Crane operation stability analysis and transmission part fault diagnosis integrated device
By combining eddy current sensors and coded displacement sensors with empirical mode decomposition and machine learning algorithms, the problem of fault diagnosis of key components in crane transmission systems has been solved, improving the operational stability and safety of cranes and reducing the risk of accidents.
Patent Information
- Application Number
- CN202511730816.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-24
- Publication Date
- 2026-02-06
AI Technical Summary
Existing technologies are insufficient to effectively identify and diagnose early failures in critical components such as rolling bearings and gearboxes in cranes, affecting the operational stability and safety of cranes. Furthermore, the lack of a comprehensive understanding of the transmission system leads to potential economic losses and safety hazards.
By combining eddy current sensors and coded displacement sensors with empirical mode decomposition, traditional machine learning, and deep learning algorithms, vibration signal features and fault diagnosis of key components of crane transmission systems can be achieved, including fault identification and location of trolley bearings, guide wheels, wire ropes, gearboxes, etc.
It enables fault diagnosis and stability analysis of key components of the crane's transmission system, improves the safety and reliability of the crane, reduces the occurrence of catastrophic accidents, and provides a scientific assessment of the crane's health status.
Smart Images
Figure SMS_8 
Figure SMS_9 
Figure SMS_22
Abstract
Description
Technical Field
[0001] This invention relates to the field of crane testing technology, and in particular to an integrated device for crane operation stability analysis and transmission component fault diagnosis. Background Technology
[0002] Lifting machinery is widely used in industrial production and infrastructure construction fields such as mining, construction, and road and bridge construction. It is an indispensable and important piece of equipment in modern industrial production and transportation. To ensure the safety of cranes during periodic operations, a series of indicators are used to characterize the reliability of the working performance of each component of the crane. TSGQ7016—2016 "Periodic Inspection Rules for Lifting Machinery" requires: whether the crane's running track is free from obvious loosening and defects that affect its safe operation; whether there is any rail wear during the crane's full-length operation along the track; and verification of the travel distance of the trolley and crane under no-load conditions. GBT5972-2016 "Maintenance, Maintenance, Inspection and Scrapping of Crane Wire Ropes" and TSG Q7015-2016 "Periodic Inspection Rules for Lifting Machinery" require: excessive wear of broken wires in the wire rope of the hoisting mechanism guide wheel. When passing over the pulley, broken wires will press on other parts, causing localized deterioration. Inflexible pulley rotation or severe and uneven wear of the rolling elements will cause severe wear of the wire rope. A balancing pulley that fails to provide balance will lead to an uneven load on the wire rope winding system.
[0003] Rolling bearings in crane trolleys, carriages, and guide wheels play a crucial role in supporting and fixing rotating bodies in rotating machinery, and their health significantly affects the smooth operation of the machine. Studies show that rolling bearings are among the most easily damaged components in industrial equipment, directly causing 40-50% of rotating machinery failures. Defects in rolling bearings of different types and locations affect the overall performance and service life of the machine; even minor faults can lead to serious economic losses in industrial production and even personal injury. Therefore, accurate and effective fault diagnosis of rolling bearings has significant research and practical value.
[0004] For the detection of defects in the trolley and crane tracks, commonly used non-destructive testing methods for detecting cracks include magnetic particle testing, penetrant testing, ultrasonic testing, X-ray testing, and eddy current testing. Each of these techniques has its own advantages and disadvantages. The traditional eddy current testing method utilizes the impedance change of the excitation coil caused by the reverse magnetic field of the eddy current to create an impedance change diagram, from which information about the nature of the defect is obtained.
[0005] The electric motor, brake, and gearbox are key fundamental components of a crane, widely used in cranes such as large gantry cranes, loading and unloading bridges, and large portal cranes, enabling power transmission and motion transformation of mechanical equipment. As cranes develop towards higher power density and larger sizes, the working environment of gearboxes becomes more complex and harsh, increasing the probability of failure and seriously affecting the accuracy and reliability of large cranes. Timely detection of early-stage gearbox failure vibration characteristics allows for effective countermeasures to reduce economic losses and catastrophic accidents. Therefore, accurate extraction and timely identification of early-stage gearbox failure vibration characteristics are key factors limiting the success rate of fault diagnosis, and have significant theoretical and practical engineering value for improving the safe service performance of gearboxes. Summary of the Invention
[0006] The purpose of this invention is to provide an integrated device for crane operation stability analysis and transmission component fault diagnosis. It can realize fault diagnosis of crane motors, gearboxes, brakes and gearboxes, as well as operation stability analysis and defect diagnosis of guide wheels, wire ropes and trolleys of the lifting mechanism. It can collect vibration signals of key components of crane transmission system, bearing fault characteristics, identification information of guide wheels, wire ropes and track crack defects, extract vibration signal characteristics of key components of crane transmission system for fault diagnosis analysis, and detect, identify and track the wire rope broken strands, periodic faults of trolley and trolley bearings and track crack defects.
[0007] To achieve the above objectives, the present invention adopts the following technical solution: An integrated device for crane operation stability analysis and transmission component fault diagnosis includes: The unit for fault diagnosis and operational stability analysis of trolley bearings is used to extract fault vibration characteristics, which include signal noise reduction and feature calculation. The large and small vehicle track crack defect analysis unit is used to analyze the vibration mode of the track when the wheel passes through the track in order to obtain the defects of the wheel track. The hoisting mechanism guide wheel defect and wire rope broken wire and loose strand analysis unit is used to collect and analyze the defect characteristic signals generated when the wire rope passes through the guide wheel by utilizing defects such as broken wires, loose strands, extrusion of the core of single-layer wire rope, local reduction of wire rope diameter, strand extrusion or twisting, and protrusion of strands inside the rotating wire rope. The fault diagnosis and analysis unit for key components of crane transmission is used to extract and identify the vibration signal characteristics of brake failures, accurately extract and promptly identify the vibration characteristics of early gearbox failures, detect faults by analyzing the vibration signal spectrum of crane drive motors, and identify potential faults in key crane components.
[0008] In practical applications, the number of rolling elements in the fault diagnosis and operational stability analysis unit for the large and small vehicle bearings is set to... rolling element diameter sprocket bearing raceway pitch sprocket bearing contact angle Inner raceway radius Outer raceway radius sprocket bearing inner ring speed The characteristic frequency table of sprocket bearings is as follows: The following is a table showing the failure frequency of sprocket bearing components: When analyzing the fault category of a bearing through spectrum analysis, the frequency value corresponding to the highest peak in the spectrum is approximately the characteristic frequency value calculated by the empirical formula of the fault frequency. The essence of bearing fault diagnosis is to characterize the various characteristic frequencies of the fault, which helps to screen the modal components of the sprocket bearing vibration signal.
[0009] In the analysis unit for defects in the guide wheel of the hoisting mechanism and broken or loose strands in the wire rope, the defect characteristic signals include, but are not limited to: The impact generated when local defects appear on the inner or outer raceways or rolling element surfaces of the guide wheel bearing will excite high-frequency vibration of the bearing. Defects in the guide wheel groove affect the smooth passage of the wire rope, causing a jerky feeling and accelerating the deterioration of the defect; Excessive clearance between the wire rope and the guide wheel will cause the wire rope to sway from side to side, affecting the stability of the lifting operation. If the gap between the wire rope and the guide wheel is too small, the guide wheel may get the rope stuck.
[0010] Specifically, when the fault diagnosis and analysis unit for key components of crane transmission is used to accurately extract and timely identify early fault vibration characteristics of gearboxes, it determines the fault feature extraction method of crane gearboxes from the perspective of time-frequency domain analysis features, extracts the characteristics of vibration acceleration peak value, peak-to-peak value, kurtosis, IMF component, vibration frequency, power spectral density, and energy distribution, and determines the traditional machine learning model and deep model algorithm based on the artificial intelligence-based crane gearbox fault hazard identification method for model training, testing, and evaluation.
[0011] Furthermore, when the fault diagnosis and analysis unit for key components of crane transmission is used to detect faults by analyzing the vibration signal spectrum of the crane drive motor, when an abnormality occurs inside the motor, the vibration will intensify and the motor operating parameters will change. The abnormal phenomenon corresponds to a specific fault frequency. By comparing and analyzing the output signal spectrum of the vibration sensor with known fault characteristics, the nature and location of the fault can be determined.
[0012] Furthermore, potential electrical vibration hazards include, but are not limited to: uneven magnetic field, broken cage bars, and uneven air gap. Potential mechanical abnormal vibration hazards include, but are not limited to: rotor imbalance, rolling bearing failure, sliding bearing failure, shaft defects, and component rubbing.
[0013] Furthermore, EMD (Empirical Mode Analysis) can be used to effectively analyze non-stationary signals.
[0014] Furthermore, the spectral characteristics of different vibration types are also different; By analyzing and calculating the characteristic frequencies of each component of the rolling bearing and comparing them with the actual collected vibration signals, the faults of the rolling bearing can be identified.
[0015] In practical applications, the fault diagnosis and analysis unit for key components of crane transmission is used to identify potential faults in key components of cranes. It determines the characteristics of various mechanical hazards in the time and frequency domains of vibration signal, including maximum, minimum, average, peak-to-peak, absolute average, variance, standard deviation, kurtosis, skewness, root mean square, waveform factor, peak factor, impulse factor, margin, and power spectral entropy, and performs hazard characteristic analysis.
[0016] Specifically, six time-domain and frequency-domain features—mean value, peak-to-peak value, root mean square, waveform factor, impulse factor, and power spectral entropy—are extracted and comprehensively used as the data basis for traditional machine learning hazard judgment; among them, the time-domain features are selected as follows: The mean μ is: ; The root mean square (RMS) is: ; The pulse factor I is: ; The waveform factor is: ; For frequency domain extraction, power spectral entropy is selected. The basic steps for extracting power spectral entropy from a discrete-time sequence signal of length N {x(n) | n = 0, 1, N-1} are as follows. Perform Discrete Fourier Transform on {x(n) | n=0,1, N-1} In the formula, k = 1, 2, 3, ..., N-1 is the frequency order; Based on the relationship between signal energy and power, the power spectrum of each order of spectrum can be obtained, that is, the power density is used for calculation. The power spectrum entropy Hf can be calculated from the power spectrum S(k) of each frequency band using the above formula.
[0017] Compared with existing technologies, the integrated crane operation stability analysis and transmission component fault diagnosis device of the present invention has the following advantages: The integrated crane operation stability analysis and transmission component fault diagnosis device provided by this invention uses eddy current sensors to detect cracks and defects in the running tracks of the trolley and main trolley, and coded displacement sensors to measure the travel position and locate the fault. It can also verify the travel distance of the trolley and main trolley. Empirical mode decomposition is performed on the bearings, brakes, gearboxes, motors, and vibration signal faults of the gantry crane to obtain their time-frequency domain quantities. Combined with algorithms, it classifies the fault diagnoses of brakes, gearboxes, motors, and main bearings of the trolley and main trolley. This enables a scientific analysis and evaluation of the crane's health status, effectively solving the problem of a lack of comprehensive and systematic understanding of the actual performance of crane gearboxes after long-term use. It has significant practical implications for ensuring the safe and reliable operation of cranes and minimizing the occurrence of catastrophic crane accidents. Detailed Implementation
[0018] For ease of understanding, the integrated device for crane operation stability analysis and transmission component fault diagnosis provided in the embodiments of the present invention will be described in detail below.
[0019] This invention provides an integrated device for crane operation stability analysis and transmission component fault diagnosis, comprising: The unit for fault diagnosis and operational stability analysis of trolley bearings is used to extract fault vibration characteristics, which include signal noise reduction and feature calculation. The large and small vehicle track crack defect analysis unit is used to analyze the vibration mode of the track when the wheel passes through the track in order to obtain the defects of the wheel track. The hoisting mechanism guide wheel defect and wire rope broken wire and loose strand analysis unit is used to collect and analyze the defect characteristic signals generated when the wire rope passes through the guide wheel by utilizing defects such as broken wires, loose strands, extrusion of the core of single-layer wire rope, local reduction of wire rope diameter, strand extrusion or twisting, and protrusion of strands inside the rotating wire rope. The fault diagnosis and analysis unit for key components of crane transmission is used to extract and identify the vibration signal characteristics of brake failures, accurately extract and promptly identify the vibration characteristics of early gearbox failures, detect faults by analyzing the vibration signal spectrum of crane drive motors, and identify potential faults in key crane components.
[0020] Compared with existing technologies, the integrated crane operation stability analysis and transmission component fault diagnosis device described in this embodiment of the invention has the following advantages: The integrated crane operation stability analysis and transmission component fault diagnosis device provided in this invention uses eddy current sensors to detect cracks and defects in the running tracks of the trolley and main trolley, and coded displacement sensors to measure the travel position and locate the fault. It also verifies the travel distance of the trolley and main trolley. Empirical mode decomposition is performed on the bearings, brakes, gearboxes, motors, and vibration signal faults of the gantry crane to obtain their time-frequency domain quantities. Combined with algorithms, the device classifies the fault diagnoses of the brakes, gearboxes, motors, and main bearings of the trolley and main trolley. This enables a scientific analysis and evaluation of the crane's health status, effectively solving the problem of a lack of comprehensive and systematic understanding of the actual performance of crane gearboxes after long-term use. This has significant practical implications for ensuring the safe and reliable operation of cranes and minimizing the occurrence of catastrophic crane accidents.
[0021] In practical applications, the above-mentioned unit for fault diagnosis and operational stability analysis of large and small vehicle bearings assumes the number of rolling elements... rolling element diameter sprocket bearing raceway pitch sprocket bearing contact angle Inner raceway radius Outer raceway radius sprocket bearing inner ring speed The characteristic frequency table of sprocket bearings is as follows: The following is a table showing the failure frequency of sprocket bearing components: When analyzing the fault category of a bearing through spectrum analysis, the frequency value corresponding to the highest peak in the spectrum is approximately the characteristic frequency value calculated by the empirical formula of the fault frequency. The essence of bearing fault diagnosis is to characterize the various characteristic frequencies of the fault, which helps to screen the modal components of the sprocket bearing vibration signal.
[0022] Among them, the defect characteristic signals in the above-mentioned hoisting mechanism guide wheel defect and wire rope broken strand analysis unit include, but are not limited to: The impact generated when local defects appear on the inner or outer raceways or rolling element surfaces of the guide wheel bearing will excite high-frequency vibration of the bearing. Defects in the guide wheel groove affect the smooth passage of the wire rope, causing a jerky feeling and accelerating the deterioration of the defect; Excessive clearance between the wire rope and the guide wheel will cause the wire rope to sway from side to side, affecting the stability of the lifting operation. If the gap between the wire rope and the guide wheel is too small, the guide wheel may get the rope stuck.
[0023] Specifically, when the aforementioned fault diagnosis and analysis unit for key components of crane transmission is used to accurately extract and promptly identify early fault vibration characteristics of gearboxes, it determines the fault feature extraction method for crane gearboxes from the perspective of time-frequency domain analysis features, extracts features such as peak vibration acceleration, peak-to-peak value, kurtosis, IMF components, vibration frequency, power spectral density, and energy distribution, and determines the traditional machine learning model and deep model algorithm based on the artificial intelligence-based crane gearbox fault hazard identification method for model training, testing, and evaluation.
[0024] Furthermore, when the aforementioned fault diagnosis and analysis unit for key components of crane transmission is used to detect faults by analyzing the vibration signal spectrum of the crane drive motor, when an abnormality occurs inside the motor, the vibration will intensify and the motor operating parameters will change. The abnormal phenomenon corresponds to a specific fault frequency. By comparing and analyzing the output signal spectrum of the vibration sensor with known fault characteristics, the nature and location of the fault can be determined.
[0025] Furthermore, potential electrical vibration hazards include, but are not limited to: uneven magnetic field, broken cage bars, and uneven air gap. Potential mechanical abnormal vibration hazards include, but are not limited to: rotor imbalance, rolling bearing failure, sliding bearing failure, shaft defects, and component rubbing.
[0026] Furthermore, EMD (Empirical Mode Analysis) can be used to effectively analyze non-stationary signals.
[0027] Furthermore, the spectral characteristics of different vibration types are also different; By analyzing and calculating the characteristic frequencies of each component of the rolling bearing and comparing them with the actual collected vibration signals, the faults of the rolling bearing can be identified.
[0028] In practical applications, the aforementioned fault diagnosis and analysis unit for key components of crane transmission is used to identify potential faults in key components of cranes. It determines the characteristics of various mechanical hazards in the time and frequency domains of vibration signal values, including maximum, minimum, average, peak-to-peak, absolute average, variance, standard deviation, kurtosis, skewness, root mean square, waveform factor, peak factor, impulse factor, margin, and power spectral entropy, and performs hazard characteristic analysis.
[0029] Specifically, six time-domain and frequency-domain features—mean value, peak-to-peak value, root mean square, waveform factor, impulse factor, and power spectral entropy—are extracted and comprehensively used as the data basis for traditional machine learning hazard judgment; among them, the time-domain features are selected as follows: The mean μ is: ; The root mean square (RMS) is: ; The pulse factor I is: ; The waveform factor is: ; For frequency domain extraction, power spectral entropy is selected. The basic steps for extracting power spectral entropy from a discrete-time sequence signal of length N {x(n) | n = 0, 1, N-1} are as follows. Perform Discrete Fourier Transform on {x(n) | n=0,1, N-1} In the formula, k = 1, 2, 3, ..., N-1 is the frequency order; Based on the relationship between signal energy and power, the power spectrum of each order of spectrum can be obtained, that is, the power density is used for calculation. The power spectrum entropy Hf can be calculated from the power spectrum S(k) of each frequency band using the above formula.
[0030] It should be added that fault characteristic signals can be reflected not only in the time domain, but also in the frequency domain. Therefore, the acquired signals can be analyzed in the frequency domain. Common frequency domain analysis methods include spectrum, energy spectrum, and power spectrum. Through these methods, the energy distribution of the signal in the frequency domain can be obtained. Combining this energy distribution with information entropy can achieve a quantitative description of the signal in the frequency domain.
[0031] Power spectral analysis is based on Passeuvar's theorem, which states that the total energy of a signal sequence is always equal to the sum of the energy components of that signal over a complete set of orthogonal functions. Passeuvar's theorem is described as follows: In the above equation, X(f) is the continuous Fourier transform, where f represents the frequency component of the signal. Passevar's theorem states that the total energy of the signal in the time domain is equal to the sum of the energy of X(f) after its Fourier transform in the frequency domain f. That is, the total energy of the signal remains unchanged after the Fourier transform, i.e., the energy in the time domain is always equal to the energy in the frequency domain. For a discrete-time sequence signal {x(n) | n, 0, 1, N-1}, another form of Passevar's theorem can be obtained after the discrete Fourier transform, as shown in the following equation: , In the formula, S(k) represents the energy partition of the signal in the frequency domain, and DFT[xn] is the discrete Fourier transform of the original signal. The sample length remains unchanged before and after the transform. After obtaining the power spectrum of the signal, it can be combined with the information entropy to obtain the power spectrum Hf of the signal, as shown in the following formula: In the formula This indicates the proportion of the energy in the k-th frequency band of the signal to the total energy.
[0032] The above analysis shows that power spectral entropy is used to represent the uncertainty of signal energy under power spectral division. When the frequency composition of the signal is simple, the power spectrum is concentrated in some frequency components, and the corresponding frequency spectral lines are relatively few. The probability of the corresponding components is also less, resulting in a smaller value of power spectral entropy Hf. Conversely, if the signal is more complex, the power spectrum of the signal is more dispersed, the corresponding power spectral lines will increase, and the value of power spectral entropy fH will increase. Therefore, power spectral entropy is a quantitative description of the complexity of the energy distribution of a signal in the frequency domain.
[0033] Furthermore, in the integrated device for crane operation stability analysis and transmission component fault diagnosis provided in this embodiment of the invention, time-domain feature parameters are extracted from the first 10 groups of vibration signals (each group consisting of 1000 vibration signals) for each of the following states: normal state, broken gear teeth, missing teeth, tooth surface wear / tooth root wear state, bearing inner ring, outer ring, inner and outer ring fault state, bearing outer ring fault state, and step roller wear state. The feature parameter evaluation index SD of each parameter is then calculated.
[0034] In summary, time-domain and frequency-domain indicators such as mean, peak-to-peak value, root mean square, waveform factor, impulse factor, and power spectral entropy are selected. Waveform factor and impulse factor are dimensionless indicators. The impulse factor is used to detect whether there is an impact in the signal. Power spectral entropy can reflect the frequency distribution characteristics from the frequency domain perspective, thereby reflecting certain characteristics of the fault.
[0035] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. An integrated device for crane operation stability analysis and transmission component fault diagnosis, characterized in that, include: The unit for fault diagnosis and operational stability analysis of trolley bearings is used to extract fault vibration characteristics, which include signal noise reduction and feature calculation. The large and small vehicle track crack defect analysis unit is used to analyze the vibration mode of the track when the wheel passes through the track in order to obtain the defects of the wheel track. The hoisting mechanism guide wheel defect and wire rope broken wire and loose strand analysis unit is used to collect and analyze the defect characteristic signals generated when the wire rope passes through the guide wheel by utilizing defects such as broken wires, loose strands, extrusion of the core of single-layer wire rope, local reduction of wire rope diameter, strand extrusion or twisting, and protrusion of strands inside the rotating wire rope. The fault diagnosis and analysis unit for key components of crane transmission is used to extract and identify the vibration signal characteristics of brake failures, accurately extract and promptly identify the vibration characteristics of early gearbox failures, detect faults by analyzing the vibration signal spectrum of crane drive motors, and identify potential faults in key crane components.
2. The integrated device for crane operation stability analysis and transmission component fault diagnosis according to claim 1, characterized in that, In the aforementioned unit for fault diagnosis and operational stability analysis of the large and small vehicle bearings, the number of rolling elements is set as follows: rolling element diameter sprocket bearing raceway pitch sprocket bearing contact angle Inner raceway radius Outer raceway radius sprocket bearing inner ring speed The characteristic frequency table of sprocket bearings is as follows: The following is a table showing the failure frequency of sprocket bearing components: When analyzing the fault category of a bearing through spectrum analysis, the frequency value corresponding to the highest peak in the spectrum is approximately the characteristic frequency value calculated by the empirical formula of the fault frequency. The essence of bearing fault diagnosis is to characterize the various characteristic frequencies of the fault, which helps to screen the modal components of the sprocket bearing vibration signal.
3. The integrated device for crane operation stability analysis and transmission component fault diagnosis according to claim 1, characterized in that, In the analysis unit for defects in the hoisting mechanism guide wheel and broken / loose wires in the wire rope, the defect characteristic signals include, but are not limited to: The impact generated when local defects appear on the inner or outer raceways or rolling element surfaces of the guide wheel bearing will excite high-frequency vibration of the bearing. Defects in the guide wheel groove affect the smooth passage of the wire rope, causing a jerky feeling and accelerating the deterioration of the defect; Excessive clearance between the wire rope and the guide wheel will cause the wire rope to sway from side to side, affecting the stability of the lifting operation. If the gap between the wire rope and the guide wheel is too small, the guide wheel may get the rope stuck.
4. The integrated device for crane operation stability analysis and transmission component fault diagnosis according to claim 1, characterized in that, The fault diagnosis and analysis unit for key components of crane transmission is used to accurately extract and promptly identify early fault vibration characteristics of gearboxes. From the perspective of time-frequency domain analysis, it determines the fault feature extraction method for crane gearboxes, extracts features such as peak vibration acceleration, peak-to-peak value, kurtosis, IMF components, vibration frequency, power spectral density, and energy distribution, and determines the traditional machine learning model and deep learning model algorithm based on artificial intelligence for crane gearbox fault hazard identification, so as to carry out model training, testing, and evaluation.
5. The integrated device for crane operation stability analysis and transmission component fault diagnosis according to claim 1, characterized in that, The fault diagnosis and analysis unit for key components of crane transmission is used to detect faults by analyzing the vibration signal spectrum of the crane drive motor. When an abnormality occurs inside the motor, the vibration will intensify and the motor operating parameters will change. The abnormal phenomenon corresponds to a specific fault frequency. By comparing and analyzing the output signal spectrum of the vibration sensor with known fault characteristics, the nature and location of the fault can be determined.
6. The integrated device for crane operation stability analysis and transmission component fault diagnosis according to claim 5, characterized in that, Electrical abnormal vibration hazards include, but are not limited to: uneven magnetic field, broken cage bars, uneven air gap; Potential mechanical abnormal vibration hazards include, but are not limited to: rotor imbalance, rolling bearing failure, sliding bearing failure, shaft defects, and component rubbing.
7. The integrated device for crane operation stability analysis and transmission component fault diagnosis according to claim 5 or 6, characterized in that, EMD—Empirical Mode Analysis—can be used to effectively analyze non-stationary signals.
8. The integrated device for crane operation stability analysis and transmission component fault diagnosis according to claim 6, characterized in that, Different types of vibrations have different spectral characteristics. By analyzing and calculating the characteristic frequencies of each component of the rolling bearing and comparing them with the actual collected vibration signals, the faults of the rolling bearing can be identified.
9. The integrated device for crane operation stability analysis and transmission component fault diagnosis according to claim 1, characterized in that, The fault diagnosis and analysis unit for key components of crane transmission is used to identify potential faults in key components of cranes, determine the characteristics of various mechanical hazards in the time and frequency domains of vibration signal maximum, minimum, average, peak-to-peak, absolute average, variance, standard deviation, kurtosis, skewness, root mean square, waveform factor, peak factor, impulse factor, margin, and power spectral entropy, and perform hazard characteristic analysis.
10. The integrated device for crane operation stability analysis and transmission component fault diagnosis according to claim 9, characterized in that, Six time-domain and frequency-domain features—mean value, peak-to-peak value, root mean square, waveform factor, impulse factor, and power spectral entropy—are extracted and comprehensively used as the data basis for traditional machine learning hazard judgment. The time-domain features are selected as follows: The mean μ is: ; The root mean square (RMS) is: ; The pulse factor I is: ; The waveform factor is: ; For frequency domain extraction, power spectral entropy is selected. The basic steps for extracting power spectral entropy for a discrete-time sequence signal of length N {x(n) | n = 0, 1, N-1} are as follows. Perform Discrete Fourier Transform on {x(n) | n=0,1, N-1} In the formula, k = 1, 2, 3, ..., N-1 is the frequency order; Based on the relationship between signal energy and power, the power spectrum of each order of spectrum can be obtained, that is, the power density is used for calculation. The power spectrum entropy Hf can be calculated from the power spectrum S(k) of each frequency band using the above formula.