Workshop operation state real-time monitoring management and control system

Abstract

The invention, which relates to the technical field of workshop supervision, discloses a workshop operation state real-time monitoring management and control system comprising a data acquisition processing module, an analysis processing module, a monitoring early warning module and a central control module. The data acquisition and processing module is used for acquiring vibration data generated by the mechanical equipment, processing the acquired vibration data, generating a vibration data set and interconnecting the vibration data set with the analysis and processing module; and the analysis processing module is used for carrying out superposition noise reduction processing on the obtained vibration data set, calculating a superposition noise reduction processing result, obtaining a position difference value and a position difference value variance, calculating a module length through the position difference value variance, obtaining the module length, calculating an abnormal score Abn, and judging a workshop operation state and an equipment operation state. And the workshop operation state and the equipment operation state data are sent to the monitoring and early warning module.

Description

Technical Field

[0001] The present invention relates to the technical field of workshop supervision, and in particular to a real-time monitoring and control system for workshop operation status. Background Art

[0002] With the development of Industry 4.0 and smart manufacturing, more and more companies are beginning to adopt automation and digital tools to achieve a higher level of real-time monitoring and control. For example, big data analysis, artificial intelligence technology and cloud computing platforms are used to process massive amounts of data to make more accurate predictions and decisions. After searching, the Chinese patent number CN117826717A discloses a machine shop equipment management system and method, which has the functions of collecting the capacity information, status information and task information of each device in the machine shop, analyzing and statistically obtaining corresponding monitoring information based on the collected information and displaying it; and providing the functions of adding, querying, editing and deleting task reports based on the information collected by the data processing module and the monitoring information; assigning tasks to the equipment in the machine shop based on the information collected by the data processing module and the monitoring information, and analyzing and statistically obtaining corresponding monitoring information based on the collected capacity information, status information and task information of each device in the machine shop, so as to monitor the capacity, operation status and task completion status of the equipment in the machine shop in real time, realize effective monitoring and management of the equipment, and ensure the reliable, safe and stable operation of the equipment, and realize task reporting and planned operations based on the collected information and monitoring information, so as to make task reporting and task allocation conform to the real-time status of the equipment, which is more flexible and reasonable; however, there is a lack of corresponding equipment abnormality detection methods, and there is a lack of effective monitoring management and early warning of equipment abnormalities, so that the equipment lacks corresponding emergency control plans during operation; After searching, the Chinese patent number CN113299042B discloses a safety warning system for industrial electrical frequency conversion equipment, which has the function of analyzing the working data of the frequency conversion equipment through a data analysis module, obtaining the operating temperature value and operating vibration value of the frequency conversion equipment, classifying the operating temperature value with a temperature higher than the temperature threshold into an abnormal set, classifying the operating vibration value with a vibration higher than the vibration threshold into an abnormal set, performing data analysis on the operating temperature value and operating vibration value in the abnormal set, calculating the mean temperature change and the mean vibration change of the frequency conversion equipment, substituting the mean temperature change and the mean vibration change into a formula to calculate the operating value of the frequency conversion equipment when it is working; however, it lacks the capture of vibration analysis interference at different points of the equipment and superposition noise reduction processing. In the acquisition of vibration data, there is a certain degree of interference, so the probability of misjudging the equipment failure is relatively high, and it focuses more on the threshold judgment of basic indicators (such as temperature and vibration), and it is difficult to sensitively capture subtle changes in the equipment, especially for equipment failures that require early warning and preventive maintenance; After searching, the Chinese patent number CN108415381A discloses a distributed remote monitoring system and monitoring method for a machining workshop, which has the function of setting fault monitoring warning points, quality inspection warning points and tool replacement warning points for each device through the equipment warning control module; the equipment warning control module monitors the fault monitoring warning points, and when the device is about to reach the fault warning point, it prompts to perform fault inspection; the equipment warning control module monitors the quality inspection warning points, and when the equipment processing time exceeds the set value or the cumulative number of completed items exceeds the set value, the monitoring system controls the device to not work and prompts to perform quality inspection; the equipment warning control module monitors the tool replacement warning points, and when the tool working time of the CNC lathe exceeds the set value or the cumulative number of completed items exceeds the set value, it prompts to perform tool change operation; it mainly relies on preset thresholds and counters to trigger warnings, for example, when a specific working time or number of completed items is reached, it prompts to change tools or perform quality inspection; this method is more of a rule-based reactive maintenance, lacking dynamic evaluation of the equipment's operating status.

[0003] At the same time, traditional methods may rely on manual records or simple sensors, which may lead to inaccurate data or untimely updates. Due to the lack of corresponding monitoring capabilities, when abnormal situations occur, decision makers often find it difficult to take quick action. Maintaining a complex monitoring system requires professional technicians. Faced with rapidly changing market demands and technological advances, traditional monitoring systems may find it difficult to quickly find the location of equipment abnormalities, and the response methods are difficult to quickly give response opinions to solve abnormal situations in the operation of mechanical equipment. In view of the above technical defects, a solution is now proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time monitoring and control system for workshop operation status to solve the above-mentioned technical defects. The present invention obtains vibration data of different monitoring points generated by workshop machinery and equipment, and performs superposition noise reduction processing on the vibration data of different monitoring points, calculates the average position values ​​of different monitoring points, reduces the influence of noise, and effectively smoothes out random noise by calculating the average position value of the monitoring points to make the signal clearer. The average position value is subjected to noise reduction processing again, and the processed frequency domain data is converted into time series data. The abnormal score Abn is calculated through the position difference value, and whether the abnormal score is abnormal is judged, data warning information is obtained, and data of the warning information is sent and presented, and the workshop operation is controlled and coordinated.

[0005] The purpose of the present invention can be achieved by the following technical solutions: a real-time monitoring and control system for workshop operation status, a data acquisition and processing module, an analysis and processing module, a monitoring and early warning module and a central control module; A data acquisition and processing module is used to acquire vibration data generated by mechanical equipment, process the acquired vibration data, generate a vibration data set, and output the vibration data set; The analysis and processing module performs superposition noise reduction processing on the vibration data set, and calculates the superposition noise reduction processing results to obtain the position difference value and the position difference variance, and calculates the modulus through the position difference variance, calculates the abnormal score Abn, determines the workshop operation status and equipment operation status, and outputs the workshop operation status and equipment operation status data; The monitoring and early warning module is used to obtain data on workshop operation status and equipment operation status, and output the obtained early warning information; The central control module is used to obtain data transmitted by the data acquisition and processing module, the analysis and processing module, and the monitoring and early warning module, and to manage and coordinate workshop operations.

[0006] Preferably, the vibration data collection process is as follows: Vibration data from at least three different monitoring points are obtained through a three-axis acceleration sensor and a high-precision timer. The vibration data from three different points are measured. The vibration data include the position values ​​and timestamp t of the x-axis, y-axis, and z-axis. The timestamp t is obtained through the built-in high-precision timer. The timestamp t is the time point at the moment. The position values ​​of the x-axis, y-axis, and z-axis are obtained through the three-axis acceleration sensor. The vibration data of different monitoring points are obtained, denoted as h. The vibration data include the origin coordinates and the relative position.

[0007] Preferably, the process of obtaining the origin coordinates and relative position in the vibration data is as follows: Before the mechanical equipment is operated, the three-axis accelerometer records the position values ​​of the x-axis, y-axis and z-axis as the origin coordinates. When the mechanical equipment generates vibration during operation, the three-axis accelerometer obtains the vibration data within the continuous timestamp t, as well as the relative positions of the x-axis, y-axis and z-axis relative to the origin coordinates, and packages the vibration data within the continuous timestamp t into a vibration data set.

[0008] Preferably, the vibration data set is subjected to superposition noise reduction processing as follows: By obtaining the vibration data sets of different monitoring points at timestamp t, superposition and noise reduction processing are performed, the vibration data sets of different monitoring points are spatially aligned, and the average position values ​​of different monitoring points are calculated by superposition of different monitoring points. .

[0009] Preferably, after obtaining the average position values ​​of different monitoring points, the noise reduction process is performed as follows: By obtaining the average position values ​​of different monitoring points under the actual operating state of the mechanical equipment The average position values ​​under the actual operating state within the continuous time stamp t are obtained and sorted into average position vibration data sets, and vibration-time data sets under the actual state are established respectively; At the same time, obtain the position value of the mechanical equipment under the ideal operating state , and organize the position values ​​under the ideal operating state within the continuous time stamp t0 into a vibration data set, and establish the vibration-time data set under the ideal state respectively; The vibration-time data set of the mechanical equipment under ideal conditions is compared with the vibration-time data set under actual conditions, the frequency range of the signal and noise is distinguished, the noise part is removed, and the processed frequency domain data is converted into time series data.

[0010] Preferably, the process of obtaining the superimposed noise reduction processing result and calculating the position difference value and the position difference variance is as follows: The position difference value is calculated by obtaining the average position vibration data after superimposing the noise reduction processing results and the difference between the ideal position vibration data. The position difference value calculation formula is: ; in, is the position difference value; and the position difference variance is calculated by calculating the position difference value ; Preferably, the process of calculating the modulus length is as follows: Get the data modulus length in the position difference variance respectively and the data modulus length of the position value under the ideal operating state , the formula is: ;

[0011] In the formula, is the data modulus length in x, y and z in the position difference variance, It is the data modulus length of x, y and z in the position value under the ideal operating condition.

[0012] Preferably, the process of calculating the abnormal score Abn and judging the workshop operation status and equipment operation status is as follows: Through Obtain and calculate the outlier scores for different timestamps t by obtaining The anomaly score Abn is calculated by the mode length of the data in x, y and z in the variance and the mode length of the data in x, y and z in the position value under the ideal operating state. The formula is:

[0013] in, is the data modulus length in x, y and z in the position difference variance, is the data modulus length of x, y and z in the position value under the ideal operating state. When the actual vibration data set coincides with the ideal vibration data set, the anomaly score is 1, that is, the anomaly score of 1 is used as the judgment threshold to judge whether the anomaly score is abnormal: When the anomaly score is less than or equal to 1, it means that the data point is a normal value; When the anomaly score is greater than 1, it indicates that the data point is an outlier and a warning message is generated.

[0014] Preferably, the process of sending and presenting the warning information is as follows: By obtaining the warning information from the analysis and processing module, the mechanical equipment is self-checked for abnormalities, the position difference value at the continuous timestamp t where the abnormal score Abn is located, and the database of abnormal position difference values ​​of the mechanical equipment are obtained, the position difference value is compared with the data of the abnormal position difference value in the database, and the warning information is automatically generated and sent to the central control module.

[0015] Preferably, the process of control and coordination of workshop operations is as follows; Obtain monitoring and early warning information. When receiving the early warning information, adjust the data collection interval of the data acquisition and processing module and the analysis and processing frequency of the vibration data, coordinate and manage the communication and data exchange between the sub-modules, and coordinate and control the data acquisition system, data analysis platform and user interface based on the collected data.

[0016] The beneficial effects of the present invention are as follows: (1) The present invention obtains vibration data from different monitoring points generated by workshop machinery and equipment, performs superposition and noise reduction processing on the vibration data from different monitoring points, calculates the average position values ​​of different monitoring points, and reduces the influence of noise. By calculating the average position value of the monitoring points, the random noise is effectively smoothed out to make the signal clearer, and the average position value is subjected to noise reduction processing again, so that there are fewer interference waveforms in the vibration data after noise reduction, which is conducive to judging abnormalities of mechanical equipment.

[0017] (2) The present invention converts the processed frequency domain data into time series data, and calculates the abnormality score Abn through the position difference value, so as to judge whether the abnormality score is abnormal. The vibration data of different monitoring points generated by the workshop machinery and equipment are obtained to obtain the operating status of the equipment, and the vibration data running under the ideal state are aligned and compared to obtain the operating status of the machinery and equipment, and timely issue early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The present invention will be further described below in conjunction with the accompanying drawings; Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example: See Figure 1 As shown, this embodiment provides a real-time monitoring and control system for workshop operation status, including the following modules: The data acquisition and processing module is used to obtain vibration data generated by mechanical equipment. The vibration data is the mechanical signal generated by the workshop mechanical equipment when it runs in three-dimensional space. The collected vibration data is processed to generate a vibration data set, and the vibration data set is interconnected with the analysis and processing module. The vibration data are obtained from different monitoring points, which are denoted as h, and there are at least three different monitoring points. Vibration data at three different points are measured through a three-axis acceleration sensor and a high-precision timer. The vibration data includes the position values ​​and timestamp t of the x-axis, y-axis, and z-axis. The timestamp t is obtained through the built-in high-precision timer. The timestamp t is the time point at the moment. The position values ​​of the x-axis, y-axis, and z-axis are obtained through the three-axis acceleration sensor. The triaxial acceleration sensor is fixedly installed inside the workshop machinery and equipment to measure the acceleration changes in three mutually perpendicular directions during the vibration of the machinery and equipment; The high-precision timer is set inside the three-axis acceleration sensor and interconnected with the three-axis acceleration sensor, using the piezoelectric effect of the quartz crystal to generate a stable oscillation frequency to monitor the frequency and time data; Before the mechanical equipment is operated, the position values ​​of the x-axis, y-axis and z-axis of the three-axis acceleration sensor are recorded as the origin coordinates. When the mechanical equipment generates vibration during operation, the three-axis acceleration sensor obtains the vibration data within the continuous time stamp t, as well as the relative positions of the x-axis, y-axis and z-axis relative to the origin coordinates. The position value acquisition frequency of the three-axis acceleration sensor is 30 Hz, and the vibration data within the continuous time stamp t is packaged into a vibration data set. Example: In the workshop, large rice husking equipment is equipped with triaxial accelerometers by identifying at least three key monitoring points, including the base of the main drive motor, the bracket of the rice husking roller (or sand disc), and the transmission belt or chain tensioner. By firmly mounting the triaxial accelerometers at the selected locations, ensure that they can accurately sense the vibration conditions in the area. The base of the main drive motor: This is the connection point between the motor and the equipment, and usually has significant vibrations; The support of the rice husking roller (or sand tray): It is the core working part of the equipment, and its vibration can reflect the working status of the equipment; Belt or chain tensioner: It is a key part of power transmission, and its vibration can reflect the health of the transmission system; The high-precision timer is used to set the acceleration sensor to sample at a frequency of 30 Hz, synchronize the data of each sensor, and provide an accurate timestamp. Before the rice huller is started, the initial acceleration values ​​of each sensor in the three axes of X, Y, and Z are recorded as the origin coordinates. Each sampling will generate a set of data points containing the timestamp t and the acceleration values ​​of the X, Y, and Z axes. The vibration data set is saved in CSV, JSON, and XML file formats that are easy to read and process, which is convenient for subsequent data analysis software to load. Compression algorithms are used to reduce storage space usage and speed up data transmission. The analysis and processing module is used to perform superposition noise reduction processing on the acquired vibration data set, and calculate the superposition noise reduction processing result to obtain the position difference value, associate the position difference value with the time stamp t, analyze the change of the position difference value within the continuous time stamp t, monitor the change of the position difference value in real time, judge the workshop operation status and equipment operation status, and send the workshop operation status and equipment operation status data to the monitoring and early warning module; By obtaining the vibration data sets of different monitoring points at timestamp t, superposition and noise reduction processing is performed, and the vibration data sets of different monitoring points are spatially aligned using image registration technology. By superimposing different monitoring points, the average position values ​​of different monitoring points are calculated to reduce the impact of noise. The formula is: ; in, is the vibration data of different monitoring points, the average position value after superposition, H is the total number of monitoring points, h is the number of the current monitoring point, h = 1, 2..., H, To obtain the position value at the monitoring point h, the random noise is effectively smoothed out by calculating the average position value of the monitoring points, making the signal clearer, which is beneficial for subsequent data analysis and reducing the extreme difference of vibration data at different monitoring points at the same timestamp t. After obtaining the average position values ​​of different monitoring points, the average position values ​​of different monitoring points are subjected to noise reduction processing; By obtaining the average position values ​​of different monitoring points under the actual operating state of the mechanical equipment The average position values ​​under the actual operating state within the continuous time stamp t are sorted into the average position vibration data set, and the vibration-time data set under the actual state is established respectively, that is, the relationship between the position values ​​of the x-axis, y-axis, and z-axis and the time stamp t: the relationship of xt, the relationship of yt, and the relationship of zt; at the same time, the position values ​​of the mechanical equipment under the ideal operating state are obtained , and organize the position values ​​under the ideal operating state within the continuous time stamp t0 into a vibration data set, and establish the vibration-time data set under the ideal state, that is, the relationship between the position values ​​of the x0 axis, y0 axis, and z0 axis and the time stamp t0: the relationship between x0-t0, the relationship between y0-t0, and the relationship between z0-t0; Compare the vibration-time data set of the mechanical equipment under ideal state and the vibration-time data set under actual state, perform discrete Fourier transform respectively, use numpy.fft.fft function to perform Fourier transform, convert the time domain data into frequency domain, check the spectrum to determine the location of the main components of the signal, usually noise will appear in the higher frequency part, compare with the ideal vibration data set, distinguish the frequency range of signal and noise, remove the noise part, and convert the processed frequency domain data into time series data; Discrete Fourier transform: a linear transformation method that converts a time series signal of finite length into its spectrum representation, revealing the distribution of the signal at different frequency components to analyze the characteristics of the signal; numpy.fft.fft function: a function in the NumPy library used to perform a one-dimensional discrete Fourier transform (DFT). It accepts a complex or real number sequence as input and returns the DFT result of the sequence. The DFT result is also a complex sequence, containing the complex values ​​of the input signal at different frequency components, including the modulus of the complex value representing the amplitude of the corresponding frequency component, and the phase representing the phase angle of these components. Code example: Get a set of ideal vibration-time data sets and actual vibration-time data sets when the rice husker is running, read the data files, and use Python language as an example to use the NumPy library for calculation: ```Python import pandas as pd # Load ideal data ideal_data = pd.read_csv('ideal_vibration.csv') # Load data in actual state actual_data = pd.read_csv('actual_vibration.csv') # Perform Fourier transform on ideal data ideal_fft = np.fft.fft(ideal_data['vibration']) # Perform Fourier transform on actual data actual_fft = np.fft.fft(actual_data['vibration']) Python # Calculate the power spectral density of ideal data ideal_psd = np.abs(ideal_fft)**2 # Calculate the power spectral density of the actual data actual_psd = np.abs(actual_fft)**2 ```Python import matplotlib.pyplot as plt # Create frequency array freqs = np.fft.fftfreq(len(ideal_data)) plt.figure(figsize=(10, 5)) plt.plot(freqs[:len(freqs) / / 2], ideal_psd[:len(freqs) / / 2]) plt.title('Ideal State Power Spectral Density') plt.xlabel('Frequency [Hz]') plt.ylabel('Power spectral density') plt.show() plt.figure(figsize=(10, 5)) plt.plot(freqs[:len(freqs) / / 2], actual_psd[:len(freqs) / / 2]) plt.title('Actual State Power Spectral Density') plt.xlabel('Frequency [Hz]') plt.ylabel('Power spectral density') plt.show() ``` Use NumPy's `fft.fft()` function to perform Fourier transform on the two sets of data. It should be noted that the result of the Fourier transform contains complex numbers, and the real and imaginary parts correspond to the sine and cosine components; By observing the spectrum, the vibration data sets of different monitoring points are spatially aligned using image registration technology. By superimposing different monitoring points, the average position values ​​of different monitoring points are calculated to reduce the impact of noise. Then use the inverse Fourier transform (`np.fft.ifft()`) to convert the processed frequency domain data back to the time domain; The average position vibration data after the superposition noise reduction processing is obtained, and the difference between the average position vibration data and the ideal position vibration data is calculated to calculate the position difference value. The position difference value includes: the vibration caused by external interference of the mechanical equipment and the resonance caused by external noise. The formula for obtaining the position difference value is: ; in is the position difference value; By obtaining the position difference value, the position difference variance is calculated, and the formula is: ; in is the variance, which reflects the fluctuation of the position difference value, t is the timestamp, H-1 is the sample calculated for the previous timestamp t, and T is the number of consecutive timestamps t {t1, t2, t3...t T}, t=1, 2, 3...T, Subtract the square of the average position vibration data from the difference value at each timestamp t to eliminate the influence of positive and negative values, amplify the degree of difference, and obtain ; Example: The vibration data of large rice hullers during operation is collected regularly and compared with the pre-defined ideal vibration data. An abnormality score is obtained by calculating the difference between the actual data and the ideal data and their statistical characteristics. When the score exceeds the preset threshold, it indicates that the equipment may be abnormal, which may be caused by wear, imbalance, looseness, bearing failure or other mechanical problems. At this time, the system should automatically alarm and prompt maintenance personnel to check and repair; Wear: As bearings, gears and other parts wear more, more high-frequency components will appear in the vibration signal. At the same time, wear will lead to increased friction, which will cause an increase in vibration intensity. Unbalance: causes the rotating parts to produce a noticeable vibration every time they rotate. This vibration is periodic and its frequency is proportional to the rotation speed. The amplitude of the vibration usually increases with the increase of the rotation speed. Looseness: Looseness can cause broadband vibrations in the entire structure. This vibration has no obvious frequency characteristics, but contains a large number of frequency components. The vibration caused by looseness is usually random and has no fixed periodicity. Bearing failure: usually generates specific frequency components in the vibration signal, such as rolling element passing frequency (BPFO), inner race fault frequency (BPFI), etc. Bearing failure is often accompanied by impact vibration, which is manifested as a spike in the vibration signal; Through Obtain and calculate the anomaly scores at different timestamps t. By obtaining the data modulus lengths of x, y, and z in the position difference variance and the data modulus lengths of x, y, and z in the position value under the ideal operating state, calculate the anomaly score Abn. The formula is: ; in, is the data modulus length in x, y and z in the position difference variance, is the data modulus length of x, y and z in the position value under the ideal operating state. When the actual vibration data set coincides with the ideal vibration data set, the anomaly score is 1, that is, the anomaly score of 1 is used as the judgment threshold to judge whether the anomaly score is abnormal: When the anomaly score is less than or equal to 1, it means that the data point is a normal value; When the anomaly score is greater than 1, it indicates that the data point is an outlier and generates a warning message; and The modulus length is obtained by using the Euclidean norm, and the formula is: ; ; The monitoring and early warning module is used to obtain early warning information, send and present the early warning information, and send the early warning information to the central control module; By obtaining the warning information of the analysis and processing module, the mechanical equipment is self-checked for abnormalities. Once the abnormal warning information issued by the analysis and processing module is received, the position difference value on the continuous time stamp t where the abnormal score Abn is located and the database of the abnormal position difference value of the mechanical equipment are obtained, and the position difference value is compared with the data of the abnormal position difference value in the database. The vibration signal is converted into the frequency domain, and then the characteristic frequency, amplitude, etc. are compared. The analysis is performed directly on the time series, and the statistical characteristics such as peak value, root mean square value, kurtosis coefficient, etc. are compared. The energy distribution of the signal is calculated, especially the energy proportion in different frequency bands is compared; When the position difference value matches the data in the abnormal position difference value database, the abnormal name of the mechanical equipment in the database is obtained, and the mechanical equipment solution and decision deployment in the database are matched, and the response decision in the database is implemented. At the same time, the system will automatically generate early warning information, which will be sent to the relevant control system or personnel, including email notifications, text messages, and mobile application push in various forms to ensure that relevant personnel can receive the alarm in time. In addition to sending early warning information, the monitoring and early warning module clearly displays the status and early warning information of the equipment through the user interface, and records the early warning events, formulates a data backup plan, and regularly backs up the early warning information to the external storage medium or remote server for later analysis and report generation; The central control module is used to obtain the data transmitted by the data acquisition and processing module, the analysis and processing module, and the monitoring and early warning module, and to control and coordinate the workshop operations; The central control module can provide decision support functions by acquiring early warning information. Before acquiring the early warning information issued by the early warning module, the data information of each module is monitored in real time, and the abnormal data of the workshop is monitored in real time. After acquiring the early warning information issued by the early warning module, the data collection interval of the data collection and processing module is reduced, and the analysis and processing frequency of the vibration data is increased. By acquiring the collected data, the vibration data is collected in real time, and the data with continuous timestamp t is collected, the collection of mechanical equipment vibration data is increased; Usually, three-axis acceleration sensors and high-precision timers stop collecting vibration data after collecting data with continuous timestamp t, and continue collecting vibration data after a period of time E. When early warning information is obtained, the interval of E is shortened and the amount of vibration data collected is increased. Sufficient vibration data can be obtained in a smaller time interval. By real-time monitoring of sufficient vibration data, it is possible to determine whether the mechanical equipment has any abnormal conditions. By performing negative feedback adjustment on the analysis and processing module, the data acquisition module is regulated, and the communication and data exchange between the modules are coordinated and managed to ensure the efficient operation of the entire system. Information from various data sources is received. Based on the collected data, the data acquisition system, data analysis platform, and user interface are coordinated to ensure the smooth operation of the entire system.

[0021] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above are only preferred specific implementations of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, make equivalent replacements or changes, which should be covered within the protection scope of the present invention.

Claims

1. The real-time monitoring and control system for workshop operation status is characterized by: It includes data acquisition and processing module, analysis and processing module, monitoring and early warning module and central control module; A data acquisition and processing module is used to acquire vibration data generated by mechanical equipment, process the acquired vibration data, generate a vibration data set, and output the vibration data set; The analysis and processing module performs superposition noise reduction processing on the vibration data set, and calculates the superposition noise reduction processing results to obtain the position difference value and the position difference variance, and calculates the modulus through the position difference variance, calculates the abnormal score Abn, determines the workshop operation status and equipment operation status, and outputs the workshop operation status and equipment operation status data; The monitoring and early warning module is used to obtain data on workshop operation status and equipment operation status, and output the obtained early warning information; The central control module is used to obtain data transmitted by the data acquisition and processing module, the analysis and processing module, and the monitoring and early warning module, and to manage and coordinate workshop operations.

2. The real-time monitoring and control system for workshop operation status according to claim 1 is characterized in that: The vibration data collection process is as follows: Vibration data of at least three different monitoring points are obtained through a three-axis acceleration sensor and a high-precision timer. The vibration data includes the position values ​​and timestamp t of the x-axis, y-axis, and z-axis. The timestamp t is obtained through the built-in high-precision timer. The timestamp t is the time point at the moment. The position values ​​of the x-axis, y-axis, and z-axis are obtained through the three-axis acceleration sensor. The vibration data of different monitoring points are obtained, denoted as h. The vibration data includes the origin coordinates and the relative position.

3. The real-time monitoring and control system for workshop operation status according to claim 2 is characterized in that: The process of obtaining the origin coordinates and relative position in the vibration data is as follows: Before the mechanical equipment is operated, the three-axis accelerometer records the position values ​​of the x-axis, y-axis and z-axis as the origin coordinates. When the mechanical equipment generates vibration during operation, the three-axis accelerometer obtains the vibration data within the continuous timestamp t, as well as the relative positions of the x-axis, y-axis and z-axis relative to the origin coordinates, and packages the vibration data within the continuous timestamp t into a vibration data set.

4. The real-time monitoring and control system for workshop operation status according to claim 1 is characterized in that: The process of superposition denoising of vibration data set is as follows: By obtaining the vibration data sets of different monitoring points at timestamp t, superposition and noise reduction processing are performed, the vibration data sets of different monitoring points are spatially aligned, and the average position values ​​of different monitoring points are calculated by superposition of different monitoring points. .

5. The real-time monitoring and control system for workshop operation status according to claim 4 is characterized in that: After obtaining the average position values ​​of different monitoring points, the noise reduction process is as follows: By obtaining the average position values ​​of different monitoring points under the actual operating state of the mechanical equipment The average position values ​​under the actual operating state within the continuous time stamp t are obtained and sorted into average position vibration data sets, and vibration-time data sets under the actual state are established respectively; At the same time, obtain the position value of the mechanical equipment under the ideal operating state , and organize the position values ​​under the ideal operating state within the continuous time stamp t0 into a vibration data set, and establish the vibration-time data set under the ideal state respectively; The vibration-time data set of the mechanical equipment under ideal conditions is compared with the vibration-time data set under actual conditions, the frequency range of the signal and noise is distinguished, the noise part is removed, and the processed frequency domain data is converted into time series data.

6. The real-time monitoring and control system for workshop operation status according to claim 5 is characterized in that: The process of obtaining the superposition noise reduction processing results and calculating the position difference value and the position difference variance is as follows: The position difference value is calculated by obtaining the average position vibration data after superimposing the noise reduction processing results and the difference between the ideal position vibration data. The position difference value calculation formula is: ； in, is the position difference value; and the position difference variance is calculated by calculating the position difference value .

7. The real-time monitoring and control system for workshop operation status according to claim 6 is characterized in that: The process of calculating the modulus length is as follows: Get the data modulus length in the position difference variance respectively and the data modulus length of the position value under the ideal operating state , the formula is: ； ； In the formula, is the data modulus length in x, y and z in the position difference variance, It is the data modulus length of x, y and z in the position value under the ideal operating condition.

8. The real-time monitoring and control system for workshop operation status according to claim 1 is characterized in that: The process of calculating the abnormal score Abn and judging the workshop operation status and equipment operation status is as follows: Through Obtain and calculate the outlier scores for different timestamps t by obtaining The anomaly score Abn is calculated by the mode length of the data in x, y and z in the variance and the mode length of the data in x, y and z in the position value under the ideal operating state. The formula is: ； in, is the data modulus length in x, y and z in the position difference variance, is the data modulus length of x, y and z in the position value under the ideal operating state. When the actual vibration data set coincides with the ideal vibration data set, the anomaly score is 1, that is, the anomaly score of 1 is used as the judgment threshold to judge whether the anomaly score is abnormal: When the anomaly score is less than or equal to 1, it means that the data point is a normal value; When the anomaly score is greater than 1, it indicates that the data point is an outlier and a warning message is generated.

9. The real-time monitoring and control system for workshop operation status according to claim 1 is characterized in that: The process of sending and presenting early warning information is as follows: By obtaining the warning information from the analysis and processing module, the mechanical equipment is self-checked for abnormalities, the position difference value at the continuous timestamp t where the abnormal score Abn is located, and the database of abnormal position difference values ​​of the mechanical equipment are obtained, the position difference value is compared with the data of the abnormal position difference value in the database, and the warning information is automatically generated and sent to the central control module.

10. The real-time monitoring and control system for workshop operation status according to claim 1 is characterized in that: The process of control and coordination of workshop operations is as follows; Obtain monitoring and early warning information. When receiving the early warning information, adjust the data collection interval of the data acquisition and processing module and the analysis and processing frequency of the vibration data, coordinate and manage the communication and data exchange between the sub-modules, and coordinate and control the data acquisition system, data analysis platform and user interface based on the collected data.

Images