Tower crane maintenance and fault warning intelligent management system

Abstract

The present invention relates to the technical field of crane fault early warning, and discloses an intelligent management system for tower crane maintenance and fault early warning, comprising: a meteorological score calculation module for calculating and obtaining a meteorological score; an aging score calculation module for calculating and obtaining an aging score; a data acquisition module for collecting image data and vibration data; a load eccentricity value calculation module for calculating and obtaining a load eccentricity value; a vibration feature extraction module for calculating and obtaining a vibration feature value; a brake fault score calculation module for calculating and obtaining a brake fault score; a dynamic threshold generation module for obtaining a fault prediction score threshold through a prediction model; and a brake fault judgment module for judging that a fault risk exists when the brake fault score exceeds the fault prediction score threshold. The present invention quantifies meteorological factors, aging factors of the tower crane, force factors of the hook, and vibration factors of multiple positions of the brake component to generate a brake fault score and a dynamic threshold, thereby improving the accuracy of fault early warning for the tower crane.

Description

Technical Field

[0001] The present invention relates to the technical field of crane fault early warning, and more particularly to a tower crane maintenance and fault early warning intelligent management system. Background Art

[0002] Tower cranes are a key piece of machinery widely used in high-rise building construction. Their primary function is to vertically transport construction materials and equipment to designated locations. Traditional tower crane fault monitoring typically uses fixed thresholds. For example, these methods record the time from the gear reset signal, the inverter's lifting brake signal, and the brake feedback signal to the hook's actual braking. If the hook speed remains non-zero within the preset braking time, this indicates a brake failure.

[0003] However, fixed thresholds fail to account for the aging of tower cranes and meteorological factors during operation, such as temperature, wind speed, and rainfall, which can affect their braking performance. This results in low fault monitoring accuracy and a lack of a fault warning mechanism. With the development of artificial intelligence, existing methods collect vibration data from brake components and analyze it in the time and frequency domains using wavelet transforms combined with machine learning to achieve fault warnings.

[0004] However, the above solution does not take into account the correlation between different positions of the braking components. The vibration data of a single position may be biased, which may lead to deviations in fault warning. In addition, the weight, shape and mounting method of the object mounted on the hook will also affect the force distribution of the hook, thereby affecting the accuracy of fault prediction. Summary of the Invention

[0005] The present invention provides a tower crane maintenance and fault warning intelligent management system to solve the technical problems in the above-mentioned background technology.

[0006] The present invention provides an intelligent management system for tower crane maintenance and fault warning, comprising:

[0007] A meteorological score calculation module is used to calculate a meteorological score based on meteorological data;

[0008] Meteorological data include: temperature, wind speed and rainfall;

[0009] An aging score calculation module, which is used to calculate an aging score based on the operation data of the tower crane;

[0010] Operation data includes: cumulative working hours, average daily usage times and historical failure times;

[0011] A data acquisition module, which is used to simultaneously collect image data of the object and vibration data of N preset points after the object is fully lifted by the tower crane;

[0012] The vibration data is represented by the vibration acceleration at M time points;

[0013] A load eccentricity calculation module is used to calculate the horizontal deviation distance between the center of gravity of the object and the hook center of the tower crane based on the image data of the object, and mark it as the load eccentricity value;

[0014] A vibration feature extraction module is used to extract features from vibration data of N preset points to obtain vibration feature values;

[0015] A brake fault score calculation module is used to calculate a brake fault score based on a meteorological score, an aging score, a load eccentricity value, and a vibration characteristic value;

[0016] A dynamic threshold generation module is used to input the meteorological score, aging score, load eccentricity value and vibration characteristic value into the prediction model to obtain the fault prediction score threshold;

[0017] The brake fault judgment module is used to judge that the brake fault score is greater than or equal to the fault prediction score threshold, and then immediately notify the tower crane to immediately lower the hoisted object.

[0018] Furthermore, the number N of preset points and the number M of time points of vibration data are both custom parameters.

[0019] Furthermore, a larger value of the weather score indicates a worse weather condition. The calculation formula is as follows:

[0020] ;

[0021] T, Wind and Rain represent temperature, wind speed and rainfall respectively. 、 and Respectively represent the custom temperature reference value, wind speed reference value and rainfall reference value, 、 and Represent the customized first weight coefficient, second weight coefficient and third weight coefficient respectively, and 、 and The sum of the values ​​is 1.

[0022] Furthermore, a larger value of the aging score indicates a greater degree of aging of the tower crane. The calculation formula is as follows:

[0023] ;

[0024] Work, Freq and Break represent the cumulative working hours, average daily usage times and historical failure times respectively. 、 and represent the fourth, fifth, and sixth custom weight coefficients, respectively, and 、 and The sum of is 1, and e represents a natural constant.

[0025] Furthermore, the load eccentricity value is calculated, including the following steps:

[0026] Step S201, identifying the center of gravity of the object and the hook center of the tower crane through the target detection model;

[0027] Step S202, calculating the horizontal pixel difference between the center of gravity of the object and the center of the hook of the tower crane;

[0028] Step S203: Calculate the horizontal deviation distance between the center of gravity of the object and the hook center of the tower crane based on the horizontal pixel difference, and mark it as the load eccentricity value;

[0029] Load eccentricity The calculation formula is as follows: ;

[0030] in represents the horizontal pixel difference, Width represents the physical width of the camera sensor, represents the real distance between the camera and the object, f represents the focal length of the camera, Indicates the number of pixels in the horizontal direction of the image data.

[0031] Furthermore, feature extraction is performed on the vibration data of N preset points to obtain vibration feature values, including the following steps:

[0032] Step S301, taking the average value of the vibration acceleration of the vibration data of N preset points at M time points as basic vibration data;

[0033] Step S302 , calculating the mean value, standard deviation, root mean square value, peak value, form factor, impulse factor, and margin factor of the basic vibration data;

[0034] The crest factor is the ratio of the peak value to the RMS value, the pulse factor is the ratio of the peak value to the average value, and the margin factor is the ratio of the peak value to the standard deviation.

[0035] Step S303, converting the basic vibration data into frequency domain data through fast Fourier transform, and calculating the main frequency, center frequency and spectrum energy of the frequency domain data;

[0036] Step S304 : taking the peak value, form factor, pulse factor and margin factor of the basic vibration data and the main frequency, center frequency and spectrum energy of the frequency domain data as vibration characteristic values.

[0037] Furthermore, a larger value of the brake fault score indicates a greater risk of brake failure. The brake fault score is obtained by weighted summation of the meteorological score, aging score, load eccentricity value, and vibration characteristic value, and the corresponding weight coefficients are all custom parameters.

[0038] Furthermore, the prediction model consists of hidden layers and classifiers;

[0039] The hidden layer is used to update the concatenated vector composed of the meteorological score, aging score, load eccentricity value and vibration eigenvalue, and output the hidden vector. The number of dimensions of the hidden vector is a custom parameter.

[0040] The classifier inputs the hidden vector output by the hidden layer, and the class space of the classifier represents the fault prediction score threshold.

[0041] Furthermore, the calculation formula of the hidden layer includes:

[0042] ;

[0043] in represents the hidden vector of the hidden layer output, H represents the concatenated vector of the hidden layer input, 、 and Represent the first weight matrix, the second weight matrix and the third weight matrix respectively, and they are all custom hyperparameters. 、 and They represent the first bias vector, the second bias vector, and the third bias vector, respectively, and are all custom hyperparameters. e represents a natural constant, T represents a transpose operation, PReLU represents a PReLU activation function, and Swish represents a Swish activation function.

[0044] Furthermore, constructing sample labels for training samples of the prediction model includes the following steps:

[0045] Step S401, calculating a brake fault score after the object is completely lifted by the tower crane;

[0046] Step S402: After the tower crane completes the preset transfer distance, it brakes. If it is determined that there is a fault, it gradually reduces the weight and returns to step S401 until the fault is no longer present. 90% of the corresponding brake fault score is recorded as the sample label of the training sample. Otherwise, it proceeds to step S403.

[0047] Step S403: If it is determined that there is no fault, the weight is gradually increased until a fault occurs, and 90% of the corresponding brake fault score is recorded as the sample label of the training sample;

[0048] Step S404, repeating steps S401 to S403 until U training samples are obtained;

[0049] The number of training samples U is a custom parameter.

[0050] The beneficial effects of the present invention are as follows: the present invention comprehensively analyzes meteorological factors, tower crane aging factors, hook stress factors, and vibration factors at multiple positions of the brake components, and quantifies the above factors to generate a brake fault score and predict dynamic thresholds, thereby improving the accuracy of fault warnings for tower cranes. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of the tower crane maintenance and fault warning intelligent management system of the present invention;

[0052] Figure 2 This is a flow chart of the present invention for calculating and obtaining the load eccentricity value;

[0053] Figure 3 This is a flow chart of the feature extraction of the present invention to obtain vibration characteristic values;

[0054] Figure 4 It is a flow chart of the sample labels of the training samples for constructing the prediction model of the present invention.

[0055] In the figure: meteorological score calculation module 101, aging score calculation module 102, data acquisition module 103, load eccentricity value calculation module 104, vibration feature extraction module 105, brake fault score calculation module 106, dynamic threshold generation module 107, brake fault judgment module 108. DETAILED DESCRIPTION

[0056] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. In addition, features described with respect to some examples may also be combined in other examples.

[0057] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in one or more embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprising" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0058] like Figures 1 to 4 As shown in the figure, the tower crane maintenance and fault warning intelligent management system includes:

[0059] A meteorological score calculation module 101 is used to calculate a meteorological score based on meteorological data;

[0060] Meteorological data include: temperature, wind speed and rainfall;

[0061] An aging score calculation module 102 is configured to calculate an aging score based on the operation data of the tower crane;

[0062] Operation data includes: cumulative working hours, average daily usage times and historical failure times;

[0063] A data acquisition module 103 is configured to simultaneously acquire image data of the object and vibration data of N preset points after the object is fully lifted by the tower crane;

[0064] The vibration data is represented by the vibration acceleration at M time points;

[0065] A load eccentricity calculation module 104 is configured to calculate a horizontal deviation distance between the center of gravity of the object and the hook center of the tower crane based on the image data of the object, and mark the deviation distance as a load eccentricity value;

[0066] A vibration feature extraction module 105 is used to extract features from the vibration data of N preset points to obtain vibration feature values;

[0067] A brake fault score calculation module 106 is configured to calculate a brake fault score based on the weather score, the aging score, the load eccentricity value, and the vibration characteristic value;

[0068] A dynamic threshold generation module 107 is used to input the meteorological score, aging score, load eccentricity value and vibration characteristic value into the prediction model to obtain a fault prediction score threshold;

[0069] The brake fault judgment module 108 is configured to immediately notify the tower crane to lower the hoisted object if the brake fault score is greater than or equal to a fault prediction score threshold.

[0070] In one embodiment of the present invention, the number N of preset points and the number M of time points of vibration data are both custom parameters; for example, the preset points can be set on the brake housing (to monitor the wear of the brake), the reducer housing (to monitor the wear of the internal gears of the reducer), the lifting motor mounting seat (to monitor the linkage vibration of the motor and the drive shaft), etc., and each preset point can be installed with multiple vibration sensors to eliminate errors; the number M of time points of vibration data is related to the collection time and collection frequency, where the collection time and collection frequency are both custom parameters, for example, if the collection time is set to 2 seconds and the collection frequency is set to 500Hz, then the number M of time points of vibration data = 2×500 = 1000.

[0071] In one embodiment of the present invention, a larger value of the weather score indicates a worse weather condition. The calculation formula is as follows:

[0072] ;

[0073] T, Wind and Rain represent temperature, wind speed and rainfall respectively. 、 and Respectively represent the custom temperature reference value, wind speed reference value and rainfall reference value, 、 and Represent the customized first weight coefficient, second weight coefficient and third weight coefficient respectively, and 、 and The sum of the values ​​is 1.

[0074] It should be noted that the calculation of meteorological scores does not involve dimensional calculations, and the default values ​​of the customized temperature reference value, wind speed reference value, and rainfall reference value are 25°C, 5m / s, and 10mm / h, respectively. The default values ​​of the customized first weight coefficient, second weight coefficient, and third weight coefficient are 0.2, 0.4, and 0.4, respectively.

[0075] In one embodiment of the present invention, a larger value of the aging score indicates a greater degree of aging of the tower crane. The calculation formula is as follows:

[0076] ;

[0077] Work, Freq and Break represent the cumulative working hours, average daily usage times and historical failure times respectively. 、 and represent the fourth, fifth, and sixth custom weight coefficients, respectively, and 、 and The sum of is 1, and e represents a natural constant.

[0078] It should be noted that the calculation of the aging score does not involve dimension calculation, and the default values ​​of the user-defined fourth weight coefficient, fifth weight coefficient, and sixth weight coefficient are 0.2, 0.3, and 0.5, respectively.

[0079] In one embodiment of the present invention, Figure 2 As shown, the calculation of load eccentricity value includes the following steps:

[0080] Step S201, identifying the center of gravity of the object and the hook center of the tower crane through the target detection model;

[0081] The target detection model can be YOLOv8, Mask R-CNN, etc., and the training samples for training the target detection model are constructed through annotation tools. The annotation tools can be LabelImg, COCO Annotator, etc., which are not described in detail here;

[0082] Step S202, calculating the horizontal pixel difference between the center of gravity of the object and the center of the hook of the tower crane;

[0083] That is, the difference in pixel values ​​in the horizontal direction between the center of gravity of the object and the center of the tower crane's hook;

[0084] Step S203: Calculate the horizontal deviation distance between the center of gravity of the object and the hook center of the tower crane based on the horizontal pixel difference, and mark it as the load eccentricity value;

[0085] Load eccentricity The calculation formula is as follows: ;

[0086] in represents the horizontal pixel difference, Width represents the physical width of the camera sensor, represents the real distance between the camera and the object, f represents the focal length of the camera, Indicates the number of pixels in the horizontal direction of the image data.

[0087] For example, if the horizontal pixel difference is 100 pixels, the physical width of the camera sensor is 6.17 mm = 0.00617 m, the camera focal length is 5.1 mm = 0.0051 m, the actual distance between the camera and the object is 10 m, and the number of pixels in the horizontal direction (image width) of the image data is 1920 pixels, then the load eccentricity value obtained according to the above calculation formula is approximately 63.01 cm ≈ 0.63 m.

[0088] In one embodiment of the present invention, Figure 3 As shown, feature extraction is performed on the vibration data of N preset points to obtain vibration feature values, including the following steps:

[0089] Step S301, taking the average value of the vibration acceleration of the vibration data of N preset points at M time points as basic vibration data;

[0090] That is, the basic vibration data is represented by the average value of the vibration acceleration at M time points;

[0091] Step S302 , calculating the mean value, standard deviation, root mean square value, peak value, form factor, impulse factor, and margin factor of the basic vibration data;

[0092] The crest factor is the ratio of the peak value to the RMS value, the pulse factor is the ratio of the peak value to the average value, and the margin factor is the ratio of the peak value to the standard deviation.

[0093] Step S303, converting the basic vibration data into frequency domain data through fast Fourier transform, and calculating the main frequency, center frequency and spectrum energy of the frequency domain data;

[0094] Frequency domain data is represented by the amplitude spectrum, which is the amplitude of different frequency components. The main frequency represents the frequency component with the largest amplitude, the center frequency represents the frequency component corresponding to the "center of gravity" of the amplitude spectrum, which is used to reflect the overall frequency distribution, and the spectrum energy represents the sum of the amplitudes of all frequency components, which is used to reflect the vibration intensity.

[0095] Step S304 : taking the peak value, form factor, pulse factor and margin factor of the basic vibration data and the main frequency, center frequency and spectrum energy of the frequency domain data as vibration characteristic values.

[0096] It should be noted that the center frequency The calculation formula is as follows: ,in represents the i-th frequency component, Represents the amplitude of the i-th frequency component. The calculation formula of the spectrum energy E is as follows: In addition, the spectrum entropy, harmonic ratio, spectrum bandwidth, etc. of frequency domain data can also be calculated, which will not be described in detail here.

[0097] In one embodiment of the present invention, a larger value of the brake fault score indicates a greater risk of brake failure. The brake fault score is obtained by weighted summation of the meteorological score, aging score, load eccentricity value and vibration characteristic value. The corresponding weight coefficients are all custom parameters and are not described here.

[0098] In one embodiment of the present invention, the prediction model consists of a hidden layer and a classifier;

[0099] The hidden layer is used to update the concatenated vector composed of the meteorological score, aging score, load eccentricity value and vibration eigenvalue, and output the hidden vector. The number of dimensions of the hidden vector is a custom parameter.

[0100] That is, the number of dimensions of the splicing vector is 10, which are the meteorological score, aging score, load eccentricity value, peak value, form factor, pulse factor and margin factor of basic vibration data, and main frequency, center frequency and spectrum energy of frequency domain data;

[0101] The classifier inputs the hidden vector output by the hidden layer, and the class space of the classifier represents the fault prediction score threshold.

[0102] In one embodiment of the present invention, the calculation formula of the hidden layer includes:

[0103] ;

[0104] in represents the hidden vector of the hidden layer output, H represents the concatenated vector of the hidden layer input, 、 and Represent the first weight matrix, the second weight matrix and the third weight matrix respectively, and they are all custom hyperparameters. 、 and They represent the first bias vector, the second bias vector, and the third bias vector, respectively, and are all custom hyperparameters. e represents a natural constant, T represents a transpose operation, PReLU represents a PReLU activation function, and Swish represents a Swish activation function.

[0105] It should be noted that the first weight matrix can be defined as 64×10, so the dimension of the first bias vector is 64, the second weight matrix can be defined as 32×64, so the dimension of the second bias vector is 32, and the third weight matrix can be defined as 16×32, so the dimension of the third bias vector is 16, that is, the dimension of the hidden vector output by the final hidden layer is 16; in addition, compared with the fixed slope of Leaky ReLU, PReLU can adaptively adjust the slope, and Swish is smoother than ReLU, which can retain the contribution of negative numbers and improve the expressive power of the deep learning model. Similarly, the activation function of the classifier can also use the Swish activation function to map the hidden vector to the fault prediction score threshold, which is not elaborated here.

[0106] In one embodiment of the present invention, Figure 4 As shown in Figure 2, constructing sample labels for training samples of the prediction model includes the following steps:

[0107] Step S401, calculating a brake fault score after the object is completely lifted by the tower crane;

[0108] Step S402: After the tower crane completes the preset transfer distance, it brakes. If it is determined that there is a fault, it gradually reduces the weight and returns to step S401 until the fault is no longer present. 90% of the corresponding brake fault score is recorded as the sample label of the training sample. Otherwise, it proceeds to step S403.

[0109] Step S403: If it is determined that there is no fault, the weight is gradually increased until a fault occurs, and 90% of the corresponding brake fault score is recorded as the sample label of the training sample;

[0110] Step S404, repeating steps S401 to S403 until U training samples are obtained;

[0111] The number of training samples U is a custom parameter, and the default value of the number of training samples U is 2000.

[0112] It should be noted that the sample label of the training sample is the fault prediction score threshold. During the training of the prediction model, the mean square error between the value output by the prediction model at each iteration and the sample label of the training sample is specified as the loss function, and the adaptive gradient optimizer (such as Adam, AMSGrad, etc.) is used to reversely update the parameters of the prediction model to minimize the loss value calculated by the loss function. In addition, the prediction model can be used to set a dynamic threshold, thereby improving the accuracy of brake fault prediction. In order to reduce the experimental cost of training samples for constructing the prediction model, a simulation model can be used to model the tower crane. The simulation model can be Adams, Simscape Multibody, etc., which will not be described in detail here.

[0113] It should be noted that the intervals and thresholds are set for ease of comparison. The threshold size depends on the amount of sample data and the cardinality set by those skilled in the art for each set of sample data, as long as it does not affect the proportional relationship between the parameter and the quantized value. Furthermore, the above formulas are all dimensionless numerical calculations. These formulas are derived from software simulations of the most recent real-world conditions using large amounts of data. The preset parameters in these formulas are set by those skilled in the art based on actual conditions.

[0114] The above describes the embodiments of this embodiment, but this embodiment is not limited to the above specific implementation methods. The above specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. The tower crane maintenance and fault warning intelligent management system is characterized by: include: A meteorological score calculation module is used to calculate a meteorological score based on meteorological data; Meteorological data include: temperature, wind speed and rainfall; An aging score calculation module, which is used to calculate an aging score based on the operation data of the tower crane; Operation data includes: cumulative working hours, average daily usage times and historical failure times; A data acquisition module, which is used to simultaneously collect image data of the object and vibration data of N preset points after the object is fully lifted by the tower crane; The vibration data is represented by the vibration acceleration at M time points; A load eccentricity calculation module is used to calculate the horizontal deviation distance between the center of gravity of the object and the hook center of the tower crane based on the image data of the object, and mark it as the load eccentricity value; A vibration feature extraction module is used to extract features from vibration data of N preset points to obtain vibration feature values; A brake fault score calculation module is used to calculate a brake fault score based on a meteorological score, an aging score, a load eccentricity value, and a vibration characteristic value; A dynamic threshold generation module is used to input the meteorological score, aging score, load eccentricity value and vibration characteristic value into the prediction model to obtain the fault prediction score threshold; A brake fault judgment module is used to judge that if the brake fault score is greater than or equal to the fault prediction score threshold, the tower crane is immediately notified to lower the hoisted object; The larger the weather score value, the worse the weather conditions. The calculation formula is as follows: ； T, Wind and Rain represent temperature, wind speed and rainfall respectively. 、 and Respectively represent the custom temperature reference value, wind speed reference value and rainfall reference value, 、 and Represent the customized first weight coefficient, second weight coefficient and third weight coefficient respectively, and 、 and The sum of is 1; The larger the aging score value is, the greater the aging degree of the tower crane is. The calculation formula is as follows: ； Work, Freq and Break represent the cumulative working hours, average daily usage times and historical failure times respectively. 、 and represent the fourth, fifth, and sixth custom weight coefficients, respectively, and 、 and The sum of is 1, and e represents a natural constant; Calculating the load eccentricity value includes the following steps: Step S201, identifying the center of gravity of the object and the hook center of the tower crane through the target detection model; Step S202, calculating the horizontal pixel difference between the center of gravity of the object and the center of the hook of the tower crane; Step S203: Calculate the horizontal deviation distance between the center of gravity of the object and the hook center of the tower crane based on the horizontal pixel difference, and mark it as the load eccentricity value; Load eccentricity The calculation formula is as follows: ； in represents the horizontal pixel difference, Width represents the physical width of the camera sensor, represents the real distance between the camera and the object, f represents the focal length of the camera, Indicates the number of pixels of the image data in the horizontal direction; Feature extraction is performed on the vibration data of N preset points to obtain vibration characteristic values, including the following steps: Step S301, taking the average value of the vibration acceleration of the vibration data of N preset points at M time points as basic vibration data; Step S302 , calculating the mean value, standard deviation, root mean square value, peak value, form factor, impulse factor, and margin factor of the basic vibration data; The crest factor is the ratio of the peak value to the RMS value, the pulse factor is the ratio of the peak value to the average value, and the margin factor is the ratio of the peak value to the standard deviation. Step S303, converting the basic vibration data into frequency domain data through fast Fourier transform, and calculating the main frequency, center frequency and spectrum energy of the frequency domain data; Step S304 : taking the peak value, form factor, pulse factor and margin factor of the basic vibration data and the main frequency, center frequency and spectrum energy of the frequency domain data as vibration characteristic values.

2. The tower crane maintenance and fault warning intelligent management system according to claim 1 is characterized in that: The number N of preset points and the number M of time points of vibration data are both custom parameters.

3. The tower crane maintenance and fault warning intelligent management system according to claim 1 is characterized in that: A larger brake failure score indicates a greater risk of brake failure. The brake failure score is calculated by weighted summation of the meteorological score, aging score, load eccentricity value, and vibration characteristic value. The corresponding weight coefficients are all custom parameters.

4. The tower crane maintenance and fault warning intelligent management system according to claim 1 is characterized in that: The prediction model consists of hidden layers and classifiers; The hidden layer is used to update the concatenated vector composed of the meteorological score, aging score, load eccentricity value and vibration eigenvalue, and output the hidden vector. The number of dimensions of the hidden vector is a custom parameter. The classifier inputs the hidden vector output by the hidden layer, and the class space of the classifier represents the fault prediction score threshold.

5. The tower crane maintenance and fault warning intelligent management system according to claim 4 is characterized in that: The calculation formula for the hidden layer includes: ； in represents the hidden vector of the hidden layer output, H represents the concatenated vector of the hidden layer input, 、 and Represent the first weight matrix, the second weight matrix and the third weight matrix respectively, and they are all custom hyperparameters. 、 and They represent the first bias vector, the second bias vector, and the third bias vector, respectively, and are all custom hyperparameters. e represents a natural constant, T represents a transpose operation, PReLU represents a PReLU activation function, and Swish represents a Swish activation function.

6. The tower crane maintenance and fault warning intelligent management system according to claim 1, characterized in that: Constructing sample labels for training samples of the prediction model includes the following steps: Step S401, calculating a brake fault score after the object is completely lifted by the tower crane; Step S402: After the tower crane completes the preset transfer distance, it brakes. If it is determined that there is a fault, it gradually reduces the weight and returns to step S401 until the fault is no longer present. 90% of the corresponding brake fault score is recorded as the sample label of the training sample. Otherwise, it proceeds to step S403. Step S403: If it is determined that there is no fault, the weight is gradually increased until a fault occurs, and 90% of the corresponding brake fault score is recorded as the sample label of the training sample; Step S404, repeating steps S401 to S403 until U training samples are obtained; The number of training samples U is a custom parameter.

Images