Helical gear speed reducer fault diagnosis method under intelligent monitoring

Abstract

The invention provides a helical gear speed reducer fault diagnosis method under intelligent monitoring, and relates to the technical field of fault diagnosis, and the method comprises the steps: obtaining real-time operation parameters of an inclined logistics conveyor belt, carrying out the load state evaluation of a helical gear speed reducer, configuring a first monitoring frequency and a first monitoring index number based on a load scale, activating a first sensing device, and carrying out the fault diagnosis of the helical gear speed reducer; monitoring is carried out according to the first monitoring frequency to obtain a first fault risk coefficient, if the first fault risk coefficient exceeds a first fault risk threshold, the sensing monitoring array is activated to obtain a second fault risk coefficient, and if the second fault risk coefficient exceeds a second fault risk threshold, the acousto-optic early warning device is activated to send out an early warning signal to carry out fault early warning. The technical problem of low fault diagnosis efficiency and accuracy caused by the lack of real-time monitoring and intelligent diagnosis means of the helical gear speed reducer in the prior art is solved. The technical effects of monitoring the running state of the helical gear speed reducer in real time and improving the fault diagnosis efficiency and accuracy are achieved.

Description

Technical Field

[0001] The invention relates to the technical field of fault diagnosis, and in particular to a fault diagnosis method for a helical gear reducer under intelligent monitoring. Background Art

[0002] With the rapid development of modern warehousing and logistics industry, inclined conveyor belts, as key equipment, play a vital role in the process of cargo transportation and sorting. Among them, the helical gear reducer is the core driving component of the inclined conveyor belt, and its operating status directly affects the working efficiency and operating stability of the conveyor belt. However, in the prior art, the maintenance of the helical gear reducer mainly relies on manual regular inspection or post-fault repair, and lacks real-time monitoring and intelligent diagnosis of its operating status. This passive maintenance method not only fails to meet the real-time requirements of the logistics system for efficient operation, but also makes it difficult to timely and accurately detect potential fault hazards, which seriously affects the overall efficiency of the logistics system.

[0003] The existing technology has the technical problem that the helical gear reducer lacks real-time monitoring and intelligent diagnosis means, resulting in low fault diagnosis efficiency and accuracy. Summary of the invention

[0004] The present application provides a helical gear reducer fault diagnosis method under intelligent monitoring, which is used to solve the technical problem that the prior art lacks real-time monitoring and intelligent diagnosis means for helical gear reducers, resulting in low fault diagnosis efficiency and accuracy.

[0005] In view of the above problems, the present application provides a fault diagnosis method for a helical gear reducer under intelligent monitoring, the method comprising: obtaining real-time operating parameters of an inclined logistics conveyor belt through fixed-point monitoring, evaluating the load state of the helical gear reducer according to the real-time operating parameters, and determining the load scale, wherein the helical gear reducer is a driving component of the inclined logistics conveyor belt; configuring a first monitoring frequency and a first monitoring indicator quantity based on the load scale, screening in a predetermined monitoring indicator library according to the first monitoring indicator quantity, and determining a first monitoring indicator; activating a first sensing device according to the first monitoring indicator, monitoring the helical gear reducer of the inclined logistics conveyor belt according to the first monitoring frequency, and obtaining a first fault risk coefficient based on the first monitoring data analysis; if the first fault risk coefficient exceeds the first fault risk threshold, activating a sensing monitoring array, comprehensively monitoring the helical gear reducer according to the second monitoring frequency, and obtaining a second fault risk coefficient based on the second monitoring data analysis; if the second fault risk coefficient exceeds the second fault risk threshold, activating an acoustic and visual warning device to send a warning signal, and performing a fault warning on the helical gear reducer of the inclined logistics conveyor belt, wherein the second fault risk threshold is greater than the first fault risk threshold.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The method provided in the embodiment of the present application obtains the real-time operating parameters of the inclined logistics conveyor belt through fixed-point monitoring, evaluates the load state of the helical gear reducer according to the real-time operating parameters, and determines the load scale, wherein the helical gear reducer is the driving component of the inclined logistics conveyor belt; configures the first monitoring frequency and the first monitoring index number based on the load scale, and screens in the predetermined monitoring index library according to the first monitoring index number to determine the first monitoring index; activates the first sensor device according to the first monitoring index, monitors the helical gear reducer of the inclined logistics conveyor belt according to the first monitoring frequency, and obtains the first fault risk coefficient based on the first monitoring data analysis; if the first fault risk coefficient exceeds the first fault risk threshold, activates the sensor monitoring array, comprehensively monitors the helical gear reducer according to the second monitoring frequency, and obtains the second fault risk coefficient based on the second monitoring data analysis; if the second fault risk coefficient exceeds the second fault risk threshold, activates the sound and light warning device to send a warning signal, and performs a fault warning on the helical gear reducer of the inclined logistics conveyor belt, wherein the second fault risk threshold is greater than the first fault risk threshold. The technical effect of real-time monitoring of the operating state of the helical gear reducer and improving the efficiency and accuracy of fault diagnosis is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0009] Figure 1 A flow chart of a helical gear reducer fault diagnosis method under intelligent monitoring provided in this application;

[0010] Figure 2 A schematic diagram of a process for determining a first monitoring indicator in a helical gear reducer fault diagnosis method under intelligent monitoring provided in the present application. DETAILED DESCRIPTION

[0011] The present application provides a helical gear reducer fault diagnosis method under intelligent monitoring, which is used to solve the technical problem that the helical gear reducer lacks real-time monitoring and intelligent diagnosis means in the prior art, resulting in low fault diagnosis efficiency and accuracy. The technical effect of real-time monitoring of the operating status of the helical gear reducer and improving the fault diagnosis efficiency and accuracy is achieved.

[0012] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. 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. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0013] like Figure 1 As shown, the present application provides a helical gear reducer fault diagnosis method under intelligent monitoring, the method comprising:

[0014] The real-time operating parameters of the inclined logistics conveyor belt are acquired by fixed-point monitoring, and the load state of the helical gear reducer is evaluated according to the real-time operating parameters to determine the load scale, wherein the helical gear reducer is the driving component of the inclined logistics conveyor belt.

[0015] Specifically, fixed-point monitoring devices, such as high-definition cameras, are deployed at key locations of the inclined conveyor belt of warehouse logistics, such as near the drive roller and the load-bearing area. The layout position of the monitoring device is optimized through experiments to ensure that the conveying area of ​​the logistics conveyor belt can be fully covered to avoid monitoring blind spots. Then, the real-time operating parameters of the inclined conveyor belt are continuously obtained through the fixed-point monitoring device. The real-time operating parameters include cargo load overflow, cargo load uniformity, and cargo transportation uniformity. Then, the load state of the helical gear reducer is evaluated based on the real-time operating parameters to determine the load scale currently borne by the helical gear reducer. The load scale reflects the size and nature of the working load of the helical gear reducer. As the driving component of the inclined logistics conveyor belt, the performance of the gear reducer is directly related to the stability and efficiency of the conveyor belt. Through real-time load state evaluation, the load abnormality of the helical gear reducer can be discovered in time, and potential failure risks can be warned to avoid equipment damage and transmission interruption.

[0016] Furthermore, real-time operating parameters of the inclined logistics conveyor belt are acquired through fixed-point monitoring, and the load state of the helical gear reducer is evaluated based on the real-time operating parameters to determine the load scale, including: acquiring a monitoring video of the inclined logistics conveyor belt at a fixed point, and obtaining real-time operating parameters based on analysis of the monitoring video, wherein the real-time operating parameters include cargo load overflow, cargo load uniformity and cargo transportation uniformity; evaluating the load state of the helical gear reducer based on the cargo load overflow, cargo load uniformity and cargo transportation uniformity to generate a load scale, wherein the load scale is positively correlated with the cargo load overflow, and negatively correlated with the cargo load uniformity and cargo transportation uniformity.

[0017] Specifically, high-performance video devices, such as high-definition cameras, are placed at key locations on inclined logistics conveyor belts to ensure panoramic capture of the cargo transportation process. The video devices use high-definition resolution and dynamic capture technology to record the dynamic position, distribution status and transportation speed of the cargo in real time. Fixed-point monitoring collects data at fixed locations to ensure the continuity and comparability of video data. The monitoring video of the inclined logistics conveyor belt is obtained through a fixed-point monitoring device, and then the boundary overflow of the goods on the inclined logistics conveyor belt is analyzed according to the video frame, the distribution uniformity of the cargo load on the conveyor belt is analyzed, and the uniformity of the cargo transmission speed is analyzed through trajectory tracking and motion analysis to obtain real-time operation parameters, which include cargo load overflow, cargo load uniformity and cargo delivery uniformity. The cargo load overflow refers to the boundary overflow of the goods on the conveyor belt, which is used to measure the risk of overloading and reflect the potential load pressure caused by the goods on the helical gear reducer. The cargo load uniformity is used to describe the distribution uniformity of the goods on the conveyor belt. The lower the cargo load uniformity, the more concentrated the local load is, and the higher the risk of equipment loss is. The cargo delivery uniformity refers to the uniformity of the cargo delivery speed. Low cargo delivery uniformity indicates poor operation or abnormal mechanical state of the conveyor belt. Then, according to the cargo load overflow, cargo load uniformity and cargo delivery uniformity, the load state of the helical gear reducer is comprehensively evaluated and the load scale is generated. The load scale is positively correlated with the cargo load overflow, that is, the larger the cargo load overflow, the larger the load scale of the reducer. It is negatively correlated with the uniformity of cargo load and cargo transportation, indicating that the more uniform the load distribution and the more stable the transmission speed, the smaller the load scale of the reducer. Optionally, the load scale is generated by the load state evaluation formula, which is as follows: Load scale = W1·Overflow + W2·(1-load uniformity) + W3·(1-transport uniformity), where W1, W2 and W3 are weight coefficients, which are pre-set according to actual needs, expert experience and historical data. Obtaining real-time operating parameters through fixed-point monitoring for comprehensive load state evaluation can accurately reflect the real-time load pressure of the helical gear reducer, improve the accuracy of fault prediction, and ensure the stable operation of the logistics conveyor belt.

[0018] A first monitoring frequency and a first monitoring indicator quantity are configured based on the load scale, and a first monitoring indicator is determined by screening in a predetermined monitoring indicator library according to the first monitoring indicator quantity.

[0019] Furthermore, configuring a first monitoring frequency and a first monitoring indicator quantity based on the load scale includes: obtaining component attributes of the helical gear reducer, wherein the component attributes include gear width, gear pitch, gear module and gear tooth number; evaluating and obtaining a gear strength coefficient based on the gear width, gear pitch, gear module and gear tooth number, and multiplying the ratio of the gear strength coefficient to the standard gear strength coefficient by the load scale to obtain a corrected load scale; setting the ratio of the corrected load scale to the historical maximum load scale as the real-time monitoring scale, and multiplying the real-time monitoring scale by the second monitoring frequency, and rounding to obtain the first monitoring frequency; multiplying the real-time monitoring scale by the number of monitoring indicators in a predetermined monitoring indicator library, and rounding to obtain the first monitoring indicator quantity.

[0020] Specifically, the component properties of the helical gear reducer directly determine its load-bearing capacity under different load conditions. The component properties of the helical gear reducer are obtained, including gear width, gear pitch, gear module and gear teeth number. The gear width represents the lateral dimension of the gear. The larger the width, the stronger the load resistance. The gear pitch describes the gear meshing angle, which affects the transmission stability and load-bearing capacity. The gear module is the reference parameter of the gear size, reflecting the structural strength of the gear. The more gear teeth, the higher the transmission accuracy and the stronger the load-bearing capacity. Then, the gear skin coefficient is calculated according to the component properties of the helical gear reducer to quantify the strength of the gear tolerance. The higher the gear skin coefficient, the better the compression and shear resistance of the gear under load conditions. The gear skin coefficient calculation formula is: Ks = k1·W + k2·tan(α) + k3·m·z, where Ks is the gear skin coefficient, k1, k2, k3 are weight coefficients, reflecting the contribution of each parameter to the gear load resistance, W is the gear width, α is the gear pitch, m is the gear module, and z is the number of gear teeth. Then, the ratio of the gear skin solid coefficient to the standard gear skin solid coefficient is multiplied by the load scale to obtain the corrected load scale. The positive load scale is the value obtained after adjusting the load scale, taking into account the difference between the actual load-bearing capacity of the helical gear reducer and the industry standard reference value. The real-time monitoring scale is determined by the ratio of the corrected load scale to the historical maximum load scale. The real-time monitoring scale is used to dynamically adjust the monitoring frequency. The formula is: real-time monitoring scale = corrected load scale / historical maximum load scale. The real-time monitoring scale reflects the proportion of the current load relative to the historical operating limit of the equipment. The larger the value, the closer the current load is to the maximum capacity of the equipment, and a higher monitoring frequency and more monitoring indicators are required. Further, the real-time monitoring scale is multiplied by the second monitoring frequency and rounded to obtain the first monitoring frequency. The second monitoring frequency is the preset maximum monitoring frequency, which can be set to the maximum monitoring frequency required by the equipment under high load conditions. The first monitoring frequency refers to the equipment monitoring frequency dynamically calculated based on the real-time monitoring scale, which is used to adjust the time interval or cycle for the monitoring device to collect data from the helical gear reducer. At the same time, the real-time monitoring scale is multiplied by the number of monitoring indicators in the predetermined monitoring indicator library and rounded to obtain the first number of monitoring indicators. The predetermined monitoring indicator library contains multiple monitoring parameters for comprehensive evaluation of the reducer status, including speed monitoring (input / output speed), temperature, noise, vibration, etc. By dynamically adjusting the number of monitoring indicators according to the real-time monitoring scale, it is ensured that the monitoring indicators are increased at high loads and reduced at low loads, thereby optimizing the allocation of monitoring resources. By dynamically configuring the first monitoring frequency and the first number of monitoring indicators according to the load scale, the balance between resource utilization efficiency and monitoring coverage is improved, and intelligent monitoring of helical gear reducers is realized.

[0021] In one embodiment, Figure 2As shown, screening is performed in a predetermined monitoring indicator library according to the first number of monitoring indicators to determine the first monitoring indicator, including: obtaining a number of monitoring indicators from the predetermined monitoring indicator library, wherein the monitoring indicators include at least rotational speed, temperature, noise and vibration; combining the regional environmental characteristics of the inclined logistics conveyor belt, respectively performing monitoring difficulty and environmental interference analysis on the several monitoring indicators, and determining a number of monitoring simplicity coefficients and a number of monitoring accuracies; weighted calculation is performed based on the several monitoring simplicity coefficients and a number of monitoring accuracies to obtain a number of indicator fitness, and the several monitoring indicators are sorted from large to small according to the indicator fitness to generate a monitoring indicator sequence; the first number of monitoring indicators are selected from the monitoring indicator sequence as the first monitoring indicators.

[0022] Specifically, the predetermined monitoring index library is a pre-set database containing a variety of monitoring indicators that affect the operating status of the helical gear reducer. Multiple monitoring indicators are obtained from the predetermined monitoring index library. The multiple monitoring indicators include at least speed, temperature, noise and vibration. The speed is used to evaluate the running smoothness of the input / output shaft, the temperature is used to reflect the heat loss of gears and bearings, the noise is used to monitor the meshing state and mechanical friction of the equipment, and the vibration is used to reflect the stability and abnormal characteristics of the equipment operation. Different environmental characteristics will directly affect the difficulty and accuracy of monitoring. For example, if the noise in the factory production in the area where the conveyor belt is located is loud, then the noise monitoring indicator will be greatly disturbed, thereby affecting its monitoring accuracy. Comprehensively identify the environment of the area where the inclined logistics conveyor belt is located to obtain specific environmental characteristics of the area where the conveyor belt is located, such as temperature, humidity, noise level, vibration level, etc. Then, for each monitoring indicator, such as speed, temperature, noise, vibration, etc., according to the adaptability of the monitoring equipment and the complexity of data collection, the difficulty of monitoring in the current environment is evaluated, and multiple monitoring simplicity coefficients are assigned. The higher the simplicity coefficient, the lower the difficulty. The monitoring simplicity coefficient = 1-difficulty score. For example, the noise signal needs noise reduction processing, which increases the complexity. The speed monitoring is directly read by the standard sensor, which has low difficulty. At the same time, the interference of the environment on the monitoring accuracy is analyzed, such as the direct impact of noise on noise monitoring, and several monitoring accuracies are obtained. The greater the environmental interference, the lower the monitoring accuracy, which is quantified by the following formula: monitoring accuracy = 1-interference score. Then, according to several monitoring simplicity coefficients and several monitoring accuracies, several indicator adaptability is obtained by weighted calculation. Indicator adaptability = W4·monitoring simplicity coefficient + W5·monitoring accuracy, where W4 and W5 are weights, which are adjusted according to the importance of the indicator. After calculating and obtaining the fitness of multiple monitoring indicators, a monitoring indicator sequence is generated by sorting them from large to small according to the fitness, and indicators with high fitness are given priority. The monitoring indicator sequence is based on the applicability and accuracy of the monitoring indicators in the current environment, which can ensure the effectiveness and reliability of the selected monitoring indicators. Finally, the monitoring indicators of the first number of monitoring indicators are selected from the monitoring indicator sequence and set as the first monitoring indicators. By selecting the first N indicators from the monitoring indicator sequence, where N is the number of the first monitoring indicators, it is ensured that the selected indicators meet the monitoring requirements and can achieve effective monitoring in the current environment. By comprehensively considering the ease of monitoring indicators and environmental interference characteristics, the indicator combination that best suits the current environment and monitoring requirements is screened out, thereby ensuring the effectiveness and accuracy of the monitoring work, and providing accurate and reliable data support for the monitoring of helical gear reducers for inclined logistics conveyor belts.

[0023] The first sensing device is activated according to the first monitoring indicator, the helical gear reducer of the inclined logistics conveyor belt is monitored according to the first monitoring frequency, and a first fault risk coefficient is obtained based on the first monitoring data analysis.

[0024] Specifically, the first sensing device is activated according to the determined first monitoring index. The first sensing device refers to the sensor corresponding to the first monitoring index, which is used to collect real-time data of the operating status of the reducer. For example, for the speed index, the speed sensor installed on the input / output shaft is activated, for the temperature index, the temperature sensor installed at the gear box or the bearing is activated, for the vibration index, the acceleration sensor installed on the housing of the helical gear reducer is activated, and for the noise index, the sound level meter near the helical gear reducer is activated. After the corresponding sensing device is dynamically activated according to the screened first monitoring index, the sensing device monitors the helical gear reducer of the inclined logistics conveyor belt according to the determined first monitoring frequency, obtains the first monitoring data, analyzes the first monitoring data, calculates the fault probability under the current operating state, and outputs the first fault risk coefficient. The first fault risk coefficient indicates the possibility of a fault under the current operating state. The higher the coefficient value, the closer the equipment operating state is to the fault state. When the first fault risk coefficient is less than the first fault risk threshold, it means that the equipment is operating normally and the existing monitoring frequency is maintained. The first fault risk threshold is a risk assessment critical value set in advance, which is determined according to the safe operation requirements of the helical gear reducer equipment and historical fault experience. If the threshold is exceeded, the system enters high-intensity monitoring mode and further enables the sensor monitoring array for comprehensive diagnosis. By dynamically activating the corresponding sensors and adjusting the monitoring frequency and monitoring equipment as needed, resource utilization efficiency is improved, over- or under-monitoring is avoided, and fault diagnosis efficiency and accuracy are improved.

[0025] If the first fault risk coefficient exceeds a first fault risk threshold, the sensor monitoring array is activated, the helical gear reducer is comprehensively monitored at a second monitoring frequency, and a second fault risk coefficient is obtained based on second monitoring data analysis.

[0026] Specifically, when the first fault risk coefficient is greater than or equal to the first fault risk threshold, it indicates that the helical gear reducer has an abnormal condition. At this time, the monitoring mode is upgraded, the sensor monitoring array is activated, data is collected according to the second monitoring frequency, and the second fault risk coefficient is calculated through comprehensive analysis. The sensor monitoring array includes multiple types of sensors, each sensor corresponds to a specific monitoring indicator, and the sensor monitoring array can cover all key parameters of the helical gear reducer operation and provide comprehensive status information. The sensor monitoring array is dynamically activated according to the trigger condition, and the mode of monitoring only some indicators is switched to full coverage monitoring. For example, in addition to speed, temperature, and vibration, new monitoring items such as noise and pressure are also added to ensure the comprehensiveness of the data. The second monitoring frequency is a predetermined maximum monitoring frequency that can capture subtle anomalies in a short period of time. For example, if the first monitoring frequency is 5 times per second, the second monitoring frequency is increased to 10 times per second. Each sensor in the sensor monitoring array synchronously collects real-time data according to the second monitoring frequency to form a multi-dimensional equipment operation status data set, namely the second monitoring data, and then analyzes the second monitoring data to obtain the second fault risk coefficient. Through preliminary monitoring by the first sensing device and the first monitoring frequency, with fewer monitoring indicators, high adaptability and high analysis efficiency, real-time monitoring can detect abnormalities in a timely manner, and then upgrade when abnormalities are found, to achieve comprehensive fault analysis and improve the efficiency and accuracy of helical gear reducer fault diagnosis.

[0027] If the second fault risk coefficient exceeds the second fault risk threshold, the sound and light warning device is activated to send out a warning signal, and a fault warning is issued for the helical gear reducer of the inclined logistics conveyor belt, wherein the second fault risk threshold is greater than the first fault risk threshold.

[0028] Specifically, the second fault risk coefficient is a fault probability value calculated based on comprehensive monitoring data, which indicates the degree of fault risk of the current state of the equipment. The second fault risk threshold is a preset higher level fault risk judgment standard. If it is greater than the first fault risk threshold, it indicates that the equipment is approaching or reaching a dangerous operating state. When the first fault risk coefficient is less than or equal to the second fault risk threshold, continuous monitoring is maintained. Based on the current monitoring data, it is compared with the monitoring data in the past period of time to evaluate the changing trend of the fault risk. If the risk coefficient remains stable or decreases, it means that the equipment state is tending to be normal, and the monitoring frequency can be appropriately reduced. When the first fault risk coefficient is greater than or equal to the second fault risk threshold, it is determined that the helical gear reducer has a high fault risk, and the sound and light warning device is immediately activated to send a warning signal to warn of the fault of the helical gear reducer of the inclined logistics conveyor belt. The sound and light warning device consists of a high-decibel alarm and a high-brightness LED light. The sound signal is used to quickly attract the attention of the on-site operator, and the light signal facilitates visual perception at a long distance and in a complex environment. When the sound and light warning device is activated, a warning report is generated based on the current second fault risk factor and related operating parameters. Fault warning information is sent to the equipment maintenance team and management personnel through various means such as SMS, email or mobile APP notification to ensure timely response. The warning report includes risk details, i.e. the specific values ​​of the second fault risk factor and abnormal indicators. Through the hierarchical threshold fault warning, it can ensure that no fault risk is missed while saving resources, providing key protection for the intelligent monitoring and safety management of helical gear reducers.

[0029] Furthermore, the helical gear reducer of the inclined logistics conveyor belt is monitored according to the first monitoring frequency, and a first fault risk coefficient is obtained based on the first monitoring data analysis, including: monitoring the helical gear reducer of the inclined logistics conveyor belt according to the first monitoring frequency to obtain first monitoring data; calling the first fault diagnosis plug-in of the first monitoring indicator, predicting the fault probability of the first monitoring data, and outputting a first predicted fault probability, which is set as the first fault risk coefficient, wherein the first fault diagnosis plug-in is constructed based on random forest, and is trained with sample first monitoring data and sample first fault probability until convergence.

[0030] Specifically, the first sensing device monitors and collects the helical gear reducer of the inclined logistics conveyor belt according to the first monitoring frequency, obtains multiple state indicator data of the helical gear reducer, and forms the first monitoring data. Based on machine learning technology, the random forest constructs the first fault diagnosis plug-in, and the first fault diagnosis plug-in is used to predict the fault probability of the first monitoring data. Random forest is an integrated learning algorithm that predicts by building multiple decision trees and integrating the judgment results of multi-dimensional data, and has high accuracy and stability. The construction process of the first fault diagnosis plug-in is to obtain a large amount of sample data, and the sample data includes sample first monitoring data and sample one-point fault probability. The sample first monitoring data is monitoring data such as speed, temperature, vibration, etc. under different load conditions. The sample first fault probability is a fault probability label obtained by statistically analyzing the proportion of faults in the sample monitoring data within a historical predetermined time interval. Through supervised learning of sample data, the decision tree parameters are optimized until the model converges to form the first fault diagnosis plug-in, and the first fault diagnosis plug-in has efficient and accurate fault probability prediction capabilities. The first fault diagnosis plug-in of the first monitoring indicator is called, the first monitoring data collected in real time is input into the first diagnosis plug-in, the fault probability of the current operating state is calculated using the trained model, and the output is the first predicted fault probability. The first predicted fault probability is used as the first fault risk coefficient, a quantitative indicator of the current fault risk of the helical gear reducer, ranging from 0 to 1. The higher the value of the first fault risk coefficient, the higher the fault risk of the current operating state of the helical gear reducer. By calling the first fault diagnosis plug-in of the first monitoring indicator to predict the fault probability of the first monitoring data and outputting the first predicted fault probability, the accuracy and efficiency of fault diagnosis can be improved.

[0031] Furthermore, if the first fault risk coefficient exceeds the first fault risk threshold, the sensor monitoring array is activated, the helical gear reducer is comprehensively monitored at a second monitoring frequency, and a second fault risk coefficient is obtained based on the second monitoring data analysis, including: if the first fault risk coefficient exceeds the first fault risk threshold, the sensor monitoring array is activated, wherein the sensor monitoring array includes a plurality of sensor devices, and the sensor devices correspond to monitoring indicators; through the sensor monitoring array, the helical gear reducer is comprehensively monitored at the second monitoring frequency, and second monitoring data is output; a comprehensive fault diagnosis channel is pre-constructed, the second monitoring data is input into the comprehensive fault diagnosis channel for prediction, and the second fault risk coefficient is output.

[0032] Furthermore, a comprehensive fault diagnosis channel is pre-constructed, including: based on the operation log of the same type of helical gear reducer of the inclined logistics conveyor belt, a sample monitoring data set is collected with a number of monitoring indicators as constraints, and the fault proportion of different sample monitoring data in a predetermined historical time zone is statistically analyzed, which is set as a sample fault risk coefficient to obtain a sample fault risk coefficient set; the sample monitoring data set and the sample fault risk coefficient set are used as training data, and are equally divided into K parts to obtain K training sets, where K is an integer greater than 9; the K training sets are used to supervise the training of the random forest until convergence, and K comprehensive fault diagnosis plug-ins that have been trained are obtained, which are combined to obtain the comprehensive fault diagnosis channel.

[0033] Specifically, when the first fault risk coefficient is greater than or equal to the preset first fault risk threshold, it indicates that the helical gear reducer may have a fault risk. At this time, the sensor monitoring array is activated. The sensor monitoring array includes multiple sensor devices corresponding to different monitoring indicators, covering the key operating parameters of the helical gear reducer. The sensor monitoring array includes several sensor devices, and the sensor devices correspond to the monitoring indicators. Through the sensor monitoring array, multiple monitoring data are synchronously collected according to the second monitoring frequency to form comprehensive second monitoring data.

[0034] The operation log of the same type of helical gear reducer on the inclined logistics conveyor belt is called. The operation log records the operation data of the same type of helical gear reducer under various working conditions, including the monitoring record data of the monitoring system, the equipment maintenance log and the fault data that has occurred. Several monitoring indicators that can directly or indirectly reflect the operating status of the helical gear reducer are selected as constraints, such as speed, temperature, vibration and noise, and sample monitoring data sets are collected. The sample monitoring data contains the operation records of the helical gear reducer under different time periods and different working conditions, such as speed fluctuation range, temperature change trend, vibration spectrum characteristics and noise value. In a predetermined historical time zone, such as the time period of the past year, the probability of failure of each sample monitoring data is statistically analyzed to obtain the sample failure risk coefficient. The sample failure risk coefficient reflects the probability or frequency of failure in each sample data. The sample failure risk coefficient = the number of failures in the corresponding time period of the sample / the total number of observations. For example, if a sample has 10 failures in 100 operation records, its failure risk coefficient is 0.1. The failure risk coefficients corresponding to all sample monitoring data are calculated to form a sample failure risk coefficient set. The sample monitoring data set and the sample fault risk coefficient set are used as training data, and the sample monitoring data set and the sample fault risk coefficient set are randomly disrupted in sample order, and the data is divided into K parts, where K is an integer greater than 9. The random forest algorithm is used to supervise the training of the K training sets, and the K training data are respectively input into the random forest model, including the input feature sample monitoring data and the target value sample fault risk coefficient. In each training, multiple decision trees are constructed by random sampling and feature selection of sample data. By adjusting the number, depth and splitting strategy of decision trees, the convergence and accuracy of the random forest are ensured, and the hyperparameters are optimized until the model converges, that is, the performance of the model reaches a stable state. In K trainings, a high-precision random forest model is obtained for each training, and K comprehensive fault diagnosis plug-ins that have been trained are obtained. All the K plug-ins that have been trained are combined to form a comprehensive fault diagnosis channel. The comprehensive fault diagnosis channel covers multi-dimensional indicators and data characteristics, and can analyze the operating status of the helical gear reducer of the inclined logistics conveyor belt under different loads and environmental conditions, and improve the efficiency and accuracy of fault diagnosis. After obtaining the comprehensive fault diagnosis channel, the second monitoring data is input into the comprehensive fault diagnosis channel for prediction to obtain a second fault risk coefficient, which is calculated based on the comprehensive data of the comprehensive fault diagnosis channel and can accurately reflect the current comprehensive fault risk of the equipment. Through the integrated learning ability of random forests, the comprehensive fault diagnosis channel can extract key features from complex multi-dimensional monitoring data and accurately predict the fault risk of the helical gear reducer.

[0035] Furthermore, the second monitoring data is input into the comprehensive fault diagnosis channel for prediction, and the second fault risk coefficient is output, including: calculating the deviation value between the first fault risk coefficient and the first fault risk threshold, setting it as the first deviation coefficient; multiplying the ratio of the first deviation coefficient to the maximum deviation coefficient by K and rounding it up to obtain Q, wherein the maximum deviation coefficient is the deviation value between the second fault risk threshold and the first fault risk threshold; randomly selecting Q comprehensive fault diagnosis plug-ins from the K comprehensive fault diagnosis plug-ins of the comprehensive fault diagnosis channel, and inputting the second monitoring data into the Q comprehensive fault diagnosis plug-ins, outputting Q fault risk coefficients, and obtaining the second fault risk coefficient after average calculation.

[0036] Specifically, the first fault risk coefficient and the first fault risk threshold are subjected to deviation calculation to obtain the first deviation coefficient, which reflects the degree to which the first fault risk coefficient exceeds the first threshold, and the first deviation coefficient = the first fault risk coefficient - the first fault risk threshold. The second fault risk threshold and the first fault risk threshold are subjected to deviation calculation to obtain the maximum deviation coefficient, and the maximum deviation coefficient = the second fault risk threshold - the first fault risk threshold. Then, the ratio of the first deviation coefficient to the maximum deviation coefficient is multiplied by K and rounded to obtain the number of selected diagnostic plug-ins Q, that is, Q = (first deviation coefficient / maximum deviation coefficient) × K rounded, where K is the total number of diagnostic plug-ins in the comprehensive fault diagnosis channel. The larger the deviation, the more plug-ins are selected. The comprehensive fault diagnosis channel contains K comprehensive fault diagnosis plug-ins, each of which is based on the random forest model and can independently analyze the second monitoring data. Q comprehensive fault diagnosis plug-ins are randomly selected from the K comprehensive fault diagnosis plug-ins of the comprehensive fault diagnosis channel for current analysis. Random selection can improve the robustness of diagnosis and avoid the overfitting risk that may be caused by fixed plug-in selection. The second monitoring data is input into the selected Q comprehensive fault diagnosis plug-ins, and each diagnostic plug-in outputs a fault risk coefficient to obtain Q fault risk coefficients, and then the Q fault risk coefficients are averaged to obtain the second fault risk coefficient. The second fault risk coefficient is a comprehensive diagnostic result, which accurately and reliably reflects the failure probability of the helical gear reducer in the current state. The number of diagnostic plug-ins is adjusted by the first deviation coefficient to ensure the analysis accuracy under high-risk conditions and avoid resource waste under low-risk conditions. Through comprehensive analysis of multiple plug-ins, the characteristics of different models are used to reduce the error of a single model, improve the reliability and accuracy of fault diagnosis of the helical gear reducer, shorten downtime, and thus improve the technical effect of the overall efficiency of the logistics system.

[0037] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0038] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A helical gear reducer fault diagnosis method under intelligent monitoring, characterized in that: Methods include: The fixed-point monitoring obtains the real-time operating parameters of the inclined logistics conveyor belt, and the load state of the helical gear reducer is evaluated according to the real-time operating parameters to determine the load scale, wherein the helical gear reducer is the driving component of the inclined logistics conveyor belt; Configure a first monitoring frequency and a first monitoring indicator quantity based on the load scale, and screen a predetermined monitoring indicator library according to the first monitoring indicator quantity to determine a first monitoring indicator; activating a first sensor device according to the first monitoring indicator, monitoring the helical gear reducer of the inclined logistics conveyor belt according to the first monitoring frequency, and obtaining a first fault risk coefficient based on the first monitoring data analysis; If the first fault risk coefficient exceeds a first fault risk threshold, the sensor monitoring array is activated, the helical gear reducer is fully monitored according to a second monitoring frequency, and a second fault risk coefficient is obtained based on the second monitoring data analysis; If the second fault risk coefficient exceeds the second fault risk threshold, the sound and light warning device is activated to send out a warning signal, and a fault warning is issued for the helical gear reducer of the inclined logistics conveyor belt, wherein the second fault risk threshold is greater than the first fault risk threshold.

2. The helical gear reducer fault diagnosis method under intelligent monitoring according to claim 1 is characterized in that: The fixed-point monitoring obtains the real-time operating parameters of the inclined logistics conveyor belt, and the load state of the helical gear reducer is evaluated according to the real-time operating parameters to determine the load scale, including: Obtaining a monitoring video of the inclined logistics conveyor belt at a fixed point, and obtaining real-time operating parameters based on the monitoring video analysis, wherein the real-time operating parameters include cargo load overflow, cargo load uniformity, and cargo delivery uniformity; The load state of the helical gear reducer is evaluated according to the cargo load overflow degree, cargo load uniformity and cargo transportation uniformity to generate a load scale, wherein the load scale is positively correlated with the cargo load overflow degree, and negatively correlated with the cargo load uniformity and cargo transportation uniformity.

3. The helical gear reducer fault diagnosis method under intelligent monitoring according to claim 2 is characterized in that: Configuring a first monitoring frequency and a first monitoring indicator quantity based on the load scale includes: Acquire component attributes of the helical gear reducer, wherein the component attributes include gear width, gear pitch, gear module and gear teeth number; The gear solidity coefficient is obtained by evaluating the gear width, gear pitch, gear module and gear teeth number, and the ratio of the gear solidity coefficient to the standard gear solidity coefficient is multiplied by the load scale to obtain the correction load scale; The ratio of the correction load scale to the historical maximum load scale is set as the real-time monitoring scale, and the real-time monitoring scale is multiplied by the second monitoring frequency, and the first monitoring frequency is obtained after rounding; The real-time monitoring scale is multiplied by the number of monitoring indicators in the predetermined monitoring indicator library, and the result is rounded to obtain the first monitoring indicator number.

4. The helical gear reducer fault diagnosis method under intelligent monitoring according to claim 3 is characterized in that: Screening in a predetermined monitoring indicator library according to the number of the first monitoring indicators to determine the first monitoring indicator includes: Acquire a plurality of monitoring indicators from a predetermined monitoring indicator library, wherein the monitoring indicators at least include rotation speed, temperature, noise and vibration; Combined with the regional environmental characteristics of the inclined logistics conveyor belt, the monitoring difficulty and environmental interference analysis are respectively performed on the several monitoring indicators, and several monitoring simplicity coefficients and several monitoring accuracies are determined; Based on the plurality of monitoring simplicity coefficients and the plurality of monitoring precisions, weighted calculations are performed to obtain a plurality of indicator fitnesses, and the plurality of monitoring indicators are sorted from large to small according to the indicator fitnesses to generate a monitoring indicator sequence; The monitoring indicators before the first monitoring indicator number are selected from the monitoring indicator sequence and are set as the first monitoring indicators.

5. The helical gear reducer fault diagnosis method under intelligent monitoring according to claim 4 is characterized in that: The helical gear reducer of the inclined logistics conveyor belt is monitored according to the first monitoring frequency, and a first fault risk coefficient is obtained based on the first monitoring data analysis, including: Monitoring the helical gear reducer of the inclined logistics conveyor belt according to the first monitoring frequency to obtain first monitoring data; Call a first fault diagnosis plug-in of the first monitoring indicator, predict the fault probability of the first monitoring data, and output a first predicted fault probability, which is set as the first fault risk coefficient, wherein the first fault diagnosis plug-in is constructed based on a random forest and is trained with sample first monitoring data and sample first fault probability until convergence.

6. The helical gear reducer fault diagnosis method under intelligent monitoring according to claim 5 is characterized in that: If the first fault risk coefficient exceeds the first fault risk threshold, the sensor monitoring array is activated, the helical gear reducer is fully monitored according to the second monitoring frequency, and a second fault risk coefficient is obtained based on the second monitoring data analysis, including: If the first fault risk coefficient exceeds a first fault risk threshold, activating a sensor monitoring array, wherein the sensor monitoring array includes a plurality of sensor devices, and the sensor devices correspond to monitoring indicators; Through the sensor monitoring array, the helical gear reducer is comprehensively monitored according to the second monitoring frequency, and second monitoring data is output; A comprehensive fault diagnosis channel is pre-constructed, the second monitoring data is input into the comprehensive fault diagnosis channel for prediction, and the second fault risk coefficient is output.

7. The helical gear reducer fault diagnosis method under intelligent monitoring according to claim 6 is characterized in that: Pre-built comprehensive troubleshooting pipeline including: Based on the operation log of the same type of helical gear reducer of the inclined logistics conveyor belt, a sample monitoring data set is collected with several monitoring indicators as constraints, and the failure proportion of different sample monitoring data in the predetermined historical time zone is statistically analyzed and set as the sample failure risk coefficient to obtain the sample failure risk coefficient set; The sample monitoring data set and the sample fault risk coefficient set are used as training data, and are equally divided into K parts to obtain K training sets, where K is an integer greater than 9; The K training sets are used to perform supervised training on the random forest until convergence, and K trained comprehensive fault diagnosis plug-ins are obtained, which are combined to obtain the comprehensive fault diagnosis channel.

8. The helical gear reducer fault diagnosis method under intelligent monitoring according to claim 6 is characterized in that: Inputting the second monitoring data into the comprehensive fault diagnosis channel for prediction, and outputting the second fault risk coefficient, comprises: Calculating a deviation value between the first failure risk coefficient and the first failure risk threshold, and setting it as a first deviation coefficient; The ratio of the first deviation coefficient to the maximum deviation coefficient is multiplied by K and rounded to obtain Q, wherein the maximum deviation coefficient is the deviation value between the second fault risk threshold and the first fault risk threshold; Q comprehensive fault diagnosis plug-ins are randomly selected from the K comprehensive fault diagnosis plug-ins of the comprehensive fault diagnosis channel, and the second monitoring data is input into the Q comprehensive fault diagnosis plug-ins, Q fault risk coefficients are output, and the second fault risk coefficient is obtained after mean calculation.

Images