Agricultural machine driver operation state identification method based on driving behaviors

Abstract

The invention discloses an agricultural machine driver operation state recognition method based on driving behaviors, and relates to the technical field of agricultural machine intelligence and driving safety monitoring. The problems that an existing operation state recognition method is poor in environment adaptability, insufficient in multi-source data fusion, poor in operation state recognition accuracy and lack of targeted behavior modeling are solved. From the aspects of vehicle speed instability detection, field turning recognition, lane instability detection and operation efficiency detection, the operation state of a driver is accurately evaluated by utilizing multi-source data modeling, and reliable support is provided for intelligent monitoring and active safety control of agricultural machinery. The method is mainly applied to the field of agricultural machine driver operation states.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent agricultural machinery and driving safety monitoring. BACKGROUND

[0002] With the rapid development of intelligent and information technology of agricultural machinery, the operation intensity and complexity of agricultural machinery in agricultural production are continuously improved. During long-time and high-load operation in the field, the driver may cause problems such as speed fluctuation, steering deviation, and operation efficiency reduction due to fatigue, distraction, or operation incoordination, thereby affecting operation efficiency and equipment safety.

[0003] The existing driver operation state recognition technology mainly includes three types of methods based on visual features, physiological signals, and driving behaviors. The visual recognition method is difficult to operate stably in the field environment and has poor environmental applicability due to the influence of light changes, dust shielding, and driver protective equipment. The physiological signal method has high accuracy, but it relies on attached or wearable sensors, is complex to use, and has strong invasiveness, which is not conducive to popularization. The method based on driving behavior has non-invasiveness and real-time performance, but it mainly uses simple threshold judgment or linear weighting model at present, which cannot fully reveal the nonlinear relationship between mechanical characteristics and human control characteristics, and it is also difficult to dynamically reflect the time accumulation effect of the driver's operation state, and the data source is single.

[0004] Therefore, it is necessary to construct a driving behavior recognition system that can fuse multi-source feature signals such as vehicle speed, steering, operation efficiency, field turning, and hydraulic system, and realize mechanical-human feature decoupling and dynamic state evaluation through a nonlinear mathematical model, so as to accurately identify the operation state of the driver while ensuring the operation efficiency, and provide reliable support for intelligent monitoring and active safety control of agricultural machinery. SUMMARY

[0005] The purpose of the present application is to solve the problems of poor environmental adaptability, insufficient multi-source data fusion, poor operation state recognition accuracy, and lack of targeted behavior modeling in the existing operation state recognition method. The present application provides a driving behavior-based agricultural machinery driver operation state recognition method.

[0006] A driving behavior-based agricultural machinery driver operation state recognition method for recognizing the operation state under the operation task, the method comprising:

[0007] According to the deviation of the agricultural machinery operation speed Performing vehicle speed instability detection to obtain a vehicle speed instability index ;

[0008] According to the path deviation amount And the vehicle curvature change rate Performing lane instability detection to obtain a path instability index ;

[0009] Based on turning speed deviation Field turning behavior recognition to obtain turning stability index ;

[0010] Based on the normalized efficiency deviation index Conduct operational efficiency analysis to obtain the driver's operational efficiency anomaly index. ;

[0011] according to and The overall index of unstable pedal operation ;

[0012] according to and Construction direction controls instability index ;

[0013] according to Abnormal index of hydraulic lift ;

[0014] based on , and Calculate the driver's comprehensive work status index ,according to Determine the job status level and complete the job status identification.

[0015] Preferably, the vehicle speed instability index is obtained. The implementation methods include:

[0016] S11, Obtain the deviation of agricultural machinery operation speed The resulting velocity fluctuation energy ;

[0017] ;

[0018] ;

[0019] in, For velocity fluctuation energy, To analyze the length of the time window, At the starting time, For time variables, This refers to the actual operating speed of the vehicle. Given a target vehicle speed;

[0020] S12, according to Determine the vehicle speed instability index ;

[0021] ;

[0022] wherein,

[0023] is a normalization reference energy, is an adjustment factor, is a non-linear amplification coefficient.

[0024] Preferably, the path instability index is implemented by:

[0025] S21, calculating a directional deviation comprehensive energy based on the path deviation amount and the vehicle curvature change rate ;

[0026] ;

[0027] wherein, respectively represent first and second weight coefficients for balancing position deviation and curvature change, is an analysis time window length, is a sampling starting time, is a time variable;

[0028] S22, calculating the path instability index based on ;

[0029] ;

[0030] wherein, is a path deviation reference value.

[0031] Preferably, the turning smoothness index is implemented by:

[0032] S31, calculating a cooperative deviation amount between direction and pedal based on the turning speed deviation ;

[0033] ;

[0034] wherein, is an analysis time window length, is a sampling starting time, is a steering wheel angular velocity, respectively are first and second relative influence degree coefficients representing the first and second relative influence degree coefficients between steering action and speed fluctuation;

[0035] S32, calculating a turning dynamic energy index ;

[0036] ;

[0037] wherein,

[0038] is the analysis time window length (s);

[0039] is the lateral acceleration;

[0040] is the longitudinal acceleration;

[0041] is the start time, is the time variable;

[0042] S33, calculating the cornering smoothness index and the cornering dynamic energy index ; ;

[0043] ;

[0044] wherein, are respectively used for the first and second adjustment coefficients between the balance direction-pedal coordination item and the energy fluctuation item, is the gravity acceleration.

[0045] Preferably, the driver's work efficiency abnormality index is obtained by the following implementation manner:

[0046] ;

[0047] ;

[0048] ;

[0049] ;

[0050] wherein, is the sensitivity adjustment coefficient, is the operation-efficiency correlation index, is the normalized efficiency deviation change rate at the th sampling time, is the actual work efficiency parameter value at the th sampling time, is the actual work efficiency parameter value at the th sampling time, , is the total number of samples within the time window, is a fluctuation coefficient of the work efficiency parameter, is a sampling time interval, is an actual work efficiency parameter mean value, is a work efficiency target value, is a speed of the hydraulic hoist at the is a given constant, is a sign function.

[0051] Preferably, the implementation of the pedal operation instability comprehensive index includes:

[0052] ;

[0053] ;

[0054] wherein, is a coupling disturbance energy, is a reference energy value, is a turning smoothness adjustment factor, is an analysis time window length, is a starting time, is a time variable, is a pedal dynamics deviation, is a vehicle speed fluctuation sensitive coefficient, is a natural constant, is a time decay factor.

[0055] Preferably, the implementation of the direction control instability index includes:

[0056] ;

[0057] ;

[0058] ;

[0059] ;

[0060] wherein, is a direction control cumulative energy, is a direction control reference energy, is a turning smoothness adjustment factor (dimensionless), is an analysis time window length, is a starting time, is a time variable, is a direction response deviation, is a steering wheel angular velocity, is a theoretical direction angle response speed,​ is the actual working vehicle speed, is the front wheel steering angle, is the cornering influence coefficient, is the time growth factor, is the cornering smoothness coupling coefficient, is the front-rear wheel center distance.

[0061] Preferably, the implementation of the hydraulic hoist anomaly index includes:

[0062] ;

[0063] ;

[0064] ;

[0065] wherein, is the key frequency band energy ratio, is the phase lock value, is the efficiency stability adjustment factor, is a given constant, is the total number of samples within the time window, is the imaginary unit, satisfying , is the Hilbert transform, is the complex conjugate operator, the speed of the hydraulic hoist at the th sampling time, is the upper and lower limit value of the key frequency band, is the frequency domain representation of the hydraulic cylinder speed signal, is the frequency variable, is the efficiency anomaly coupling coefficient, is the maximum analysis frequency of the signal.

[0066] Preferably, the implementation of the calculation of includes:

[0067] ;

[0068] ;

[0069] wherein, is the comprehensive feature value, is the sensitivity coefficient, is the natural constant, is the pedal-direction coupling coefficient, is the direction-hoist coupling coefficient, is the hoist-pedal coupling coefficient.

[0070] Preferably, according to The implementation mode of determining the operation state level includes:

[0071] .

[0072] The beneficial effects of the present application:

[0073] The technical scheme of the present application integrates multiple signal sources and adopts dynamic nonlinear calculation, so that the judgment of the driver's state is more accurate and stable. The method does not rely on cameras or wearable devices, avoiding environmental interference such as field light and dust, and is more adaptable. The system simultaneously collects data such as vehicle speed, steering, operation efficiency, turning action, and hydraulic system, forming a complete behavior characteristic system and improving the comprehensiveness of identification. Through nonlinear calculation and dynamic energy model, the complex changes and state accumulation process of driving operation can be effectively described. All analysis is based on the data of the agricultural machinery itself, without the need to increase equipment, and is convenient for integrated application. Finally, according to the comprehensive index, four levels of evaluation of "excellent, general, warning, and danger" are given, and the driver is reminded in time to ensure operation safety and efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0074] Figure 1 is a principle diagram of a driving behavior-based agricultural machinery driver operation state recognition method according to the present application. DETAILED DESCRIPTION

[0075] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0076] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0077] The present application will be further described below in combination with the drawings and specific embodiments, but is not limited by the present application. Specific embodiment one, in combination Figure 1 The present embodiment is described, and the driving behavior-based agricultural machinery driver operation state recognition method according to the present embodiment is used to recognize the operation state under the operation task, and the method includes:

[0078] According to the deviation of the agricultural machinery operation speed The vehicle speed instability detection is performed to obtain the vehicle speed instability index ;

[0079] According to the path deviation amount and vehicle curvature rate of change Lane instability detection is performed, and a path instability index is obtained

[0080] According to the turning speed deviation Field turning behavior recognition is performed, and a turning smoothness index is obtained

[0081] According to the normalized efficiency deviation index Operation efficiency analysis is performed, and a driver operation efficiency anomaly index is obtained

[0082] According to and , a pedal operation instability comprehensive index is constructed

[0083] According to and , a direction control instability index is constructed

[0084] According to , a hydraulic lifter anomaly index is constructed

[0085] Based on , and , a driver comprehensive operation state index is calculated According to , the operation state level is determined, and operation state recognition is completed.

[0086] The present application aims to collect agricultural machinery operation parameters and driver operation behavior data, analyze the characteristics in terms of speed, path, field turning, operation efficiency, etc., and calculate the stability of pedal operation, direction control and lifter operation of the driver, so as to realize the recognition of the driver operation state.

[0087] ​​​​​​The application adopts multi-angle data to construct a feature system, covers multiple dimensions such as vehicle speed, steering, turning behavior and work efficiency, changes the limitation of traditional methods relying on a single signal, and provides more sufficient information for state judgment. Through nonlinear modeling, index calculation, coupling energy and dynamic threshold are introduced to accurately describe the complexity of driving behavior and improve the accuracy and sensitivity of state recognition. Based on time window analysis, energy accumulation and response delay evaluation, the system can capture the law of state change over time, thereby effectively identifying abnormal states such as fatigue and distraction that gradually occur. By analyzing the mutual influence among the pedals, the direction and the lifter, the system can accurately judge the composite operation abnormality. In addition, the model also adopts adaptive mechanisms such as normalization benchmark, sensitivity coefficient and adjustment factor, which can adapt to different operating conditions and driver operation habits, and ensure the stability and practicality of the system.

[0088] Further, according to the deviation of the agricultural machinery operating speed , the speed instability detection is performed to obtain a speed instability index . The implementation mode includes:

[0089] S11, obtaining the speed fluctuation energy caused by the deviation of the agricultural machinery operating speed ; ;

[0090] ;

[0091] ;

[0092] wherein, is the speed fluctuation energy, is the analysis time window length, is the starting time, is the time variable, is the actual operating speed, is the given target speed;

[0093] S12, determining the speed instability index according to ;

[0094] ;

[0095] wherein, is the normalized benchmark energy, used to maintain the comparability between different working conditions, is the adjustment factor, with a value range of [0, 1], used to weight the influence of high-order fluctuation characteristics, is a nonlinear amplification coefficient, usually k≥1, used to enhance the sensitivity when there is a large deviation.

[0096] The preferred embodiment of the vehicle speed instability index acquisition method can sensitively capture abnormal fluctuations in vehicle speed, especially large deviations, through the calculation of speed fluctuation energy and nonlinear amplification processing, and effectively reflects the driver's control stability of the accelerator and brake. By identifying the speed fluctuations caused by the driver's accelerator and brake operation during the operation, the operation speed control stability is quantitatively reflected.

[0097] Further, according to the path deviation amount and the vehicle curvature change rate , the lane instability detection is performed to obtain the path instability index The implementation method includes:

[0098] S21, according to the path deviation amount and the vehicle curvature change rate , the direction deviation comprehensive energy is calculated;

[0099] ;

[0100] wherein, respectively represent the first and second weight coefficients for balancing position deviation and curvature change, is the analysis time window length, is the sampling start time, is the time variable, is used to measure the vehicle path deviation and turning smoothness, is the lateral velocity component (m / s) calculated by the vehicle steering model;

[0101] S22, according to , the path instability index is calculated;

[0102] ;

[0103] wherein, is the path deviation reference value, used to normalize the results under different terrains.

[0104] The preferred embodiment of the path instability index acquisition method combines the path deviation amount and the vehicle curvature change rate to comprehensively evaluate the stability of the driving trajectory, considering both position deviation and turning smoothness, and is suitable for stability analysis of irregular paths in the field.

[0105] The above process is used to identify the stability of the driver's direction control, and whether the driving trajectory is smooth is determined through path deviation and turning curvature analysis.

[0106] Further, according to the turning speed deviation , the field turning behavior recognition is performed to obtain the turning stability index Implementations of the method include:

[0107] S31, calculating a coordination deviation between the steering and the pedals according to the steering speed deviation ;

[0108] ;

[0109] wherein, is the analysis time window length, is the sampling start time, is a dimensionless number, the larger the value, the more uncoordinated the operation; is the steering wheel angular velocity, are respectively the first and second relative influence degree coefficients representing the first and second relative influence degree coefficients between the steering action and the speed fluctuation;

[0110] S32, calculating a steering dynamic energy index ;

[0111] ;

[0112] wherein, is used to reflect the acceleration fluctuation intensity in the steering process;

[0113] is the analysis time window length (s);

[0114] is the lateral acceleration (m / s2), measured by the IMU or the acceleration sensor;

[0115] is the longitudinal acceleration (m / s2), calculated by vehicle dynamics or directly measured by the sensor;

[0116] is the start time, is the time variable;

[0117] S33, calculating a steering smoothness index according to the coordination deviation and the steering dynamic energy index ;

[0118] ;

[0119] wherein, takes a value (0-1), the closer to 1, the more stable the operation, are respectively the first and second adjustment coefficients for balancing the first and second adjustment coefficients between the steering-pedal coordination item and the energy fluctuation item, is the gravitational acceleration.

[0120] ​In this preferred embodiment, the method of obtaining the turning stability index is to achieve a quantitative assessment of the coordination between the steering wheel angular velocity and speed fluctuation, combined with the dynamic energy of lateral and longitudinal acceleration, thereby improving the accuracy of turning behavior recognition.

[0121] By constructing a lateral-longitudinal motion coupling model based on vehicle dynamics, the coordination between steering wheel and pedal operation during turning is analyzed, thereby achieving a quantitative assessment of the accuracy, smoothness, and operational coordination of turning actions.

[0122] Furthermore, based on the normalized efficiency deviation index Conduct operational efficiency analysis to obtain the driver's operational efficiency anomaly index. The implementation methods include:

[0123] ;

[0124] ;

[0125] ;

[0126] ;

[0127] in, The operation-efficiency correlation index is dimensionless and ranges from [0,1]. A larger value indicates a greater mismatch between changes in operation and efficiency. This is the sensitivity adjustment coefficient. For the first The rate of change of normalized efficiency deviation at each sampling time For the first The actual measured value of the work efficiency parameter at each sampling time. For the first The actual measured value of the work efficiency parameter at each sampling time. , The total number of samples within the time window. The fluctuation coefficient is the parameter for work efficiency. The sampling time interval, This represents the average of the actual measured work efficiency parameters. The target value for work efficiency. For the first The speed of the hydraulic lift at each sampling time. Given a constant, It is a symbolic function.

[0128] The driver work efficiency anomaly index obtained in this preferred embodiment In one implementation, the degree of matching between operation and efficiency is revealed by correlating the hydraulic lift speed and the work efficiency change, the efficiency reduction caused by improper operation can be identified, and the control perception of work quality can be enhanced. The above process is used to monitor the actual work (plowing, seeding, fertilizing, etc.) efficiency, analyze the degree of correlation between the driver's operation (especially the lift action) and the work efficiency, and then identify the operation stability and abnormal fluctuations.

[0129] Further, according to and , the pedal operation instability comprehensive index is constructed. The implementation of the pedal operation instability comprehensive index includes:

[0130] ;

[0131] ;

[0132] wherein, is the coupling disturbance energy, is the reference energy value, is the turning stability adjustment factor, is the analysis time window length, is the starting time, is the time variable, is the pedal dynamics deviation, is the vehicle speed fluctuation sensitive coefficient (dimensionless), is a natural constant, is a time decay factor, is the time variable.

[0133] The preferred embodiment of the pedal operation instability comprehensive index implementation integrates vehicle speed instability and turning stability, dynamically evaluates the coordination of pedal operation in straight and turning processes through the coupling disturbance energy model, and improves the identification ability of pedal rhythm imbalance.

[0134] Further, according to and , the direction control instability index is constructed. The implementation of the direction control instability index includes:

[0135] ;

[0136] ;

[0137] ;

[0138] ;

[0139] wherein, is the direction control cumulative energy, is the direction control reference energy, is the turning smoothness adjustment factor (dimensionless), is the analysis time window length, is the starting time, is the time variable, is the direction response deviation, is the steering wheel angular velocity, is the theoretical direction angle response speed, is the actual working vehicle speed, is the front wheel turning angle, is the turning influence coefficient, is the time growth factor, is the turning smoothness coupling coefficient, is the front-rear wheel center distance.

[0140] The preferred embodiment is configured to construct a direction control instability index In the implementation mode, the path stability and the turning smoothness are combined, the direction response lag and the dynamics analysis are realized, the nonlinear evaluation of the steering wheel operation quality is realized, and the direction control stability identification suitable for straight line and turning scene is realized. It is used to evaluate the smoothness of the driver's steering wheel operation and the coordination of the direction control, especially the direction response quality in the process of straight line driving and turning. The path instability index and the turning smoothness index are combined, the direction dynamics and response lag analysis are realized, and the nonlinear evaluation of the direction control stability is realized.

[0141] Further, according to , the hydraulic lifter abnormality index is constructed

[0142] ;

[0143] ;

[0144] ;

[0145] wherein, is the key frequency band energy ratio, is the phase locking value, is the efficiency stability adjustment factor, is a given constant, is the total number of samples in the time window, is the imaginary unit, satisfying , is the Hilbert transform, is the complex conjugate operator, The first a speed of the hydraulic hoist at a sampling moment, upper and lower limit values of a critical frequency band, a frequency domain representation of the hydraulic cylinder speed signal, a frequency variable, an abnormal coupling coefficient of efficiency, a maximum analysis frequency of a signal.

[0146] The preferred embodiment constructs an abnormal index of the hydraulic hoist In an implementation mode of the abnormal index of the hydraulic hoist, a frequency domain analysis and a phase coupling mechanism are introduced, and an operation efficiency abnormal index is constructed, which can dynamically identify whether the hydraulic system operation is stable and matches the current operation demand, and improves the diagnosis capability of the abnormal state of the hoist.

[0147] Further, based on , and , an implementation mode of calculating a comprehensive operation state index of the driver includes:

[0148] ;

[0149] ;

[0150] An implementation mode of determining the operation state level according to includes:

[0151] ;

[0152] wherein, is a comprehensive feature value, is a sensitivity coefficient, is a natural constant, is a pedal-direction coupling coefficient (dimensionless), a system preset parameter, used to adjust the interaction between pedal operation instability and direction instability, is a direction-hoist coupling coefficient (dimensionless), a system preset parameter, used to adjust the interaction between direction instability and hoist abnormality, is a hoist-pedal coupling coefficient (dimensionless), a system preset parameter, used to adjust the interaction between hoist abnormality and pedal operation instability.

[0153] In the above mode of calculating the comprehensive operation state index of the driver , the instability indexes of the three dimensions of the pedal, the direction and the hoist are fused by a nonlinear method, and coupling coefficients are introduced to model the interaction, so as to realize comprehensive, dynamic and graded evaluation of the overall operation state of the driver, and support intelligent early warning and safety decision.

[0154] The final decision step of the present application is used to comprehensively evaluate the overall working state of the driver and output a state grade. , and As the main basis, through nonlinear fusion and dynamic threshold mapping, the intelligent identification of the driver's "excellent", "general", "warning" and "danger" states is realized.

[0155] While the application has been described with reference to particular embodiments, it will be understood that the examples are merely illustrative of the principles and applications of the application. It will be understood that numerous modifications can be made to the illustrative examples and that other arrangements can be devised without departing from the spirit and scope of the present application as defined by the appended claims. It will be understood that the features of the various embodiments can be combined with each other, in different ways than as described in the examples. It will be understood that features described in relation to one example can be used in other examples.

Claims

1. A driving behavior-based agricultural machine operator work state recognition method, characterized by, The method for identifying the working state of a working task comprises: According to the deviation of the agricultural machinery operation speed A vehicle speed instability detection is performed to obtain a vehicle speed instability index ; According to the path deviation amount And the vehicle curvature change rate Carry out lane instability detection, obtain path instability index ; According to the turning speed deviation The field turning behavior recognition is performed to obtain the turning stability index ; According to the normalized efficiency deviation index An operation efficiency analysis is performed to obtain a driver operation efficiency abnormality index ; According to and , a pedal operation instability comprehensive index is configured; According to and , the direction control instability index is configured According to , a hydraulic hoist anomaly index ; Based on , and , the driver comprehensive work state index is calculated, the work state level is determined according to , and the work state recognition is completed.

2. The method according to claim 1, characterized in that, Obtaining a vehicle speed instability index Implementations include: S11, obtaining a speed deviation caused by agricultural machinery operation energy of speed fluctuation caused by agricultural machinery operation ; ； ； wherein, is the speed fluctuation energy, is the analysis time window length, is the start time, is the time variable, is the actual work vehicle speed, is the given target vehicle speed; S12、According to , determining the vehicle speed instability index ; ； Wherein, is a normalization reference energy, is a modulation factor, is a nonlinear amplification coefficient.

3. The method according to claim 1, characterized in that, Acquiring a path instability index Implementations include: S21, calculating the path deviation amount and the vehicle curvature change rate , calculating the directional deviation comprehensive energy ; ； wherein, respectively represent first and second weight coefficients for balancing position deviation and curvature variation, is an analysis time window length, is a sampling start time, is a time variable; S22、According to , the path instability index is calculated ; ； wherein is the path deviation reference value.

4. The method according to claim 1, characterized in that, Obtaining a cornering stability index Implementations include: S31, calculating a deviation of the direction from the pedal in accordance with the turning speed deviation ;​ ； wherein, is the analysis time window length, is the sampling start time, is the steering wheel angular velocity, are the first and second relative influence degree coefficients representing the first and second relative influence degree between steering action and speed fluctuation, respectively; S32, calculate the turning dynamic energy index ; ； Wherein, to analyze the length of the time window (s); is the lateral acceleration; is the longitudinal acceleration; t0 is the start time, t is the time variable; S33、according to the cooperative deviation amount and the turning dynamic energy index , calculate the turning smoothness index ; ； wherein, respectively for balancing the first and second adjustment coefficients between the direction-pedal coordination term and the energy fluctuation term, is the gravitational acceleration.

5. The method according to claim 1, wherein Acquiring a driver work efficiency abnormality index Implementations include: ； ； ； ； wherein, is a sensitivity adjustment coefficient, is an operation-efficiency correlation index, is a normalized efficiency deviation change rate at the th sampling time, is an actual operation efficiency parameter value at the th sampling time, is an actual operation efficiency parameter value at the th sampling time, , is a total number of samplings within a time window, is an operation efficiency parameter fluctuation coefficient, is a sampling time interval, is an actual operation efficiency parameter mean value, is an operation efficiency target value, is a velocity of the hydraulic hoist at the th sampling time, is a given constant, is a sign function.

6. The method according to claim 1, wherein A constructed pedal operation instability index Implementations include: ； ； wherein, is a coupling disturbance energy, is a reference energy value, is a turn smoothness adjustment factor, is an analysis time window length, is a start time instant, is a time variable, is a pedal dynamics deviation, is a vehicle speed fluctuation sensitivity coefficient, is a natural constant, is a time decay factor.

7. The method according to claim 1, wherein A construction direction control instability index Implementations include: ； ； ； ； wherein, is a direction control accumulated energy, is a direction control reference energy, is a turning smoothness adjustment factor (dimensionless), is an analysis time window length, is a start time, is a time variable, is a direction response deviation, is a steering wheel angular velocity, is a theoretical direction angle response speed, is an actual work vehicle speed, is a front wheel turning angle, is a turning influence coefficient, is a time growth factor, is a turning smoothness coupling coefficient, is a front-rear wheel center distance.

8. The method according to claim 5, wherein Constructing a hydraulic hoist anomaly index Implementations include: ； ； ； wherein, is a key band energy ratio, is a phase lock value, is an efficiency stability adjustment factor, is a given constant, is a total number of samples within a time window, is an imaginary unit satisfying , is a Hilbert transform, is a complex conjugate operator, the speed of the hydraulic hoist at the th sampling instant, are upper and lower limit values of the key band, is a frequency domain representation of the hydraulic cylinder speed signal, is a frequency variable, is an efficiency abnormal coupling coefficient, is a signal maximum analysis frequency.

9. The method according to claim 1, wherein Computing Implementations include: ； ； wherein, is a comprehensive characteristic value, is a sensitivity coefficient, is a natural constant, is a pedal-direction coupling coefficient, is a direction-lifter coupling coefficient, is a lifter-pedal coupling coefficient.

10. The method according to claim 1, wherein According to The implementation of determining the job status level includes: 。

Images