Crane remote operation control method and system

Abstract

The present application relates to the technical field of crane remote operation control, and specifically discloses a crane remote operation control method and system, the method comprising: collecting the theoretical feedback force and the actual feedback force of crane remote operation, and extracting the cumulative distortion sequence through joint distortion criterion; secondly, extracting the coupling analysis features of the dynamic parameters of the hoisted object and the cumulative distortion sequence, customizing the dynamic calibration baseline of the actual feedback force for different risks; and thirdly, adjusting the output force of the operating lever based on the calibration baseline, analyzing the matching of the operator behavior features and the distortion accumulation, and determining whether cognitive overload exists; if overload exists, constructing an overload scene dataset to determine the early warning feature time, and generating the personalized optimal feedback force mapping relationship through a relationship adaptation model. The system comprises a distortion extraction module, a baseline calibration module, an overload identification module, and a feedback adjustment module. The present application is conducive to correcting feedback force distortion and relieving operator cognitive overload.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of remote operation control of cranes, in particular to a crane remote operation control method and system. BACKGROUND

[0002] Although the current crane remote operation technology has broken through the spatial limitations of traditional on-site operation, there are problems of feedback force distortion and operator cognitive overload in the core interaction link of remote operation, which directly restrict the control accuracy and safety of remote operation.

[0003] Feedback force distortion causes the force information obtained by the operator to be disconnected from the actual state of the hoisted object, and cognitive overload further causes the operator to be unable to judge the timing and force of operation, reducing the control accuracy of remote operation, which can easily cause problems such as hoisted object shaking and positioning deviation in precise hoisting and narrow space operation scenarios, and even has safety hazards.

[0004] Therefore, the present application provides a crane remote operation control method and system. SUMMARY

[0005] The present application aims to provide a crane remote operation control method and system to solve the above background problems.

[0006] The purpose of the present application can be achieved by the following technical solutions:

[0007] A crane remote operation control method: comprising the following steps:

[0008] Collecting the feedback deviation gradient of crane remote operation, establishing a joint distortion criterion based on the feedback deviation gradient and extracting a cumulative distortion sequence;

[0009] By extracting the coupling analysis features of the hoisted object dynamic parameters and the cumulative distortion sequence, constructing a historical risk group based on the coupling analysis features and extracting a real-time risk label type, formulating a dynamic calibration baseline of actual feedback force for different types;

[0010] Based on the dynamic calibration baseline, the output force of the operating lever is adjusted in real time, the matching of the length of the continuous same direction correction chain of the operator after adjustment and the distortion accumulation is evaluated, if they are not matched, the cognitive load of the operator is analyzed, the cognitive load degree is obtained, and it is determined whether the cognitive load of the operator is overloaded;

[0011] If the cognitive load is in an overloaded state, the overload scene data set of distortion accumulation and calibration lag is extracted, the warning time of the scene data set is extracted to determine the warning feature time, and a relationship adaptation model is constructed to formulate an optimal feedback force mapping relationship for different operators.

[0012] As a further scheme of the present application: the joint distortion criterion is established in the following manner:

[0013] obtaining a window average gradient in the sliding window;

[0014] establishing an instantaneous pulse distortion criterion based on the feedback deviation gradient and the window average gradient, identifying and eliminating the instantaneous pulse distortion existing in the sliding window;

[0015] based on the eliminated instantaneous pulse distortion, constructing a cumulative distortion criterion to identify the cumulative distortion in the sliding window;

[0016] If the feedback deviation gradient meets the cumulative distortion criterion, a cumulative distortion sequence containing the feedback deviation gradient meeting the cumulative distortion criterion is constructed.

[0017] As a further scheme of the present application: the way to formulate the dynamic calibration baseline of the actual feedback force is:

[0018] The sub-features of the historical coupling analysis features are labeled as the label types of risks, and the historical label types of risks and the coupling analysis features are taken as historical risk groups;

[0019] The number proportion of different label types of risks in all historical risk groups is extracted as the prior distribution of each risk label type;

[0020] The joint probability density function of the coupling analysis features containing the sub-features is extracted;

[0021] The current coupling analysis features are obtained to establish a new real-time risk group, and the posterior probability is obtained by combining the prior distribution, the joint probability density function and the Bayes formula;

[0022] The risk label types of the real-time risk group are extracted based on the posterior probability, and different dynamic calibration baselines of the actual feedback force are formulated based on different risk label types.

[0023] As a further scheme of the present application: the way to obtain the sub-features of the coupling analysis features is:

[0024] The peak value of the cumulative distortion sequence and the time stamp corresponding to the extreme value of the swing phase sequence are obtained, the peak value of the feedback deviation gradient is matched with the extreme value of the swing phase sequence closest to the time stamp based on the nearest neighbor pairing method, and a synchronous matching pair is obtained;

[0025] The difference between the time stamps corresponding to the peak value and the extreme value in the synchronous matching pair is calculated to obtain a swing phase difference;

[0026] The swing phase difference of the synchronous matching pair is subjected to phase synchronization analysis to obtain a phase synchronization coefficient;

[0027] The hoisting inertia moment and the hoisting shape coefficient of the hoisting dynamic parameters are extracted, and a distortion amplification coefficient is obtained by constructing a distortion amplification equation;

[0028] extracting a length of a continuous same-direction gradient chain in a cumulative distortion sequence to obtain a maximum gradient chain length;

[0029] taking the maximum gradient chain length, a distortion amplification coefficient and a phase synchronization coefficient as sub-features of coupling analysis features of feedback force and a state of a hoisted object for remote operation of the crane.

[0030] As a further scheme of the present application, the way of performing the cognitive load analysis is:

[0031] obtaining a probability of a standard deviation of the feedback correlation coefficient falling in different sub-intervals, and inputting an entropy value equation to obtain fluctuation entropy of the feedback correlation coefficient;

[0032] extracting a feedback deviation gradient in the corrected cumulative distortion sequence, and calculating distortion complexity entropy;

[0033] obtaining cognitive load degree based on the distortion complexity entropy and the fluctuation entropy of the feedback correlation coefficient by constructing a cognitive load equation;

[0034] performing comparison analysis based on the cognitive load degree to obtain a determination result of whether the cognitive load of the operator is in an overload state.

[0035] As a further scheme of the present application, the way of obtaining the feedback correlation coefficient is:

[0036] extracting a continuous same-direction correction chain length of the operator, performing chain length correction analysis on the continuous same-direction correction chain length in combination with the maximum gradient chain length to obtain a chain length correction ratio and evaluate matching of the continuous correction behavior of the operator and distortion accumulation;

[0037] if the matching is not matched, performing correlation analysis based on behavior characteristics of the operator in combination with dynamic adjustment characteristics of the actual feedback force to obtain the feedback correlation coefficient.

[0038] As a further scheme of the present application, the way of performing the chain length correction analysis is:

[0039] obtaining a maximum number of continuous same-direction corrections of the operator to obtain a continuous same-direction correction chain length;

[0040] obtaining a maximum gradient chain length of the cumulative distortion sequence, calculating a deviation ratio of the continuous same-direction correction chain length and the maximum gradient chain length to obtain a chain length correction ratio;

[0041] evaluating matching of a direction and a continuous number of times of the continuous same-direction correction behavior of the operator and distortion accumulation based on the chain length correction ratio.

[0042] As a further scheme of the present application, the way of formulating the preferred feedback force mapping relationship is:

[0043] collecting overload scene data in a cognitive overload period to construct an overload scene data set;

[0044] Based on the overload scene data set, the distortion accumulation is associated with the time chain after calibration, and the lag feature vector forming each overload scene is extracted;

[0045] Based on the lag feature vector of each overload scene, the early warning feature time of cognitive overload of different operators is determined; and the operator behavior adaptation type is extracted based on the early warning feature time window;

[0046] Based on the determined operator behavior adaptation type, a relationship adaptation model is constructed, the operator behavior features in the overload scene data set are input into the relationship adaptation model, and an optimal feedback force mapping relationship is generated.

[0047] As a further scheme of the application: the way of dividing the operator behavior type is:

[0048] The time window from T seconds before the early warning feature time point to the early warning time point is intercepted as the early warning analysis window;

[0049] Wherein, T is the early warning feature time value;

[0050] The continuous same direction correction chain length and the force change rate original sequence in the early warning analysis window are extracted from the pre-overload data; the distribution density of the continuous same direction correction chain length and the peak value coefficient of the force change rate in the early warning analysis window are calculated;

[0051] In combination with the time sequence change trend of the feedback correlation coefficient in the early warning analysis window, the operator behavior type is divided: the operator behavior adaptation type is determined based on the distribution density and the peak value coefficient of the force change rate.

[0052] A crane remote operation control system: comprising the following modules:

[0053] The distortion extraction module is used for collecting the feedback deviation gradient of the crane remote operation, establishing a joint distortion criterion based on the feedback deviation gradient, and extracting a cumulative distortion sequence;

[0054] The baseline calibration module extracts the coupling analysis features of the lifting object dynamic parameters and the cumulative distortion sequence, constructs a historical risk group based on the coupling analysis features, extracts a real-time risk label type, and formulates a dynamic calibration baseline of the actual feedback force for different types;

[0055] The overload identification module adjusts the output force of the operating lever in real time based on the dynamic calibration baseline, evaluates the matching of the continuous same direction correction chain length and the distortion accumulation of the operator after adjustment, extracts the adjusted feedback correlation coefficient if they are not matched, performs cognitive load analysis on the operator based on the feedback correlation coefficient, obtains the cognitive load degree, and determines whether the cognitive load of the operator is overloaded;

[0056] The feedback adjustment module: if the cognitive load is in an overload state, the overload scene data set of distortion accumulation and calibration lag is extracted, the early warning time is extracted from the scene data set to determine the early warning feature time, and the relationship adaptation model is constructed to develop an optimal feedback force mapping relationship for different operators.

[0057] The beneficial effects of the present application are:

[0058] The actual weight of the hoisted object is collected by the crane hook pressure sensor to correlate the theoretical feedback force, the actual feedback force of the operating lever is collected by the sensor of the remote control device, the feedback deviation gradient is calculated through time alignment and sliding window, accidental interference is removed through the instantaneous pulse criterion, and the continuous distortion sequence is extracted through the cumulative distortion criterion. It is beneficial to realize that the extracted cumulative distortion sequence fits the real long-term change law of the feedback force, and provides data support for subsequent calibration.

[0059] Synchronous extraction of dynamic parameters such as hoisted object swing phase and moment of inertia, calculation of phase synchronization coefficient through nearest neighbor pairing, construction of distortion amplification coefficient combined with hoisted object characteristics, extraction of maximum gradient chain length as coupling feature; based on historical risk group and Bayes formula to determine risk label, customize differentiated baseline for high, medium and low risk scenarios, through making baseline adapt to hoisted object dynamics and distortion risk depth, it is beneficial to calibrate strategy to be away from actual working conditions, and improve the flexibility and accuracy of remote operation feedback force adjustment.

[0060] After adjusting the operating lever output force based on the calibration baseline, the operator's continuous same direction correction chain length and force change rate are collected, the matching of behavior and distortion is evaluated through chain length correction ratio; when not matched, calculate the feedback correlation coefficient, and calculate the cognitive load degree through the fluctuation entropy and distortion complexity entropy. It is beneficial to quantify the adaptability of operator behavior and feedback force, and can identify signs of cognitive overload in time to reduce operation errors caused by heavy cognitive burden of operators.

[0061] A data set containing overload preposition, scene and calibration data is constructed, the lag feature vector is determined by time chain to determine the early warning time, the operator type is divided according to the behavior index, and the gradient boosting regression model is used to generate personalized feedback mapping. It is beneficial to early warning of potential overload risk, and can adapt to different operator habits to reduce the probability of subsequent cognitive overload. BRIEF DESCRIPTION OF DRAWINGS

[0062] The present application will be further described below in conjunction with the drawings.

[0063] Figure 1 is a flowchart of a crane remote operation control method of the present application;

[0064] Figure 2 is a determination flowchart of whether the cognitive load of the operator is overloaded in the present application;

[0065] Figure 3It is a module diagram of a crane remote operation control system. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present application will be clearly and completely described 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 work fall within the scope of protection of the present application.

[0067] Embodiment 1

[0068] As shown in the figure, the present application is a crane remote operation control method, comprising the following steps: Figure 1

[0069] S1, collecting the feedback deviation gradient of the crane remote operation, establishing a joint distortion criterion based on the feedback deviation gradient and extracting a cumulative distortion sequence;

[0070] Among them, the way of collecting the feedback deviation gradient of the crane remote operation is:

[0071] Preferably, the actual weight of the hoisted object is collected through the pressure sensor at the crane hook, and the actual weight of the hoisted object is input into the crane control system;

[0072] Obtaining the mapping relationship between the actual weight of the hoisted object and the preset theoretical feedback force, and extracting the theoretical feedback force corresponding to the actual weight of the hoisted object;

[0073] Based on the pressure sensor of the crane remote control device, the actual feedback force of the operating rod on the remote control device is collected;

[0074] The theoretical feedback force and the actual feedback force are data preprocessed, and the theoretical feedback force and the actual feedback force are time-aligned;

[0075] Based on the time-aligned theoretical feedback force and the actual feedback force, the deviation between the theoretical feedback force and the actual feedback force in each sliding window is calculated by setting a sliding window, and the feedback deviation value is obtained;

[0076] Obtaining all feedback deviation values in the sliding window, calculating the change gradient of adjacent feedback deviation values, and obtaining the feedback deviation gradient;

[0077] Among them, the joint distortion criterion is established based on the feedback deviation gradient, and the cumulative distortion sequence is extracted;

[0078] The mean value of the absolute value of the feedback deviation gradient in the sliding window is calculated as the window average gradient .

[0079] ​Wherein, the way of establishing the joint distortion criterion and extracting the cumulative distortion sequence is:

[0080] It should be noted that the joint distortion criterion includes: the instantaneous impulse distortion criterion and the cumulative distortion criterion;

[0081] S101, based on the feedback bias gradient and the window average gradient, an instantaneous impulse distortion criterion is established, and the instantaneous impulse distortion existing in the sliding window is identified and removed;

[0082] Preferably, the instantaneous impulse criterion is established by the equation:

[0083] Preferably, ;

[0084] Wherein, is the k feedback bias gradient in the sliding window, is the window average gradient, and k is the number of feedback bias gradients;

[0085] If the feedback bias gradient of the feedback bias value satisfies the instantaneous impulse criterion, the feedback bias value is determined as the instantaneous impulse distortion;

[0086] The instantaneous impulse distortion in the sliding window is removed;

[0087] S102, based on the removed instantaneous impulse distortion, a cumulative distortion criterion is constructed to identify the cumulative distortion in the sliding window;

[0088] Preferably, the cumulative distortion criterion is established by the equation:

[0089]

[0090] Wherein, is the feedback bias gradient removed from the instantaneous impulse distortion, b is the number of feedback bias gradients, and m is the number of feedback bias gradients;

[0091] Preferably, ;

[0092] M is the total number of instantaneous impulse distortions in the sliding window;

[0093] If the feedback bias gradient satisfies the cumulative distortion criterion, the corresponding feedback bias gradient is obtained, and a cumulative distortion sequence containing the feedback bias gradient satisfying the cumulative distortion criterion is constructed;

[0094] It can be understood that the function of obtaining the feedback bias gradient is:

[0095] ​​Action I: By establishing a transient pulse distortion criterion with the window average gradient to eliminate incidental interference, and then constructing a cumulative distortion criterion based on the feedback deviation gradient after eliminating interference, the cumulative distortion sequence is finally extracted, providing effective data support for subsequent feedback force distortion correction;

[0096] Action II: Feedback deviation gradient supports coupling analysis feature extraction and cognitive load quantification analysis: on the one hand, the cumulative distortion sequence generated can provide sub-features such as peak value and maximum gradient chain length, helping to determine risk labels and develop dynamic calibration baselines; on the other hand, the feedback deviation gradient in the corrected cumulative distortion sequence can be used to calculate distortion complexity entropy, thereby assisting in cognitive load calculation and overload determination.

[0097] S2, by extracting the coupling analysis features of the hoisted object dynamic parameters and the cumulative distortion sequence, constructing a historical risk group based on the coupling analysis features, and extracting real-time risk label types, a dynamic calibration baseline of actual feedback force is developed for different types;

[0098] Obtain the start time and end time of the cumulative distortion sequence, and synchronously extract the hoisted object dynamic parameters of the crane from the start time to the end time;

[0099] The hoisted object dynamic parameters include: swing phase, swing acceleration, and moment of inertia of the hoisted object;

[0100] Based on the hoisted object dynamic parameters of the crane from the start time to the end time, the swing phase of the hoisted object is extracted, and a swing phase sequence is established;

[0101] Calculate the peak value of the feedback deviation gradient in the cumulative distortion sequence, and the extreme value of the swing phase sequence;

[0102] Obtain the time stamp corresponding to the peak value and the extreme value, and based on the nearest neighbor pairing method, match the extreme value of the swing phase sequence closest to the peak value of the feedback deviation gradient, to obtain a synchronous matching pair;

[0103] Calculate the difference between the time stamps corresponding to the peak value and the extreme value in the synchronous matching pair, to obtain the swing phase difference;

[0104] Perform phase synchronization analysis on the swing phase difference of the synchronous matching pair to obtain a phase synchronization coefficient;

[0105] The phase synchronization analysis is performed in the following manner:

[0106] It should be noted that the peak value and the extreme value can only be uniquely matched when matched by the nearest neighbor pairing method; if the number of peak values and extreme values is not equal, the nearest neighbor pairing is performed according to the parameter with the smallest number (peak value or extreme value);

[0107] Perform screening processing on the swing phase difference of the synchronous matching pair, screen the synchronous matching pairs with strong synchronization, and extract the corresponding number;

[0108] Preferably, when the swing phase difference is lower than or equal to 0.5s, the synchronous matching pair is considered as a strong synchronous synchronous matching pair;

[0109] The number of strong synchronous synchronous matching pairs is ratio processed with the number of all synchronous matching pairs to obtain a phase synchronization coefficient S;

[0110] The hoisting object inertia moment I and the hoisting object shape coefficient Xz of the hoisting object dynamic parameter are extracted, and a distortion amplification equation is constructed: A distortion amplification coefficient A is obtained;

[0111] wherein, is a calibration coefficient, which is obtained by fitting historical data;

[0112] It should be noted that the hoisting object shape coefficient is based on the geometric shape of the hoisting object (such as block, column, irregular, etc.), the hoisting force mode (such as single-point hoisting, multi-point hoisting), and is obtained by querying a preset hoisting object shape coefficient database (containing coefficient values corresponding to different shapes and hoisting modes) or using an industry general shape coefficient calculation model, and finally used to construct a distortion amplification equation together with the hoisting object inertia moment to calculate the distortion amplification coefficient;

[0113] The calibration coefficient is an empirical fitting coefficient, which is obtained based on distortion experiments of 100 different types of hoisting objects (including block, column, irregular shape);

[0114] is a reference inertia moment, for example, the inertia moment of a 100kg standard block-shaped hoisting object;

[0115] The length of the continuous same direction gradient chain in the cumulative distortion sequence is extracted to obtain the maximum gradient chain length L;

[0116] It should be noted that the maximum gradient chain length refers to the maximum continuous number of times that the feedback deviation gradient direction remains consistent (all positive or all negative) in the cumulative distortion sequence;

[0117] The maximum gradient chain length, the distortion amplification coefficient and the phase synchronization coefficient are used as sub-features of the coupling analysis features of the feedback force of the remote operation of the crane and the state of the hoisting object;

[0118] The label type d of the historical coupling analysis features marked as risk is obtained, and the historical risk label type and the coupling analysis features are used as a historical risk group;

[0119] wherein, the risk label type d=0, 1, 2, respectively corresponding to high risk, medium risk and low risk;

[0120] The number proportion of different risk label types in all historical risk groups is extracted as the prior distribution of each risk label type;

[0121] For each risk label type d, the joint probability density function of the maximum gradient chain length L, the distortion amplification coefficient A and the phase synchronization coefficient S of the historical risk group is fitted by kernel density estimation ;

[0122] Those skilled in the art can understand that, for each risk label type d, the risk scene marked as d in the historical data is first screened, the maximum gradient chain length L, the distortion amplification coefficient A and the phase synchronization coefficient S under the scene are extracted to form a three-dimensional sample set, and then a kernel function such as Gaussian kernel is selected, and the sample set is fitted by kernel density estimation algorithm (such as non-parametric kernel regression) to generate the joint probability density function of the three;

[0123] Obtain the current coupling analysis feature to establish a new real-time risk group , the posterior probability is obtained by Bayes formula: ; ;

[0124] The risk label type D of the real-time risk group is obtained by formula: ;

[0125] Different actual feedback force dynamic calibration baselines are formulated based on different risk label types;

[0126] Preferably, the way to formulate different actual feedback force dynamic calibration baselines is:

[0127] When the risk label type D=0, that is, corresponding to high risk, the equation of the dynamic calibration baseline is:

[0128] Obtain the calibrated actual feedback force ;

[0129] Wherein, is the theoretical feedback force corresponding to the weight of the hoisted object, is the cumulative difference value between the actual feedback force and the theoretical feedback force;

[0130] It can be understood that in the high-risk scene, the feedback deviation is caused by long-term same-direction accumulation L and strong coupling with the hoisted object dynamics, which has formed a vicious cycle of distortion amplification-oscillation aggravation-distortion more serious. The equation of the dynamic calibration baseline is aimed at the error accumulation divergence risk, and the corrects the stock deviation, A matches the distortion amplification characteristics of the inertia and shape of the hoisted object, weights the accumulation trend of continuous same-direction gradient chain, and blocks the loss through strong robust compensation;

[0131] When the risk label type D=1, that is, corresponding to medium;

[0132] Through formula one: Obtaining a predicted next sliding window bias prediction increment ;

[0133] wherein, the historical average maximum gradient chain length under the same risk label;

[0134] It can be understood that the medium risk is a high risk precursor, the deviation has been accumulated but not out of control, and the core is to block the deterioration trend. The formula first predicts the deviation increment: the higher S is, the more closely the distortion-swing coupling is, and the more certain the future deviation growth is; Compare the gradient chain length of the current and historical medium risk to determine whether the accumulation is overspeed. Then execute the correction through formula one, take 70% of the stock and increment to intervene, which is beneficial to both advance to curb deviation deterioration and leave 30% buffer to avoid system shock, balance safety and stability;

[0135] Through formula two: Obtaining a calibrated actual feedback force ;

[0136] When the risk label type D=2, that is, corresponding to low risk;

[0137] Then the equation of the dynamic calibration baseline is:

[0138] Obtaining a calibrated actual feedback force ;

[0139] It can be understood that in the low risk scenario, the feedback distortion and the dynamic coupling of the suspended object are weak, the deviation accumulation is slow, and the calibration needs to be lightly intervened to preserve the operation experience. In the equation of the dynamic calibration baseline: Weaken the correction weight of the coupling related deviation (the lower the synchronization is, the weaker the coupling is, and the less the correction is); The calibration amplitude of the heavy load is inversely proportional to the inertia (the greater the inertia is, the more need to avoid the sudden change of the feedback force to interfere with the operation), within the controllable risk range, the smoothness of the operator's feeling is preferred.

[0140] Embodiment 2

[0141] As shown in Figure 1 The present application is a kind of crane remote operation control method, further comprising the following steps:

[0142] S3, based on the dynamic calibration baseline, the output force of the operating rod is adjusted in real time, the matching of the continuous same direction correction chain length and the distortion accumulation of the operator after adjustment is evaluated, if it is not matched, then the feedback correlation coefficient of adjustment is extracted, the cognitive load of the operator is analyzed based on the feedback correlation coefficient, the cognitive load degree is obtained, and it is judged whether the cognitive load of the operator is overloaded;

[0143] Based on constructing a dynamic calibration baseline as an initial adjustment reference of the output force of the operating lever, the output force of the operating lever is adjusted in real time by a servo motor as a force feedback actuator;

[0144] The actual feedback force of the operating lever in the monitoring period after real-time adjustment and the behavior characteristics of the operator are obtained;

[0145] The behavior characteristics of the operator include: the change rate of the operating force for two consecutive times, and the continuous same direction correction chain length of the operator;

[0146] The actual feedback force and the behavior characteristics of the operator are subjected to fitness analysis to obtain behavior fitness;

[0147] The fitness analysis is performed in the following manner:

[0148] S301, the continuous same direction correction chain length of the operator is extracted, and the chain length correction analysis is performed on the continuous same direction correction chain length in combination with the maximum gradient chain length to obtain a chain length correction ratio and evaluate the matching of the continuous correction behavior of the operator and the distortion accumulation;

[0149] The maximum number of continuous same direction correction (such as continuously increasing or decreasing the operating force) of the operator is obtained to obtain the continuous same direction correction chain length;

[0150] The maximum gradient chain length of the cumulative distortion sequence is obtained, and the deviation ratio of the continuous same direction correction chain length and the maximum gradient chain length is calculated to obtain the chain length correction ratio;

[0151] The matching of the direction and continuous number characteristics of the continuous same direction correction behavior of the operator and the distortion accumulation is evaluated based on the chain length correction ratio;

[0152] It can be understood that if the chain length correction ratio is in the interval of 0.8-1.2, it indicates that the number of continuous same direction correction of the operator is close to the continuous number characteristics of the distortion accumulation; at the same time, the continuous correction direction of the operator is compared with the feedback deviation gradient chain direction of the distortion accumulation, if both are in the same direction (both positive or both negative), it is determined that the direction and continuous number characteristics of the continuous same direction correction behavior of the operator and the distortion accumulation match; if the ratio deviates from the interval (such as far greater than 1 indicating that the correction is too frequent, and far less than 1 indicating that the correction is lagging), or the directions are inconsistent, it is determined that they do not match, and further cognitive adaptability analysis is required through feedback correlation coefficient analysis;

[0153] S302, if they do not match, the behavior characteristics of the operator are analyzed in combination with the dynamic adjustment characteristics of the actual feedback force to obtain a feedback correlation coefficient;

[0154] A force change sequence corresponding to the change rate of the force in the monitoring period is constructed;

[0155] The rate of change of the actual feedback force adjustment for two consecutive times is obtained when the dynamic baseline adjustment is obtained, and a feedback correction sequence is constructed;

[0156] Correlation analysis is performed on the feedback change sequence and the feedback correction sequence to obtain a feedback correlation coefficient;

[0157] Preferably, the correlation analysis is realized by calculating the Pearson correlation coefficient of the feedback change sequence and the feedback correction sequence to obtain the feedback correlation coefficient;

[0158] S303, based on the feedback correlation coefficient, human-machine cognitive collaborative analysis is performed to determine whether the cognitive load of the operator is in an overload state;

[0159] Preferably, the standard deviation of the feedback correlation coefficient in N sliding windows is obtained, and i sub-intervals are divided according to the size of the standard deviation, and the value range of i is [1, M], and M is the maximum value of the number of sub-intervals;

[0160] The probability that the standard deviation of the feedback correlation coefficient falls in different sub-intervals is calculated to obtain ;

[0161] The fluctuation entropy of the feedback correlation coefficient is obtained through an entropy equation: ;

[0162] The feedback deviation gradient in the corrected cumulative distortion sequence is extracted, and the distortion complexity entropy is calculated ;

[0163] Preferably, the distortion complexity entropy is calculated in the following manner:

[0164] Based on the cumulative distortion sequence, combined with the phase synchronization coefficient S, the modified gradient is calculated through the formula: modified gradient = feedback deviation gradient ;

[0165] Wherein, the phase synchronization coefficient reflects the coupling of distortion and the swing of the suspended object, and the distortion amplification coefficient reflects the amplification effect of the suspended object characteristics on the distortion, which describes the distortion influence from the 'dynamic coupling' and'static characteristics' dimensions respectively; The modified gradient introduces S in order to highlight the influence of'real-time coupling state' on the distortion analysis, and A supports the cognitive load degree calculation together, and the logic of the two is: S focuses on real-time dynamics, and A focuses on inherent characteristics of the suspended object;

[0166] It can be understood that the role of the modified gradient is:

[0167] Role one, by combining the feedback deviation gradient in the cumulative distortion sequence with the phase synchronization coefficient for correction, and then calculating the standard deviation distribution probability of the modified gradient and substituting it into the entropy equation, the distortion complexity entropy obtained can support the cognitive load degree calculation together with the fluctuation entropy of the feedback correlation coefficient, and provides a key quantitative basis for determining the cognitive overload of the operator; ​

[0168] Action II, the modified gradient can better reflect the actual impact of feedback force distortion, by integrating the phase synchronization coefficient, reducing the deviation caused by ignoring the distortion-swing coupling relationship when only using the original feedback deviation gradient analysis, providing distortion data that fits the actual working condition for subsequent cognitive load analysis, and ensuring the rationality of the cognitive overload determination result;

[0169] Obtain the standard deviation of the modified gradient in the N sliding windows, divide i sub-intervals according to the size of the standard deviation of the modified gradient, and the value of i is in the range [1, M], M is the maximum value of the number of sub-intervals;

[0170] Calculate the probability of the modified gradient falling into different sub-intervals to obtain

[0171] Obtain the distortion complexity entropy by the entropy equation: ;

[0172] Obtain the cognitive load degree by constructing the cognitive load equation ;

[0173] As shown in Figure 2 , compare the cognitive load degree with the preset cognitive load threshold value, if the cognitive load degree is lower than the cognitive load threshold value, determine that the cognitive load of the operator is in an overload state;

[0174] If the cognitive load degree is higher than or equal to the preset cognitive load threshold value, continue to monitor the cognitive load degree;

[0175] Wherein, the purpose of obtaining the cognitive load degree is;

[0176] Purpose I, determine whether the cognitive load of the operator is overloaded, by comparing the calculated cognitive load degree with the preset threshold value, if the cognitive load degree is lower than the threshold value, determine that the operator is in a cognitive overload state, provide a basis for subsequent targeted intervention;

[0177] Purpose II, when determining that the cognitive load is overloaded, use the overload period as a reference to collect the cumulative distortion sequence, dynamic calibration baseline, feedback correlation coefficient and other data in the period, construct an overload scene data set, and provide data support for subsequent analysis of overload reasons;

[0178] Purpose III, obtaining the cognitive load degree is a prerequisite for generating personalized feedback force mapping relationship, only after determining the cognitive overload state, can the warning feature time of the overload scene data set be further extracted, the operator behavior adaptation type be divided, and then the relationship adaptation model be constructed, to customize the optimal feedback force mapping relationship for different operators.

[0179] ​​​S4, if the cognitive load is in an overload state, extract the distortion accumulation and the overload scenario data set of the calibration lag, determine the warning time extraction of the scenario data set, construct the relationship adaptation model to develop the optimal feedback force mapping relationship for different operators;

[0180] If the cognitive load is in an overload state, the starting and ending time in the overload state is taken as the cognitive overload period of the cognitive overload period;

[0181] S401, collect the overload scenario data of the cognitive overload period, and construct the overload scenario data set;

[0182] Preferably, the cumulative distortion sequence of the cognitive overload period, the starting and mutation time stamp of the distortion accumulation are collected, and the cumulative distortion sequence and the starting and mutation time stamp are taken as the overload scenario data;

[0183] The dynamic calibration baseline and the phase synchronization coefficient are taken as the calibration scenario data;

[0184] The feedback correlation coefficient sequence before the cognitive overload period, the continuous same direction correction chain length, and the force change rate are taken as the pre-overload data;

[0185] The overload scenario data set containing the pre-overload data, the overload scenario data, and the calibration scenario data is constructed;

[0186] S402, based on the overload scenario data set, the time chain correlation after distortion accumulation and calibration is established, and the lag feature vector of each overload scenario is extracted;

[0187] Preferably, from the overload scenario data, the starting time stamp (the first time the feedback deviation gradient meets the cumulative distortion criterion) and the mutation time stamp (the time when the absolute value of the feedback deviation gradient increases by ≥50%) of the cumulative distortion sequence are located;

[0188] From the calibration scenario data, the first adjustment time stamp of the dynamic calibration baseline (the first calibration action for the cumulative distortion) is extracted;

[0189] From the pre-overload data, the determination time stamp of cognitive overload (the time when Rz first reaches the threshold) is determined;

[0190] Based on the starting time stamp, the mutation time stamp, the first adjustment time stamp, and the determination time stamp, the time chain of distortion starting-distortion mutation-calibration adjustment-cognitive overload is constructed;

[0191] The time difference of each node (such as the lag length of distortion starting to calibration adjustment , the evolution length of calibration adjustment to cognitive overload ) is calculated to form the lag feature vector of each overload scenario ,

[0192] S403、based on the hysteresis eigenvector of each overload scene, determine the early warning characteristic time of cognitive overload of different operators;

[0193] Preferably, the hysteresis eigenvector of all overload scenes of the operator is counted, and the typical hysteresis mode with the highest frequency of occurrence is screened out;

[0194] For example, 70% of the overload of an operator corresponds to And ;

[0195] Take the total evolution time of the typical mode ( + ) as the basis, reserve a safety redundancy (such as taking 60% of the total time as the early warning advance), and get the early warning characteristic time of the operator (such as the total evolution time is 5s, the early warning time = 5s×60%=3s);

[0196] Dynamic updating mechanism: every 3 new overload scenes, recalculate the typical hysteresis mode and adjust the early warning characteristic time to ensure the adaptation to the changes of operator behavior habits (such as the shortening of hysteresis time after proficiency, the synchronous reduction of early warning time);

[0197] S404, extract the operator behavior adaptation type based on the early warning characteristic time window;

[0198] Preferably, the time window from T seconds before the early warning characteristic time point to the early warning time point (T is the early warning characteristic time value) is intercepted as the early warning analysis window;

[0199] Extract the continuous same direction correction chain length and the original sequence of force change rate in the early warning analysis window from the overload front data;

[0200] Calculate the distribution density of the continuous same direction correction chain length and the peak value coefficient (the ratio of the peak value to the average value) of the force change rate in the early warning analysis window;

[0201] Combine the time sequence change trend of the feedback correlation coefficient in the early warning analysis window to divide the operator behavior type:

[0202] Determine the operator behavior adaptation type based on the distribution density and the peak value coefficient of the force change rate;

[0203] It can be understood that based on the parameter calculation results in the early warning characteristic time window, the adaptation type is determined by three threshold values:

[0204] ​If the distribution density of the continuous same direction correction chain length is ≥ 3 times per second (high frequency correction) and the peak value coefficient of the force change rate is > 1.5 (strong fluctuation), the operator is determined to be sensitive, that is, the operator is too sensitive to the fluctuation of the feedback force and is prone to frequent correction due to slight deviation, and the gradient smoothing mapping of the model needs to be customized (such as reducing the feedback force change slope in the low weight section) to reduce the cognitive overload caused by excessive correction;

[0205] If the distribution density is ≤ 1 time per second (low frequency correction) and the peak value coefficient is ≤ 1.2 (weak fluctuation), the operator is determined to be robust, that is, the operator's correction rhythm is slow, and the key section needs to be strengthened by customizing the mapping of the model (such as amplifying the feedback force difference in the high weight section) to reduce the correction lag caused by insufficient feedback;

[0206] If the distribution density is between 1-3 times per second (medium frequency correction) and the peak value coefficient is between 1.2-1.5 (medium fluctuation), the operator is determined to be adaptive, that is, the operator's behavior characteristics match the existing feedback force mapping, and the existing mapping can meet the cognitive load control requirements;

[0207] S405, based on the determined operator behavior adaptation type, a relationship adaptation model is constructed, the behavior characteristics of the operators in the overload scenario data set are input into the relationship adaptation model, and an optimized feedback force mapping relationship is generated;

[0208] Preferably, if the operator is sensitive and robust, the actual weight of the hoisted object in the overload scenario data set is used as the input characteristic, and the ideal feedback force of the operator when there is no overload is used as the output label (the ideal feedback force is obtained by back calculation during the operation period when the continuous same direction correction chain length is stable and the force change rate is ≤ 10%);

[0209] The mean of the continuous same direction correction chain length and the standard deviation of the force change rate of the operator are included as behavior characteristics of the model adjustment parameters, and a gradient boosting regression model with regularization is used to train the relationship adaptation model to output a personalized mapping function , W is the actual weight of the hoisted object;

[0210] The mapping is tested in a non-overload scenario, and if the feedback correlation coefficient of the operator is improved by ≥ 15% and the matching degree of the continuous same direction correction chain length and the maximum gradient chain length is improved by ≥ 20%, the optimized feedback force mapping relationship is determined;

[0211] Based on the optimized feedback force mapping relationship, the feedback force mapping relationship of the operator is updated;

[0212] It needs to be explained that when the operator feedback force mapping relationship is updated based on the preferred feedback force mapping relationship, the behavior adaptation type (sensitive type, robust type or adaptive type) corresponding to the operator is determined, the personalized feedback force mapping function generated for the type (such as the gradient smoothing mapping of the sensitive type and the key segment strengthening mapping of the robust type) is introduced into the force feedback control module of the crane remote control system, and the original general feedback force mapping logic is replaced; in subsequent operations, the system will take the actual weight of the hoisted object as input, calculate and output the actual feedback force of the operating lever in real time through the updated mapping function, and at the same time, every 3 times of overload scene is added, the relationship adaptation model will be retrained combined with the new overload data, the mapping function is dynamically optimized, and the updated feedback force mapping relationship is continuously adapted to the operator behavior habit, so as to realize the effect of relieving cognitive overload and correcting feedback force distortion.

[0213] Embodiment 3

[0214] As shown in Figure 3 , the application is a kind of crane remote operation control system, also includes the following modules:

[0215] Distortion extraction module: used for collecting feedback deviation gradient of crane remote operation, establishing joint distortion criterion based on feedback deviation gradient and extracting cumulative distortion sequence;

[0216] Baseline calibration module: by extracting the coupling analysis characteristics of the dynamic parameters of the hoisted object and the cumulative distortion sequence, constructing the historical risk group based on the coupling analysis characteristics, and extracting the real-time risk label type, formulating the dynamic calibration baseline of the actual feedback force for different types;

[0217] Overload identification module: based on the dynamic calibration baseline, the output force of the operating lever is adjusted in real time, the matching of the length of the continuous same direction correction chain of the operator and the distortion accumulation after adjustment is evaluated, if it is not matched, the feedback correlation coefficient of adjustment is extracted, the cognitive load of the operator is analyzed based on the feedback correlation coefficient, the cognitive load degree is obtained, and it is judged whether the cognitive load of the operator is overloaded;

[0218] Feedback adjustment module: if the cognitive load is in the state of overload, the overload scene data set of distortion accumulation and calibration lag is extracted, the warning time of the scene data set is extracted to determine the warning feature time, and the relationship adaptation model is constructed to formulate the preferred feedback force mapping relationship for different operators.

[0219] The above describes one embodiment of the application in detail, but the content described is only the preferred embodiment of the application, and cannot be considered as limiting the scope of the implementation of the application. Any equivalent changes and improvements made within the scope of the application shall still belong to the scope of the application.

Claims

1. A crane remote operation control method, characterized by: The method comprises the following steps: Collecting feedback deviation gradient of remote operation of the crane, establishing joint distortion criterion based on the feedback deviation gradient and extracting cumulative distortion sequence; The establishment of the joint distortion criterion is as follows: Obtaining window average gradient in the sliding window; Establishing instantaneous pulse distortion criterion based on the feedback deviation gradient and the window average gradient, identifying and eliminating the instantaneous pulse distortion existing in the sliding window; Based on the eliminated instantaneous pulse distortion, constructing the cumulative distortion criterion to identify the cumulative distortion in the sliding window; If the feedback deviation gradient meets the cumulative distortion criterion, a cumulative distortion sequence containing the feedback deviation gradient meeting the cumulative distortion criterion is constructed; Through extraction of the coupling analysis features of the load dynamic parameters and the cumulative distortion sequence, a historical risk group is constructed based on the coupling analysis features, a real-time risk label type is extracted, and a dynamic calibration baseline of the actual feedback force is formulated for different types; The dynamic calibration baseline of the actual feedback force is formulated as follows: The sub-features of the historical coupling analysis features are labeled as the risk label type, and the historical risk label type and the coupling analysis features are taken as the historical risk group; The number proportion of different risk label types in all historical risk groups is extracted as the prior distribution of each risk label type; The joint probability density function of the coupling analysis features containing the sub-features is extracted; The current coupling analysis features are obtained to establish a new real-time risk group, and the posterior probability is obtained through the Bayes formula by combining the prior distribution and the joint probability density function; Based on the posterior probability, the risk label type of the real-time risk group is extracted, and the dynamic calibration baseline of the actual feedback force is formulated for different risk label types; The sub-features of the coupling analysis features are obtained as follows: The peak value of the cumulative distortion sequence and the time stamp corresponding to the extreme value of the swing phase sequence are obtained, the nearest neighbor pairing method is used to match the peak value of the feedback deviation gradient with the extreme value of the swing phase sequence closest to the time stamp, and a synchronous matching pair is obtained; The difference between the time stamps corresponding to the peak value and the extreme value in the synchronous matching pair is calculated to obtain the swing phase difference; Phase synchronization analysis is performed on the swing phase difference of the synchronous matching pair to obtain the phase synchronization coefficient; The load inertia moment and the load shape coefficient of the load dynamic parameters are extracted, and the distortion amplification coefficient is obtained by constructing a distortion amplification equation; The length of the continuous same-direction gradient chain in the cumulative distortion sequence is extracted to obtain the maximum gradient chain length; The maximum gradient chain length, the distortion amplification coefficient and the phase synchronization coefficient are taken as the sub-features of the coupling analysis features of the feedback force of the remote operation of the crane and the state of the load; The output force of the operating lever is adjusted in real time based on the dynamic calibration baseline, the matching of the continuous same-direction correction chain length and the distortion accumulation of the operator after the adjustment is evaluated, and if the matching is not matched, cognitive load analysis is performed on the operator to obtain the cognitive load degree, and it is determined whether the cognitive load of the operator is overloaded; The cognitive load analysis is performed as follows: The probability that the standard deviation of the feedback correlation coefficient falls in different sub-intervals is obtained, and the fluctuation entropy of the feedback correlation coefficient is obtained by inputting an entropy value equation; The feedback deviation gradient in the corrected cumulative distortion sequence is extracted, and the distortion complexity entropy is calculated; The fluctuation entropy based on the distortion complex entropy and the feedback correlation coefficient obtains the cognitive load degree by constructing a cognitive load equation; The cognitive load degree is compared and analyzed to obtain a determination result of whether the cognitive load of the operator is in an overload state; If the cognitive load is in an overload state, the overload scene data set of the distortion accumulation and the calibration lag is extracted, the early warning feature time is determined by extracting the early warning time of the scene data set, and a relationship adaptation model is constructed to develop an optimal feedback force mapping relationship for different operators.

2. A remote control method of a crane according to claim 1, characterized in that: The feedback correlation coefficient is obtained in the following manner: The continuous same direction correction chain length of the operator is extracted, the chain length correction analysis is performed on the continuous same direction correction chain length in combination with the maximum gradient chain length, a chain length correction ratio is obtained, and the matching of the continuous correction behavior of the operator and the distortion accumulation is evaluated; If the matching is not matched, the correlation analysis is performed based on the behavior characteristics of the operator in combination with the dynamic adjustment characteristics of the actual feedback force to obtain the feedback correlation coefficient.

3. A remote control method of a crane according to claim 2, characterized in that: The chain length correction analysis is performed in the following manner: The maximum number of continuous same direction corrections of the operator is obtained to obtain the continuous same direction correction chain length; The maximum gradient chain length of the cumulative distortion sequence is obtained, the deviation ratio of the continuous same direction correction chain length and the maximum gradient chain length is calculated to obtain the chain length correction ratio, and the matching of the direction and continuous number characteristics of the continuous same direction correction behavior of the operator and the distortion accumulation is evaluated. The optimal feedback force mapping relationship is developed in the following manner:

4. A remote control method of a crane according to claim 1, characterized in that: The overload scene data in the cognitive overload period is collected to construct an overload scene data set; The time chain correlation of the distortion accumulation and the calibration lag is established based on the overload scene data set, and the lag feature vector of each overload scene is extracted; The early warning feature time of the cognitive overload of different operators is determined based on the lag feature vector of each overload scene; The operator behavior adaptation type is extracted based on the early warning feature time window; The relationship adaptation model is constructed based on the determined operator behavior adaptation type, the behavior characteristics of the operator in the overload scene data set are input into the relationship adaptation model, and the optimal feedback force mapping relationship is generated. The operator behavior adaptation type is extracted in the following manner:

5. A remote control method of a crane according to claim 4, characterized in that: The time window from T seconds before the early warning feature time point to the early warning feature time point is intercepted as an early warning analysis window; Wherein, T is the early warning feature time value; The continuous same direction correction chain length and the force change rate original sequence in the early warning analysis window are extracted from the pre-overload data; The distribution density of the continuous same direction correction chain length and the peak coefficient of the force change rate in the early warning analysis window are calculated; The operator behavior type is divided based on the time sequence change trend of the feedback correlation coefficient: the operator behavior adaptation type is determined based on the distribution density and the peak coefficient of the force change rate. The following modules are included:

6. A remote control system for a crane for implementing a remote control method for a crane according to any one of claims 1-5, characterized in that: A distortion extraction module is used to collect the feedback deviation gradient of the remote operation of the crane, establish a joint distortion criterion based on the feedback deviation gradient, and extract a cumulative distortion sequence; A baseline calibration module is used to extract the coupling analysis characteristics of the dynamic parameters of the hoisted object and the cumulative distortion sequence, construct a historical risk group based on the coupling analysis characteristics, extract a real-time risk label type, and develop a dynamic calibration baseline for the actual feedback force of different types; ​ The overload recognition module is configured to adjust the output force of the operating rod in real time based on a dynamic calibration baseline, evaluate matching of a continuous same-direction correction chain length of the operator after adjustment and distortion accumulation, extract a feedback correlation coefficient if the matching is not matched, analyze cognitive load of the operator based on the feedback correlation coefficient, obtain a cognitive load degree, and determine whether the cognitive load of the operator is overloaded. The feedback adjustment module is configured to extract an overload scene data set of the distortion accumulation and the calibration lag if the cognitive load is in an overloaded state, extract a warning time to determine a warning feature time for the scene data set, and construct a relationship adaptation model to develop an optimal feedback force mapping relationship for different operators.

Images