Monitoring and maintaining method and system for forging and pressing equipment

Abstract

The invention discloses a monitoring and maintaining method and system for forging and pressing equipment, and relates to the technical field related to the forging and pressing equipment, and the method comprises the steps: obtaining a plurality of pieces of data sensing information, analyzing the plurality of pieces of data sensing information, and generating a plurality of data monitoring signals. And traversing the plurality of data monitoring signals to carry out frequency spectrum transformation, drawing a frequency spectrum change trend chart, and carrying out operation analysis according to the frequency spectrum change trend chart to obtain equipment health state data. And performing aging analysis based on the equipment health state data to obtain an equipment recession coefficient, performing fault prediction according to the equipment recession coefficient, and determining an equipment fault mode. And formulating a maintenance report to perform resource scheduling optimization on the forging and pressing equipment based on the equipment fault mode in combination with the equipment health state data. The technical problem that the operation state and potential fault mode recognition accuracy of the forging and pressing equipment is low due to the fact that a monitoring and maintaining method of the forging and pressing equipment in the prior art is difficult to efficiently process and analyze multi-source data from a wireless sensor network is solved.

Description

Technical Field

[0001] The present application relates to the technical field related to forging equipment, and in particular to a monitoring and maintenance method and system for forging equipment. Background Art

[0002] Forging equipment plays a key role in industrial manufacturing, and its operating efficiency and reliability directly affect production quality and cost control. Traditional forging equipment monitoring methods mainly rely on regular manual inspections and data collection from a single type of sensor. This method is not only time-consuming and labor-intensive, but also difficult to detect potential equipment failures in a timely manner, resulting in increased maintenance costs and increased risks of production interruptions. With the development of the Internet of Things and wireless sensor network technologies, more and more sensors are installed in key parts of forging equipment, such as presses, dies, and cooling systems, to achieve real-time data collection through wireless sensor networks. However, the processing and analysis of massive multi-source sensor data is complex, making it difficult to efficiently and accurately identify the operating status and potential failure modes of forging equipment.

[0003] Therefore, in the prior art, it is difficult for the monitoring and maintenance method of forging equipment to efficiently process and analyze multi-source data from wireless sensor networks, resulting in a technical problem of low accuracy in identifying the operating status and potential failure modes of the forging equipment. Summary of the invention

[0004] This application provides a monitoring and maintenance method and system for forging equipment, which solves the technical problem that the monitoring and maintenance method for forging equipment in the prior art is difficult to efficiently process and analyze multi-source data from wireless sensor networks, resulting in low accuracy in identifying the operating status and potential fault patterns of forging equipment. The real-time collection and efficient transmission of multi-source data are achieved through wireless sensor networks, and the spectrum change trend chart and recursive analysis method are combined to achieve accurate monitoring of the operating status of forging equipment and fault prediction, which significantly improves the scientificity and timeliness of equipment maintenance, prolongs the service life of equipment and reduces maintenance costs.

[0005] The present application provides a monitoring and maintenance method for forging equipment, the method comprising: collecting data on the forging equipment through a wireless sensor network to obtain multiple data sensor information; transmitting the multiple data sensor information to a central monitoring platform for analysis to generate multiple data monitoring signals for the forging equipment; traversing the multiple data monitoring signals to perform spectrum transformation, drawing a spectrum change trend graph, performing operation analysis based on the spectrum change trend graph to obtain equipment health status data; performing aging analysis on the forging equipment based on the equipment health status data to obtain an equipment decay coefficient, performing fault prediction based on the equipment decay coefficient, and determining an equipment failure mode; based on the equipment failure mode and in combination with the equipment health status data, feeding back to the central monitoring platform, formulating a maintenance report, and optimizing resource scheduling for the forging equipment according to the maintenance report.

[0006] In the implementation, the multiple data sensor information is transmitted to the central monitoring platform for analysis to generate multiple data monitoring signals of the forging equipment. The method includes: traversing the multiple data sensor information and matching them with N sensor nodes of the wireless sensor network, packaging the multiple data sensor information according to the node matching results to generate N data packets, where N is an integer greater than 1; performing data aggregation according to a time series based on the N data packets to generate M data packets, where M is an integer greater than 0 and less than N; transmitting the M data packets to the central monitoring platform for data synchronization to generate data synchronization results, and standardizing the M data packets according to the data synchronization results to generate M standard data; performing operation analysis on the forging equipment according to the M standard data to obtain multiple operation characteristics, converting the M standard data based on the multiple operation characteristics, and determining the multiple data monitoring signals.

[0007] In the implementation, the multiple data monitoring signals are traversed to perform spectrum transformation, and a spectrum change trend graph is drawn. The method includes: traversing the multiple data monitoring signals for analysis, extracting multiple time domain signals, and the multiple time domain signals have a corresponding relationship with the multiple data monitoring signals; using Fourier transform function to convert the multiple time domain signals into multiple frequency domain signals, and the multiple frequency domain signals have multiple spectrum information; calculating according to the multiple spectrum information to obtain multiple signal amplitude spectra and multiple signal phase spectra; bandpass filtering the multiple spectrum information based on the multiple signal amplitude spectra combined with the multiple signal phase spectra to generate multiple filtered signals, performing fluctuation analysis based on the multiple filtered signals, and extracting multiple spectrum peaks; performing spectrum calculation on the multiple filtered signals according to the multiple spectrum peaks, and drawing the spectrum change trend graph.

[0008] In the implementation, spectrum calculation is performed on the multiple filtered signals according to the multiple spectrum peaks, and the spectrum change trend diagram is drawn. The method includes: dividing the multiple filtered signals according to the sampling frequency and determining a plurality of time windows; performing calculation based on the multiple time windows in combination with the multiple spectrum peaks to obtain frequency distribution data; setting a first coordinate axis according to the multiple time windows, and setting a second coordinate axis according to the frequency distribution data; setting a coordinate origin, integrating the first coordinate axis and the second coordinate axis according to the coordinate origin, constructing a spectrum coordinate system, filling the multiple spectrum information into the spectrum coordinate system according to the time series, and obtaining the spectrum change trend diagram.

[0009] In the implementation, an operation analysis is performed according to the spectrum change trend graph to obtain equipment health status data, and the method includes: traversing the spectrum change trend graph to perform vibration operation analysis to generate a first analysis result; traversing the spectrum change trend graph to perform load operation analysis to generate a second analysis result; traversing the spectrum change trend graph to perform temperature operation analysis to generate a third analysis result; recursively performing the first analysis result, the second analysis result, and the third analysis result to generate an abnormal operation parameter set; mapping the abnormal operation parameter set to the spectrum change trend graph to perform spectrum change analysis to generate a fourth analysis result, and performing status identification on the forging equipment according to the fourth analysis result to generate the equipment health status data.

[0010] In an implementation, an aging analysis is performed on the forging equipment based on the equipment health status data to obtain an equipment decay coefficient, and the method includes: performing a vibration score based on the first analysis result in combination with the fourth analysis result to generate a first health score; performing a load score based on the second analysis result in combination with the fourth analysis result to generate a second health score; performing a temperature score based on the third analysis result in combination with the fourth analysis result to generate a third health score; performing a decay calculation based on the first health score, the second health score, and the third health score to obtain a decay rate; fitting the equipment health status data with historical operating data to determine the equipment remaining service life data; performing an aging calculation based on the equipment remaining service life data at the decay rate to obtain the equipment decay coefficient.

[0011] In the implementation, fault prediction is performed based on the equipment decay coefficient to determine the equipment failure mode, and the method includes: performing variable analysis according to the decay rate based on the equipment decay coefficient to obtain a decay change curve diagram; performing decay identification according to the decay change curve diagram to determine multiple decay modes, traversing the multiple decay modes and training in combination with the equipment health status data to build a decision tree model; synchronizing the equipment remaining service life data to the decision tree model and performing regression in combination with the multiple decay modes to obtain a predicted probability of failure occurrence; determining multiple decay stages according to the decay change curve diagram and the multiple decay modes, traversing the multiple decay stages and performing association identification in accordance with the predicted probability of failure occurrence to generate the equipment failure mode.

[0012] The present application also provides a monitoring and maintenance system for forging equipment, including: a data acquisition module, which is used to collect data on the forging equipment through a wireless sensor network to obtain multiple data sensor information; a data analysis module, which is used to transmit the multiple data sensor information to a central monitoring platform for analysis, and generate multiple data monitoring signals for the forging equipment; a trend chart acquisition module, which is used to traverse the multiple data monitoring signals to perform spectrum transformation, draw a spectrum change trend chart, perform operation analysis based on the spectrum change trend chart, and obtain equipment health status data; a fault mode acquisition module, which is used to perform aging analysis on the forging equipment based on the equipment health status data, obtain equipment degradation coefficient, perform fault prediction based on the equipment degradation coefficient, and determine equipment failure mode; a scheduling optimization module, which is used to feed back to the central monitoring platform based on the equipment failure mode in combination with the equipment health status data, formulate a maintenance report, and optimize resource scheduling for the forging equipment according to the maintenance report.

[0013] The monitoring and maintenance method and system of forging equipment proposed in this application is to collect data from the forging equipment through a wireless sensor network to obtain multiple data sensor information; transmit the multiple data sensor information to the central monitoring platform for analysis to generate multiple data monitoring signals of the forging equipment; traverse the multiple data monitoring signals to perform spectrum transformation, draw a spectrum change trend chart, perform operation analysis based on the spectrum change trend chart, and obtain equipment health status data; perform aging analysis on the forging equipment based on the equipment health status data to obtain the equipment decay coefficient, perform fault prediction based on the equipment decay coefficient, and determine the equipment failure mode; based on the equipment failure mode and the equipment health status data, feedback is sent to the central monitoring platform to formulate a maintenance report, and optimize the resource scheduling of the forging equipment according to the maintenance report. This solves the technical problem that the monitoring and maintenance method of forging equipment in the prior art is difficult to efficiently process and analyze multi-source data from the wireless sensor network, resulting in low accuracy in identifying the operating status and potential failure modes of the forging equipment. Through the wireless sensor network, real-time collection and efficient transmission of multi-source data are realized. Combined with the spectrum trend chart and recursive analysis method, accurate monitoring of the operating status of forging equipment and fault prediction are achieved, which significantly improves the scientificity and timeliness of equipment maintenance, extends the service life of equipment and reduces maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A flow chart of a monitoring and maintenance method for forging equipment provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of the structure of a monitoring and maintenance system for forging equipment provided in an embodiment of the present application.

[0017] Explanation of reference numerals: data acquisition module 11 , data analysis module 12 , trend chart acquisition module 13 , fault mode acquisition module 14 , scheduling optimization module 15 . DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The present application embodiment provides a monitoring and maintenance method and system for forging equipment, such as Figure 1 As shown, the method includes: Data is collected from the forging equipment through a wireless sensor network to obtain multiple data sensor information; the multiple data sensor information is transmitted to a central monitoring platform for analysis to generate multiple data monitoring signals of the forging equipment; the multiple data monitoring signals are traversed to perform spectrum transformation, a spectrum change trend graph is drawn, and operation analysis is performed according to the spectrum change trend graph to obtain equipment health status data; Temperature sensors, vibration sensors and pressure sensors are installed at key parts of the forging equipment (such as presses, dies and cooling systems). Real-time data collection of the forging equipment is performed through a network composed of a large number of sensor nodes, namely a wireless sensor network, to obtain multiple data sensing information. Subsequently, the multiple data sensing information is transmitted to the central monitoring platform for analysis to generate multiple data monitoring signals of the forging equipment. Each of the central monitoring platforms is a system platform for centralized processing and analysis of data from various sensors, and usually includes data storage, processing and analysis modules. Further, the multiple data monitoring signals are traversed to perform spectrum transformation and draw a spectrum change trend graph. Each spectrum change trend graph corresponds to a type of sensor data, and operation analysis is performed according to the spectrum change trend graph to obtain equipment health status data.

[0022] The method provided in the embodiment of the present application also includes: traversing the multiple data sensor information and matching them with N sensor nodes of the wireless sensor network, packaging the multiple data sensor information according to the node matching results to generate N data packets, where N is an integer greater than 1; aggregating data according to a time series based on the N data packets to generate M data packets, where M is an integer greater than 0 and less than N; transmitting the M data packets to the central monitoring platform for data synchronization to generate data synchronization results, standardizing the M data packets according to the data synchronization results to generate M standard data; performing operation analysis on the forging equipment according to the M standard data to obtain multiple operation characteristics, converting the M standard data based on the multiple operation characteristics, and determining the multiple data monitoring signals.

[0023] The multiple data sensor information is transmitted to the central monitoring platform for analysis, and multiple data monitoring signals of the forging equipment are generated. The method includes: traversing the multiple data sensor information and matching them with N sensor nodes of the wireless sensor network, where N is an integer and is the same as the number of data sensor information. The sensor node is a basic unit in the wireless sensor network, and has data acquisition, processing and communication functions. After matching the data sensor information with the sensor node, the multiple data sensor information is packaged according to the node matching result, so that the data sensor information is organized into data packets according to certain rules, and N data packets are generated, where N is an integer greater than 1, and each data packet corresponds to a type of data sensor information. Further, data aggregation is performed based on the N data packets in accordance with the time series, that is, data aggregation is performed in time order according to the start time of the data recorded in the N data packets, so that different data packets are aligned in time order, and M data packets after aggregation are obtained, and each of the M data packets contains one or more data sensor information with the same start time. Further, the M data packets are transmitted to the central monitoring platform for data synchronization, so that each of the M data packets has the same start time and end time, ensuring the time consistency of the data transmitted to the central monitoring platform, and generating a synchronization result after the synchronization is completed. Further, the M data packets are standardized according to the data synchronization result to generate M standard data.

[0024] Finally, the operation of the forging equipment is analyzed according to the M standard data to obtain multiple operation characteristics. The operation characteristics are the maximum and minimum values ​​of the electrical signals collected by the sensor. Through the correspondence between the operation characteristics and the measurement values ​​of the actual measurement objects, the M standard data are converted so that the standardized electrical data are converted into data signals to determine the multiple data monitoring signals.

[0025] The method provided in the embodiment of the present application also includes: traversing the multiple data monitoring signals for analysis, extracting multiple time domain signals, and the multiple time domain signals have a corresponding relationship with the multiple data monitoring signals; using a Fourier transform function to convert the multiple time domain signals into multiple frequency domain signals, and the multiple frequency domain signals have multiple spectrum information; calculating according to the multiple spectrum information to obtain multiple signal amplitude spectra and multiple signal phase spectra; bandpass filtering the multiple spectrum information based on the multiple signal amplitude spectra combined with the multiple signal phase spectra to generate multiple filtered signals, performing fluctuation analysis based on the multiple filtered signals, and extracting multiple spectrum peaks; performing spectrum calculation on the multiple filtered signals according to the multiple spectrum peaks, and drawing the spectrum change trend graph.

[0026] The method comprises: traversing the multiple data monitoring signals to perform spectrum transformation and drawing a spectrum change trend diagram, and the method comprises: traversing the multiple data monitoring signals to perform analysis, extracting the characteristics of the signal changing over time, and obtaining multiple time domain signals. The multiple time domain signals correspond to the multiple data monitoring signals. The multiple time domain signals are converted into multiple frequency domain signals using a Fourier transform function, and the multiple frequency domain signals have multiple spectrum information. According to the multiple spectrum information combined with the multiple operating characteristics, calculations are performed to obtain multiple signal amplitude spectra and multiple signal phase spectra, wherein the signal amplitude spectrum reflects the energy distribution of the signal, and the signal phase spectrum reflects the phase information of each frequency component of the signal. Bandpass filtering is performed on the multiple spectrum information based on the multiple signal amplitude spectra combined with the multiple signal phase spectra, wherein the parameters of the bandpass filtering frequency are selected according to the signal amplitude spectrum and the signal phase spectrum, and the parameters of the bandpass filtering of different spectrum information are different, thereby obtaining multiple filtered signals. Fluctuation analysis is performed according to the multiple filtered signals to extract multiple spectrum peaks, wherein the spectrum peak is a point in the frequency domain signal whose amplitude is significantly higher than other frequency components, and the point is usually related to a specific operating state or fault mode of the device. Finally, spectrum calculation is performed on the multiple filtered signals according to the multiple spectrum peaks, and the spectrum change trend diagram is drawn.

[0027] The method provided in the embodiment of the present application also includes: dividing the multiple filtered signals according to the sampling frequency to determine multiple time windows; performing calculations based on the multiple time windows in combination with the multiple spectrum peaks to obtain frequency distribution data; setting a first coordinate axis according to the multiple time windows, and setting a second coordinate axis according to the frequency distribution data; setting a coordinate origin, integrating the first coordinate axis and the second coordinate axis according to the coordinate origin to construct a spectrum coordinate system, filling the multiple spectrum information into the spectrum coordinate system according to the time series, and obtaining the spectrum change trend graph.

[0028] According to the sampling frequency, the corresponding division time length is set to obtain the preset division time length. The higher the sampling frequency, the shorter the corresponding division time length, and vice versa. The multiple filter signals are divided respectively according to the preset division time length, so that the filter signals are divided into multiple time windows according to the corresponding preset division time length. Calculation is performed based on the multiple time windows combined with the multiple spectrum peaks to obtain frequency distribution data. Further, a first coordinate axis is set according to the multiple time windows, and a second coordinate axis is set according to the frequency distribution data. Each time window corresponds to a section of data on the first coordinate axis, and corresponds to specific frequency data on the second coordinate axis. A coordinate origin is set, and the first coordinate axis and the second coordinate axis are integrated according to the coordinate origin to construct a spectrum coordinate system. The multiple spectrum information is filled into the spectrum coordinate system according to the time series to obtain the spectrum change trend graph.

[0029] The method provided in the embodiment of the present application also includes: traversing the spectrum change trend graph to perform vibration operation analysis and generate a first analysis result; traversing the spectrum change trend graph to perform load operation analysis and generate a second analysis result; traversing the spectrum change trend graph to perform temperature operation analysis and generate a third analysis result; recursively performing the first analysis result, the second analysis result, and the third analysis result to generate an abnormal operation parameter set; mapping the abnormal operation parameter set to the spectrum change trend graph to perform spectrum change analysis and generate a fourth analysis result, and performing status identification on the forging equipment according to the fourth analysis result to generate the equipment health status data.

[0030] According to the spectrum change trend graph, operation analysis is performed to obtain equipment health status data. The method includes: traversing the spectrum change trend graph to obtain the spectrum related to vibration, obtaining the frequency components related to vibration, such as vibration amplitude, frequency change, etc., and generating a first analysis result. Traversing the spectrum change trend graph to perform load operation analysis, obtaining the spectrum related to load, obtaining the data related to load to obtain the front load, load change trend, load volatility, etc., and generating a second analysis result, wherein the load volatility is the difference between the maximum load value and the minimum load value. Traversing the spectrum change trend graph to perform temperature operation analysis, extracting the data related to temperature from the spectrum change trend graph, and obtaining the temperature mean, temperature peak, temperature variance, etc. The first analysis result, the second analysis result, and the third analysis result are recursively analyzed to identify abnormal factors and generate an abnormal operation parameter set. The abnormal operation parameter set includes all abnormal factors in the first analysis result, the second analysis result, and the third analysis result. For example, vibration abnormality: if the equipment has abnormal vibration in certain specific frequency bands, it may indicate wear, poor matching or imbalance of mechanical parts. Load anomaly: If the load frequency fluctuates outside the normal range, it may indicate that the device is overloaded during operation or there is a device failure. Temperature anomaly: Temperature changes in the spectrum may be related to overheating or insufficient cooling of the device, usually accompanied by large high-frequency changes.

[0031] Finally, the abnormal operation parameter set is mapped to the spectrum change trend diagram for spectrum change analysis. For example, vibration frequency: normal equipment should exhibit stable low-frequency vibration characteristics. Changes with excessively high frequencies or large fluctuations usually indicate wear or failure. Relationship between temperature and vibration: The temperature changes in the spectrum diagram can be used to analyze the heat dissipation efficiency of the equipment and whether there is an overheating problem. Load fluctuation: Excessive load fluctuation may mean that the equipment's tolerance is close to its limit and there is a risk of failure. Different spectrum changes correspond to different fault categories. The corresponding fault categories are obtained based on the spectrum changes, and a fourth analysis result is generated. The state of the forging equipment is identified according to the fourth analysis result, such as abnormal load, abnormal temperature state, etc., to generate the equipment health status data, and the equipment health status data is the highest equipment health percentage of 1. The equipment health status data is the health status score corresponding to the equipment status, and different equipment statuses correspond to different status data.

[0032] The method provided in the embodiment of the present application also includes: performing vibration scoring based on the first analysis result in combination with the fourth analysis result to generate a first health score; performing load scoring based on the second analysis result in combination with the fourth analysis result to generate a second health score; performing temperature scoring based on the third analysis result in combination with the fourth analysis result to generate a third health score; performing decay calculation based on the first health score, the second health score, and the third health score to obtain a decay rate; determining the remaining service life data of the equipment using the equipment health status data; and performing aging calculation based on the remaining service life data of the equipment according to the decay rate to obtain the equipment decay coefficient.

[0033] According to the first analysis result combined with the fourth analysis result, a vibration score is performed, and the product of the vibration intensity in the first analysis result and the fourth analysis result is obtained to generate a first health score. According to the second analysis result combined with the fourth analysis result, a load score is performed, and the product of the load volatility in the second analysis result and the fourth analysis result is obtained to generate a second health score. According to the third analysis result combined with the fourth analysis result, a temperature score is performed, and the product of the temperature variance in the third analysis result and the fourth analysis result is obtained to generate a third health score. Finally, a decay calculation is performed according to the first health score, the second health score, and the third health score. The decay calculation process is a weighted summation, and the specific weight is determined according to the actual health impact ratio. For example, the higher the impact of temperature on health, the greater the corresponding weight. The decay calculation result is obtained, and a specific decay parameter interval is matched according to the decay calculation result, and the corresponding decay rate is obtained according to the decay parameter interval. Among them, different decay parameter intervals are preset to correspond to specific decay rate data. Further, the remaining service life data of the equipment is determined according to the equipment health status data, and the remaining service life data is equal to the difference between 1 and the equipment health status data multiplied by the design life. The design life is the design use time of the equipment. Based on the remaining service life data of the equipment, an aging calculation is performed according to the decay rate to obtain the equipment decay coefficient. The aging calculation formula is: ; Among them, a is the decay coefficient of the equipment at the corresponding time, b is the initial health state of the equipment, usually 1, e is the natural logarithm, λ is the decay rate, which indicates the speed of equipment decay, and t is the remaining service life. The equipment decay coefficient is an indicator to quantify the degree of equipment aging, usually ranging from 0 to 1, where: 0 means that the equipment is completely healthy and has no signs of aging. 1 means that the equipment has completely decayed or failed.

[0034] Based on the equipment health status data, an aging analysis is performed on the forging equipment to obtain the equipment degradation coefficient, and fault prediction is performed based on the equipment degradation coefficient to determine the equipment failure mode; based on the equipment failure mode combined with the equipment health status data, feedback is given to the central monitoring platform to formulate a maintenance report, and resource scheduling optimization is performed on the forging equipment according to the maintenance report.

[0035] Based on the equipment health status data, the forging equipment is subjected to aging analysis to obtain the equipment decay coefficient, and the fault prediction is performed according to the equipment decay coefficient to determine the equipment failure mode, which is the decay mode with the highest predicted failure probability of multiple decay modes. Finally, based on the equipment failure mode combined with the equipment health status data, the central monitoring platform is fed back to formulate a maintenance report, which contains specific failure modes and equipment health status data. According to the maintenance report, the forging equipment is optimized for resource scheduling, such as preventive maintenance such as regular inspection and replacement of parts to improve the operating reliability of the equipment. The technical problem that the monitoring and maintenance method of forging equipment in the prior art is difficult to efficiently process and analyze multi-source data from the wireless sensor network, resulting in low accuracy in identifying the operating status and potential fault modes of the forging equipment is solved. The real-time acquisition and efficient transmission of multi-source data are realized through the wireless sensor network, and the spectrum change trend diagram and the recursive analysis method are combined to realize the accurate monitoring and fault prediction of the operating status of the forging equipment, which significantly improves the scientificity and timeliness of equipment maintenance, prolongs the service life of the equipment and reduces the technical effect of maintenance cost.

[0036] The method provided in the embodiment of the present application also includes: performing variable analysis according to the decay rate based on the equipment decay coefficient to obtain a decay change curve diagram; performing decay identification according to the decay change curve diagram to determine multiple decay modes, traversing the multiple decay modes and training in combination with the equipment health status data to build a decision tree model; synchronizing the equipment remaining service life data to the decision tree model and performing regression in combination with the multiple decay modes to obtain a predicted probability of failure occurrence; determining multiple decay stages according to the decay change curve diagram and the multiple decay modes, traversing the multiple decay stages and performing association identification in accordance with the predicted probability of failure occurrence to generate the equipment failure mode.

[0037] According to the equipment decay coefficient, fault prediction is performed to determine the equipment failure mode. The method includes: performing variable analysis based on the equipment decay coefficient according to the decay rate, obtaining the decay coefficient data of the equipment decay coefficient changing with time at the corresponding decay rate, and obtaining a decay change curve graph, wherein the horizontal axis represents time and the vertical axis represents the decay coefficient. According to the decay change curve graph, decay recognition is performed to identify multiple decay modes corresponding to the decay change curve graph, such as bearing wear, insufficient lubrication, structural fatigue, etc. Different curve graphs correspond to one or more decay modes. Further, the multiple decay modes are traversed to combine the equipment health status data and the failure probability under the corresponding mode to perform decision tree training, and a decision tree model is constructed. The decision tree model can quickly predict the failure probability according to the equipment health status data and the decay change curve graph. The remaining service life data of the equipment is synchronized to the decision tree model and the multiple decay modes are combined for regression to obtain the predicted failure probability. According to the decay change curve graph and the multiple decay modes, multiple decay stages are determined, and the multiple decay stages are traversed to perform association recognition according to the predicted failure probability of the multiple decay modes, and the equipment failure mode is generated, and the equipment failure mode is the decay mode with the largest predicted failure probability among the multiple decay modes.

[0038] In the above, refer to Figure 1 A monitoring and maintenance method for forging equipment according to an embodiment of the present invention is described in detail. Figure 2 A monitoring and maintenance system for forging equipment according to an embodiment of the present invention is described.

[0039] A monitoring and maintenance system for forging equipment according to an embodiment of the present invention solves the technical problem that the monitoring and maintenance methods for forging equipment in the prior art are difficult to efficiently process and analyze multi-source data from wireless sensor networks, resulting in low accuracy in identifying the operating status and potential fault modes of forging equipment. Real-time collection and efficient transmission of multi-source data are achieved through wireless sensor networks, and combined with spectrum change trend graphs and recursive analysis methods, accurate monitoring of the operating status of forging equipment and fault prediction are achieved, which significantly improves the scientificity and timeliness of equipment maintenance, extends the service life of equipment and reduces maintenance costs. A monitoring and maintenance system for forging equipment includes: a data acquisition module 11, a data analysis module 12, a trend graph acquisition module 13, a fault mode acquisition module 14, and a scheduling optimization module 15.

[0040] The data acquisition module 11 is used to collect data from the forging equipment through a wireless sensor network to obtain a plurality of data sensing information; A data analysis module 12, used to transmit the plurality of data sensing information to a central monitoring platform for analysis, and generate a plurality of data monitoring signals of the forging equipment; A trend graph acquisition module 13 is used to traverse the multiple data monitoring signals to perform spectrum transformation, draw a spectrum change trend graph, perform operation analysis according to the spectrum change trend graph, and obtain equipment health status data; A failure mode acquisition module 14 is used to perform an aging analysis on the forging equipment based on the equipment health status data, obtain an equipment degradation coefficient, perform a failure prediction based on the equipment degradation coefficient, and determine an equipment failure mode; The scheduling optimization module 15 is used to formulate a maintenance report based on the equipment failure mode combined with the equipment health status data fed back to the central monitoring platform, and optimize the resource scheduling of the forging equipment according to the maintenance report.

[0041] The specific configuration of the data analysis module 12 will be described in detail below. The data analysis module 12 may further include: transmitting the multiple data sensor information to the central monitoring platform for analysis, generating multiple data monitoring signals of the forging equipment, the method including: traversing the multiple data sensor information and matching with the N sensor nodes of the wireless sensor network, packaging the multiple data sensor information according to the node matching results, generating N data packets, N is an integer greater than 1; performing data aggregation according to the time series based on the N data packets, generating M data packets, where M is an integer greater than 0 and less than N; transmitting the M data packets to the central monitoring platform for data synchronization, generating data synchronization results, and standardizing the M data packets according to the data synchronization results to generate M standard data; performing operation analysis on the forging equipment according to the M standard data, obtaining multiple operation characteristics, converting the M standard data based on the multiple operation characteristics, and determining the multiple data monitoring signals.

[0042] The specific configuration of the data analysis module 12 will be described in detail below. The data analysis module 12 further includes: traversing the multiple data monitoring signals to perform spectrum transformation and draw a spectrum change trend graph, the method includes: traversing the multiple data monitoring signals to analyze and extract multiple time domain signals, the multiple time domain signals and the multiple data monitoring signals have a corresponding relationship; using Fourier transform function to convert the multiple time domain signals into multiple frequency domain signals, the multiple frequency domain signals have multiple spectrum information; according to the multiple spectrum information, calculate to obtain multiple signal amplitude spectra and multiple signal phase spectra; based on the multiple signal amplitude spectra combined with the multiple signal phase spectra, the multiple spectrum information is band-pass filtered to generate multiple filtered signals, and fluctuation analysis is performed according to the multiple filtered signals to extract multiple spectrum peaks; the multiple filtered signals are spectrum calculated according to the multiple spectrum peaks, and the spectrum change trend graph is drawn.

[0043] The specific configuration of the data analysis module 12 will be described in detail below. The data analysis module 12 may further include: performing spectrum calculation on the multiple filtered signals according to the multiple spectrum peaks, and drawing the spectrum change trend graph, the method including: dividing the multiple filtered signals according to the sampling frequency, and determining multiple time windows; performing calculation based on the multiple time windows combined with the multiple spectrum peaks to obtain frequency distribution data; setting a first coordinate axis according to the multiple time windows, and setting a second coordinate axis according to the frequency distribution data; setting a coordinate origin, integrating the first coordinate axis and the second coordinate axis according to the coordinate origin, constructing a spectrum coordinate system, filling the multiple spectrum information into the spectrum coordinate system according to the time series, and obtaining the spectrum change trend graph.

[0044] The specific configuration of the trend chart acquisition module 13 will be described in detail below. The trend chart acquisition module 13 further includes: performing operation analysis according to the spectrum change trend chart to obtain equipment health status data, and the method includes: traversing the spectrum change trend chart to perform vibration operation analysis to generate a first analysis result; traversing the spectrum change trend chart to perform load operation analysis to generate a second analysis result; traversing the spectrum change trend chart to perform temperature operation analysis to generate a third analysis result; recursively performing the first analysis result, the second analysis result, and the third analysis result to generate an abnormal operation parameter set; mapping the abnormal operation parameter set to the spectrum change trend chart to perform spectrum change analysis to generate a fourth analysis result, and performing state identification on the forging equipment according to the fourth analysis result to generate the equipment health status data.

[0045] The specific configuration of the trend graph acquisition module 13 will be described in detail below. The trend graph acquisition module 13 further includes: performing aging analysis on the forging equipment based on the equipment health status data to obtain the equipment decay coefficient, the method including: performing vibration scoring according to the first analysis result combined with the fourth analysis result to generate a first health score; performing load scoring according to the second analysis result combined with the fourth analysis result to generate a second health score; performing temperature scoring according to the third analysis result combined with the fourth analysis result to generate a third health score; performing decay calculation according to the first health score, the second health score, and the third health score to obtain a decay rate; performing fitting according to the equipment health status data and historical operation data to determine the equipment remaining service life data; performing aging calculation according to the decay rate based on the equipment remaining service life data to obtain the equipment decay coefficient.

[0046] The specific configuration of the fault mode acquisition module 14 will be described in detail below. The fault mode acquisition module 14 further includes: performing fault prediction according to the equipment decay coefficient and determining the equipment failure mode, the method including: performing variable analysis according to the decay rate based on the equipment decay coefficient to obtain a decay change curve; performing decay identification according to the decay change curve to determine multiple decay modes, traversing the multiple decay modes and combining with the equipment health status data for training to build a decision tree model; synchronizing the equipment remaining service life data to the decision tree model and combining with the multiple decay modes for regression to obtain a predicted probability of failure; determining multiple decay stages according to the decay change curve and combining with the multiple decay modes, traversing the multiple decay stages and performing association identification according to the predicted probability of failure, and generating the equipment failure mode.

[0047] A monitoring and maintenance system for forging equipment provided by an embodiment of the present invention can execute a monitoring and maintenance method for forging equipment provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0048] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0049] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A monitoring and maintenance method for forging equipment, characterized in that: The method comprises: Data collection of forging equipment is performed through a wireless sensor network to obtain multiple data sensing information; Transmitting the plurality of data sensing information to a central monitoring platform for analysis to generate a plurality of data monitoring signals for the forging equipment; Traversing the multiple data monitoring signals to perform spectrum transformation, drawing a spectrum change trend graph, performing operation analysis according to the spectrum change trend graph, and obtaining equipment health status data; Performing aging analysis on the forging equipment based on the equipment health status data to obtain an equipment degradation coefficient, performing fault prediction based on the equipment degradation coefficient, and determining an equipment failure mode; Based on the equipment failure mode and the equipment health status data fed back to the central monitoring platform, a maintenance report is formulated, and resource scheduling optimization of the forging equipment is performed according to the maintenance report.

2. A monitoring and maintenance method for forging equipment according to claim 1, characterized in that: The plurality of data sensing information are transmitted to a central monitoring platform for analysis to generate a plurality of data monitoring signals of the forging equipment, the method comprising: Traversing the plurality of data sensor information and matching them with N sensor nodes of the wireless sensor network, and packaging the plurality of data sensor information according to the node matching result to generate N data packets, where N is an integer greater than 1; Aggregate the N data packets in time series to generate M data packets, where M is an integer greater than 0 and less than N; Transmitting the M data packets to the central monitoring platform for data synchronization to generate data synchronization results, and performing standardization processing on the M data packets according to the data synchronization results to generate M standard data; The operation of the forging equipment is analyzed according to the M standard data to obtain a plurality of operation characteristics, and the M standard data are converted based on the plurality of operation characteristics to determine the plurality of data monitoring signals.

3. A monitoring and maintenance method for forging equipment as claimed in claim 2, characterized in that: Traversing the plurality of data monitoring signals to perform spectrum transformation and draw a spectrum change trend graph, the method comprising: Traversing the multiple data monitoring signals for analysis, extracting multiple time domain signals, wherein the multiple time domain signals correspond to the multiple data monitoring signals; Using a Fourier transform function to convert the multiple time domain signals into multiple frequency domain signals, the multiple frequency domain signals having multiple frequency spectrum information; Calculate according to the multiple frequency spectrum information to obtain multiple signal amplitude spectra and multiple signal phase spectra; Performing bandpass filtering on the multiple frequency spectrum information based on the multiple signal amplitude spectra combined with the multiple signal phase spectra to generate multiple filtered signals, performing fluctuation analysis based on the multiple filtered signals to extract multiple frequency spectrum peaks; Spectra of the multiple filtered signals are calculated according to the multiple spectrum peaks, and a spectrum change trend graph is drawn.

4. A monitoring and maintenance method for forging equipment as claimed in claim 3, characterized in that: Calculating the spectrum of the multiple filtered signals according to the multiple spectrum peaks and drawing the spectrum change trend graph, the method includes: Dividing the plurality of filtered signals according to sampling frequencies to determine a plurality of time windows; Perform calculation based on the multiple time windows combined with the multiple spectrum peaks to obtain frequency distribution data; Setting a first coordinate axis according to the multiple time windows, and setting a second coordinate axis according to the frequency distribution data; A coordinate origin is set, the first coordinate axis and the second coordinate axis are integrated according to the coordinate origin, a spectrum coordinate system is constructed, the plurality of spectrum information are filled into the spectrum coordinate system according to the time series, and the spectrum change trend graph is obtained.

5. A monitoring and maintenance method for forging equipment as claimed in claim 1, characterized in that: Performing operation analysis according to the spectrum change trend diagram to obtain equipment health status data includes: Traversing the frequency spectrum change trend graph to perform vibration operation analysis and generate a first analysis result; Traversing the frequency spectrum change trend graph to perform load operation analysis and generate a second analysis result; Traversing the frequency spectrum change trend graph to perform temperature operation analysis and generate a third analysis result; Recursively perform the first analysis result, the second analysis result, and the third analysis result to generate an abnormal operation parameter set; The abnormal operation parameter set is mapped to the frequency spectrum change trend diagram to perform frequency spectrum change analysis to generate a fourth analysis result, and the state of the forging equipment is identified according to the fourth analysis result to generate the equipment health status data.

6. A monitoring and maintenance method for forging equipment as claimed in claim 5, characterized in that: Based on the equipment health status data, an aging analysis is performed on the forging equipment to obtain an equipment degradation coefficient, the method comprising: Performing vibration scoring according to the first analysis result and the fourth analysis result to generate a first health score; Perform load scoring according to the second analysis result and the fourth analysis result to generate a second health score; Performing a temperature score according to the third analysis result combined with the fourth analysis result to generate a third health score; Perform a decay calculation according to the first health score, the second health score, and the third health score to obtain a decay rate; Determine the remaining service life of the equipment by fitting the equipment health status data with the historical operation data; The equipment decay coefficient is obtained by performing an aging calculation based on the equipment remaining service life data according to the decay rate.

7. A monitoring and maintenance method for forging equipment as claimed in claim 6, characterized in that: Fault prediction is performed according to the equipment degradation coefficient to determine the equipment failure mode, the method comprising: Perform variable analysis based on the equipment decay coefficient according to the decay rate to obtain a decay change curve diagram; Performing recession identification according to the recession change curve diagram, determining multiple recession modes, traversing the multiple recession modes and combining with the equipment health status data for training, and constructing a decision tree model; Synchronizing the remaining useful life data of the equipment to the decision tree model and performing regression in combination with the multiple decay modes to obtain a predicted probability of failure occurrence; Determine multiple decay stages according to the decay change curve diagram in combination with the multiple decay modes, traverse the multiple decay stages, perform association identification according to the predicted failure occurrence probability, and generate the equipment failure mode.

8. A monitoring and maintenance system for forging equipment, characterized in that: The system comprises: A data acquisition module is used to collect data from the forging equipment through a wireless sensor network to obtain multiple data sensing information; A data analysis module, used to transmit the plurality of data sensing information to a central monitoring platform for analysis, and generate a plurality of data monitoring signals of the forging equipment; A trend graph acquisition module, used to traverse the multiple data monitoring signals to perform spectrum transformation, draw a spectrum change trend graph, perform operation analysis according to the spectrum change trend graph, and obtain equipment health status data; A failure mode acquisition module is used to perform aging analysis on the forging equipment based on the equipment health status data, obtain the equipment degradation coefficient, perform failure prediction according to the equipment degradation coefficient, and determine the equipment failure mode; The scheduling optimization module is used to formulate a maintenance report based on the equipment failure mode combined with the equipment health status data fed back to the central monitoring platform, and optimize the resource scheduling of the forging equipment according to the maintenance report.

Images