Crane slewing bearing working condition evaluation method, system and storage medium

Abstract

The present invention discloses a method, system and storage medium for evaluating the working status of a crane slewing bearing. This scheme collects operation monitoring data, audio monitoring data, vibration monitoring data and the like of the crane slewing bearing during operation, and then individually judges abnormal conditions of each data, thereby realizing the evaluation of the working status of the crane slewing bearing. This scheme starts from multiple factors and can more comprehensively monitor the working status of the crane slewing bearing, thereby improving the reliability and safety of operation monitoring during the operation of the equipment, and providing an effective reference for maintenance personnel to formulate maintenance plans; this scheme also integrates the monitoring weight values ​​calculated from each monitoring data when judging the working status, and comprehensively judges the comprehensive condition of the crane slewing bearing during operation, thereby indirectly knowing the working stability and reliability of the crane, and providing auxiliary judgment and prediction for the service life evaluation of the crane slewing bearing.

Description

Technical Field

[0001] The present invention relates to the technical field of crane slewing bearing monitoring, and in particular to a crane slewing bearing working state evaluation method, system and storage medium. Background Art

[0002] Slewing bearings, also known as turntable bearings, are widely used in industry and are often referred to as "machine joints." They are essential transmission components for machines that require relative rotation between two objects while simultaneously bearing axial force, radial force, and tipping torque. With the rapid development of the machinery industry, slewing bearings have found widespread application in a variety of industries, including marine equipment, construction machinery, light industrial machinery, metallurgical machinery, medical machinery, and industrial machinery.

[0003] Cranes are common engineering machinery, and slewing bearings are key connecting components in cranes. Due to the complex working environment of cranes, slewing bearings may be interfered with by various external and internal factors during the process of being driven. Since the working environment of slewing bearings is complex and changeable during service, there are many factors that affect their service life. Existing simulation model-based or data-driven methods mostly use a single or a small number of factors to predict whether there is a fault or service life of the slewing bearing. However, in actual applications, there are often many factors that lead to slewing bearing failures and the end of their service life, which often lead to incorrect predictions. At the same time, the current full life cycle usage monitoring data of slewing bearings is difficult to reuse and learn from due to statistical factors and small data volume. Therefore, how to carry out working status assessment of large slewing bearings under dynamic service and formulate scientific and reasonable maintenance plans and early warning plans to ensure their safe and reliable operation is a very positive and practical topic. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to propose a crane slewing bearing working condition assessment method, system and storage medium that are reliable in implementation, quick in response, have good reference results, and have low difficulty in reusing and referencing monitoring data.

[0005] In order to achieve the above technical objectives, the technical solution adopted by the present invention is:

[0006] A method for evaluating the working condition of a crane slewing bearing, comprising:

[0007] Responding to the crane's work start signal, it monitors and records the crane's work instructions and load conditions in real time. At the same time, it also monitors and records the motion of the inner or outer ring of the slewing bearing to generate operation monitoring data;

[0008] Acquire the audio signal of the preset area of ​​the slewing bearing according to the preset conditions and generate audio monitoring data;

[0009] Acquire vibration signals from a preset area of ​​the slewing bearing according to preset conditions and generate vibration monitoring data;

[0010] Obtain the working environment temperature of the slewing bearing and the temperature of the slewing bearing body according to preset conditions and generate temperature monitoring data;

[0011] Obtain operation monitoring data, audio monitoring data, vibration monitoring data and temperature monitoring data, judge the operation monitoring data, audio monitoring data and vibration monitoring data according to preset conditions, and then output status evaluation results based on the judgment results.

[0012] As a possible implementation method, further, the method of judging the operation monitoring data according to the preset conditions in this solution is:

[0013] Obtain the time when the work instruction about the slewing bearing action is issued and the time and amplitude of the action of the inner ring or outer ring of the slewing bearing as the moving ring from the operation monitoring data;

[0014] Select a point on the inner ring or outer ring of the slewing bearing as the moving ring, and establish a virtual two-dimensional coordinate system with the common virtual axis of the inner ring and outer ring of the slewing bearing as the origin;

[0015] An operation monitoring weight evaluation model is established, and the operation monitoring data is imported into the following mathematical model for calculation:

[0016]

[0017] Among them, Y is the operation monitoring weight, T f T is the time when the work instruction about the slewing bearing action is issued. z T is the time when the inner ring or outer ring of the slewing bearing acts as the moving ring. b is the allowable delay time threshold of the slewing bearing in response to the slewing bearing action work instruction, and in terms of time, T z Greater than T f , Y1 is the preset response weight value; F z F is the expected rotation amplitude of the slewing bearing under the working instruction, f F is the actual rotation amplitude of the slewing bearing under the working instruction, b is the allowable error amplitude threshold value of the slewing bearing when it rotates under the work instruction, Y2 is the preset amplitude deviation weight value; x1 is the current x-axis coordinate value of the selected point on the slewing bearing moving coil, x0 is the initial x-axis coordinate value of the selected point on the slewing bearing moving coil, which is determined after the slewing bearing is installed and debugged, y1 is the current y-axis coordinate value of the selected point on the slewing bearing moving coil, y0 is the initial y-axis coordinate value of the selected point on the slewing bearing moving coil, which is determined after the slewing bearing is installed and debugged, P bis the allowable eccentricity distance threshold of the slewing bearing moving coil, and Y3 is the preset eccentricity weight value;

[0018] The operation monitoring weight calculated in the operation monitoring weight assessment model is compared with the preset threshold value, and then the operation warning information and / or operation warning intervention information is output as one of the status assessment results according to the preset conditions.

[0019] As a possible implementation method, further, the present solution obtains the audio signal of the preset area of ​​the slewing bearing according to the preset conditions, and the method for generating the audio monitoring data is as follows:

[0020] Respond to the crane's work start signal and obtain the audio signal of the preset area of ​​the slewing bearing in real time;

[0021] In response to the start and end signals of the slewing bearing's action, the audio signal acquired in real time is edited according to preset conditions, so that the audio signals of the preset length before the slewing bearing takes action, during the action, and after the action are extracted to generate audio monitoring data.

[0022] As a possible implementation method, further, the method of judging the audio monitoring data according to the preset conditions in this solution is:

[0023] Acquire audio monitoring data, cut it, and generate pre-action audio monitoring data, in-action audio monitoring data, and post-action audio monitoring data associated with the slewing bearing, wherein the pre-action audio monitoring data and the post-action audio monitoring data have the same duration, which is at least 3 to 5 seconds;

[0024] Match the audio monitoring data before the action with the audio monitoring data after the action, and output the matching results.

[0025] When the matching result meets the preset requirements, the audio monitoring data before the action or the audio monitoring data after the action is used as the background noise, and then the audio monitoring data during the action is denoised in combination with the background noise to obtain the audio monitoring data during the action after noise reduction.

[0026] When the matching result does not meet the preset requirements, the pre-action audio monitoring data and the post-action audio monitoring data are superimposed and averaged to generate synthetic audio data, which is set as background noise. The audio monitoring data during the action is then denoised in combination with the background noise to obtain the denoised audio monitoring data during the action. When the matching result does not meet the preset requirements, audio anomaly information is also generated.

[0027] Obtain temperature monitoring data and feed it, along with the noise-reduced motion audio monitoring data, as input to a trained first detection neural network to determine the probability of abnormal sound in the motion audio monitoring data. The detection results are then normalized to a probability of [0, 1], and the audio detection results are output.

[0028] An audio monitoring weight evaluation model is established to calculate the audio monitoring data. The formula is as follows:

[0029] S=Q1×S1+2×S2

[0030] Among them, S is the audio monitoring weight, S1 is the preset audio abnormality weight value, which is used to evaluate the audio conditions of the slewing bearing before and after the action, Q1 is the audio abnormality assignment value, when there is audio abnormality information, its value is 1, when there is no audio abnormality information, its value is 0, S2 is the preset audio abnormal sound weight value, which is used to evaluate the audio conditions of the slewing bearing during action, and Q2 is the probability value of the presence of abnormal sound in the audio monitoring data during action;

[0031] The audio monitoring weight calculated in the audio monitoring weight evaluation model is compared and judged with the preset threshold, and then the abnormal sound warning information and / or operation warning intervention information is output as one of the status evaluation results according to the preset conditions.

[0032] As a possible implementation method, further, the present solution obtains the vibration signal of the preset area of ​​the slewing bearing according to the preset conditions, and the method for generating vibration monitoring data is as follows:

[0033] Responding to the crane's work start signal, the vibration signal of the preset area of ​​the slewing bearing is obtained in real time;

[0034] In response to the start and end signals of the slewing bearing's action, the vibration signal acquired in real time is clipped according to the preset conditions, so that the vibration signals of the preset time before the slewing bearing takes action, during the action, and after the action are extracted to generate vibration monitoring data.

[0035] As a possible implementation method, further, the method of judging the vibration monitoring data according to the preset conditions in this solution is:

[0036] Acquire vibration monitoring data, cut it, and generate pre-action vibration monitoring data, in-action vibration monitoring data, and post-action vibration monitoring data associated with the slewing bearing, wherein the pre-action vibration monitoring data and the post-action audio monitoring data have the same duration and both cover at least one cycle of the vibration waveform;

[0037] Match the vibration monitoring data before the action with the vibration monitoring data after the action, and output the matching results.

[0038] When the matching result meets the preset requirements, a periodic vibration waveform in the vibration monitoring data before or after the action is extracted as the vibration noise data, and then the vibration monitoring data during the action is denoised in combination with the vibration noise data to obtain the vibration monitoring data during the action after noise reduction.

[0039] When the matching result does not meet the preset requirements, at least one cycle of vibration waveform is extracted from the vibration monitoring data before the action and the vibration monitoring data after the action, and the average value is calculated after superposition to generate synthetic vibration data and set it as vibration noise data. Then, the vibration monitoring data during the action is denoised in combination with the vibration noise data to obtain the vibration monitoring data during the action after noise reduction. When the matching result does not meet the preset requirements, vibration abnormality information is also generated.

[0040] Obtain temperature monitoring data and import it into the trained second detection neural network as input together with the noise-reduced vibration monitoring data during operation to obtain the probability of a suspected fault in the vibration monitoring data during operation. Then, the detection results are normalized to a probability of [0, 1], and finally, the vibration detection results are output;

[0041] A vibration monitoring weight evaluation model is established to calculate the vibration monitoring data. The formula is as follows:

[0042] Z=K1×Z1+2×Z2

[0043] Among them, Z is the vibration monitoring weight, K1 is the preset vibration abnormality weight value, which is used to evaluate the vibration conditions of the slewing bearing before and after the action, Z1 is the vibration abnormality value, when there is vibration abnormality information, its value is 1, when there is no vibration abnormality information, its value is 0, K2 is the preset suspected fault weight value, which is used to evaluate the vibration conditions of the slewing bearing during action, and Z2 is the probability value of the suspected fault in the vibration monitoring data during action;

[0044] The vibration monitoring weight calculated in the vibration monitoring weight assessment model is compared with the preset threshold value, and then the potential fault warning information and / or operation warning intervention information are output as one of the status assessment results according to the preset conditions.

[0045] Among them, when outputting fault warning information and / or operation warning intervention information, the operation monitoring data of the corresponding preset time interval will also be output in an associated manner. In this way, maintenance personnel can conduct a preliminary investigation of the load conditions under the operation monitoring data, the work instructions of the crane, and the motion monitoring of the inner or outer ring of the slewing bearing to confirm whether the operator has any abnormal operation or load abnormality. At the same time, if the abnormal condition of the crane may be sporadic, and there is no inoperable fault in the crane at the moment, the abnormality can be attempted to be reproduced by repeating the working conditions in the operation monitoring data to determine whether the abnormality is sporadic or occurs under specific circumstances.

[0046] Based on the above, the present invention further provides a method for evaluating the service life of a crane slewing bearing, which includes the above-mentioned method for evaluating the working condition of a crane slewing bearing, and further includes:

[0047] Obtain the condition assessment results of the same crane slewing bearing generated at different times, assign weights to various factors in the condition assessment results generated at the same time according to preset conditions, generate condition assessment weight values, and then compare the weights with preset thresholds to generate comparison results;

[0048] The comparison results corresponding to the status evaluation results generated at different times are collected, and then the number N of comparison results exceeding the preset threshold within the latest preset time period is counted, and then the numerical range of N is judged.

[0049] When M≥N≥0, the crane slewing bearing is inspected and maintained for the preset time period T0;

[0050] When L≥N>M, the time period for maintenance of the crane slewing bearing is updated to T0 / 2;

[0051] When N>L, the crane slewing bearing life end information is output.

[0052] As a possible implementation method, this solution further obtains the status assessment results generated at different times for the same crane slewing bearing, and assigns weights to various factors in the status assessment results generated at the same time according to preset conditions. The method for generating the status assessment weight values ​​includes:

[0053] The condition assessment results of the same crane slewing bearing generated at different times are obtained and then classified according to the assessment factors to form a data set, which includes:

[0054] Operation monitoring weight data set Y = [Y t1 , Y t2 , Y t3 ,……Y tn ];

[0055] Audio monitoring weighted dataset S = [S t1 , S t2 , S t3 ,……S tn ];

[0056] Vibration monitoring weight dataset Z = [Z t1 , Z t2 , Z t3 , ... Z tn ];

[0057] Among them, Y tn 、S tn , Z tn They are the operation monitoring weight value, audio monitoring weight value, and vibration monitoring weight value at different times;

[0058] A mathematical model of the state assessment weight value is established, and its formula is as follows:

[0059] W=α×Y tn +×S tn +×Z tn

[0060] Among them, W is the state assessment weight value, and α, β, and γ are all preset weight coefficients.

[0061] Based on the above, the present invention further provides a crane slewing bearing working condition assessment system, which includes:

[0062] A working sensing unit, used to sense the working start signal of the crane;

[0063] The operation monitoring unit is used to monitor and record the crane's working instructions and load conditions in real time. It also monitors and records the motion of the inner or outer ring of the slewing bearing to generate operation monitoring data.

[0064] An audio monitoring unit is provided in a preset area of ​​the slewing bearing of the crane and is used to obtain an audio signal of the preset area of ​​the slewing bearing according to preset conditions and generate audio monitoring data;

[0065] A vibration monitoring unit is provided in a preset area of ​​the slewing bearing of the crane and is used to obtain a vibration signal of the preset area of ​​the slewing bearing according to preset conditions and generate vibration monitoring data;

[0066] The temperature monitoring units are multiple and are arranged in a preset area of ​​the slewing bearing of the crane, and are used to obtain the working environment temperature of the slewing bearing and the temperature of the slewing bearing body according to preset conditions to generate temperature monitoring data;

[0067] The status judgment unit is used to obtain operation monitoring data, audio monitoring data, vibration monitoring data and temperature monitoring data, judge the operation monitoring data, audio monitoring data and vibration monitoring data according to preset conditions, and then output the status evaluation result according to the judgment result.

[0068] Based on the above, the present invention also provides a computer-readable storage medium, wherein the storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the above-mentioned crane slewing bearing working condition assessment method.

[0069] By adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art: the present solution cleverly collects the operation monitoring data, audio monitoring data, vibration monitoring data and temperature monitoring data of the crane's slewing bearing during operation, and then independently determines whether each data has any abnormality, thereby achieving an assessment of the working status of the crane's slewing bearing. Starting from multiple factors, the present solution can more comprehensively monitor the working status of the crane's slewing bearing, improve the reliability and safety of operation monitoring during the equipment's operation, and provide an effective reference for maintenance personnel to formulate maintenance plans; the present solution further integrates the monitoring weight values ​​calculated when judging the working status of the crane's slewing bearing's operation monitoring data, audio monitoring data, vibration monitoring data and temperature monitoring data, and comprehensively judges the comprehensive working status of the crane's slewing bearing, thereby indirectly knowing the working stability and reliability of the crane, providing a more refined auxiliary judgment and prediction for the service life assessment of the crane's slewing bearing, reducing the difficulty of maintenance personnel's work and providing a better reference for judging the service life of the slewing bearing. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0071] Figure 1 This is one of the schematic diagrams of the simplified implementation process of the method of the present invention;

[0072] Figure 2 This is the second schematic diagram of a brief implementation process of the method of the present invention;

[0073] Figure 3 This is a simplified unit module connection diagram of the system of the present invention. DETAILED DESCRIPTION

[0074] The present invention will be described in further detail below with reference to the accompanying drawings and examples. It is particularly noted that the following examples are intended only to illustrate the present invention and are not intended to limit the scope of the present invention. Similarly, the following examples are only some embodiments of the present invention and are not intended to be exhaustive. All other embodiments obtained by those of ordinary skill in the art without creative effort are intended to fall within the scope of protection of the present invention.

[0075] like Figure 1 As shown, this embodiment provides a method for evaluating the working condition of a crane slewing bearing, which includes:

[0076] S01. Responding to the crane's work start signal, the crane's work instructions and load conditions are monitored and recorded in real time. At the same time, the movement of the inner or outer ring of the slewing bearing is monitored and recorded to generate operation monitoring data.

[0077] S021. Acquire audio signals from a preset area of ​​the slewing bearing according to preset conditions and generate audio monitoring data;

[0078] S022. Acquire vibration signals of a preset area of ​​the slewing bearing according to preset conditions and generate vibration monitoring data;

[0079] S023. Obtain the working environment temperature of the slewing bearing and the temperature of the slewing bearing body according to preset conditions, and generate temperature monitoring data;

[0080] S03. Obtain operation monitoring data, audio monitoring data, vibration monitoring data, and temperature monitoring data, judge the operation monitoring data, audio monitoring data, and vibration monitoring data according to preset conditions, and then output a status evaluation result based on the judgment result.

[0081] Among them, steps S021, S022, and S023 can be steps that can be executed in parallel. Of course, they are not limited to this, and they can also be steps that are executed sequentially.

[0082] In addition, in this solution, after obtaining the operation monitoring data, audio monitoring data, vibration monitoring data and temperature monitoring data, the evaluation results on the working status of the slewing bearing can be generated by judging them separately, or they can be combined to judge and generate the evaluation results on the working status of the slewing bearing.

[0083] As a possible implementation, further, in this solution S03, the method for judging the operation monitoring data according to the preset conditions is:

[0084] S0301. Obtaining the time when the work instruction regarding the slewing bearing action is issued and the time and amplitude of the action of the inner ring or outer ring of the slewing bearing as the moving ring from the operation monitoring data;

[0085] S0302. Select a point on the inner ring or outer ring of the slewing bearing that serves as the moving ring, and establish a virtual two-dimensional coordinate system with the common virtual axis of the inner ring and outer ring of the slewing bearing as the origin;

[0086] S0303. Establish an operation monitoring weight evaluation model and import the operation monitoring data into the following mathematical model for calculation:

[0087]

[0088] Among them, Y is the operation monitoring weight, T f T is the time when the work instruction about the slewing bearing action is issued. z T is the time when the inner ring or outer ring of the slewing bearing acts as the moving ring. b is the allowable delay time threshold of the slewing bearing in response to the slewing bearing action work instruction, and in terms of time, T z Greater than T f , Y1 is the preset response weight value; F z F is the expected rotation amplitude of the slewing bearing under the working instruction, f F is the actual rotation amplitude of the slewing bearing under the working instruction, b is the allowable error amplitude threshold value of the slewing bearing when it rotates under the work instruction, Y2 is the preset amplitude deviation weight value; x1 is the current x-axis coordinate value of the selected point on the slewing bearing moving coil, x0 is the initial x-axis coordinate value of the selected point on the slewing bearing moving coil, which is determined after the slewing bearing is installed and debugged, y1 is the current y-axis coordinate value of the selected point on the slewing bearing moving coil, y0 is the initial y-axis coordinate value of the selected point on the slewing bearing moving coil, which is determined after the slewing bearing is installed and debugged, P b is the allowable eccentricity distance threshold of the slewing bearing moving coil, and Y3 is the preset eccentricity weight value;

[0089] S0304. Compare and judge the operation monitoring weight calculated in the operation monitoring weight evaluation model with the preset threshold, and then output the operation warning information and / or operation warning intervention information as one of the status evaluation results according to the preset conditions.

[0090] The purpose of making judgments in the operation monitoring data is to accurately evaluate the crane's work instruction response and operation response, so as to realize the evaluation of the crane's working status. In order to comprehensively consider various factors, the temperature monitoring data can be further combined with the operation monitoring data. After correlation, the influence of ambient temperature and slewing bearing temperature on the crane's work instructions and action accuracy can be obtained through multiple time and multiple monitoring data. With the increasing popularity of automation, the scenario of directly controlling the crane to work through computer instructions will become more and more widespread in the future. Therefore, the crane's work response efficiency and the accuracy of action operation response will be important working indicators of the crane; and this scheme conducts operation monitoring, evaluation and judgment on it, which can effectively realize the effective evaluation of the working quality and status of the crane's slewing bearing and its corresponding drive components, and use the threshold method to determine whether to output warning or intervention information, so that maintenance personnel can intervene in maintenance in time to avoid the situation where the crane continues to work "with illness".

[0091] In terms of audio monitoring, since the crane's slewing bearing is a dynamic connection, it will produce a certain degree of coordination noise during operation due to various mechanical coordination. In addition, the crane's startup and operation will also generate a certain degree of background noise. Therefore, as a possible implementation method for audio data collection, this solution further obtains audio signals from a preset area of ​​the slewing bearing according to preset conditions, and the method for generating audio monitoring data is as follows:

[0092] S0211. Respond to the crane's work start signal and obtain the audio signal of the preset area of ​​the slewing bearing in real time;

[0093] S0212. In response to the start and end signals of the slewing bearing, the audio signals acquired in real time are edited according to preset conditions, so that the audio signals of the preset length before the slewing bearing moves, during the movement, and after the movement are extracted to generate audio monitoring data.

[0094] In terms of application judgment of audio monitoring data, as a possible implementation method, further, the method of judging audio monitoring data according to preset conditions in this solution is:

[0095] S0311. Acquire audio monitoring data and cut it to generate pre-action audio monitoring data, in-action audio monitoring data, and post-action audio monitoring data associated with the slewing bearing, wherein the pre-action audio monitoring data and the post-action audio monitoring data have the same duration, which is at least 3 to 5 seconds.

[0096] S0312, matching the audio monitoring data before the action with the audio monitoring data after the action, and outputting the matching result,

[0097] When the matching result meets the preset requirements, the audio monitoring data before the action or the audio monitoring data after the action is used as the background noise, and then the audio monitoring data during the action is denoised in combination with the background noise to obtain the audio monitoring data during the action after noise reduction.

[0098] When the matching result does not meet the preset requirements, the pre-action audio monitoring data and the post-action audio monitoring data are superimposed and averaged to generate synthetic audio data, which is set as background noise. The audio monitoring data during the action is then denoised in combination with the background noise to obtain the denoised audio monitoring data during the action. When the matching result does not meet the preset requirements, audio anomaly information is also generated.

[0099] S0313. Obtain temperature monitoring data and import it together with the noise-reduced motion audio monitoring data as input items into the trained first detection neural network for detection to obtain the probability of the presence of abnormal sound in the motion audio monitoring data. Then, the detection result is normalized to a probability of [0, 1], and finally, the audio detection result is output.

[0100] S0314. Establish an audio monitoring weight evaluation model to calculate the audio monitoring data. The formula is as follows:

[0101] S=Q1×S1+2×S2

[0102] Among them, S is the audio monitoring weight, S1 is the preset audio abnormality weight value, which is used to evaluate the audio conditions of the slewing bearing before and after the action, Q1 is the audio abnormality assignment value, when there is audio abnormality information, its value is 1, when there is no audio abnormality information, its value is 0, S2 is the preset audio abnormal sound weight value, which is used to evaluate the audio conditions of the slewing bearing during action, and Q2 is the probability value of the presence of abnormal sound in the audio monitoring data during action;

[0103] S0315. Compare and judge the audio monitoring weight calculated in the audio monitoring weight evaluation model with the preset threshold, and then output abnormal sound warning information and / or operation warning intervention information as one of the status evaluation results according to the preset conditions.

[0104] The above-mentioned audio monitoring data is generated by collecting and extracting audio signals of a preset length of time before the slewing bearing moves, during the movement, and after the movement. This can facilitate the subsequent preliminary acquisition of information about possible faults before and after the crane slewing bearing works based on the difference between the audio monitoring data before the movement and the audio monitoring data after the movement, thereby assisting maintenance personnel in timely troubleshooting. In addition, the audio signals of the preset length of time before the slewing bearing moves and the preset length of time after the movement can also be reused as background noise for subsequent denoising of the audio signals in action, thereby optimizing the first detection neural network's judgment on the audio signals in the crane slewing bearing movement and improving the reliability of its results. The purpose of normalizing the results is to avoid the deviation caused by the results being "yes" or "no", and to indirectly reflect the judgment possibility of the first detection neural network through probability.

[0105] In this embodiment, the first detection neural network is trained using existing technology, that is, a database is constructed to store the action audio data (including audio data under normal conditions and under different abnormal conditions) and working temperature of multiple slewing bearings of the same or similar specifications throughout their life cycle, and then the data are segmented and labeled, and different data are extracted as training data and verification data. The training data is imported into the neural network for training, and the verification data is imported into the trained neural network for verification. This process is repeated until the model converges, thereby obtaining the first detection neural network. Since the training method of the neural network is relatively well known, its details are not described in detail.

[0106] Since the slewing bearing of the crane will further generate vibration when it is in motion, as a possible implementation method, this solution further obtains the vibration signal of the preset area of ​​the slewing bearing according to preset conditions and generates vibration monitoring data by the following method:

[0107] S0221. Respond to the crane's work start signal and obtain a vibration signal of a preset area of ​​the slewing bearing in real time;

[0108] S0222. In response to the start and end signals of the slewing bearing, the vibration signals acquired in real time are trimmed according to preset conditions, so that vibration signals of the slewing bearing for a preset time before the action, during the action, and after the action are extracted to generate vibration monitoring data.

[0109] In the application of vibration monitoring data, as a possible implementation method, further, the method of judging the vibration monitoring data according to the preset conditions in this solution is:

[0110] S0321. Acquire vibration monitoring data and cut it to generate pre-action vibration monitoring data, in-action vibration monitoring data, and post-action vibration monitoring data associated with the slewing bearing, wherein the pre-action vibration monitoring data and the post-action audio monitoring data have the same duration and both cover at least one cycle of the vibration waveform.

[0111] S0322, matching the vibration monitoring data before the action with the vibration monitoring data after the action, and outputting the matching result,

[0112] When the matching result meets the preset requirements, a periodic vibration waveform in the vibration monitoring data before or after the action is extracted as the vibration noise data, and then the vibration monitoring data during the action is denoised in combination with the vibration noise data to obtain the vibration monitoring data during the action after noise reduction.

[0113] When the matching result does not meet the preset requirements, at least one cycle of vibration waveform is extracted from the vibration monitoring data before the action and the vibration monitoring data after the action, and the average value is calculated after superposition to generate synthetic vibration data and set it as vibration noise data. Then, the vibration monitoring data during the action is denoised in combination with the vibration noise data to obtain the vibration monitoring data during the action after noise reduction. When the matching result does not meet the preset requirements, vibration abnormality information is also generated.

[0114] S0323. Obtain temperature monitoring data, and import the temperature monitoring data and the noise-reduced vibration monitoring data into a trained second detection neural network as input items for detection to obtain the probability of a suspected fault in the vibration monitoring data, and then normalize the detection result to a probability of [0, 1], and finally output the vibration detection result;

[0115] S0324. Establish a vibration monitoring weight assessment model to calculate vibration monitoring data. The formula is as follows:

[0116] Z=K1×Z1+2×Z2

[0117] Among them, Z is the vibration monitoring weight, K1 is the preset vibration abnormality weight value, which is used to evaluate the vibration conditions of the slewing bearing before and after the action, Z1 is the vibration abnormality value, when there is vibration abnormality information, its value is 1, when there is no vibration abnormality information, its value is 0, K2 is the preset suspected fault weight value, which is used to evaluate the vibration conditions of the slewing bearing during action, and Z2 is the probability value of the suspected fault in the vibration monitoring data during action;

[0118] S0325. Compare and judge the vibration monitoring weight calculated in the vibration monitoring weight assessment model with the preset threshold, and then output potential fault warning information and / or operation warning intervention information as one of the status assessment results according to the preset conditions.

[0119] The above-mentioned generation of vibration monitoring data by collecting and extracting vibration signals of a preset time before the slewing bearing moves, during the movement and after the movement can facilitate the subsequent preliminary acquisition of information about possible faults before and after the operation of the crane slewing bearing based on the difference between the vibration monitoring data before the movement and the vibration monitoring data after the movement, thereby assisting maintenance personnel in timely investigation. In addition, the vibration signals of the preset time before the slewing bearing moves and the preset time after the movement can also be reused as background noise for subsequent denoising of the audio signal in the movement, thereby optimizing the second detection neural network's judgment on the vibration signal in the movement of the crane slewing bearing and improving the reliability of its results. The purpose of normalizing the results is to avoid the deviation caused by the result being "yes" or "no", and to indirectly reflect the judgment possibility of the second detection neural network through probability.

[0120] In this embodiment, the second detection neural network is trained using existing technology, that is, a database is constructed to store the motion vibration data (including vibration data under normal conditions and under different abnormal conditions) and working temperature of multiple slewing bearings of the same or similar specifications throughout their life cycle, and then the data are segmented and labeled, and different data are extracted as training data and verification data. The training data is imported into the neural network for training, and the verification data is imported into the trained neural network for verification. This process is repeated until the model converges, thereby obtaining the second detection neural network. Since the training method of the neural network is relatively well known, its details are not described in detail.

[0121] The above-mentioned method collects the operation monitoring data, audio monitoring data, vibration monitoring data and temperature monitoring data of the crane's slewing bearing during operation, and then independently determines whether there is any abnormality in each data, thereby evaluating the working status of the crane's slewing bearing. Starting from multiple factors, this scheme can more comprehensively monitor the working status of the crane's slewing bearing, thereby improving the reliability and safety of operation monitoring during the equipment operation process.

[0122] On the basis of the above, further combining Figure 2 As shown, based on the above, this embodiment further provides a crane slewing bearing service life assessment method, which includes the crane slewing bearing working condition assessment method described above, and further includes:

[0123] S04. Obtaining condition assessment results generated at different times for the same crane slewing bearing, assigning weights to various factors in the condition assessment results generated at the same time according to preset conditions to generate condition assessment weight values, and then comparing the weights with preset thresholds to generate comparison results;

[0124] S05, collect the comparison results corresponding to the status evaluation results generated at different times, then count the number N of comparison results within the latest preset time period that exceed the preset threshold, and then determine the numerical range of N.

[0125] When M≥N≥0, the crane slewing bearing is inspected and maintained for the preset time period T0;

[0126] When L≥N>M, the time period for maintenance of the crane slewing bearing is updated to T0 / 2;

[0127] When N>L, the crane slewing bearing life end information is output.

[0128] Preferably, in this solution S04, the method of obtaining the status evaluation results generated at different times for the same crane slewing bearing and assigning weights to the factors in the status evaluation results generated at the same time according to preset conditions, and generating the status evaluation weight values ​​includes:

[0129] S041. Obtain the condition assessment results of the slewing bearing of the same crane generated at different times, and then classify them according to the assessment factors to form a data set, which includes:

[0130] Operation monitoring weight data set Y = [Y t1 , Y t2 , Y t3 ,……Y tn ];

[0131] Audio monitoring weighted dataset S = [S t1 , S t2 , S t3 ,……S tn ];

[0132] Vibration monitoring weight dataset Z = [Z t1 , Z t2 , Z t3 , ... Z tn ];

[0133] Among them, Y tn 、S tn , Z tn They are the operation monitoring weight value, audio monitoring weight value, and vibration monitoring weight value at different times;

[0134] S042. Establish a mathematical model for the state assessment weight value, the formula of which is as follows:

[0135] W=α×Y tn +×S tn +×Z tn

[0136] Among them, W is the state assessment weight value, and α, β, and γ are all preset weight coefficients.

[0137] The above-mentioned monitoring weight values ​​calculated when judging the working status of the crane slewing bearing are integrated by comprehensively judging the comprehensive working condition of the crane slewing bearing, thereby indirectly knowing the working stability and reliability of the crane, providing more refined auxiliary judgment and prediction for the service life assessment of the crane slewing bearing, reducing the work difficulty of maintenance personnel and providing a better reference judgment for the service life of the slewing bearing.

[0138] In addition, the operation monitoring weight data set, audio monitoring weight data set, and vibration monitoring weight data set can be used to further judge the working stability of the crane and substitute them into the following mathematical model for evaluation, specifically:

[0139] H=Y max + max + max

[0140] Among them, H is the stability weight value of the crane slewing bearing, Y max 、S max and Z max They respectively represent the maximum operation monitoring weight value, maximum audio monitoring weight value and maximum vibration monitoring weight value of the crane slewing bearing within the preset time. They reflect the maximum value of the instability factor of the crane within the preset time. This value can be used to assist in judging the working stability of the crane slewing bearing.

[0141] Combine Figure 3 As shown, based on the above, the present invention also provides a crane slewing bearing working condition assessment system, which includes:

[0142] A working sensing unit, used to sense the working start signal of the crane;

[0143] The operation monitoring unit is used to monitor and record the crane's working instructions and load conditions in real time. It also monitors and records the motion of the inner or outer ring of the slewing bearing to generate operation monitoring data.

[0144] An audio monitoring unit is provided in a preset area of ​​the slewing bearing of the crane and is used to obtain an audio signal of the preset area of ​​the slewing bearing according to preset conditions and generate audio monitoring data;

[0145] A vibration monitoring unit is provided in a preset area of ​​the slewing bearing of the crane and is used to obtain a vibration signal of the preset area of ​​the slewing bearing according to preset conditions and generate vibration monitoring data;

[0146] The temperature monitoring units are multiple and are arranged in a preset area of ​​the slewing bearing of the crane, and are used to obtain the working environment temperature of the slewing bearing and the temperature of the slewing bearing body according to preset conditions to generate temperature monitoring data;

[0147] The status judgment unit is used to obtain operation monitoring data, audio monitoring data, vibration monitoring data and temperature monitoring data, judge the operation monitoring data, audio monitoring data and vibration monitoring data according to preset conditions, and then output the status evaluation result according to the judgment result.

[0148] In addition, the functional units in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0150] The above descriptions are only some embodiments of the present invention and do not limit the scope of protection of the present invention. Any equivalent device or equivalent process transformation made by using the contents of the description and drawings of the present invention, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for evaluating the working condition of a crane slewing bearing, characterized in that: include: Responding to the crane's work start signal, it monitors and records the crane's work instructions and load conditions in real time. At the same time, it also monitors and records the motion of the inner or outer ring of the slewing bearing to generate operation monitoring data; Acquire the audio signal of the preset area of ​​the slewing bearing according to the preset conditions and generate audio monitoring data; Acquire vibration signals from a preset area of ​​the slewing bearing according to preset conditions and generate vibration monitoring data; Obtain the working environment temperature of the slewing bearing and the temperature of the slewing bearing body according to preset conditions and generate temperature monitoring data; Acquire operation monitoring data, audio monitoring data, vibration monitoring data, and temperature monitoring data, judge the operation monitoring data, audio monitoring data, and vibration monitoring data according to preset conditions, and then output a status evaluation result based on the judgment result; Among them, the method for judging the operation monitoring data according to the preset conditions is: Obtain the time when the work instruction about the slewing bearing action is issued and the time and amplitude of the action of the inner ring or outer ring of the slewing bearing as the moving ring from the operation monitoring data; Select a point on the inner ring or outer ring of the slewing bearing as the moving ring, and establish a virtual two-dimensional coordinate system with the common virtual axis of the inner ring and outer ring of the slewing bearing as the origin; An operation monitoring weight evaluation model is established, and the operation monitoring data is imported into the following mathematical model for calculation: Among them, Y is the operation monitoring weight, T f T is the time when the work instruction about the slewing bearing action is issued. z T is the time when the inner ring or outer ring of the slewing bearing acts as the moving ring. b is the allowable delay time threshold of the slewing bearing in response to the slewing bearing action work instruction, and in terms of time, T z Greater than T f , Y1 is the preset response weight value; F z F is the expected rotation amplitude of the slewing bearing under the working instruction, f F is the actual rotation amplitude of the slewing bearing under the working instruction, b is the allowable error amplitude threshold value of the slewing bearing when it rotates under the work instruction, Y2 is the preset amplitude deviation weight value; x1 is the current x-axis coordinate value of the selected point on the slewing bearing moving coil, x0 is the initial x-axis coordinate value of the selected point on the slewing bearing moving coil, which is determined after the slewing bearing is installed and debugged, y1 is the current y-axis coordinate value of the selected point on the slewing bearing moving coil, y0 is the initial y-axis coordinate value of the selected point on the slewing bearing moving coil, which is determined after the slewing bearing is installed and debugged, P b is the allowable eccentricity distance threshold of the slewing bearing moving coil, and Y3 is the preset eccentricity weight value; The operation monitoring weight calculated in the operation monitoring weight assessment model is compared with the preset threshold value, and then the operation warning information and / or operation warning intervention information is output as one of the status assessment results according to the preset conditions.

2. The crane slewing bearing working condition evaluation method according to claim 1, characterized in that: The method for obtaining the audio signal of the preset area of ​​the slewing bearing according to the preset conditions and generating the audio monitoring data is as follows: Respond to the crane's work start signal and obtain the audio signal of the preset area of ​​the slewing bearing in real time; In response to the start and end signals of the slewing bearing's action, the audio signal acquired in real time is edited according to preset conditions, so that the audio signals of the preset length before the slewing bearing takes action, during the action, and after the action are extracted to generate audio monitoring data.

3. The crane slewing bearing working condition evaluation method according to claim 2, characterized in that: The method for judging audio monitoring data according to preset conditions is: Acquire audio monitoring data, cut it, and generate pre-action audio monitoring data, in-action audio monitoring data, and post-action audio monitoring data associated with the slewing bearing, wherein the pre-action audio monitoring data and the post-action audio monitoring data have the same duration, which is 3 to 5 seconds; Match the audio monitoring data before the action with the audio monitoring data after the action, and output the matching results. When the matching result meets the preset requirements, the audio monitoring data before the action or the audio monitoring data after the action is used as the background noise, and then the audio monitoring data during the action is denoised in combination with the background noise to obtain the audio monitoring data during the action after noise reduction. When the matching result does not meet the preset requirements, the pre-action audio monitoring data and the post-action audio monitoring data are superimposed and averaged to generate synthetic audio data, which is set as background noise. The audio monitoring data during the action is then denoised in combination with the background noise to obtain the denoised audio monitoring data during the action. When the matching result does not meet the preset requirements, audio anomaly information is also generated. Obtain temperature monitoring data and feed it, along with the noise-reduced motion audio monitoring data, as input to a trained first detection neural network to determine the probability of abnormal sound in the motion audio monitoring data. The detection results are then normalized to a probability of [0, 1], and the audio detection results are output. An audio monitoring weight evaluation model is established to calculate the audio monitoring data. The formula is as follows: S=Q1×S1+Q2×S2 Among them, S is the audio monitoring weight, S1 is the preset audio abnormality weight value, which is used to evaluate the audio conditions of the slewing bearing before and after the action, Q1 is the audio abnormality assignment value, when there is audio abnormality information, its value is 1, when there is no audio abnormality information, its value is 0, S2 is the preset audio abnormal sound weight value, which is used to evaluate the audio conditions of the slewing bearing during action, and Q2 is the probability value of the presence of abnormal sound in the audio monitoring data during action; The audio monitoring weight calculated in the audio monitoring weight evaluation model is compared and judged with the preset threshold, and then the abnormal sound warning information and / or operation warning intervention information is output as one of the status evaluation results according to the preset conditions.

4. The crane slewing bearing working condition evaluation method according to claim 3, characterized in that: The method for obtaining the vibration signal of the preset area of ​​the slewing bearing according to the preset conditions and generating vibration monitoring data is as follows: Responding to the crane's work start signal, the vibration signal of the preset area of ​​the slewing bearing is obtained in real time; In response to the start and end signals of the slewing bearing's action, the vibration signal acquired in real time is edited according to preset conditions, so that the vibration signals of the preset time length before the slewing bearing takes action, during the action, and after the action end are extracted to generate vibration monitoring data.

5. The crane slewing bearing working condition evaluation method according to claim 4, characterized in that: The method for judging vibration monitoring data according to preset conditions is: Acquire vibration monitoring data, cut it, and generate pre-action vibration monitoring data, in-action vibration monitoring data, and post-action vibration monitoring data associated with the slewing bearing, wherein the pre-action vibration monitoring data and the post-action vibration monitoring data have the same duration and both cover at least one cycle of the vibration waveform; Match the vibration monitoring data before the action with the vibration monitoring data after the action, and output the matching results. When the matching result meets the preset requirements, a periodic vibration waveform in the vibration monitoring data before or after the action is extracted as the vibration noise data, and then the vibration monitoring data during the action is denoised in combination with the vibration noise data to obtain the vibration monitoring data during the action after noise reduction. When the matching result does not meet the preset requirements, at least one cycle of vibration waveform is extracted from the vibration monitoring data before the action and the vibration monitoring data after the action, and the waveforms are superimposed and averaged to generate synthetic vibration data, which is set as vibration noise data. The vibration monitoring data during the action is then denoised in combination with the vibration noise data to obtain the denoised vibration monitoring data during the action. When the matching result does not meet the preset requirements, vibration abnormality information is also generated. Obtain temperature monitoring data and import it into the trained second detection neural network as input together with the noise-reduced vibration monitoring data during operation to obtain the probability of a suspected fault in the vibration monitoring data during operation. Then, the detection results are normalized to a probability of [0, 1], and finally, the vibration detection results are output; A vibration monitoring weight evaluation model is established to calculate the vibration monitoring data. The formula is as follows: Z=K1×Z1+K2×Z2 Among them, Z is the vibration monitoring weight, K1 is the preset vibration abnormality weight value, which is used to evaluate the vibration conditions of the slewing bearing before and after the action, Z1 is the vibration abnormality value, when there is vibration abnormality information, its value is 1, when there is no vibration abnormality information, its value is 0, K2 is the preset suspected fault weight value, which is used to evaluate the vibration conditions of the slewing bearing during action, and Z2 is the probability value of the suspected fault in the vibration monitoring data during action; The vibration monitoring weight calculated in the vibration monitoring weight assessment model is compared with the preset threshold value, and then the potential fault warning information and / or operation warning intervention information are output as one of the status assessment results according to the preset conditions.

6. A method for evaluating the service life of a crane slewing bearing, characterized in that: It includes the crane slewing bearing working condition assessment method according to claim 5, and further includes: Obtain the condition assessment results of the same crane slewing bearing generated at different times, assign weights to various factors in the condition assessment results generated at the same time according to preset conditions, generate condition assessment weight values, and then compare the weights with preset thresholds to generate comparison results; The comparison results corresponding to the status evaluation results generated at different times are collected, and then the number N of comparison results exceeding the preset threshold within the latest preset time period is counted, and then the numerical range of N is judged. When M≥N≥0, the crane slewing bearing is inspected and maintained for the preset time period T0; When L≥N>M, the time period for maintenance of the crane slewing bearing is updated to T0 / 2; When N>L, the crane slewing bearing service life end information is output.

7. The crane slewing bearing service life evaluation method according to claim 6, characterized in that: Obtaining the condition assessment results generated at different times for the same crane slewing bearing, and assigning weights to various factors in the condition assessment results generated at the same time according to preset conditions. The method for generating the condition assessment weight values ​​includes: The condition assessment results of the same crane slewing bearing generated at different times are obtained and then classified according to the assessment factors to form a data set, which includes: Operation monitoring weight data set y = [Y t1 , Y t2 , Y t3 ,……Y tn ]; Audio monitoring weighted dataset S = [S t1 , S t2 , S t3 ,……S tn ]; Vibration monitoring weight dataset Z = [Z t1 , Z t2 , Z t3 , ... Z tn ]; Among them, Y tn 、S tn , Z tn They are the operation monitoring weight value, audio monitoring weight value, and vibration monitoring weight value at different times; A mathematical model of the state assessment weight value is established, and its formula is as follows: W=α×Y tn +β×S tn +γ×Z tn Among them, W is the state assessment weight value, and α, β, and γ are all preset weight coefficients.

8. A crane slewing bearing working condition evaluation system, which is applied with the crane slewing bearing working condition evaluation method according to any one of claims 1 to 5, characterized in that: It includes: A working sensing unit, used to sense the working start signal of the crane; The operation monitoring unit is used to monitor and record the crane's working instructions and load conditions in real time. It also monitors and records the motion of the inner or outer ring of the slewing bearing to generate operation monitoring data. An audio monitoring unit is provided in a preset area of ​​the slewing bearing of the crane and is used to obtain an audio signal of the preset area of ​​the slewing bearing according to preset conditions and generate audio monitoring data; A vibration monitoring unit is provided in a preset area of ​​the slewing bearing of the crane and is used to obtain a vibration signal of the preset area of ​​the slewing bearing according to preset conditions and generate vibration monitoring data; The temperature monitoring units are multiple and are arranged in a preset area of ​​the slewing bearing of the crane, and are used to obtain the working environment temperature of the slewing bearing and the temperature of the slewing bearing body according to preset conditions to generate temperature monitoring data; The status judgment unit is used to obtain operation monitoring data, audio monitoring data, vibration monitoring data and temperature monitoring data, judge the operation monitoring data, audio monitoring data and vibration monitoring data according to preset conditions, and then output the status evaluation result according to the judgment result.

9. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the crane slewing bearing working condition assessment method according to any one of claims 1 to 5.

Images