Method for predicting residual life of steel wire rope of four-rope grab crane

Abstract

A steel wire rope remaining life prediction method of a four-rope grab crane comprises the steps that 1, an electromagnetic device is used for magnetization in the axial direction of a steel wire rope; 2, a Hall sensor is installed at the fixed end of the steel wire rope; 3, a Hall sensor monitors changes of a magnetic field around the steel wire rope in real time; 4, whether missing values and abnormal values exist in the collected digital signal sequence or not is checked; if missing values exist, a linear interpolation method is adopted for filling; 5, extracting characteristics related to the damage and residual life of the steel wire rope from the cleaned digital signal data; 6, establishing a magnetization prediction model; 7, magnetic field change characteristic data of the steel wire rope in different use stages are collected, a least square method is adopted for the magnetization prediction model to estimate model parameters, and a loss function is minimized; and 8, predicting the real-time residual life of the steel wire rope. The method can predict the service life of the steel wire rope at high frequency and accurately predict the residual service life of the steel wire rope.

Description

Technical Field

[0001] The invention belongs to the field of computer science and technology, and relates to a method for predicting the remaining life of a steel wire rope of a four-rope grab crane. Background Art

[0002] As a key material handling equipment, four-rope grab crane is widely used in many industrial fields such as ports, mines, electricity, cement, etc. In actual operation, the wire rope will inevitably suffer various damages such as wire breakage, wear, rust, etc. due to long-term complex loads (including stretching, bending, torsion, etc.), environmental factors (such as moisture, corrosion, dust, etc.), and its own fatigue accumulation. Once the wire rope fails suddenly, it will cause the grab to fall, which may cause serious casualties, equipment damage, production interruption and other major accidents. Therefore, it is of great research significance to use sensor technology and prediction algorithms to predict the remaining life of the wire rope.

[0003] The traditional wire rope maintenance methods mainly have the following problems: 1. Mainly rely on regular manual inspections, and the inspection results depend to a large extent on the experience and professional level of the inspectors.

[0004] 2. It requires a lot of manpower costs, and due to the complexity of actual operations, it is difficult to carry out high-frequency inspections. Summary of the invention

[0005] The technical problems to be solved by the present invention are: (1) how to solve the problem of low accuracy of manual maintenance of wire ropes; and (2) how to solve the problem of low frequency of wire rope inspection. Therefore, the present invention provides a method for predicting the remaining life of the wire rope of a four-rope grab crane.

[0006] To solve the above problems, the present invention is achieved through the following technical solutions: A method for predicting the remaining life of a steel wire rope of a four-rope grab crane comprises the following steps: Step 1: Use an electromagnetic device to magnetize the wire rope along its axial direction, so that the wire rope generates a relatively stable magnetic field environment that can be sensed by the Hall sensor during operation; Step 2: Install a Hall sensor at the fixed end of the wire rope. The installation direction of the Hall sensor is perpendicular to the magnetic field generated by the wire rope. Step 3: The Hall sensor monitors the changes in the magnetic field around the wire rope in real time and converts it into an electrical signal output; the electrical signal output by the Hall sensor is collected according to the set sampling frequency, and converted into a digital signal form and stored, recorded as B(t), where t represents time; Step 4: Check whether the collected digital signal sequence B(t) has missing values ​​and outliers; if there are missing values, use linear interpolation to fill them, and the missing values ​​are ; Identify outliers by calculating the mean μ and standard deviation σ of the digital signal sequence. , ; A threshold is preset, and if the outlier exceeds the threshold, the outlier is removed; Step 5: Extract the features related to wire rope damage and remaining life from the cleaned digital signal data, including the magnetic field change amplitude feature A and the magnetic field change frequency feature f dom ; Step 6: According to the remaining life of the wire rope L and the magnetic field change amplitude characteristic A, the magnetic field change frequency characteristic f dom And the wire rope has been used for t used The linear relationship between the magnetization and magnetization prediction model is established. The magnetization prediction model expression is: L = β0 + β1A + β2f dom +β3t used +ε, where β0, β1, β2, β3 are model parameters and ε is a random error term; Step 7: Collect the characteristic data of the magnetic field change of the wire rope at different use stages, and use the least squares method to estimate the model parameters for the magnetization prediction model to minimize the loss function: ; Step 8: Substitute the real-time collected and preprocessed magnetic field change characteristic data into the trained prediction model to predict the real-time remaining life L of the wire rope. When the predicted remaining life of the wire rope is lower than the set safety threshold, an early warning signal is issued to remind relevant personnel to take timely action to ensure the safety of equipment and personnel.

[0007] Sampling frequency f S =50HZ.

[0008] The magnetic field change characteristic data of the wire rope at different use stages are collected, and the test set and training set are divided into 3:7.

[0009] Compared with the prior art, the present invention has the following beneficial effects: by adopting the above algorithm, the life of the steel wire rope can be predicted at a high frequency, and the remaining life of the steel wire rope can be accurately predicted. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 The present invention is a flowchart of the steps of a method for predicting the remaining life of a steel wire rope of a four-rope grab crane. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] In the description of the present invention, it is necessary to understand that the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside", "outside", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0013] like Figure 1 As shown, a method for predicting the remaining life of a steel wire rope of a four-rope grab crane comprises the following steps: Step 1: Use an electromagnetic device to magnetize the steel wire rope along its axial direction. During the operation of the steel wire rope, a relatively stable magnetic field environment will be generated which can be sensed by the Hall sensor. It should be noted that the electromagnetic device here is a commercially available product.

[0014] Step 2: Install a Hall sensor at the fixed end of the wire rope. The installation direction of the Hall sensor should be perpendicular to the magnetic field generated by the wire rope.

[0015] Step 3: The Hall sensor monitors the changes in the magnetic field around the wire rope in real time and converts it into an electrical signal output. Set the sampling frequency f S =50HZ; the electrical signal output by the Hall sensor is collected according to the set sampling frequency, and converted into a digital signal and stored, recorded as B(t), where t represents time.

[0016] Step 4: Check whether the collected digital signal sequence B(t) has missing values ​​and abnormal values. If there are missing values, linear interpolation can be used to fill them. ; Identify outliers by calculating the mean μ and standard deviation σ of the digital signal sequence. , ; A threshold is preset, and if the outlier exceeds the threshold, the outlier is removed.

[0017] Step 5: Extract the features related to wire rope damage and remaining life from the cleaned digital signal data, including the magnetic field change amplitude feature A and the magnetic field change frequency feature f dom .

[0018] Step 6: According to the remaining life of the wire rope L and the magnetic field change amplitude characteristic A, the magnetic field change frequency characteristic f dom And the wire rope has been used for t used The linear relationship between the magnetization and magnetization prediction model is established. The magnetization prediction model expression is: L = β0 + β1A + β2f dom +β3t used +ε, where β0, β1, β2, β3 are model parameters and ε is a random error term.

[0019] Step 7: Collect the characteristic data of the magnetic field change of the wire rope at different use stages, and divide the test set and the training set into 3:7; for the magnetization prediction model, use the least squares method to estimate the model parameters and minimize the loss function: ; Step 8: Collect and pre-process the magnetic field change characteristic data (i.e., the new A, f dom and t used The predicted remaining life L of the wire rope is predicted. When the predicted remaining life of the wire rope is lower than the set safety threshold, an early warning signal is issued to remind relevant personnel to take timely action to ensure the safety of equipment and personnel.

[0020] The above is only a preferred embodiment of the present invention. It should be pointed out that for those skilled in the art, several changes and improvements can be made without departing from the overall concept of the present invention, which should also be regarded as the scope of protection of the present invention.

Claims

1. A method for predicting the remaining life of a steel wire rope of a four-rope grab crane, characterized in that: The steps include: Step 1: Use an electromagnetic device to magnetize the wire rope along its axial direction, so that the wire rope generates a relatively stable magnetic field environment that can be sensed by the Hall sensor during operation; Step 2: Install a Hall sensor at the fixed end of the wire rope. The installation direction of the Hall sensor is perpendicular to the magnetic field generated by the wire rope. Step 3: The Hall sensor monitors the changes in the magnetic field around the wire rope in real time and converts it into an electrical signal output; the electrical signal output by the Hall sensor is collected according to the set sampling frequency, and converted into a digital signal form and stored, recorded as B(t), where t represents time; Step 4: Check whether the collected digital signal sequence B(t) has missing values ​​and abnormal values; If there are missing values, linear interpolation is used to fill them. ; Identify outliers by calculating the mean μ and standard deviation σ of the digital signal sequence. , ; A threshold is preset, and if the outlier exceeds the threshold, the outlier is removed; Step 5: Extract the features related to wire rope damage and remaining life from the cleaned digital signal data, including the magnetic field change amplitude feature A and the magnetic field change frequency feature f dom ; Step 6: According to the remaining life of the wire rope L and the magnetic field change amplitude characteristic A, the magnetic field change frequency characteristic f dom And the wire rope has been used for t used The linear relationship between the magnetization and magnetization prediction model is established. The magnetization prediction model expression is: L = β0 + β1A + β2f dom +β3t used +ε, where β0, β1, β2, β3 are model parameters and ε is a random error term; Step 7: Collect the characteristic data of the magnetic field change of the wire rope at different use stages, and use the least squares method to estimate the model parameters for the magnetization prediction model to minimize the loss function: ； Step 8: Substitute the real-time collected and preprocessed magnetic field change characteristic data into the trained prediction model to predict the real-time remaining life L of the wire rope. When the predicted remaining life of the wire rope is lower than the set safety threshold, an early warning signal is issued to remind relevant personnel to take timely action to ensure the safety of equipment and personnel.

2. The method for predicting the remaining life of the steel wire rope of a four-rope grab crane according to claim 1 is characterized in that: Sampling frequency f S =50HZ.

3. The method for predicting the remaining life of the steel wire rope of a four-rope grab crane according to claim 1, characterized in that: The magnetic field change characteristic data of the wire rope at different use stages are collected, and the test set and training set are divided into 3:7.

Images