiple actuators, and the operation data of the aerial work machine may refer to the operation data of each actuator. The data acquisition module 410 may include multiple sensors, which are respectively deployed on the aerial work machine to collect the operation data, electrical data, and hydraulic data of the aerial work machine in real time through the multiple sensors.

[0074] Specifically, Figure 1 Taking the application scenario shown as an example, the actuator of the aerial work machinery includes a scissor arm, and the operating data such as the operating angle θ and torque F of the scissor arm can be obtained in real time by collecting the signal data of the arranged angle sensor and torque sensor. At the same time, the electrical data of the aerial work machinery can be obtained in real time through the position sensor, speed sensor and temperature sensor installed on the motor. Specifically, the electrical data may include the rotor position data U, the motor speed data V and the motor temperature data T of the motor. In addition, the hydraulic data of the aerial work machinery can be obtained in real time through the pressure sensor and flow sensor installed on the hydraulic pump. Specifically, the hydraulic data may include the hydraulic pump pressure P and the hydraulic pump flow Q.

[0075] Specifically, Figure 2Taking the application scenario shown as an example, the actuator of the aerial work machinery includes a boom and multiple legs. The operating angle θ of the boom and the torque F (f1, f2, f3, f4) of the multiple legs can be acquired in real time by collecting the signal data of the arranged angle sensor and torque sensor. At the same time, the first electrical data of the aerial work machinery can be acquired in real time by the current sensor, speed sensor and temperature sensor installed on the motor. Specifically, the first electrical data may include the current data I of the motor, the speed data V of the motor and the temperature data T of the motor. In addition, the first hydraulic data of the aerial work machinery can be acquired in real time by the pressure sensor and flow sensor installed on the hydraulic pump. Specifically, the hydraulic data may include the hydraulic pump pressure P and the hydraulic pump flow Q.

[0076] Specifically, Figure 3 Taking the application scenario shown as an example, the aerial work machinery includes a boom and a fork. The operating data such as the boom's operating height H, operating range L, and fork's load M can be obtained in real time by collecting the signal data of the relative position sensor and the weighing sensor. At the same time, the electrical data of the aerial work machinery can be obtained in real time through the speed sensor and temperature sensor installed on the engine. Specifically, the electrical data can include the engine's rotor engine speed data V and the engine temperature data T. In addition, the hydraulic data of the aerial work machinery can be obtained in real time through the pressure sensor and flow sensor installed on the hydraulic pump. Specifically, the hydraulic data can include the hydraulic pump pressure P and the hydraulic pump flow Q.

[0077] In this embodiment, it should be noted that after the data acquisition module 410 collects the operating data of the aerial work machinery, the life detection module 420 will determine the real-time damage value corresponding to the operating data based on the fatigue damage library, and determine the remaining life of the actuator based on the real-time damage value, wherein the fatigue damage library includes a correspondence between multiple operating data and the damage values ​​of the actuator, and the correspondence is obtained after fatigue test training based on multiple historical operating data that meet preset conditions.

[0078] In this embodiment, Figure 1Taking the application scenario shown as an example, the fatigue damage library includes the correspondence between multiple operating angles and moments and the damage values ​​of the scissor arms, and each set of correspondence has a corresponding damage value, wherein the correspondence is obtained after fatigue test training based on multiple historical operating angles and historical moments that meet preset conditions, and the preset conditions can be set according to actual needs. Therefore, after obtaining the operating data of the scissor arm, the operating data can be matched with the fatigue damage library to determine which set of correspondences in the fatigue damage library the operating angle θ and moment F included in the operating data meet, and the damage value of the set of correspondences is determined as the real-time damage value corresponding to the operating data. Specifically, as shown in Table 1-1, a fatigue damage library is provided, which includes multiple sets of correspondences between operating angles and moments, and each set of correspondences has a corresponding damage value. For example (F1, θ 1 θ 2 ),(F1,θ 1 θ 3 ), (F1, θ 1 θ 2 ) corresponds to the damage value D1, (F1, θ 1 θ 3 ) corresponds to a damage value D2. Therefore, taking the obtained operation data T of the scissor arm as an example, the operation data T includes the torque F1, the operation angle θ 1 θ 3 , the corresponding relationship of the running data T can be matched through the fatigue damage library as (F1, θ 1 θ 3 ), then (F1, θ 1 θ 3 ) is determined as the real-time damage value Dnow corresponding to the operating data T.

[0079] Table 1-1 Fatigue damage library

[0080] Torque\operating angle <![CDATA[θ 1 i 2 ]]> <![CDATA[θ 1 i 3 ]]> …… <![CDATA[θ m-1 i m ]]> F1 D1 D2 …… …… F2 …… …… …… …… …… …… …… …… …… Fj …… …… …… DK

[0081] It should be noted that the data information of any model of aerial work machinery will be stored in the remote server. Therefore, the historical cumulative damage value Dtot-last of the scissor arm of the aerial work machinery can be obtained from the remote server through the model information of the aerial work machinery. At the same time, the total life Ttot of the scissor arm of the aerial work machinery can also be obtained. After determining the real-time damage value of the scissor arm under the current operating data based on the fatigue damage library, and obtaining the current historical cumulative damage value of the scissor arm based on the remote server, the real-time cumulative damage value Dtot=Dtot-last+Dnow can be determined based on the sum of the historical cumulative damage value Dtot-last and the real-time damage value Dnow, and the inverse of the real-time cumulative damage value 1 / Dtot is taken as the current cumulative consumed life TD=1 / Dtot. Therefore, the remaining life Tr=Ttot.-TD=Ttot-1 / Dtot of the scissor arm can be further calculated based on the total life Ttot of the scissor arm and the cumulative consumed life TD.

[0082] In this embodiment, Figure 2 Taking the application scenario shown as an example, it should be noted that the fatigue damage library includes a plurality of correspondences between operating angles and torques and the damage values ​​of the boom, and each set of correspondences has a corresponding damage value, wherein the correspondences are obtained after fatigue test training based on a plurality of historical operating angles and historical torques that meet preset conditions, and the preset conditions can be set according to actual needs. Therefore, after obtaining the operating data of the boom, the operating data can be matched with the fatigue damage library to determine which set of correspondences in the fatigue damage library the operating angle θ and torque F (f1, f2, f3, f4) included in the operating data meet, and the damage value of the set of correspondences is determined as the real-time damage value corresponding to the operating data. Specifically, as shown in Table 1-2, a fatigue damage library is provided, which includes a plurality of sets of correspondences between operating angles and torques, and each set of correspondences has a corresponding damage value. For example (F1(f1, f2, f3, f4), θ 1 θ 2 )、(F1(f1,f2,f3,f4),θ 1 θ 3 ), (F1(f1,f2,f3,f4),θ 1 θ 2 ) corresponds to the damage value D1, (F1(f1,f2,f3,f4), θ 1 θ 3 ) corresponds to a damage value D2. Therefore, taking the obtained boom operation data T as an example, the operation data T includes the moment F1 (f1, f2, f3, f4), the operation angle θ 1 θ 3, the corresponding relationship of the operation data T can be matched through the fatigue damage library as (F1(f1,f2,f3,f4),θ 1 θ 3 ), then we can convert (F1(f1,f2,f3,f4),θ 1 θ 3 ) is determined as the real-time damage value Dnow corresponding to the operating data T.

[0083] Table 1-2 Fatigue damage library

[0084] Torque\operating angle <![CDATA[θ 1 i 2 ]]> <![CDATA[θ 1 i 3 ]]> …… <![CDATA[θ m-1 i m ]]> F1(f1,f2,f3,f4) D1 D2 …… …… F2(f1,f2,f3,f4) …… …… …… …… …… …… …… …… …… Fj(f1,f2,f3,f4) …… …… …… DK

[0085] The data information of any model of aerial work machinery will be stored in the remote server. Therefore, the historical cumulative damage value Dtot-last of the boom of the aerial work machinery can be obtained from the remote server through the model information of the aerial work machinery. At the same time, the total life Ttot of the boom of the aerial work machinery can also be obtained. After determining the real-time damage value of the boom under the current operating data based on the fatigue damage library, and obtaining the current historical cumulative damage value of the boom based on the remote server, the real-time cumulative damage value Dtot=Dtot-last+Dnow can be determined based on the sum of the historical cumulative damage value Dtot-last and the real-time damage value Dnow, and the inverse of the real-time cumulative damage value 1 / Dtot is taken as the current cumulative consumed life TD=1 / Dtot. Therefore, the remaining life Tr=Ttot.-TD=Ttot-1 / Dtot of the boom can be further calculated based on the total life Ttot of the boom and the cumulative consumed life TD.

[0086] In this embodiment, Figure 3Taking the application scenario shown as an example, it should be noted that the fatigue damage library defines multiple operating areas and the damage value corresponding to each operating area, specifically, including the correspondence between multiple loads and operating areas and the damage value of the boom, and each set of correspondence has a corresponding damage value. Among them, multiple operating areas are divided according to the areas that the boom can reach under different historical operating heights and different historical operating ranges, and the damage value corresponding to each operating area is obtained by fatigue test training based on multiple historical loads of the fork in each operating area. Therefore, after obtaining the operation data of the boom, the operation data can be matched with the fatigue damage library to determine the target operating area N corresponding to the operating height H and operating range L of the boom included in the operation data in the fatigue damage library, and determine which set of correspondences in the fatigue damage library the target operating area N and the load M of the fork meet, and determine the damage value of the set of correspondences as the real-time damage value corresponding to the operation data. Specifically, as shown in Table 1-3, a fatigue damage library is provided, which includes the correspondence between multiple operating areas and loads, and each set of correspondences has a corresponding damage value. For example, (M1, N1N2), (M1, N1N3), (M1, N1N2) corresponding damage value is D1, (M1, N1N3) corresponding damage value is D2. Therefore, taking the acquired boom operation data T as an example, the operation data T includes the moment M1, the operation angle is N1N3, and the corresponding relationship of the operation data T can be matched to (M1, N1N3) through the fatigue damage library, and then the damage value D2 corresponding to (M1, N1N3) can be determined as the real-time damage value Dnow corresponding to the operation data T.

[0087] Table 1-3 Fatigue damage library

[0088] Loading\operating area N1N2 N1N3 …… Nm-1Nm M1 D1 D2 …… …… M2 …… …… …… …… …… …… …… …… …… Mj …… …… …… DK

[0089] The data information of any model of aerial work machinery will be stored in the remote server. Therefore, the historical cumulative damage value Dtot-last of the boom of the aerial work machinery can be obtained from the remote server through the model information of the aerial work machinery. At the same time, the total life Ttot of the boom of the aerial work machinery can also be obtained. After determining the real-time damage value of the boom under the current operating data based on the fatigue damage library, and obtaining the current historical cumulative damage value of the boom based on the remote server, the real-time cumulative damage value Dtot=Dtot-last+Dnow can be determined based on the sum of the historical cumulative damage value Dtot-last and the real-time damage value Dnow, and the inverse of the real-time cumulative damage value 1 / Dtot is taken as the current cumulative consumed life TD=1 / Dtot. Therefore, the remaining life Tr=Ttot.-TD=Ttot-1 / Dtot of the boom can be further calculated based on the total life Ttot of the boom and the cumulative consumed life TD.

[0090] In this embodiment, it should be noted that after the data acquisition module 410 acquires the electrical data and hydraulic data of the aerial work machine, the monitoring module 430 will perform pre-processing such as cleaning, normalization and segmentation on the acquired raw electrical data and hydraulic data in turn, and further analyze and process the pre-processed data to obtain the current operating status of the aerial work machine, so as to determine whether the aerial work machine is currently operating normally or has a fault. In the case of determining that the aerial work machine has a fault, the electrical data and hydraulic data are further processed to determine the fault type of the aerial work machine.

[0091] In the embodiments of the present application, Figure 5 As shown, the monitoring module 430 includes: a state detection module 432, which is used to analyze and process the electrical data and the hydraulic data to obtain the current operating state of the aerial work machinery, the electrical data at least includes the rotor position data, the speed data and the temperature data of the motor, and the hydraulic data at least includes the pressure data and the flow data of the hydraulic pump. When any one of the electrical data and the hydraulic data is in an abnormal state, it is determined that the aerial work machinery has a fault, wherein the operating state includes any one of normal and faulty; a fault detection module 434, which is used to output the corresponding data label based on the electrical data and the hydraulic data when the aerial work machinery fails, and determine the fault type corresponding to the data label based on the data label library, wherein the data label library includes a plurality of labels and the fault type corresponding to each label, and the fault type includes at least one of a broken rotor bar fault, a stator fault, a bearing fault, a cylinder wear, an oil leakage and a bearing wear.

[0092] In this embodiment, specifically, Figure 1 Taking the application scenario shown as an example, the electrical data of the aerial work machinery can be obtained in real time through the position sensor, speed sensor and temperature sensor installed on the motor. Specifically, the electrical data may include the rotor position data U, the motor speed data V and the motor temperature data T of the motor. At the same time, the hydraulic data of the aerial work machinery can be obtained in real time through the pressure sensor and flow sensor installed on the hydraulic pump. Specifically, the hydraulic data may include the hydraulic pump pressure P and the hydraulic pump flow Q. The state detection module 432 may refer to a deep learning model. When the deep learning model determines that any one of the electrical data and the hydraulic data is in an abnormal state, that is, when any one of the motor or the hydraulic pump fails, the deep learning model outputs that the aerial work machinery is currently faulty.

[0093] It should be noted that the deep learning model may refer to a hybrid model using a convolutional neural network (CNN) and a long short-term memory network (LSTM), where CNN is used to extract features and LSTM processes the correlation of time series. The model parameters of the hybrid model may be trained based on historical electrical data and historical hydraulic data. Specifically, the electrical and hydraulic databases in the remote server may be accessed to obtain sufficient historical electrical data and historical hydraulic data. The original historical electrical data and hydraulic data are classified and processed into three categories of data: "normal", "caution" and "fault" according to their status. The classification criteria are shown in Table 1-4, including:

[0094] Table 1-4 Data classification table

[0095]

[0096] A deep learning model to be trained is established based on a convolutional neural network (CNN) and a long short-term memory network (LSTM). After the original historical electrical data and historical hydraulic data are classified according to the classification table shown in Table 1-4, the classified original data is preprocessed by cleaning, normalization and segmentation, and the preprocessed data is divided into a training set, a validation set and a test set. The training set, the validation set and the test set are input into the deep learning model to be trained, and the model parameters are continuously adjusted and the loss function is minimized through the back propagation algorithm. At the same time, the mean square error (MSE) and the accuracy are used to measure the model performance, requiring the MSE to be less than 0.1 and the classification accuracy to be at least 90%. The model outputs the status result of the aerial work machinery, that is, "normal" or "fault". It should be noted that when the data state of the electrical data or the hydraulic data is normal or caution, the status result of the aerial work machinery output by the deep learning model is normal, and only when the data state of at least one of the electrical data or the hydraulic data is faulty, the status result of the aerial work machinery output by the deep learning model is faulty.

[0097] In this embodiment, specifically, Figure 2 Taking the application scenario shown as an example, the first electrical data of the aerial work machinery can be obtained in real time through the current sensor, speed sensor and temperature sensor installed on the motor. Specifically, the first electrical data may include the current data I, the motor speed data V and the motor temperature data T of the motor. At the same time, the first hydraulic data of the aerial work machinery can be obtained in real time through the pressure sensor and flow sensor installed on the hydraulic pump. Specifically, the hydraulic data may include the hydraulic pump pressure P and the hydraulic pump flow Q. The state detection module 432 may include a digital twin model. When it is determined based on the digital twin model that any one of the electrical data and the hydraulic data is in an abnormal state, that is, when any one of the motor or the hydraulic pump fails, it is determined that the aerial work machinery is currently faulty.

[0098] It should be noted that the data information of any model of aerial work machinery will be stored in the remote server. Therefore, the historical electrical data and historical hydraulic data of the aerial work machinery in any historical time period can be obtained from the remote server through the model information of the aerial work machinery. Among them, the required historical time period can be selected according to actual needs. After obtaining the historical electrical data and historical hydraulic data, the digital twin model of the aerial work machinery is updated based on the first electrical data, the first hydraulic data, the historical electrical data and the historical hydraulic data. Among them, it should be noted that digital twins refer to making full use of physical models, sensors, operation history and other data, integrating multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, and completing mapping in virtual space, thereby reflecting the entire life cycle process of the corresponding physical equipment. In this technical solution, a digital twin model for the aerial work machinery can be constructed based on a large amount of historical electrical data and historical hydraulic data of any model of aerial work machinery. Such as Figure 6 As shown in the figure, a flowchart for building a digital twin model is provided. Specifically, based on the geometric structure of the physical entity of the aerial work machinery and the constraints between the components, a multi-domain visualization model of electromechanical and hydraulic control is built according to the internal actual operation mechanism of the electrical and hydraulic systems. Then, based on the intelligent optimization algorithm, the dynamic adaptive update and correction of the digital twin model is realized by acquiring data from the physical entity. At the same time, the artificial neural network is used to learn the rule model obtained with a large amount of historical electrical data and historical hydraulic data to predict the evolution of the twin model. Finally, the predicted evolution results of the twin model are compared with the detection parameters of the real physical model to determine whether the parameter error between the two models is less than a given threshold. If not, the digital twin model needs to be further adaptively updated and corrected. If so, it is considered that the modeling accuracy of the digital twin model meets the requirements and the modeling is accurate.

[0099] After updating the digital twin model, the first electrical data (U1, V1, T1) and the first hydraulic data (P1, Q1) obtained are input into the digital twin model, so as to obtain the second electrical data (U2, V2, T2) and the second hydraulic data (U2, V2, T2) by simulating the digital twin model based on the first electrical data (U1, V1, T1) and the first hydraulic data (P1, Q1). Then, the first electrical data (U1, V1, T1), the first hydraulic data (P1, Q1) and the second electrical data (U2, V2, T2), the second hydraulic data (P2, Q2) can be subtracted, and the current state of the aerial work machinery can be judged by comparing the difference between the error obtained and the preset threshold. Specifically, if the error is greater than the preset threshold, the aerial work machinery can be regarded as a discontinuous state at present, that is, a sudden failure may occur at present. If the error is less than or equal to the preset threshold, the aerial work machinery can be regarded as a continuous state at present, that is, it is currently operating normally.

[0100] After the state detection module 432 determines that the aerial work machinery has a fault based on the first electrical data and the first hydraulic data, the fault detection module 434 can further determine the fault type of the aerial work machinery based on the first electrical data and the first hydraulic data. Among them, the fault detection module 434 can refer to a fault detection model. In this technical solution, features can be extracted from the physical entity of the aerial work machinery and the historical data of the digital twin model, and then the fault detection model can be trained to determine the fault type of the aerial work machinery based on the acquired real-time electrical data, hydraulic data, digital twin model state and the combination of the fault detection model. Specifically, the historical data of the digital twin model and the physical entity of the aerial work machinery are collected to form a feature parameter K = (UE, VE, TE, PP, QP), and a normal working condition sample data set and various fault working condition sample data sets are established. Then, all data sample sets are preprocessed using the maximum and minimum normalization method, and a data label library is established. The normal working condition data label in the data label library is set to ("0"), and the data labels of the classic fault types including rotor bar fault, stator fault, bearing fault, cylinder wear, oil leakage and bearing wear are set to ("1", "2", "3", "4", "5", "6"), and the training sample library and the test sample library are obtained respectively. The support vector machine algorithm model is trained using the training sample library, the accuracy of the fault detection model is tested with the test sample, and the parameters of the fault detection model are optimized to obtain a trained fault detection model. Therefore, in the case of determining that the aerial work machinery has a fault, the first electrical data and the first hydraulic data can be input into the fault detection model to output the corresponding data label through the fault detection model, and the fault type corresponding to the data label is determined based on the data label library. For example, if the data label output by the fault detection model is "1", at this time, it can be known from the data label library that the fault type corresponding to the data label "1" is a rotor bar fault.

[0101] In this embodiment, specifically, Figure 3 Taking the application scenario shown as an example, the electrical data of the aerial work machinery can be obtained in real time through the speed sensor and temperature sensor installed on the engine. Specifically, the electrical data can include the engine rotor engine speed data V and the engine temperature data T. At the same time, the hydraulic data of the aerial work machinery can be obtained in real time through the pressure sensor and flow sensor installed on the hydraulic pump. Specifically, the hydraulic data can include the hydraulic pump pressure P and the hydraulic pump flow Q. The state detection module 432 can refer to a deep learning model. When the deep learning model determines that any one of the electrical data and the hydraulic data is in an abnormal state, that is, when any one of the engine or the hydraulic pump fails, the deep learning model outputs that the aerial work machinery is currently faulty.

[0102] It should be noted that the deep learning model may refer to a hybrid model using a convolutional neural network (CNN) and a long short-term memory network (LSTM), where CNN is used to extract features and LSTM processes the correlation of time series. The model parameters of the hybrid model can be trained based on historical electrical data and historical hydraulic data. Specifically, the electrical and hydraulic databases in the remote server can be accessed to obtain sufficient historical electrical data and historical hydraulic data. The original historical electrical data and hydraulic data are classified and processed into three categories of data: "normal", "caution" and "fault" according to their status. The classification standards are shown in Table 1-5, including:

[0103] Table 1-5 Data classification table

[0104]

[0105]

[0106] A deep learning model with training is established based on convolutional neural network (CNN) and long short-term memory network (LSTM). After the original historical electrical data and historical hydraulic data are classified according to the classification table shown in Table 1-5, the classified original data are preprocessed by cleaning, normalization and segmentation, and the preprocessed data are divided into training set, validation set and test set. The training set, validation set and test set are input into the deep learning model to be trained, and the model parameters are continuously adjusted and the loss function is minimized through the back propagation algorithm. At the same time, the mean square error (MSE) and accuracy are used to measure the model performance, requiring the MSE to be less than 0.1 and the classification accuracy to reach at least 90%. The model outputs the status result of the aerial work machinery, that is, "normal" or "fault". It should be noted that when the data state of the electrical data or the hydraulic data is normal or caution, the status result of the aerial work machinery output by the deep learning model is normal, and only when the data state of at least one of the electrical data or the hydraulic data is faulty, the status result of the aerial work machinery output by the deep learning model is faulty.

[0107] The above technical scheme uses a data acquisition module to obtain the operating data of the aerial work machinery in real time, and the operating data includes at least the operating data, electrical data and hydraulic data of the aerial work machinery; a life detection module is used to determine the real-time damage value corresponding to the operating data based on a fatigue damage library, and determine the remaining life of the actuator based on the real-time damage value, the fatigue damage library includes a correspondence between multiple operating data and the damage values ​​of the actuator, wherein the correspondence is obtained after fatigue test training based on multiple historical operating data that meet preset conditions; a monitoring module is used to analyze and process the electrical data and hydraulic data to obtain the current operating status of the aerial work machinery, and in the event of a failure of the aerial work machinery, determine the fault type of the aerial work machinery based on the electrical data and hydraulic data, thereby realizing real-time and accurate monitoring of the operating status of the aerial work machinery and the fatigue life of each actuator component.

[0108] In one embodiment, Figure 5 As shown, the maintenance system for aerial work machinery also includes:

[0109] The fatigue damage library construction module 440 is used to perform fatigue test training based on a plurality of historical operation data that meet preset conditions to construct a fatigue damage library.

[0110] In this embodiment, it should be noted that the preset conditions can be set according to actual needs, and the fatigue damage library construction module 440 can perform fatigue test training based on multiple historical operating data that meet the preset conditions to construct a fatigue damage library, so that the life detection module 420 determines the real-time damage value corresponding to each actuator under the current operating data based on the constructed fatigue damage library, and further calculates the current remaining life of the actuator based on the real-time damage value.

[0111] In an embodiment of the present application, the fatigue damage library construction module 440 is also used to: obtain multiple historical operating data of the aerial work machinery within a historical time period, the multiple historical operating data including multiple historical torques and multiple historical operating angles of the actuator; for multiple historical operating angles, determine the cumulative number of occurrences of each historical operating angle within the historical time period; eliminate historical operating angles whose cumulative number of occurrences is lower than a preset number threshold, and determine the remaining historical operating angles as target operating angles that meet preset conditions; analyze multiple historical torques, and screen out target torques that meet the preset conditions; generate fatigue test conditions based on the target operating angles and target torques; for any fatigue test condition, repeat fatigue test training for the fatigue test condition until fatigue cracks exist in the actuator under the fatigue test condition, and determine the number of training times for the fatigue test condition as the fatigue life of the actuator under the fatigue test condition; determine the damage value corresponding to each fatigue test condition based on the fatigue life of the actuator under each fatigue test condition, and construct a fatigue damage library based on the correspondence between each fatigue test condition and the damage value.

[0112] In this embodiment, Figure 1 Taking the application scenario shown as an example, the actuator of the aerial work machinery includes a scissor arm, and the fatigue damage library includes a plurality of correspondences between operating angles and torques and the damage values ​​of the scissor arm, and each set of correspondences has a corresponding damage value, wherein the correspondences are obtained after fatigue test training based on a plurality of historical operating angles and historical torques that meet the preset conditions, and the preset conditions can be set according to actual needs. Therefore, the fatigue damage library can be obtained after fatigue test training based on a plurality of historical operating angles and historical torques of the scissor arm that meet the preset conditions.

[0113] Specifically, when constructing the step fatigue damage library, a historical time period can be selected first, and multiple historical operation data of the scissor arm of the aerial work machinery in the historical time period can be obtained. It should be noted that the selected historical time period should be a time period with a long time span to ensure that the number of historical operation data of the scissor arm in the historical time period is sufficient, for example, the number of historical operation angles and historical torques should be more than 1000 groups. After obtaining multiple historical operation data, the cumulative number of occurrences of each historical operation angle is counted respectively, and the historical operation angles whose cumulative number of occurrences is lower than the preset number threshold are eliminated, and the remaining historical operation angles are determined as target operation angles that meet the preset conditions. For example, the preset number threshold can be set to 10 times, that is, for any historical operation angle, if the cumulative number of occurrences of the historical operation angle is less than 10 times, it is an operation angle that does not meet the preset conditions and needs to be eliminated. If the cumulative number of occurrences is greater than or equal to 10 times, it is an operation angle that meets the preset conditions and needs to be retained. Specifically, as shown in Table 2-1, a cumulative number of occurrences of each historical operation angle in the historical time period is provided. For example, θ 1 The cumulative number of occurrences is k1, θ 2 The cumulative number of occurrences is k2. After obtaining the cumulative number of occurrences of each historical operating angle, the operating angles with a cumulative number of occurrences less than 10 times are eliminated to obtain the angle real operating condition library composed of the target operating angles that meet the preset conditions as shown in Table 3-1.

[0114] Table 2-1 Cumulative number of occurrences of each historical operation angle in the historical time period

[0115] Serial number θ[°] Cumulative number of occurrences 1 <![CDATA[θ 1 ]]> k1 2 <![CDATA[θ 2 ]]> k2 3 <![CDATA[θ 3 ]]> k3 …… …… …… …… …… …… n <![CDATA[θ n ]]> k

[0116] Table 3-1 Angle real working condition library

[0117] Serial number θ[°] 1 <![CDATA[θ 1 ]]> 2 <![CDATA[θ 2 ]]> 3 <![CDATA[θ 3 ]]> …… …… …… …… m <![CDATA[θ m ]]>

[0118] At the same time, the multiple historical moments obtained are analyzed, and the target moments that meet the preset conditions are screened out. Specifically, a normal distribution analysis can be performed on the multiple historical moments to screen out the target moments that meet the preset conditions. After obtaining the target operating angle and target torque that meet the preset conditions, a fatigue test condition is generated based on the target operating angle and the target torque. For any fatigue test condition, fatigue test training is repeated for the fatigue test condition until fatigue cracks exist in the scissors arm under the fatigue test condition. The number of training times for the fatigue test condition is determined as the fatigue life of the scissors arm under the fatigue test condition, and then the damage value corresponding to each fatigue test condition is further determined based on the fatigue life of the scissors arm under each fatigue test condition. Specifically, taking the fatigue life as Ti as an example, the inverse of the fatigue life Ti 1 / Ti is taken to determine the damage value Di corresponding to the fatigue test condition. After determining the damage value corresponding to each fatigue test condition, a fatigue damage library is constructed based on the correspondence between each fatigue test condition and the damage value.

[0119] In this embodiment, Figure 2 Taking the application scenario shown as an example, the actuator of the aerial work machinery includes a boom and multiple outriggers, and the fatigue damage library includes the correspondence between multiple operating angles and torques and the damage value of the boom. Each set of correspondences has a corresponding damage value, wherein the correspondence is obtained after fatigue test training based on multiple historical operating angles and historical torques that meet the preset conditions, and the preset conditions can be set according to actual needs. Therefore, the fatigue damage library can be obtained after fatigue test training based on multiple historical operating angles of the boom that meet the preset conditions and multiple historical torques of multiple outriggers.

[0120] Specifically, when constructing the step fatigue damage library, a historical time period can be selected first, and multiple historical operation data of the boom of the aerial work machinery in the historical time period can be obtained. It should be noted that the selected historical time period should be a time period with a long time span to ensure that the number of historical operation data of the boom in the historical time period is sufficient, for example, the number of historical operation angles and historical torques should be more than 1000 groups. After obtaining multiple historical operation data, the cumulative number of occurrences of each historical operation angle is counted respectively, and the historical operation angles with a cumulative number of occurrences lower than the preset number threshold are eliminated, and the remaining historical operation angles are determined as target operation angles that meet the preset conditions. For example, the preset number threshold can be set to 10 times, that is, for any historical operation angle, if the cumulative number of occurrences of the historical operation angle is less than 10 times, it is an operation angle that does not meet the preset conditions and needs to be eliminated. If the cumulative number of occurrences is greater than or equal to 10 times, it is an operation angle that meets the preset conditions and needs to be retained. Specifically, as shown in Table 2-2, a cumulative number of occurrences of each historical operating angle in a historical time period is provided, for example, the cumulative number of occurrences of θ1 is k1, and the cumulative number of occurrences of θ2 is k2. After obtaining the cumulative number of occurrences of each historical operating angle, the operating angles with a cumulative number of occurrences less than 10 times are eliminated to obtain an angle real operating condition library composed of target operating angles that meet the preset conditions as shown in Table 3-2.

[0121] Table 2-2 Cumulative number of occurrences of each historical operation angle in the historical time period

[0122] Serial number θ[°] Cumulative number of occurrences 1 <![CDATA[θ 1 ]]> k1 2 <![CDATA[θ 2 ]]> k2 3 <![CDATA[θ 3 ]]> k3 …… …… …… …… …… …… n <![CDATA[θ n ]]> k

[0123] Table 3-2 Angle real working condition library

[0124] Serial number θ[°] 1 <![CDATA[θ 1 ]]> 2 <![CDATA[θ 2 ]]> 3 <![CDATA[θ 3 ]]> …… …… …… …… m <![CDATA[θ m ]]>

[0125] At the same time, the obtained multiple historical moments are analyzed, and the target moments that meet the preset conditions are screened out. Specifically, normal distribution analysis can be performed on the multiple historical moments to screen out the target moments that meet the preset conditions.

[0126] In the present technical solution, after obtaining the target operating angle and target torque that meet the preset conditions, a fatigue test condition is generated based on the target operating angle and the target torque. For any fatigue test condition, fatigue test training is repeated for the fatigue test condition until fatigue cracks exist in the boom under the fatigue test condition. The number of training times for the fatigue test condition is determined as the fatigue life of the boom under the fatigue test condition, and then the damage value corresponding to each fatigue test condition is further determined based on the fatigue life of the boom under each fatigue test condition. Specifically, taking the fatigue life as Ti as an example, the inverse of the fatigue life Ti 1 / Ti is taken to determine the damage value Di corresponding to the fatigue test condition. After determining the damage value corresponding to each fatigue test condition, a fatigue damage library is constructed based on the correspondence between each fatigue test condition and the damage value.

[0127] In an embodiment of the present application, analyzing multiple historical moments and screening out target moments that meet preset conditions includes: performing normal distribution analysis on multiple historical moments to obtain a normal distribution graph for multiple historical moments; based on the normal distribution graph, eliminating historical moments outside a preset interval, and determining the remaining historical moments as target moments that meet the preset conditions.

[0128] In this embodiment, it should be noted that the preset condition can be determined based on the expected value of the normal distribution graph. For example, taking the expected value 3σ as an example, the preset interval can be [-3σ, +3σ]. Meeting the preset condition can mean being within the preset interval [-3σ, +3σ]. Therefore, the historical moments outside the preset interval [-3σ, +3σ] can be eliminated, and the remaining historical moments can be determined as the target moments that meet the preset conditions.

[0129] In this embodiment, Figure 1 Taking the application scenario shown in the figure as an example, a normal distribution analysis is performed on the multiple historical moments of the scissor arm to obtain a normal distribution diagram for the multiple historical moments. For example, as shown in Table 4-1, multiple historical moments are provided, and a normal distribution analysis is performed on the multiple historical data in Table 4-1 to obtain the following: Figure 7 A schematic diagram of a normal distribution diagram is shown in Figure . Figure 7 As shown, the expected value is 3σ, therefore, the preset interval can be set to [-3σ, +3σ], the historical moments outside the interval [-3σ, +3σ] are eliminated, and the historical moments within the interval [-3σ, +3σ] are determined as the target moments that meet the preset conditions, and the torque real working condition library shown in Table 5-1 is obtained.

[0130] Table 4-1 Multiple historical moments

[0131] Serial number F[N] 1 F1 2 F2 3 F3 …… …… …… …… n Fn

[0132] Table 5-1 Torque real working condition library

[0133] Serial number F[N] 1 F1 2 F2 3 F3 …… …… …… …… m Fm

[0134] In this embodiment, Figure 2 Taking the application scenario shown in the figure as an example, a normal distribution analysis is performed on multiple historical moments of multiple legs to obtain a normal distribution diagram for multiple historical moments. For example, as shown in Table 4-2, multiple historical moments are provided, and a normal distribution analysis is performed on multiple historical data in Table 4-2 to obtain the following: Figure 7 A schematic diagram of a normal distribution diagram is shown in Figure . Figure 7 As shown, the expected value is 3σ, therefore, the preset interval can be set to [-3σ, +3σ], the historical moments outside the interval [-3σ, +3σ] are eliminated, and the historical moments within the interval [-3σ, +3σ] are determined as the target moments that meet the preset conditions, and the torque real working condition library shown in Table 5-2 is obtained.

[0135] Table 4-2 Multiple historical moments

[0136] Serial number F[N] 1 F1(f1,f2,f3,f4) 2 F2(f1,f2,f3,f4) 3 F3(f1,f2,f3,f4) …… …… …… …… n Fn(f1,f2,f3,f4)

[0137] Table 5-2 Torque real working condition library

[0138] Serial number F[N] 1 F1(f1,f2,f3,f4) 2 F2(f1,f2,f3,f4) 3 F3(f1,f2,f3,f4) …… …… …… …… m Fm(f1,f2,f3,f4)

[0139] In an embodiment of the present application, generating fatigue test conditions based on target operating angles and target torques includes: for each target operating angle, combining the target operating angle with all other target operating angles except the target operating angle in turn to obtain multiple angle groups; sorting all target torques in ascending order to obtain torque intervals for all target torques; dividing the torque interval into multiple continuous sub-torque intervals based on a preset division ratio; and combining each sub-torque interval with each angle group in turn to generate corresponding multiple fatigue test conditions.

[0140] In this embodiment, Figure 1 Taking the application scenario shown in the figure as an example, the actuator of the aerial work machinery includes a scissor arm. After obtaining the target operating angle and target torque that meet the preset conditions, for each target operating angle, the target operating angle is sequentially combined with all other target operating angles except the target operating angle to obtain multiple angle groups. For example, as shown in Table 3-1, the angle real working condition library is θ 1 For example, let θ 1 Respectively with θ 2 …θ m By combining them in sequence, we can obtain multiple lifting starting angle groups as shown in Table 6-1, such as θ 1 θ2 ,θ 1 θ 3 wait.

[0141] Table 6-1 Lifting start angle group

[0142] Lifting start angle group <![CDATA[θ 1 i 2 ]]> <![CDATA[θ 1 i 3 ]]> <![CDATA[θ 2 i 3 ]]> …… …… <![CDATA[θ m-1 i m ]]>

[0143] At the same time, the obtained target torques are sorted in ascending order to obtain the maximum target torque and the minimum target torque, and are respectively determined as the maximum value Fmax and the minimum value Fmin of all target torques. Based on the maximum value Fmax and the minimum value Fmin, the following is obtained: Figure 8 The torque interval schematic diagram for all target torques is shown, and the value of the torque interval is [Fmin, Fmax]. It should be noted that the preset ratio can be set to 100N, so the torque interval can be divided into equal proportions with 100N as the division interval to obtain multiple consecutive sub-torque intervals. For example, as shown in Table 7-1, a lifting load F table including multiple consecutive sub-torque intervals is provided.

[0144] Table 7-1 Lifting load F table

[0145] Serial number F[N] 1 F1 2 F2 3 F3 …… …… …… …… j Fj

[0146] Each sub-torque interval obtained by the division is combined with each angle group obtained by the combination in sequence to generate corresponding multiple fatigue test conditions. Specifically, each angle group in the lifting start angle group shown in Table 6-1 can be combined in sequence with each sub-torque interval in the lifting load F table shown in Table 7-1 to obtain the fatigue test condition table shown in Table 8-1.

[0147] Table 8-1 Fatigue test conditions

[0148] Load\Start Angle <![CDATA[θ 1 i 2 ]]> <![CDATA[θ 1 i 3 ]]> …… <![CDATA[θ m-1 i m ]]> F1 Condition 1 Condition 2 …… …… F2 …… …… …… …… …… …… …… …… …… Fj …… …… …… Working condition K

[0149] Specifically, for any fatigue test condition in Table 8-1, fatigue test training is repeated for the fatigue test condition, that is, each condition is repeatedly executed according to the load and starting angle in the fatigue test condition table until the scissors arm stops after fatigue cracks exist under the fatigue test condition. The number of repeated training Ti of the fatigue test condition at this time is recorded, and Ti is determined as the fatigue life of the scissors arm under the fatigue test condition. At the same time, the reciprocal of the fatigue life Ti 1 / Ti is taken as the damage value Di corresponding to the fatigue test condition. After determining the damage value corresponding to each fatigue test condition, a fatigue damage library as shown in Table 1-1 is constructed based on the correspondence between each fatigue test condition and the damage value.

[0150] In this embodiment, Figure 2Taking the application scenario shown in the figure as an example, the actuator of the aerial work machinery includes a boom and multiple legs. After obtaining the target operating angle and target torque that meet the preset conditions, for each target operating angle, the target operating angle is sequentially combined with all other target operating angles except the target operating angle to obtain multiple angle groups. For example, as shown in Table 3-2, the angle real working condition library is θ 1 For example, let θ 1 Respectively with θ 2 …θ m By combining them in sequence, we can obtain multiple lifting starting angle groups as shown in Table 6-2, such as θ 1 θ 2 ,θ 1 θ 3 wait.

[0151] Table 6-2 Lifting start angle group

[0152] Lifting start angle group <![CDATA[θ 1 i 2 ]]> <![CDATA[θ 1 i 3 ]]> <![CDATA[θ 2 i 3 ]]> …… …… <![CDATA[θ m-1 i m ]]>

[0153] At the same time, the obtained target torques are sorted in ascending order to obtain the maximum target torque and the minimum target torque, and are respectively determined as the maximum value Fmax and the minimum value Fmin of all target torques. Based on the maximum value Fmax and the minimum value Fmin, the following is obtained: Figure 8 The torque interval schematic diagram for all target torques is shown, and the value of the torque interval is [Fmin, Fmax]. It should be noted that the preset ratio can be set to 100N, so the torque interval can be divided into equal proportions with 100N as the division interval to obtain multiple consecutive sub-torque intervals. For example, as shown in Table 7-2, a load F table including multiple consecutive sub-torque intervals is provided.

[0154] Table 7-2 Load F table

[0155] Serial number F[N] 1 F1(f1,f2,f3,f4) 2 F2(f1,f2,f3,f4) 3 F3(f1,f2,f3,f4) …… …… …… …… j Fj(f1,f2,f3,f4)

[0156] Each sub-torque interval obtained by division is combined with each angle group obtained by combination in sequence to generate corresponding multiple fatigue test conditions. Specifically, each angle group in the lifting start angle group shown in Table 6-2 can be combined with each sub-torque interval in the load F table shown in Table 7-2 in sequence to obtain the fatigue test condition table shown in Table 8-2.

[0157] Table 8-2 Fatigue test conditions

[0158] Load\Start Angle <![CDATA[θ 1 i 2 ]]> <![CDATA[θ 1 i 3 ]]> …… <![CDATA[θ m-1 i m ]]> F1(f1,f2,f3,f4) Condition 1 Condition 2 …… …… F2(f1,f2,f3,f4) …… …… …… …… …… …… …… …… …… Fj(f1,f2,f3,f4) …… …… …… Working condition K

[0159] Specifically, for any fatigue test condition in Table 8-2, fatigue test training is repeated for the fatigue test condition, that is, each condition is repeatedly executed according to the load and starting angle in the fatigue test condition table until the boom stops after fatigue cracks exist under the fatigue test condition. The number of repeated training Ti of the fatigue test condition at this time is recorded, and Ti is determined as the fatigue life of the boom under the fatigue test condition. At the same time, the reciprocal of the fatigue life Ti 1 / Ti is taken as the damage value Di corresponding to the fatigue test condition. After determining the damage value corresponding to each fatigue test condition, a fatigue damage library as shown in Table 1-2 is constructed based on the correspondence between each fatigue test condition and the damage value.

[0160] In an embodiment of the present application, the fatigue damage library construction module 440 is also used to: obtain multiple historical operation data of the aerial work machinery within a historical time period, the historical operation data including multiple historical load data of the actuator and multiple historical operation data of the actuator, wherein the multiple historical operation data include multiple historical operation heights and multiple historical operation ranges of the actuator; determine the area that the actuator can reach at multiple historical operation heights and multiple historical operation ranges, and divide the area into multiple operation areas, and define an area number for each operation area; for multiple historical operation data, determine the area number where each historical operation data is located, and determine the cumulative number of occurrences of each area number within the historical time period; eliminate the areas with a cumulative number of occurrences lower than a preset number. The historical area numbers of the times threshold are determined, and the operating areas corresponding to the remaining historical area numbers are determined as the target operating areas that meet the preset conditions; multiple historical loads are analyzed, and the target loads that meet the preset conditions are screened out; fatigue test conditions are generated based on the target operating area and the target load; for any fatigue test condition, fatigue test training is repeated for the fatigue test condition until fatigue cracks exist in the actuator under the fatigue test condition, and the number of training times for the fatigue test condition is determined as the fatigue life of the actuator under the fatigue test condition; the damage value corresponding to each fatigue test condition is determined based on the fatigue life of the actuator under each fatigue test condition, and a fatigue damage library is constructed based on the correspondence between each fatigue test condition and the damage value.

[0161] In this embodiment, Figure 3Taking the application scenario shown as an example, the actuator of the aerial work machinery includes a boom and a fork. Therefore, the fatigue damage library can be obtained after fatigue test training based on multiple historical working heights and working ranges of the boom that meet preset conditions and multiple historical loads of the fork. It should be noted that the fatigue damage library defines multiple working areas and the damage value corresponding to each working area. The multiple working areas are divided according to the areas that the boom can reach at different historical working heights and different historical working ranges, and the damage value corresponding to each working area is obtained based on fatigue test training of multiple historical loads of the fork in each working area. Therefore, when constructing the step fatigue damage library, the working range and working height range that the boom can reach can be determined based on the model information of the aerial work machinery, and the working range of the aerial work machinery can be divided into any N based on the working range and working height range that can be reached. L ×N H Each work area is divided into several areas and each work area is numbered. Fig. 9 As shown, a schematic diagram of the division of operation areas is provided, and the numbers of the operation areas can be divided into N1 to N9. It should be noted that the larger the number of divided areas, the more accurate the calculation result, but the amount of calculation and storage will also be greater.

[0162] Select a historical time period, and obtain multiple historical operating heights H and historical operating ranges L of the boom in the historical time period, and multiple historical loads M of the fork in the historical time period. It should be noted that the selected historical time period should be a time period with a longer time span to ensure that the number of historical data of the boom and fork in the historical time period is sufficient, for example, the number of historical operating heights, historical operating ranges, and historical loads should all be more than 1,000 groups.

[0163] After obtaining multiple historical operating heights and historical operating ranges of the boom, based on each set of historical operating heights and historical operating ranges, it can be determined which of N1 to N9 the operating area corresponding to each set of historical operating data is. Extract the area number N corresponding to each set of historical operating data, and count the cumulative number of occurrences of each operating area number in the historical time period, and eliminate the operating area numbers whose cumulative number of occurrences is lower than the preset number threshold, and determine the operating area corresponding to the remaining operating area numbers as the target operating area that meets the preset conditions. For example, the preset number threshold can be set to 10 times, that is, for any operating area number, if the cumulative number of occurrences of the operating area number is less than 10 times, it is determined to be an operating area number that does not meet the preset conditions and needs to be eliminated. If the cumulative number of occurrences is greater than or equal to 10 times, it is an operating area number that meets the preset conditions and needs to be retained. Specifically, as shown in Table 2-3, a cumulative number of occurrences of each operating area number in the historical time period is provided, for example, the cumulative number of occurrences of N1 is k1, and the cumulative number of occurrences of N2 is k2. After obtaining the cumulative number of occurrences of each work area number, the work area numbers with a cumulative number of occurrences less than 10 times are eliminated to obtain a real working condition library of work areas composed of target work areas that meet the preset conditions as shown in Table 3-3.

[0164] Table 2-3 Cumulative number of occurrences of each operation area number in the historical time period

[0165] Serial number Work area number Cumulative number of occurrences 1 N1 k1 2 N2 k2 3 N3 k3 …… …… …… …… …… …… n N k

[0166] Table 3-3 Real working condition database of the working area

[0167]

[0168]

[0169] At the same time, the acquired multiple historical loads are analyzed, and the target loads that meet the preset conditions are screened out. Specifically, the multiple historical loads can be analyzed for normal distribution to screen out the target loads that meet the preset conditions.

[0170] In the present technical solution, after obtaining the target operating area and target load that meet the preset conditions, a fatigue test condition is generated based on the target operating area and the target load. For any fatigue test condition, fatigue test training is repeated for the fatigue test condition until fatigue cracks exist in the boom under the fatigue test condition. The number of training times for the fatigue test condition is determined as the fatigue life of the boom under the fatigue test condition, and then the damage value corresponding to each fatigue test condition is further determined based on the fatigue life of the boom under each fatigue test condition. Specifically, taking the fatigue life as Ti as an example, the inverse of the fatigue life Ti 1 / Ti is taken to determine the damage value Di corresponding to the fatigue test condition. After determining the damage value corresponding to each fatigue test condition, a fatigue damage library is constructed based on the correspondence between each fatigue test condition and the damage value.

[0171] In an embodiment of the present application, multiple historical loads are analyzed and target loads that meet preset conditions are screened out, including: performing normal distribution analysis on multiple historical loads to obtain a normal distribution graph for multiple historical loads; based on the normal distribution graph, historical loads outside a preset interval are eliminated, and the remaining historical loads are determined as target loads that meet the preset conditions.

[0172] In this embodiment, in this embodiment, Figure 3 For example, the application scenario shown in FIG. 4 is used to perform normal distribution analysis on multiple historical loads of the obtained forks to filter out the target loads that meet the preset conditions. Specifically, normal distribution analysis is performed on multiple historical loads to obtain normal distribution graphs for multiple historical loads. For example, as shown in Table 4-3, multiple historical loads are provided, and normal distribution analysis is performed on multiple historical data in Table 4-3 to obtain the following: Figure 7 A schematic diagram of a normal distribution diagram is shown in Figure . Figure 7 As shown, the expected value is 3σ, therefore, the preset interval can be set to [-3σ, +3σ], the historical loads outside the interval [-3σ, +3σ] are eliminated, and the historical loads within the interval [-3σ, +3σ] are determined as the target loads that meet the preset conditions, and the real load condition library shown in Table 5-3 is obtained.

[0173] Table 4-3 Multiple historical loads

[0174] Serial number M[kg] 1 M1 2 M2 3 M3 …… …… …… …… n Mn

[0175] Table 5-3 Load real working condition library

[0176]

[0177]

[0178] In an embodiment of the present application, generating fatigue test conditions based on the target operating angle and the target torque includes: for each target operating area, combining the target operating area with all other target operating areas except the target operating area in turn to obtain multiple operating area groups; sorting all target loads in ascending order to obtain load ranges for all target loads; dividing the load range into multiple continuous sub-load ranges based on a preset division ratio; combining each sub-load range with each operating area group in turn to generate corresponding multiple fatigue test conditions.

[0179] In this embodiment, in this embodiment, Figure 3 Taking the application scenario shown as an example, the actuator of the aerial work machinery includes a boom and a fork. After obtaining the target operation area and target torque that meet the preset conditions, for each target operation area, the target operation area is sequentially combined with all other target operation areas except the target operation area to obtain multiple operation area groups. For example, as shown in Table 3-3, the real working condition library of the operation area, taking N1 as an example, N1 is sequentially combined with N2...Nm to obtain multiple operation area groups shown in Table 6-3, such as N1N2, N1N3, etc.

[0180] Table 6-3 Operation area groups

[0181] Working area group N1N2 N1N3 N2N3 …… …… Nm-1Nm

[0182] At the same time, the obtained target loads are sorted in ascending order to obtain the maximum target load and the minimum target load, and are respectively determined as the maximum value Mmax and the minimum value Mmin of all target loads. Based on the maximum value Mmax and the minimum value Mmin, the following is obtained: Fig.10 The load interval diagram for all target loads is shown, and the load interval value is [Mmin, Mmax]. It should be noted that the preset ratio can be set to 100 kg, so the load interval can be divided into equal proportions with 100 kg as the division interval to obtain multiple consecutive sub-load intervals. For example, as shown in Table 7-3, a working load M table including multiple consecutive sub-load intervals is provided.

[0183] Table 7-3 Operation load M table

[0184] Serial number M[N] 1 M1 2 M2 3 M3 …… …… …… …… j Mj

[0185] Each sub-load interval obtained by division is sequentially combined with each operating area group obtained by combination to generate corresponding multiple fatigue test conditions. Specifically, each operating area group in the operating area group shown in Table 6-3 can be sequentially combined with each sub-load interval in the operating load M table shown in Table 7-3 to obtain the fatigue test condition table shown in Table 8-3.

[0186] Table 8-3 Fatigue test conditions

[0187]

[0188]

[0189] Specifically, for any fatigue test condition in Table 8-3, fatigue test training is repeated for the fatigue test condition, that is, each condition is repeatedly executed according to the load and working area in the fatigue test condition table until the boom stops after fatigue cracks exist under the fatigue test condition. The number of repeated training times Ti of the fatigue test condition at this time is recorded, and Ti is determined as the fatigue life of the boom under the fatigue test condition. At the same time, the reciprocal of the fatigue life Ti 1 / Ti is taken as the damage value Di corresponding to the fatigue test condition. After determining the damage value corresponding to each fatigue test condition, a fatigue damage library as shown in Table 1-3 is constructed based on the correspondence between each fatigue test condition and the damage value.

[0190] In one embodiment, the maintenance system also includes: an alarm module 450, which is used to generate a corresponding alarm signal when the remaining life of any actuator is lower than a preset threshold or a failure of the aerial work machinery occurs; an operation and maintenance module 460, which is used to generate and push an operation and maintenance plan corresponding to the alarm signal when the alarm module 450 generates an alarm signal.

[0191] In this embodiment, it should be noted that the preset threshold can be set according to actual needs, for example, it can include but is not limited to being set to half a year. Figure 1 Taking the application scenario shown as an example, the actuator of the aerial work machine includes a scissor arm. Therefore, when the remaining life of the scissor arm is less than half a year or the aerial work machine fails, the alarm module 450 starts to issue a corresponding alarm reminder mechanism. Figure 2 Taking the application scenario shown in the figure as an example, the actuator of the aerial work machine includes a boom and a plurality of legs. Therefore, when the remaining life of the boom is less than half a year or the aerial work machine fails, the alarm module 450 starts to issue an alarm reminder mechanism. Figure 3 Taking the application scenario shown as an example, the actuator of the aerial work machine includes a boom and a fork. Therefore, when the remaining life of the boom is less than half a year or the aerial work machine fails, the alarm module 450 starts to issue an alarm reminder mechanism.

[0192] After the alarm module 450 generates an alarm signal, the configured alarm system will send the alarm signal to the service equipment via GPRS, triggering the alarm of the service equipment. The alarm system will send a text message to the pre-bound mobile phone number and email address, and push the alarm information, which includes the diagnosis result. At the same time, the operation and maintenance module 460 generates and pushes the operation and maintenance plan corresponding to the alarm signal to remind the user to perform maintenance in time.

[0193] In one embodiment, Fig.11 As shown, a system architecture diagram of a maintenance system is provided. Specifically, the system architecture involves a service equipment end, a local end, and a remote server end. The service equipment end may refer to an aerial work machine. A variety of sensors are deployed on the aerial work machine, and the various sensors can collect the operation data, electrical data, and hydraulic data of the aerial work machine in real time. The collected original operation data, electrical data, and hydraulic data will be pre-processed by the central processing unit such as cleaning, normalization, and segmentation, and the pre-processed data will be sent to the remote server end. The remote server end includes the pre-processed operation data, electrical data, and hydraulic data, as well as a real working condition library composed of historical operation data, historical electrical data, and historical hydraulic data that meet the preset conditions, and a fatigue damage library constructed after fatigue experiment training based on the real working condition library. Among them, the fatigue damage library is obtained by fatigue experiment training based on the data in the real working condition library composed of historical operation data, historical electrical data, and historical hydraulic data that meet the preset conditions on the local end. It should be noted that the local end is also used to train a deep learning model and a digital twin model for determining the current operating state of the aerial work machine based on historical electrical data and historical hydraulic data.

[0194] The remote server includes a life monitoring system and a condition monitoring system. The life monitoring system can determine the real-time damage value of the actuator of the aerial work machinery based on the real-time acquired operation data through the fatigue damage library, and further determine the real-time cumulative damage value based on the real-time damage value, so as to determine the remaining life of the actuator according to the real-time damage value and the real-time cumulative damage value. The condition monitoring system can input the acquired electrical data and hydraulic data into a deep learning model or a digital twin model to determine the current operating state of the aerial work machinery through the deep learning model or the digital twin model. The operating state can include any one of normal and faulty.

[0195] The remote server also includes an early warning system. When it is detected that the remaining life of the actuator of the aerial work machinery is lower than the preset threshold or the aerial work machinery equipment is abnormal, that is, a failure occurs, the alarm system triggers the alarm reminder mechanism. After the alarm signal is generated, the configured alarm system will send an alarm signal to the service equipment via GPRS, triggering the alarm of the service equipment. The alarm system will send a text message to the pre-bound mobile phone number and email address, and push the alarm information. The alarm information contains the diagnosis results and operation and maintenance plan to remind users to perform maintenance in time.

[0196] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0197] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A maintenance system for aerial work machinery, characterized in that: The aerial work machine includes a plurality of actuators, and the maintenance system includes: A data acquisition module, used for acquiring the operation data of the aerial work machine in real time, wherein the operation data at least includes the operation data, electrical data and hydraulic data of the aerial work machine; A life detection module, used to determine a real-time damage value corresponding to the operating data based on a fatigue damage library, and determine the remaining life of the actuator based on the real-time damage value, wherein the fatigue damage library includes a correspondence between a plurality of operating data and the damage value of the actuator, and the correspondence is obtained after fatigue test training based on a plurality of historical operating data that meet preset conditions; A monitoring module is used to analyze and process the electrical data and the hydraulic data to obtain the current operating status of the aerial work machinery, wherein the operating status includes any one of normal and faulty, and when a fault occurs in the aerial work machinery, the fault type of the aerial work machinery is determined based on the electrical data and the hydraulic data.

2. The maintenance system for aerial work machinery according to claim 1, characterized in that: The maintenance system also includes: The fatigue damage library building module is used to conduct fatigue test training based on multiple historical operating data that meet preset conditions to build a fatigue damage library.

3. The maintenance system for aerial work machinery according to claim 2, characterized in that: The fatigue damage library building module is also used to: Acquire a plurality of historical operation data of the aerial work machine in a historical time period, wherein the plurality of historical operation data includes a plurality of historical torques and a plurality of historical operation angles of an actuator; For a plurality of historical operation angles, determining the cumulative number of occurrences of each historical operation angle within the historical time period; Eliminate historical operating angles whose cumulative occurrence times are lower than a preset number threshold, and determine the remaining historical operating angles as target operating angles that meet the preset conditions; Analyze the multiple historical moments and select target moments that meet preset conditions; Generate fatigue test conditions based on target operating angle and target torque; For any fatigue test condition, repeatedly perform fatigue test training on the fatigue test condition until fatigue cracks occur in the actuator under the fatigue test condition, and determine the number of training times for the fatigue test condition as the fatigue life of the actuator under the fatigue test condition; Based on the fatigue life of the actuator under each fatigue test condition, the damage value corresponding to each fatigue test condition is determined, and a fatigue damage library is constructed based on the corresponding relationship between each fatigue test condition and the damage value.

4. The maintenance system for aerial work machinery according to claim 3, characterized in that: The analyzing the multiple historical moments and selecting the target moments meeting the preset conditions comprises: Performing normal distribution analysis on the multiple historical moments to obtain normal distribution graphs for the multiple historical moments; Based on the normal distribution diagram, historical moments outside a preset interval are eliminated, and the remaining historical moments are determined as target moments that meet preset conditions.

5. The maintenance system for aerial work machinery according to claim 3, characterized in that: The fatigue test condition generated based on the target operating angle and the target torque includes: For each target operating angle, sequentially combine the target operating angle with all other target operating angles except the target operating angle to obtain a plurality of angle groups; Sort all target moments in ascending order to obtain moment intervals for all target moments; Dividing the torque interval into a plurality of continuous sub-torque intervals in sequence based on a preset division ratio; Each sub-torque interval is combined with each angle group in sequence to generate corresponding multiple fatigue test conditions.

6. The maintenance system for aerial work machinery according to claim 2, characterized in that: The fatigue damage library building module is also used to: Acquire a plurality of historical operation data of the aerial work machine in a historical time period, wherein the historical operation data include a plurality of historical load data of the actuator and a plurality of historical operation data of the actuator, wherein the plurality of historical operation data include a plurality of historical operation heights and a plurality of historical operation amplitudes of the actuator; Determine an area that the actuator can reach at multiple historical operating heights and multiple historical operating ranges, divide the area into multiple operating areas, and define an area number for each operating area; For multiple historical operation data, determine the area number where each historical operation data is located, and determine the cumulative number of occurrences of each area number in the historical time period; Eliminate the historical area numbers whose cumulative occurrence times are lower than the preset number threshold, and determine the operation areas corresponding to the remaining historical area numbers as the target operation areas that meet the preset conditions; Analyze the multiple historical loads and select target loads that meet preset conditions; Generate fatigue test conditions based on target operating area and target load; For any fatigue test condition, repeatedly perform fatigue test training on the fatigue test condition until fatigue cracks occur in the actuator under the fatigue test condition, and determine the number of training times for the fatigue test condition as the fatigue life of the actuator under the fatigue test condition; Based on the fatigue life of the actuator under each fatigue test condition, the damage value corresponding to each fatigue test condition is determined, and a fatigue damage library is constructed based on the corresponding relationship between each fatigue test condition and the damage value.

7. The maintenance system for aerial work machinery according to claim 6, characterized in that: The analyzing the plurality of historical loads and selecting the target load that meets the preset conditions includes: Performing normal distribution analysis on the multiple historical loads to obtain normal distribution graphs for the multiple historical loads; Based on the normal distribution diagram, historical loads outside a preset interval are eliminated, and the remaining historical loads are determined as target loads that meet preset conditions.

8. The maintenance system for aerial work machinery according to claim 6, characterized in that: The fatigue test condition generated based on the target operating angle and the target torque includes: For each target operation area, the target operation area is sequentially combined with all other target operation areas except the target operation area to obtain a plurality of operation area groups; All target loads are sorted in ascending order to obtain load ranges for all target loads; Dividing the load interval into a plurality of continuous sub-load intervals in sequence based on a preset division ratio; Each sub-load interval is combined with each operating area group in sequence to generate corresponding multiple fatigue test conditions.

9. The maintenance system for aerial work machinery according to claim 1, characterized in that: The maintenance system also includes: An alarm module, used to generate a corresponding alarm signal when the remaining life of any actuator is lower than a preset threshold or when the aerial work machine fails; The operation and maintenance module is used to generate and push an operation and maintenance plan corresponding to the alarm signal when the alarm module generates an alarm signal.

10. The maintenance system for aerial work machinery according to claim 1, characterized in that: The monitoring module comprises: A state detection module, used for analyzing and processing the electrical data and the hydraulic data to obtain the current operating state of the aerial work machine, wherein the electrical data at least includes rotor position data, rotation speed data and temperature data of the motor, and the hydraulic data at least includes pressure data and flow data of the hydraulic pump, and when any one of the electrical data and the hydraulic data is in an abnormal state, it is determined that the aerial work machine has a fault, wherein the operating state includes any one of normal and fault; A fault detection module is used to output a corresponding data label based on the electrical data and the hydraulic data when a fault occurs in the aerial work machinery, and to determine a fault type corresponding to the data label based on a data label library, wherein the data label library includes a plurality of labels and a fault type corresponding to each label, and the fault type includes at least one of a broken rotor bar fault, a stator fault, a bearing fault, a cylinder wear, an oil leakage, and a bearing wear.

11. A high-altitude working machine, characterized in that: include: A maintenance system for aerial work machinery according to any one of claims 1 to 10; Multiple actuators.

Images