Crane operation controllability health state assessment method and device

Abstract

The invention discloses a crane operation controllability health state evaluation method and device in the technical field of engineering machinery, and aims to solve the problem that in the prior art, judgment is performed only by depending on a single type of signals, and collaborative analysis of multi-dimensional indexes is lacked. The method comprises the following steps: in response to a collected sensor signal, carrying out data processing to obtain sensor data; calculating a real-time index according to the sensor data; acquiring a real-time working condition, and dynamically adjusting a scoring weight according to the real-time working condition; calculating a health score according to the real-time index and the score weight; according to the method, various real-time indexes are acquired by adopting various sensor signals, and meanwhile, the score weight is adjusted according to the real-time working condition to acquire the health score, so that the health state evaluation work is cooperatively completed through different indexes, and the method has the adaptive adjustment capability for different working conditions, and is suitable for popularization and application. And the health score in a complex scene is prevented from deviating from an actual state.

Description

Technical Field

[0001] The present invention relates to a method and device for evaluating the health status of crane operation maneuverability, and belongs to the technical field of engineering machinery. Background Art

[0002] Currently, mainstream technical solutions for crane operability health assessment can be categorized into three categories: single-signal analysis-based assessment methods, historical data modeling-based prediction methods, and multi-sensor fusion-based diagnostic methods. Single-signal analysis-based assessment methods collect a single signal from a crane subsystem, extract characteristic values, and compare them with preset thresholds to determine the equipment's health status. For example, a fixed threshold is set based on the root mean square (RMS) value of the vibration acceleration signal to trigger an alarm. Historical data modeling-based prediction methods accumulate historical crane operating data (such as motor current and operating frequency) to construct statistical models to predict equipment lifespan or health trends. For example, the accumulated operating time of a hoisting motor is combined with an MTBF (mean time between failure) model to estimate the remaining lifespan. Multi-sensor fusion-based diagnostic methods deploy multiple sensor types (such as speed, pressure, and temperature) and use data fusion technology to comprehensively determine health status. Traditional methods typically rely on static thresholds based on single physical indicators (such as vibration amplitude or hydraulic pressure) or rely on periodic manual inspections to obtain discrete data. These methods struggle to achieve real-time correlation analysis between operability and health status in complex and changing crane operating scenarios. At the same time, traditional architectures often utilize centralized data processing (e.g., uploading all data to the cloud), resulting in excessive latency in the real-time calculation of key indicators, making them unable to meet low-latency control requirements such as emergency shutdowns of operating systems. Furthermore, existing models have fixed weight parameters and lack the ability to adapt to diverse crane operating conditions (e.g., varying lift weights, ambient temperature and humidity, and operating habits). This can lead to health scores deviating from actual conditions in complex scenarios.

[0003] The evaluation methods of existing technologies usually rely on only a single type of signal (such as winch speed error or vibration acceleration amplitude) for judgment, and lack the coordinated analysis of multi-dimensional indicators; and generally adopt fixed judgment criteria, but do not consider the influence of working parameters such as load weight and ambient temperature, resulting in large errors in the evaluation results, affecting the evaluation effect. Summary of the Invention

[0004] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method and device for evaluating the health status of crane operation controllability, which uses multiple sensor signals to obtain multiple real-time indicators, and adjusts the scoring weights according to the real-time working conditions to obtain a health score, thereby collaboratively completing the health status assessment work through different indicators, and having the ability to adaptively adjust to different working conditions, avoiding the health score in complex scenarios from deviating from the actual status, and ensuring the accuracy of the assessment.

[0005] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions: In a first aspect, the present invention provides a method for evaluating the health status of crane operation operability, comprising the following steps: In response to the collected sensor signals, performing data processing to obtain sensor data; Calculate real-time metrics based on sensor data; Obtain real-time working conditions and dynamically adjust the scoring weights based on the real-time working conditions; Calculate health scores based on real-time indicators and scoring weights; Obtain historical real-time indicators and corresponding health scores, input the historical real-time indicators and corresponding health scores into a pre-built and trained model, and obtain the predicted health score for a certain period of time in the future; The health score and predicted health score are compared with the preset thresholds, and the alarm strategy is determined based on the comparison results to complete the health assessment.

[0006] Furthermore, it also includes obtaining historical indicator data and using a time series clustering algorithm to divide the health level based on the historical indicator data; Compare the health score with the divided health levels, and obtain the real-time health level based on the comparison result; The health grades include excellent, good and poor.

[0007] Furthermore, the data processing specifically includes adaptive wavelet denoising, multi-signal normalization and synchronization, and abnormal data removal.

[0008] Furthermore, the sensor data includes a vibration signal, a handle signal and a speed signal; The adaptive wavelet denoising specifically includes: The method of combining wavelet decomposition with dynamic threshold is used to retain the low-frequency approximation coefficients in the vibration signal and perform nonlinear soft threshold processing on the high-frequency detail coefficients in the vibration signal. The multi-signal normalization and synchronization specifically includes: Normalize the handle and speed signals linearly to the [0, 1] range, normalize the vibration signals based on the peak value, and timestamp the sensor signals using the edge hardware clock. The abnormal data removal specifically includes: Perform windowed variance calculation on the speed signal to compare whether the sudden increase in the speed signal exceeds the historical threshold. Based on the comparison result, determine whether the speed signal during this period is included in the calculation of the real-time indicator.

[0009] Furthermore, the calculation of real-time indicators based on sensor data specifically includes: The real-time indicators include rapidity indicators, accuracy indicators and stability indicators; Obtain the motion characteristics of the actuator based on sensor data; The rapidity index is the response time from the issuance of a handle command to the arrival of the motion characteristics of the operating system actuator at the target value; The accuracy index is the steady-state error rate of the motion characteristics of the operating system actuator after the handle signal reaches stability; The stability index is the frequency domain energy of the vibration signal of the operating system actuator after the handle signal reaches stability.

[0010] Furthermore, the real-time working conditions include lifting weight, arm length, ambient temperature and engine speed.

[0011] Furthermore, the health score is calculated based on the real-time indicators and the scoring weights. The specific expression is as follows: ; Where: Score your health, 、 、 is the scoring weight, is a rapidity indicator, is the accuracy indicator, It is an indicator of stability.

[0012] Furthermore, the health score and the predicted health score are compared with a preset threshold, and an alarm strategy is determined based on the comparison result, specifically including: The preset threshold includes a first threshold and a second threshold; Compare the health score with the first threshold and issue a level 1 alert. If the health score is lower than the first threshold, an early warning is pushed to the human-machine interface; otherwise, the first-level alarm work ends; Based on the predicted health score, a limited health score is obtained, and the limited health score is compared with the second threshold to complete the second-level alarm; Among them, if the limited health score is less than the second threshold, a maintenance work order is generated and assigned to the maintenance terminal; otherwise, the second-level alarm work ends.

[0013] In a second aspect, the present invention provides a crane operation maneuverability health status assessment system, comprising a vehicle-mounted layer, an edge layer, and a cloud layer; The vehicle-mounted layer is used to collect sensor signals; The edge layer comprises: Data processing module: in response to the collected sensor signals, performs data processing and obtains sensor data; Index calculation module: calculates real-time indicators based on sensor data; The cloud layer includes: Calculation module: obtains real-time working conditions and dynamically adjusts scoring weights based on real-time working conditions; calculates health scores based on real-time indicators and scoring weights; Model output module: obtains historical real-time indicators and corresponding health scores, inputs the historical real-time indicators and corresponding health scores into the pre-built and trained model, and obtains the predicted health score; Evaluation module: compares the health score and predicted health score with the preset threshold, determines the alarm strategy based on the comparison results, and completes the health assessment.

[0014] Furthermore, it also includes a terminal layer, which is used to receive and display the health score of the calculation module, the predicted health score of the model output module and the alarm strategy of the evaluation module.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This crane operation and control health status assessment method uses multiple sensor signals to obtain multiple real-time indicators. It also adjusts the scoring weights based on the real-time operating conditions to obtain a health score. This method collaboratively completes the health status assessment through different indicators. It also has the ability to adaptively adjust to different operating conditions, preventing the health score from deviating from the actual status in complex scenarios and ensuring the accuracy of the assessment. 2. The edge layer of the crane operation control health status assessment device can be integrated into the vehicle layer, so that the corresponding calculation process is carried out in the vehicle, and then the calculation results are sent to the cloud layer, avoiding excessive calculation delays and ensuring the efficiency of the health assessment work. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 1 is a flow chart of a method for evaluating the health status of crane operation maneuverability according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the working process of a device for evaluating the health status of crane operation maneuverability according to an embodiment of the present invention; Figure 3 2 is a schematic diagram of the system structure of a crane operation maneuverability health status assessment device provided according to an embodiment of the present invention; Figure 4 Schematic diagram of the installation structure of the sensor provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0018] The term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. Additionally, the character " / " generally indicates an "or" relationship between the related objects. Example 1:

[0019] like Figure 1 As shown, the present invention provides a method for evaluating the health status of crane operation maneuverability, comprising the following steps: In response to the collected sensor signals, performing data processing to obtain sensor data; Calculate real-time metrics based on sensor data; Obtain real-time working conditions and dynamically adjust the scoring weights based on the real-time working conditions; Calculate health scores based on real-time indicators and scoring weights; Obtain historical real-time indicators and corresponding health scores, input the historical real-time indicators and corresponding health scores into a pre-built and trained model to obtain a predicted health score; The health score and predicted health score are compared with the preset thresholds, and the alarm strategy is determined based on the comparison results to complete the health assessment.

[0020] One embodiment further includes obtaining historical indicator data, and using a time series clustering algorithm to divide the health levels according to the historical indicator data; Compare the health score with the divided health levels, and obtain the real-time health level based on the comparison result; The health grades include excellent, good and poor.

[0021] Specifically, in actual applications, when it is necessary to explain the health score to the customer, the real-time health level can be used to facilitate the customer's understanding of the health status.

[0022] In one embodiment, the data processing specifically includes adaptive wavelet denoising, multi-signal normalization and synchronization, and abnormal data removal; the sensor data includes vibration signals, handle signals, and speed signals; The adaptive wavelet denoising specifically includes: In response to the mixed environmental noise in the vibration signal, a combination of wavelet decomposition and dynamic thresholding is used to retain the low-frequency approximation coefficients in the vibration signal (corresponding to the winch fundamental frequency component) and perform nonlinear soft thresholding on the high-frequency detail coefficients in the vibration signal; The multi-signal normalization and synchronization specifically includes: The handle signal and speed signal are linearly normalized to the range [0, 1], and the vibration signal is normalized based on the peak value to prevent amplitude saturation. The edge hardware clock is used to timestamp the sensor signal to solve the timing misalignment problem caused by sampling rate differences. The abnormal data removal specifically includes: Perform windowed variance calculation on the speed signal to compare whether the sudden increase in the speed signal exceeds the historical threshold (optional, the historical threshold is three times the historical mean). Based on the comparison result, determine whether the speed signal during this period is included in the calculation of real-time indicators. For example, if it exceeds the historical threshold, it is determined to be an abnormal operating condition (such as emergency braking), and the data during this period is marked as not included in the health score.

[0023] In one embodiment, the calculating of real-time indicators based on sensor data specifically includes: The real-time indicators include rapidity indicators, accuracy indicators and stability indicators; Obtain the motion characteristics of the actuator based on sensor data; The rapidity index is the response time from the issuance of a handle command to the arrival of the motion characteristics of the operating system actuator at the target value; The accuracy index is the steady-state error rate of the motion characteristics of the operating system actuator after the handle signal reaches stability; The stability index is the frequency domain energy of the vibration signal of the operating system actuator after the handle signal reaches stability.

[0024] Specifically, speed is the response time from the time the handle command is issued to the time the motion characteristics (such as speed and angular velocity) of the operating system actuator reach 90% of the preset value (i.e., the target value). To portray; Accuracy, the steady-state error rate of the motion characteristics (such as speed and angular velocity) of the operating system actuator after the handle signal reaches stability To portray; Stability, the frequency domain energy of the vibration signal of the operating system actuator after the handle signal reaches stability To portray.

[0025] In one embodiment, the real-time operating conditions include lifting weight, arm length, ambient temperature and engine speed.

[0026] In one embodiment, the health score is calculated based on the real-time indicators and the scoring weights. The specific expression is as follows: ; Where: Score your health, 、 、 is the scoring weight, is a rapidity indicator, is the accuracy indicator, It is an indicator of stability.

[0027] In one embodiment, comparing the health score and the predicted health score with a preset threshold and determining an alarm strategy based on the comparison result specifically includes: The preset threshold includes a first threshold and a second threshold; Compare the health score with the first threshold and issue a level 1 alert. If the health score is lower than the first threshold, an early warning is pushed to the human-machine interface; otherwise, the first-level alarm work ends; Based on the predicted health score, a limited health score is obtained, and the limited health score is compared with the second threshold to complete the second-level alarm; Among them, if the limited health score is less than the second threshold, a maintenance work order is generated and assigned to the maintenance terminal; otherwise, the second-level alarm work ends.

[0028] Specifically, the first threshold and the second threshold are dynamically modified according to the service life of the equipment (the longer the service life, the lower the threshold).

[0029] In one embodiment, the health assessment of a bridge crane hoisting system is as follows: The system configuration includes sensor configuration: handle displacement sensor with a range of 0-10V, corresponding to a stroke of 0-100%; winch speed encoder with a resolution of 0.1rpm; three-axis MEMS sensor (range ±50g), installed in the radial direction of the winch mechanism bearing seat, with a sampling rate of 500Hz.

[0030] Edge hardware: Embedded industrial computer (NVIDIA Jetson Xavier NX) with built-in FPGA (field programmable gate array) acceleration module and communication interfaces supporting RS485 / CAN / 4G.

[0031] The real-time indicator is calculated as follows: Speediness Index : Calculate the response time from the issuance of the handle command to the winch speed reaching 90% of the target value, and set the threshold Tmax = 2.0s (exceeding the limit triggers an early warning); Accuracy indicators : The allowable range of steady-state speed error rate is ≤5%. If it exceeds the limit for three consecutive times, the data will be marked as abnormal; Stability index : The vibration frequency domain energy threshold is set to Evibmax=1000m / s2⋅Hz.

[0032] Data input: Health score series for the past 30 days, i.e., historical real-time indicators and corresponding health scores (window length 7 days, step length 1 day), superimposed working condition parameters (lifting weight, ambient temperature); LSTM model configuration: 30 nodes in the input layer, 64 nodes in the hidden layer, and 7 nodes in the output layer (for predicting ratings for the next 7 days); Dynamic weight adjustment: When the lifting weight is greater than 40 tons, the weight From 0.3 to 0.5; Model delivery: Incremental parameter packages (average size 1.2MB) are delivered every Friday morning and loaded after verification on the edge.

[0033] The present invention uses multiple sensor signals to obtain multiple real-time indicators, and adjusts the scoring weights according to the real-time working conditions to obtain a health score, thereby collaboratively completing the health status assessment through different indicators, and has the ability to adaptively adjust to different working conditions, avoiding the health score in complex scenarios from deviating from the actual status and ensuring the accuracy of the assessment. Example 2:

[0034] like Figure 3 As shown, the present invention provides a crane operation maneuverability health status assessment system, which is characterized by comprising a vehicle-borne layer, an edge layer and a cloud layer; The vehicle-mounted layer is used to collect sensor signals; The edge layer comprises: Data processing module: in response to the collected sensor signals, performs data processing and obtains sensor data; Index calculation module: calculates real-time indicators based on sensor data; The cloud layer includes: Calculation module: obtains real-time working conditions and dynamically adjusts scoring weights based on real-time working conditions; calculates health scores based on real-time indicators and scoring weights; Model output module: obtains historical real-time indicators and corresponding health scores, inputs the historical real-time indicators and corresponding health scores into the pre-built and trained model, and obtains the predicted health score; Evaluation module: compares the health score and predicted health score with the preset threshold, determines the alarm strategy based on the comparison results, and completes the health assessment. One embodiment further includes a terminal layer, which is used to receive and display the health score of the computing module, the predicted health score of the model output module, and the alarm strategy of the evaluation module.

[0035] Among them, the vehicle-mounted layer collects sensor signals through the vehicle-mounted acquisition module; the edge computing module includes a data processing module and an indicator calculation module; the health score generation module is the calculation module; and the LSTM model training module is the model output module.

[0036] Specifically, if Figure 2 As shown, the vehicle-mounted layer is used to install the sensors required for signal acquisition of the operating subsystem and deploy the signal acquisition module. According to the data analysis requirements, the signal acquisition module performs high-frequency acquisition of specific address signals.

[0037] The edge layer is equipped with an on-board edge computing device. The computing device is based on the real-time Linux operating system and uses C++ language to develop embedded software with real-time and efficient processing capabilities. It communicates with the existing controller through the vehicle bus and requests the sensor data that has been collected and processed by the controller. The software includes signal preprocessing and real-time indicator calculation functions at the edge of the operation controllability. The operation controllability analysis includes the speed, accuracy and stability analysis of the operation system.

[0038] The cloud layer is used to receive data uploaded by the edge layer, support model training, carry out health score modeling and trend prediction, send model update packages to edge nodes, and optimize local diagnostic accuracy.

[0039] The cloud layer receives historical data uploaded by the edge layer and uses a time series clustering algorithm (K-means) to classify the health level (excellent, good, and poor). It trains an LSTM model (recurrent neural network model) to predict indicator degradation trends and generate a health score. When the score falls below the threshold, a maintenance alarm is triggered and the updated model is sent to the edge layer.

[0040] Optional, the "fast, accurate, and stable" indicators (speed index) of edge layer upload , accuracy index , stability indicators ) to perform dynamic normalization to eliminate the impact of different dimensions and construct a time series feature matrix based on the sliding time window.

[0041] The data storage cluster module is used to: use the K-means algorithm optimized by dynamic time warping (DTW) to define three health levels: excellent, good, and poor, based on the distribution of cluster centers and the association with historical maintenance records. Equipment operating condition labels (such as lifting weight and ambient temperature) are introduced as clustering constraints to ensure that equipment in the same health state has similar operating backgrounds.

[0042] An embodiment takes real-time indicators in the past 30 days and corresponding health scores as input, and takes future 7-day health score prediction values and confidence intervals (such as 80% confidence) as output; the score weight is dynamically adjusted according to the real-time working condition, and the weight adjustment rule is optimized through reinforcement learning (DQN algorithm), and the objective function is to minimize the weighted sum of prediction error and maintenance cost.

[0043] The first threshold and the second threshold are dynamically corrected according to the equipment service life (the longer the service life, the lower the threshold); the first-level alarm (health score < first threshold): push the early warning to the man-machine interface; the second-level alarm (predicted health score < second threshold for 3 consecutive days): automatically generate a maintenance work order and distribute it to the maintenance terminal.

[0044] The terminal layer includes developing an APP on a mobile terminal, displaying the degradation trend of the operation controllability indicator, the health score and the alarm information, and supporting operator feedback confirmation.

[0045] An embodiment, the installation of the sensor is as shown in Figure 4 The edge device is a sealed dustproof industrial computer, including a signal input interface, a bus receiving sensor data, a computing core and a communication unit.

[0046] The edge layer of the present application can be integrated on the vehicle layer, so that the corresponding calculation process is carried out in the vehicle, and then the calculation result is sent to the cloud layer, avoiding too high calculation delay, and ensuring the work efficiency of the health assessment work.

[0047] Optionally, the edge layer can be integrated in the cloud layer according to actual needs, and all sensor data is directly uploaded to the cloud for unified processing, and the powerful computing power of the cloud is used to realize complex model training (such as deep neural network).

[0048] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0049] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0050] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0052] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A crane operation maneuverability health status assessment method, characterized in that: The following steps are involved: In response to the collected sensor signals, performing data processing to obtain sensor data; Calculate real-time metrics based on sensor data; Obtain real-time working conditions and dynamically adjust the scoring weights based on the real-time working conditions; Calculate health scores based on real-time indicators and scoring weights; Obtain historical real-time indicators and corresponding health scores, input the historical real-time indicators and corresponding health scores into a pre-built and trained model to obtain a predicted health score; The health score and predicted health score are compared with the preset thresholds, and the alarm strategy is determined based on the comparison results to complete the health assessment.

2. The crane operation maneuverability health status assessment method according to claim 1, characterized in that: It also includes obtaining historical indicator data and using a time series clustering algorithm to divide health levels based on the historical indicator data; Compare the health score with the divided health levels, and obtain the real-time health level based on the comparison result; The health grades include excellent, good and poor.

3. The crane operation maneuverability health status assessment method according to claim 1, characterized in that: The data processing specifically includes adaptive wavelet denoising, multi-signal normalization and synchronization, and abnormal data elimination.

4. The crane operation maneuverability health status assessment method according to claim 3, characterized in that: The sensor data includes vibration signals, handle signals and speed signals; The adaptive wavelet denoising specifically includes: The method of combining wavelet decomposition with dynamic threshold is used to retain the low-frequency approximation coefficients in the vibration signal and perform nonlinear soft threshold processing on the high-frequency detail coefficients in the vibration signal. The multi-signal normalization and synchronization specifically includes: Normalize the handle and speed signals linearly to the [0, 1] range, normalize the vibration signals based on the peak value, and timestamp the sensor signals using the edge hardware clock. The abnormal data removal specifically includes: Perform windowed variance calculation on the speed signal to compare whether the sudden increase in the speed signal exceeds the historical threshold. Based on the comparison result, determine whether the speed signal during this period is included in the calculation of the real-time indicator.

5. The crane operation maneuverability health status assessment method according to claim 1, characterized in that: The calculation of real-time indicators based on sensor data specifically includes: The real-time indicators include rapidity indicators, accuracy indicators and stability indicators; Obtain the motion characteristics of the actuator based on sensor data; The rapidity index is the response time from the issuance of a handle command to the arrival of the motion characteristics of the operating system actuator at the target value; The accuracy index is the steady-state error rate of the motion characteristics of the operating system actuator after the handle signal reaches stability; The stability index is the frequency domain energy of the vibration signal of the operating system actuator after the handle signal reaches stability.

6. The crane operation maneuverability health status assessment method according to claim 1, characterized in that: The real-time working conditions include lifting weight, arm length, ambient temperature and engine speed.

7. The crane operation maneuverability health status assessment method according to claim 5, characterized in that: The health score is calculated based on real-time indicators and scoring weights. The specific expression is as follows: ； Where: Score your health, 、 、 is the scoring weight, is a rapidity indicator, is the accuracy indicator, It is an indicator of stability.

8. The crane operation maneuverability health status assessment method according to claim 1, characterized in that: The health score and the predicted health score are compared with a preset threshold, and an alarm strategy is determined based on the comparison result, specifically including: The preset threshold includes a first threshold and a second threshold; Compare the health score with the first threshold and issue a level 1 alert. If the health score is lower than the first threshold, an early warning is pushed to the human-machine interface; otherwise, the first-level alarm work ends; Based on the predicted health score, a limited health score is obtained, and the limited health score is compared with the second threshold to complete the second-level alarm; Among them, if the limited health score is less than the second threshold, a maintenance work order is generated and assigned to the maintenance terminal; otherwise, the second-level alarm work ends.

9. A crane operation maneuverability health status assessment system, characterized in that: Including vehicle layer, edge layer and cloud layer; The vehicle-mounted layer is used to collect sensor signals; The edge layer comprises: Data processing module: in response to the collected sensor signals, performs data processing and obtains sensor data; Index calculation module: calculates real-time indicators based on sensor data; The cloud layer includes: Calculation module: obtains real-time working conditions and dynamically adjusts scoring weights based on real-time working conditions; calculates health scores based on real-time indicators and scoring weights; Model output module: obtains historical real-time indicators and corresponding health scores, inputs the historical real-time indicators and corresponding health scores into the pre-built and trained model, and obtains the predicted health score; Evaluation module: compares the health score and predicted health score with the preset threshold, determines the alarm strategy based on the comparison results, and completes the health assessment.

10. The crane operation maneuverability health status assessment system according to claim 9, characterized in that: It also includes a terminal layer, which is used to receive and display the health score of the calculation module, the predicted health score of the model output module and the alarm strategy of the evaluation module.

Images