Equipment fault alarm method and system applied to production management

Abstract

The invention relates to the technical field of production management, in particular to an equipment fault alarm method and system applied to production management, and the method comprises the steps: carrying out the signal collection of a vibration signal and a temperature of equipment under a normal operation condition; calculating dynamic characteristic parameters of the equipment operation state, and establishing a reference characteristic model; comparing the real-time measured value with the dynamic change range in the reference feature model one by one, calculating a real-time deviation value, and identifying the abnormality of the running state of the equipment; classifying the abnormal states of the equipment according to the characteristics and the change trend of the deviation value; and adjusting the dynamic change range in the reference feature model, and triggering different alarm levels according to the real-time deviation value. Through the fault detection method and device, the problems that in the prior art, dynamic changes of operation conditions cannot be adapted, deviation characteristics and trends are difficult to analyze, and an anomaly classification and grading alarm mechanism is lacked are effectively solved, the accuracy and adaptability of fault detection are improved, and efficient and reliable decision support is provided for production management.

Description

Technical Field

[0001] The present invention relates to the technical field of production management, and in particular to an equipment failure alarm method and system applied to production management. Background Art

[0002] In modern industrial production, efficient operation and timely maintenance of equipment are key factors to ensure production safety and economic benefits. However, with the increasing complexity and automation of industrial equipment, traditional fault monitoring and alarm methods have been unable to meet the diverse and high-precision needs.

[0003] In the existing technology, most methods rely on fixed threshold settings for fault judgment, which is difficult to adapt to complex working conditions such as load fluctuations and ambient temperature changes, and is prone to false alarms or missed alarms. At the same time, traditional methods lack in-depth analysis of deviation value characteristics and trends, cannot refine the classification of abnormal conditions, and lack a graded alarm mechanism, which limits the rapid judgment of the nature and severity of the fault. Summary of the invention

[0004] The present invention provides an equipment failure alarm method and system for production management, thereby effectively solving the problems pointed out in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: An equipment failure alarm method for production management, comprising: Collect the vibration signal and temperature of the equipment under normal operating conditions to obtain a basic parameter information set; According to the basic parameter set, dynamic characteristic parameters of the equipment operation state are calculated, and a benchmark characteristic model is established; Acquire basic parameters of the equipment operation process in real time, compare the real-time measurement values ​​with the dynamic change range in the benchmark feature model one by one, calculate the real-time deviation value, and identify abnormalities in the equipment operation state; According to the characteristics and change trends of the deviation values, the abnormal status of the equipment is classified and the abnormal status classification results are obtained; According to the abnormal state classification result, the dynamic change range in the benchmark feature model is adjusted, different alarm levels are triggered according to the real-time deviation value, and corresponding alarm signals are output. Furthermore, according to the basic parameter set, the dynamic characteristic parameters of the equipment operation state are calculated, including: Analyze the vibration signal in the basic parameter set, determine the main frequency distribution range under normal operating conditions, calculate the amplitude fluctuation range of the vibration model, and obtain dynamic characteristic parameters of the vibration signal; The temperature data in the basic parameter set is analyzed to determine the temperature fluctuation range under normal operating conditions, calculate the rate range of temperature change per unit time, and obtain the dynamic characteristic parameters of the temperature.

[0006] Furthermore, a baseline characteristic model of the equipment is established, including: Determine the variation range of key operating parameters according to the dynamic characteristic parameters of the equipment under normal operating conditions, and generate the dynamic variation range of the equipment under normal operating conditions; Conduct statistical analysis on the time series data of key operating parameters, extract the distribution law of equipment operating status, and characterize the normal operating mode of the equipment; Based on the correlation between the key operating parameters, a multi-parameter correlation model of the equipment is constructed; The dynamic variation range, distribution law and multi-parameter correlation model are integrated into a benchmark characteristic model of the equipment. Furthermore, the benchmark feature model includes: The base layer stores the original data with dynamic range and distribution rules; Model layer, which stores the associated models of dynamic feature parameters; The application layer stores parameter adjustment rules for real-time detection and alarm. Furthermore, basic parameters of the equipment operation process are obtained in real time, the real-time measurement values ​​are compared with the dynamic change range in the benchmark feature model one by one, the real-time deviation value is calculated, and the abnormality of the equipment operation state is identified, including: By acquiring the vibration signal and temperature data of the equipment in real time, the real-time measured values ​​of the main frequency, amplitude and acceleration of the vibration signal are compared with the dynamic change range in the benchmark feature model, and the deviation value of each vibration feature is calculated; Compare the real-time measured value of the temperature data with the temperature fluctuation range and the change rate range in the reference characteristic model, and calculate the deviation value of the temperature parameter; Based on whether the vibration signal and temperature deviation value exceed the dynamic change range of the benchmark characteristic model, a preliminary judgment is made as to whether the equipment operation status is normal, and it is marked as normal or abnormal.

[0007] Furthermore, according to the characteristics and change trends of the deviation values, the abnormal state of the equipment is classified, and the abnormal state classification results are obtained, including: By analyzing the numerical characteristics of the main frequency deviation, amplitude deviation and temperature change rate deviation of the vibration signal, combined with the change trend of the deviation value in the time series, the type of abnormal state can be determined; When the deviation value continues to exceed the dynamic change range of the benchmark feature model and the trend signal increases, it is classified as a persistent anomaly; When the deviation value intermittently exceeds the dynamic range and there is no obvious trend change, it is classified as an intermittent anomaly; Based on the correlation between the vibration characteristic parameters and the temperature characteristic parameters, the specific abnormal state category is identified and the abnormal state classification result is generated.

[0008] Further, according to the abnormal state classification result, the dynamic change range in the benchmark feature model is adjusted, different alarm levels are triggered according to the real-time deviation value, and corresponding alarm signals are output, including: According to the abnormal state classification result, the dynamic change range in the reference characteristic model is dynamically adjusted to adaptively scale the main frequency range, amplitude fluctuation range and temperature change rate range of the vibration signal; Comparing the real-time deviation value with the adjusted dynamic change range, and triggering a corresponding alarm level; In combination with the alarm level and the abnormal state classification result, an alarm signal is generated and output, wherein the alarm signal includes the alarm level, the abnormality category and the possible cause of the fault.

[0009] Furthermore, the method further comprises: Perform statistics and analysis on the alarm signals during the operation of the equipment, record the triggering time, alarm level and abnormal state classification results of the alarm signals, and form a historical record of alarm data; Based on the historical records, the occurrence rules of equipment failures are extracted, and the dynamic change range and parameter adjustment rules in the benchmark feature model are optimized using the rules.

[0010] An equipment failure alarm system for production management, the system comprising: The basic information set building module collects the vibration signal and temperature of the equipment under normal operating conditions to obtain the basic parameter information set; A benchmark feature model building module calculates the dynamic feature parameters of the equipment operation state according to the basic parameter set and establishes a benchmark feature model; A real-time deviation value calculation module obtains the basic parameters of the equipment operation process in real time, compares the real-time measurement values ​​with the dynamic change range in the benchmark feature model one by one, calculates the real-time deviation value, and identifies the abnormality of the equipment operation state; The abnormal classification result acquisition module classifies the abnormal status of the equipment according to the characteristics and change trends of the deviation value and obtains the abnormal status classification result; The alarm signal trigger output module adjusts the dynamic change range in the benchmark feature model according to the abnormal state classification result, triggers different alarm levels according to the real-time deviation value, and outputs a corresponding alarm signal. Furthermore, the real-time deviation value calculation module includes: The vibration deviation calculation unit obtains the vibration signal and temperature data of the equipment in real time, compares the real-time measured values ​​of the main frequency, amplitude and acceleration of the vibration signal with the dynamic change range in the reference characteristic model, and calculates the deviation value of the vibration characteristic; The temperature deviation calculation unit compares the real-time measurement value of the temperature data with the temperature fluctuation range and the change rate range in the reference characteristic model to calculate the deviation value of the temperature parameter; The preliminary state judgment unit preliminarily judges whether the equipment operation state is normal according to whether the vibration signal and the temperature deviation value exceed the dynamic change range of the reference characteristic model, and marks it as normal state or abnormal state.

[0011] The technical solution of the present invention can achieve the following technical effects: It effectively solves the problems in existing technologies that are unable to adapt to dynamic changes in operating conditions, are difficult to analyze deviation characteristics and trends, and lack abnormal classification and graded alarm mechanisms. It improves the accuracy and adaptability of fault detection and provides efficient and reliable decision support for production management. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0013] Figure 1 A flow chart of a method for alarming equipment failures applied to production management; Figure 2 A schematic diagram of a process for calculating dynamic characteristic parameters of the operating status of a device; Figure 3 A schematic diagram of the process for establishing a baseline characteristic model of a device; Figure 4 A schematic diagram of a process for calculating real-time deviation values ​​and identifying abnormalities in the operating status of equipment; Figure 5 A flowchart for obtaining abnormal state classification results; Figure 6 A schematic diagram of a process for adjusting a reference characteristic model and outputting a corresponding alarm signal; Figure 7 A flow chart of subsequent optimization steps of an equipment failure alarm method applied to production management. DETAILED DESCRIPTION

[0014] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0016] Embodiment 1 like Figure 1 As shown, the present invention provides an equipment failure alarm method applied to production management, the method comprising: S1: collect the vibration signal and temperature of the equipment under normal operating conditions to obtain a basic parameter information set; Specifically, vibration sensors are installed at key parts of the equipment, such as the bearing positions of rotating parts, to record the vibration signals of the equipment under normal operating conditions; at the same time, temperature sensors are arranged in heat-sensitive areas of the equipment, such as near the motor housing or radiator, to measure the temperature data during operation. During the stable operation of the equipment, vibration signals and temperature data are continuously collected. The recording range of vibration signals covers the possible frequency characteristics of the equipment, and the temperature data records changes at time intervals; then, the main frequency, amplitude, acceleration and peak parameters are extracted from the vibration signal, and the average temperature, fluctuation range and change rate are extracted from the temperature data. All data are integrated to form a basic parameter information set to provide a basis for subsequent equipment operation status analysis and feature modeling.

[0017] S2: Calculate the dynamic characteristic parameters of the equipment operation status based on the basic parameter set and establish a benchmark characteristic model; Specifically, the key dynamic features related to vibration signals and temperature data in the equipment operating status are extracted. These dynamic feature parameters are used to describe the changing patterns of the equipment under normal operating conditions, and a baseline feature model that reflects the normal operating status of the equipment is constructed. The model defines the dynamic change range and distribution patterns of the equipment operation, and provides a reference standard for the comparison of deviation values ​​and the identification of abnormal conditions in real-time monitoring. At the same time, the baseline feature model also has dynamic adaptability, and the system's adaptability to complex operating conditions and the accuracy of fault detection can be improved through model adjustment, thereby laying the foundation for the subsequent links of equipment fault alarm.

[0018] S3: Obtain the basic parameters of the equipment operation process in real time, compare the real-time measurement values ​​with the dynamic change range in the benchmark feature model one by one, calculate the real-time deviation value, and identify the abnormality of the equipment operation status; Specifically, by real-time monitoring of equipment operation data, it is possible to quickly determine whether it deviates from the normal range, thereby achieving continuous tracking of the equipment operation status and preliminary abnormality identification. The calculation results of the deviation value provide basic data for subsequent abnormal status classification and alarm triggering, while effectively improving the monitoring system's sensitivity and detection accuracy to operation abnormalities.

[0019] S4: classify the abnormal state of the equipment according to the characteristics and change trend of the deviation value, and obtain the abnormal state classification result; Specifically, this step accurately identifies the specific type and nature of the abnormal state, such as persistent anomalies, intermittent anomalies, or multi-parameter coupled anomalies, and determines the development direction and severity of the anomaly based on the changing trend of the deviation value.

[0020] S5: According to the abnormal state classification result, the dynamic change range in the benchmark feature model is adjusted, different alarm levels are triggered according to the real-time deviation value, and corresponding alarm signals are output. Specifically, according to the classification results of the abnormal state, the dynamic change range in the benchmark feature model is dynamically adjusted to adapt it to the current operating state and operating characteristics of the equipment. The adjusted dynamic change range is compared with the real-time deviation value to trigger an alarm level that adapts to the severity of the abnormality and generate an alarm signal. The output alarm signal not only includes the alarm level, but also the abnormality category and possible causes of the failure.

[0021] As a preferred embodiment of the above, Figure 2 As shown, according to the basic parameter set, the dynamic characteristic parameters of the equipment operation status are calculated, including: A10: Analyze the vibration signal in the basic parameter set, determine the main frequency distribution range under normal operating conditions, calculate the amplitude fluctuation range of the vibration model, and obtain the dynamic characteristic parameters of the vibration signal; A20: Analyze the temperature data in the basic parameter set, determine the temperature fluctuation range under normal operating conditions, calculate the rate range of temperature change per unit time, and obtain the dynamic characteristic parameters of the temperature.

[0022] Specifically, the dynamic characteristic parameters of the equipment's operating state are calculated based on the basic parameter set, including the dynamic characteristic parameters of the vibration signal and the dynamic characteristic parameters of the temperature. For the vibration signal, its original data is extracted from the basic parameter set, and firstly, denoising is performed by filtering and other methods to ensure the accuracy and effectiveness of the signal; then the vibration signal is analyzed in the frequency domain to extract the main frequency components and determine the main frequency distribution range under normal operating conditions; at the same time, the amplitude fluctuation range is calculated in the time domain, including the maximum value, minimum value and mean value, so as to form the dynamic characteristic parameters of the vibration signal. For temperature data, its continuous acquisition values ​​are extracted from the basic parameter set, and outliers are eliminated to eliminate sensor errors; then the temperature fluctuation range of the equipment under normal operating conditions is statistically analyzed, and the temperature change rate range per unit time is calculated to extract the dynamic parameters of the thermal characteristics of the equipment.

[0023] As a preferred embodiment of the above, Figure 3 As shown, a baseline characteristic model of the equipment is established, including: B10: According to the dynamic characteristic parameters of the equipment under normal operating conditions, determine the variation range of key operating parameters and generate the dynamic variation range of the equipment under normal operating conditions; B20: Statistical analysis of the time series data of key operating parameters is performed to extract the distribution law of the equipment operating status and characterize the normal operating mode of the equipment; B30: Based on the correlation between key operating parameters, a multi-parameter correlation model of the equipment is constructed; B40: Integrate the dynamic change range, distribution law and multi-parameter correlation model into the benchmark characteristic model of the equipment. Specifically, according to the dynamic characteristic parameters extracted from the equipment under normal operating conditions, the variation range of key operating parameters is determined, including the main frequency distribution range of the vibration signal, the amplitude fluctuation range, and the temperature fluctuation range and change rate range. These variation ranges are integrated into the dynamic variation range of the equipment under normal operating conditions, which is used to describe the basic fluctuation characteristics of the equipment operating state; statistical analysis is performed on the time series data of key operating parameters, including calculating characteristic values ​​such as mean, standard deviation and change trend, and extracting the distribution law of the equipment operating state. For example, by statistically analyzing the frequency distribution of the main frequency of the vibration signal and the fluctuation characteristics of the temperature data, a probability distribution model of the equipment operating parameters is generated to characterize the normal operating mode of the equipment; based on the correlation between the key operating parameters, the vibration signal and the temperature characteristic parameters are jointly analyzed, for example, whether the change of the main frequency of the vibration is significantly associated with the temperature fluctuation rate is analyzed, and a multi-parameter correlation model is constructed to describe the coordinated change characteristics between the equipment operating parameters; the dynamic variation range, the distribution law of the operating state and the multi-parameter correlation model are integrated into the equipment's baseline characteristic model, which includes the parameter range and distribution characteristics of the equipment under normal operating conditions, as well as the dynamic correlation between multiple parameters, as a standard for subsequent real-time monitoring and abnormal identification.

[0024] As a preferred embodiment of the above, the reference feature model includes: The base layer stores the original data with dynamic range and distribution rules; Model layer, which stores the associated models of dynamic feature parameters; The application layer stores parameter adjustment rules for real-time detection and alarm. Specifically, in the basic layer, the original data of the dynamic change range and distribution law of the device under normal operation is stored, for example, the basic data of key operating parameters such as the main frequency distribution range, amplitude fluctuation range, temperature fluctuation range and change rate range of the vibration signal are stored. At the same time, the distribution law of key operating parameters obtained by time series statistical analysis is recorded, including statistical features such as mean, standard deviation and change trend. The data of the basic layer is the core original basis of the benchmark feature model. The model layer is used to store the multi-parameter association model built based on the correlation between dynamic feature parameters. In the model layer, the dynamic correlation relationship between the vibration signal and the temperature feature parameters is recorded, such as how the change of the main frequency of vibration affects the characteristics of temperature rate fluctuation. At the same time, the mathematical description form and association rules of the multi-parameter association model are stored to provide model support for the subsequent comprehensive evaluation of the equipment status; the application layer is used to store parameter adjustment rules for real-time detection and alarm. This layer contains rules for dynamically adjusting the benchmark feature model according to the abnormal state classification results and environmental conditions, such as appropriately expanding the dynamic change range under high load or high temperature conditions, or narrowing the change range under stable operating conditions to improve detection sensitivity. The data of the application layer directly supports real-time status monitoring and triggering of alarm levels.

[0025] As a preferred embodiment of the above, Figure 4 As shown, step S3, real-time acquisition of basic parameters of the equipment operation process, comparison of the real-time measurement values ​​with the dynamic change range in the benchmark feature model one by one, calculation of the real-time deviation value, and identification of abnormal equipment operation status, including: S31: by acquiring the vibration signal and temperature data of the device in real time, the real-time measured values ​​of the main frequency, amplitude and acceleration of the vibration signal are compared with the dynamic change range in the reference characteristic model, and the deviation value of each vibration characteristic is calculated; S32: comparing the real-time measurement value of the temperature data with the temperature fluctuation range and the change rate range in the reference characteristic model, and calculating the deviation value of the temperature parameter; S33: Preliminarily determine whether the equipment operation status is normal based on whether the vibration signal and the temperature deviation value exceed the dynamic change range of the reference characteristic model, and mark it as normal or abnormal.

[0026] Specifically, the vibration signal of the equipment is collected in real time, including the main frequency, amplitude and acceleration. The real-time main frequency value collected is compared with the dynamic change range of the main frequency stored in the benchmark characteristic model, and the deviation value of the main frequency is calculated. At the same time, the real-time measurement values ​​of the amplitude and acceleration are respectively compared with the corresponding ranges in the benchmark characteristic model to calculate the amplitude deviation value and the acceleration deviation value; the temperature data of the equipment is collected in real time, including the instantaneous temperature value and the change trend in the time series, and the real-time measurement value of the temperature is compared with the temperature fluctuation range stored in the benchmark characteristic model to calculate the temperature deviation value. At the same time, the temperature change rate of continuous sampling is compared with the change rate range in the benchmark characteristic model to calculate the rate deviation value. These deviation values ​​are used to describe whether the thermal characteristics of the equipment during operation are abnormal; all deviation values ​​of the vibration signal and temperature are comprehensively analyzed to determine whether any deviation value exceeds the dynamic change range of the benchmark characteristic model. If all deviation values ​​are within the dynamic change range, the equipment operation status is marked as normal; if at least one deviation value exceeds the range, the equipment is marked as abnormal.

[0027] As a preferred embodiment of the above, Figure 5 As shown, step S4, classifying the abnormal state of the equipment according to the characteristics and change trend of the deviation value, and obtaining the abnormal state classification result, including: S41: By analyzing the numerical characteristics of the main frequency deviation, amplitude deviation and temperature change rate deviation of the vibration signal and combining the change trend of the deviation value in the time series, the abnormal state type is determined; S42: When the deviation value continues to exceed the dynamic change range of the benchmark feature model and the trend signal increases, it is classified as a persistent anomaly; S43: When the deviation value intermittently exceeds the dynamic range and there is no obvious trend change, it is classified as intermittent anomaly; S44: Based on the correlation between the vibration characteristic parameters and the temperature characteristic parameters, identify the specific abnormal state category and generate an abnormal state classification result.

[0028] Specifically, the vibration signal deviation value and temperature change rate deviation value calculated in real time are comprehensively analyzed to extract their numerical features, such as the size, distribution and fluctuation amplitude of the deviation value. At the same time, through time series analysis, the variation trend of the deviation value over time is monitored to determine whether it is continuously growing, steadily fluctuating or intermittently fluctuating. When the deviation value continues to exceed the dynamic variation range of the benchmark characteristic model for a certain period of time, and the variation trend of the deviation value is increasing, the equipment state is determined to be a continuous abnormality. Such abnormalities usually reflect the existence of increasingly serious problems in the operation of the equipment, such as excessive load or component wear. When the deviation value exceeds the dynamic variation range only in certain time intervals, and the variation trend does not show obvious growth or stable fluctuation, the equipment state is determined to be an intermittent abnormality. Such abnormalities may be caused by occasional environmental interference or short-term abnormal fluctuations in the operation of the equipment. Based on the dynamic correlation between vibration signals and temperature data, specific abnormal states are further classified. For example, by analyzing whether the fluctuation of the main frequency of the vibration signal is accompanied by a significant change in the temperature change rate, it is identified whether the abnormality is a temperature abnormality caused by vibration or a vibration problem caused by temperature abnormality, thereby classifying it into vibration abnormality, temperature abnormality or coupling abnormality, and generating detailed abnormal state classification results.

[0029] As a preferred embodiment of the above, Figure 6 As shown, step S5, according to the abnormal state classification result, adjusts the dynamic change range in the benchmark feature model, triggers different alarm levels according to the real-time deviation value, and outputs corresponding alarm signals, including: S51: dynamically adjusting the dynamic change range in the reference characteristic model according to the abnormal state classification result, and adaptively scaling the main frequency range, amplitude fluctuation range and temperature change rate range of the vibration signal; S52: comparing the real-time deviation value with the adjusted dynamic change range, and triggering a corresponding alarm level; S53: Generate and output an alarm signal based on the alarm level and abnormal state classification result. The alarm signal includes the alarm level, abnormality category and possible fault cause.

[0030] Specifically, based on the abnormal state classification results, the characteristics of the current equipment operating state are judged, and the dynamic change range in the baseline feature model is adaptively scaled. For example, when the equipment operating load increases or the ambient temperature fluctuates greatly, the main frequency range and amplitude fluctuation range of the vibration signal are appropriately expanded to adapt to the current operating state and avoid false alarms. When the operating state is stable, the dynamic change range is narrowed to improve the detection sensitivity. For temperature characteristics, based on the abnormal state classification results, the temperature fluctuation range and change rate range are adjusted to ensure that the model dynamically adapts to the current working conditions; the deviation values ​​calculated in real time during the operation of the equipment are compared one by one with the adjusted dynamic change range, and the corresponding alarm level is triggered according to the size of the deviation value and the severity of the abnormal state. The alarm levels include: Level 1 warning: The deviation value is slightly out of range, indicating that there may be potential abnormalities; Level 2 warning: The deviation value is significantly beyond the range, and the equipment operation may be abnormal; Level 3 fault alarm: The deviation value is far beyond the range, indicating that there is a serious problem in the operation of the equipment and it needs to be dealt with immediately.

[0031] Generate an alarm signal based on the triggered alarm level and abnormal state classification results. The alarm signal includes: Alarm level: indicates the severity of the abnormality; Abnormality category: indicates the type of abnormality in combination with the classification results, such as vibration abnormality, temperature abnormality or coupling abnormality; Possible fault cause: Based on the adjustment of the dynamic change range and the classification of abnormal states, provide possible fault diagnosis tips (such as bearing wear, overload or poor heat dissipation).

[0032] As a preferred embodiment of the above, Figure 7 As shown, the method also includes: C10: Statistics and analysis of alarm signals during equipment operation, recording the triggering time, alarm level and abnormal status classification results of alarm signals, and forming a historical record of alarm data; C20: Based on historical records, extract the occurrence patterns of equipment failures, and use the patterns to optimize the dynamic change range and parameter adjustment rules in the benchmark feature model.

[0033] Specifically, through statistics and analysis of historical records, high-frequency alarm types are identified, the time distribution of alarm triggering and the impact of the operating environment on the alarm are analyzed, and the patterns of equipment failure are extracted. For example, it is found that the main frequency deviation of the vibration signal is more likely to trigger anomalies under high-load conditions, or the abnormal temperature change rate is highly correlated with ambient temperature fluctuations. Based on these patterns, the dynamic change range and parameter adjustment rules of the benchmark feature model are optimized. For example, the main frequency range under high-frequency alarm conditions is expanded, the temperature change rate range under specific time periods is narrowed, or stricter monitoring rules are applied under high-risk conditions. Through continuous optimization, the benchmark feature model can more accurately adapt to the long-term operating characteristics of the equipment and improve the system's detection sensitivity to equipment anomalies and alarm accuracy.

[0034] Embodiment 2 Based on the same inventive concept as the equipment failure alarm method applied to production management in the aforementioned embodiment, the present invention also provides an equipment failure alarm system applied to production management, the system comprising: The basic information set building module collects the vibration signal and temperature of the equipment under normal operating conditions to obtain the basic parameter information set; The benchmark feature model building module calculates the dynamic feature parameters of the equipment operation status according to the basic parameter set and establishes the benchmark feature model; The real-time deviation value calculation module obtains the basic parameters of the equipment operation process in real time, compares the real-time measurement values ​​with the dynamic change range in the benchmark feature model one by one, calculates the real-time deviation value, and identifies the abnormality of the equipment operation status; The abnormal classification result acquisition module classifies the abnormal status of the equipment according to the characteristics and change trends of the deviation value and obtains the abnormal status classification result; The alarm signal triggers the output module, which adjusts the dynamic change range in the benchmark feature model according to the abnormal state classification results, triggers different alarm levels according to the real-time deviation value, and outputs the corresponding alarm signal. The above-mentioned alarm system in the present invention can effectively implement the equipment failure alarm method applied to production management, and the technical effects that can be achieved are as described in the above-mentioned embodiments, which will not be repeated here.

[0035] As a preferred embodiment of the above, the real-time deviation value calculation module includes: The vibration deviation calculation unit obtains the vibration signal and temperature data of the equipment in real time, compares the real-time measured values ​​of the main frequency, amplitude and acceleration of the vibration signal with the dynamic change range in the reference characteristic model, and calculates the deviation value of the vibration characteristic; The temperature deviation calculation unit compares the real-time measurement value of the temperature data with the temperature fluctuation range and the change rate range in the reference characteristic model to calculate the deviation value of the temperature parameter; The preliminary state judgment unit preliminarily judges whether the equipment operation state is normal according to whether the vibration signal and the temperature deviation value exceed the dynamic change range of the reference characteristic model, and marks it as normal state or abnormal state.

[0036] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.

[0037] Although the present application has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined herein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application.

[0038] Obviously, those skilled in the art can make various changes and modifications 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 equivalent technologies, the present application is intended to include these modifications and variations.

Claims

1. A method for alarming equipment failures applied to production management, characterized in that: include: Collect the vibration signal and temperature of the equipment under normal operating conditions to obtain a basic parameter information set; According to the basic parameter set, dynamic characteristic parameters of the equipment operation state are calculated, and a benchmark characteristic model is established; Acquire basic parameters of the equipment operation process in real time, compare the real-time measurement values ​​with the dynamic change range in the benchmark feature model one by one, calculate the real-time deviation value, and identify abnormalities in the equipment operation state; According to the characteristics and change trends of the deviation values, the abnormal status of the equipment is classified and the abnormal status classification results are obtained; According to the abnormal state classification result, the dynamic change range in the benchmark feature model is adjusted, different alarm levels are triggered according to the real-time deviation value, and corresponding alarm signals are output.

2. The equipment failure alarm method for production management according to claim 1 is characterized in that: Calculating the dynamic characteristic parameters of the equipment operation state according to the basic parameter set includes: Analyze the vibration signal in the basic parameter set, determine the main frequency distribution range under normal operating conditions, calculate the amplitude fluctuation range of the vibration model, and obtain dynamic characteristic parameters of the vibration signal; The temperature data in the basic parameter set is analyzed to determine the temperature fluctuation range under normal operating conditions, calculate the rate range of temperature change per unit time, and obtain the dynamic characteristic parameters of the temperature.

3. The equipment failure alarm method for production management according to claim 1 is characterized in that: Build a baseline characteristic model of the equipment, including: Determine the variation range of key operating parameters according to the dynamic characteristic parameters of the equipment under normal operating conditions, and generate the dynamic variation range of the equipment under normal operating conditions; Conduct statistical analysis on the time series data of key operating parameters, extract the distribution law of equipment operating status, and characterize the normal operating mode of the equipment; Based on the correlation between the key operating parameters, a multi-parameter correlation model of the equipment is constructed; The dynamic variation range, distribution law and multi-parameter correlation model are integrated into a benchmark characteristic model of the equipment.

4. The equipment failure alarm method for production management according to claim 3 is characterized in that: The benchmark feature model includes: The base layer stores the original data with dynamic range and distribution rules; Model layer, which stores the associated models of dynamic feature parameters; The application layer stores parameter adjustment rules for real-time detection and alarm.

5. The equipment failure alarm method for production management according to claim 1 is characterized in that: The basic parameters of the equipment operation process are obtained in real time, the real-time measurement values ​​are compared with the dynamic change range in the benchmark feature model one by one, the real-time deviation value is calculated, and the abnormality of the equipment operation status is identified, including: By acquiring the vibration signal and temperature data of the equipment in real time, the real-time measured values ​​of the main frequency, amplitude and acceleration of the vibration signal are compared with the dynamic change range in the benchmark feature model, and the deviation value of each vibration feature is calculated; Compare the real-time measured value of the temperature data with the temperature fluctuation range and the change rate range in the reference characteristic model, and calculate the deviation value of the temperature parameter; Based on whether the vibration signal and temperature deviation value exceed the dynamic change range of the benchmark characteristic model, a preliminary judgment is made as to whether the equipment operation status is normal, and it is marked as normal or abnormal.

6. The equipment failure alarm method for production management according to claim 1, characterized in that: According to the characteristics and change trends of the deviation values, the abnormal status of the equipment is classified and the abnormal status classification results are obtained, including: By analyzing the numerical characteristics of the main frequency deviation, amplitude deviation and temperature change rate deviation of the vibration signal, combined with the change trend of the deviation value in the time series, the type of abnormal state can be determined; When the deviation value continues to exceed the dynamic change range of the benchmark feature model and the trend signal increases, it is classified as a persistent anomaly; When the deviation value intermittently exceeds the dynamic range and there is no obvious trend change, it is classified as an intermittent anomaly; Based on the correlation between the vibration characteristic parameters and the temperature characteristic parameters, the specific abnormal state category is identified and the abnormal state classification result is generated.

7. The equipment failure alarm method for production management according to claim 1, characterized in that: According to the abnormal state classification result, the dynamic change range in the benchmark feature model is adjusted, different alarm levels are triggered according to the real-time deviation value, and corresponding alarm signals are output, including: According to the abnormal state classification result, the dynamic change range in the reference characteristic model is dynamically adjusted to adaptively scale the main frequency range, amplitude fluctuation range and temperature change rate range of the vibration signal; Comparing the real-time deviation value with the adjusted dynamic change range, and triggering a corresponding alarm level; In combination with the alarm level and the abnormal state classification result, an alarm signal is generated and output, wherein the alarm signal includes the alarm level, the abnormality category and the possible cause of the fault.

8. The equipment failure alarm method for production management according to claim 1, characterized in that: The method also includes: Perform statistics and analysis on the alarm signals during the operation of the equipment, record the triggering time, alarm level and abnormal state classification results of the alarm signals, and form a historical record of alarm data; Based on the historical records, the occurrence rules of equipment failures are extracted, and the dynamic change range and parameter adjustment rules in the benchmark feature model are optimized using the rules.

9. An equipment failure alarm system used in production management, characterized in that: The system comprises: The basic information set building module collects the vibration signal and temperature of the equipment under normal operating conditions to obtain the basic parameter information set; A benchmark feature model building module calculates the dynamic feature parameters of the equipment operation state according to the basic parameter set and establishes a benchmark feature model; A real-time deviation value calculation module obtains the basic parameters of the equipment operation process in real time, compares the real-time measurement values ​​with the dynamic change range in the benchmark feature model one by one, calculates the real-time deviation value, and identifies the abnormality of the equipment operation state; The abnormal classification result acquisition module classifies the abnormal status of the equipment according to the characteristics and change trends of the deviation value and obtains the abnormal status classification result; The alarm signal trigger output module adjusts the dynamic change range in the benchmark feature model according to the abnormal state classification result, triggers different alarm levels according to the real-time deviation value, and outputs a corresponding alarm signal.

10. The equipment failure alarm system for production management according to claim 9, characterized in that: The real-time deviation value calculation module includes: The vibration deviation calculation unit obtains the vibration signal and temperature data of the equipment in real time, compares the real-time measured values ​​of the main frequency, amplitude and acceleration of the vibration signal with the dynamic change range in the reference characteristic model, and calculates the deviation value of the vibration characteristic; The temperature deviation calculation unit compares the real-time measurement value of the temperature data with the temperature fluctuation range and the change rate range in the reference characteristic model to calculate the deviation value of the temperature parameter; The preliminary state judgment unit preliminarily judges whether the equipment operation state is normal according to whether the vibration signal and the temperature deviation value exceed the dynamic change range of the reference characteristic model, and marks it as normal state or abnormal state.

Images