CN116880402A - Intelligent factory cooperative control system and method thereof - Google Patents
Intelligent factory cooperative control system and method thereof Download PDFInfo
- Publication number
- CN116880402A CN116880402A CN202310936330.0A CN202310936330A CN116880402A CN 116880402 A CN116880402 A CN 116880402A CN 202310936330 A CN202310936330 A CN 202310936330A CN 116880402 A CN116880402 A CN 116880402A
- Authority
- CN
- China
- Prior art keywords
- power
- time sequence
- training
- amplitude
- vibration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000003993 interaction Effects 0.000 claims abstract description 59
- 238000012806 monitoring device Methods 0.000 claims abstract description 15
- 238000010219 correlation analysis Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 96
- 238000012549 training Methods 0.000 claims description 69
- 238000012544 monitoring process Methods 0.000 claims description 32
- 230000008859 change Effects 0.000 claims description 23
- 238000009826 distribution Methods 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000000605 extraction Methods 0.000 claims description 21
- 238000013527 convolutional neural network Methods 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 12
- 238000012482 interaction analysis Methods 0.000 claims description 12
- 238000012546 transfer Methods 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 7
- 238000012098 association analyses Methods 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 238000012300 Sequence Analysis Methods 0.000 claims description 2
- 239000002356 single layer Substances 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 47
- 230000002159 abnormal effect Effects 0.000 abstract description 24
- 238000007726 management method Methods 0.000 description 22
- 238000004458 analytical method Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 10
- 238000007405 data analysis Methods 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 5
- 230000002829 reductive effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011260 co-administration Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
Abstract
The application discloses an intelligent factory cooperative control system and a method thereof, wherein the intelligent factory cooperative control system acquires power values of monitored equipment at a plurality of preset time points in a preset time period acquired by an equipment sensor, and vibration signals of the monitored equipment in the preset time period; performing collaborative correlation analysis on the power values of the plurality of preset time points and the vibration signal to obtain power-amplitude interaction characteristics; and determining whether the operating state of the monitoring device is normal based on the power-amplitude interaction characteristic. Thus, the method can help the factory to discover the abnormal condition of the equipment in time and take corresponding measures in time so as to reduce the downtime and the production loss.
Description
Technical Field
The application relates to the technical field of intelligent management and control, in particular to a cooperative management and control system and a cooperative management and control method for an intelligent factory.
Background
The intelligent factory realizes the intellectualization, automation and cooperation of production equipment through technologies such as integrated internet of things, big data analysis, artificial intelligence and the like so as to improve the production efficiency, reduce the cost and optimize the production process. In intelligent factories, equipment failure and shutdown can lead to interruption and delay of a production line, increasing maintenance and production recovery costs, while normal operation of equipment is a key to ensuring smooth operation of the production line. Therefore, monitoring the operation state of the equipment in the intelligent factory is a very important task.
Traditional intelligent plant equipment monitoring schemes typically use limited sensors to collect equipment data and rely on professionals to analyze the collected equipment data to effect monitoring of the equipment. However, since these sensors can only provide status information of a single device, they cannot provide comprehensive status information of the device, and thus cannot perform collaborative analysis between devices, resulting in low accuracy in monitoring the operation status of the devices. Moreover, in some existing collaborative analysis schemes of equipment states, a large amount of data processing and analysis work is required, which brings about a large workload, and the accuracy is difficult to guarantee. Meanwhile, the current monitoring scheme of the running state of intelligent factory equipment also has the problem of delay, and the state change of the equipment cannot be monitored in real time. This may result in equipment failure or an abnormal condition that has caused some loss before it is detected and handled.
Thus, an optimized intelligent factory collaborative management system is desired.
Disclosure of Invention
The embodiment of the application provides an intelligent factory cooperative control system and a method thereof, wherein the intelligent factory cooperative control system acquires power values of monitored equipment at a plurality of preset time points in a preset time period acquired by an equipment sensor, and vibration signals of the monitored equipment in the preset time period; performing collaborative correlation analysis on the power values of the plurality of preset time points and the vibration signal to obtain power-amplitude interaction characteristics; and determining whether the operating state of the monitoring device is normal based on the power-amplitude interaction characteristic. Thus, the method can help the factory to discover the abnormal condition of the equipment in time and take corresponding measures in time so as to reduce the downtime and the production loss.
The embodiment of the application also provides an intelligent factory cooperative control system, which comprises the following steps:
the data acquisition module is used for acquiring power values of the monitored equipment in a plurality of preset time points in a preset time period acquired by the equipment sensor and vibration signals of the monitored equipment in the preset time period;
the data interaction analysis module is used for carrying out collaborative association analysis on the power values of the plurality of preset time points and the vibration signal to obtain power-amplitude interaction characteristics; and
and the monitoring equipment state detection module is used for determining whether the operation state of the monitoring equipment is normal or not based on the power-amplitude interaction characteristics.
The embodiment of the application also provides an intelligent factory collaborative management and control method, which comprises the following steps:
acquiring power values of a monitored device acquired by a device sensor at a plurality of preset time points in a preset time period, and vibrating signals of the monitored device in the preset time period;
performing collaborative correlation analysis on the power values of the plurality of preset time points and the vibration signal to obtain power-amplitude interaction characteristics; and
based on the power-amplitude interaction characteristics, it is determined whether the operating state of the monitoring device is normal.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a block diagram of an intelligent factory collaborative management and control system according to an embodiment of the present application.
Fig. 2 is a block diagram of the data interaction analysis module in the intelligent factory cooperative control system according to an embodiment of the present application.
FIG. 3 is a block diagram of the training module in the intelligent factory collaborative management and control system according to an embodiment of the present application.
FIG. 4 is a flowchart of a smart factory collaborative management and control method according to an embodiment of the present application.
Fig. 5 is a schematic diagram of a system architecture of an intelligent factory cooperation control method according to an embodiment of the application.
FIG. 6 is a diagram of an intelligent factory collaborative management and control system according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present application and their descriptions herein are for the purpose of explaining the present application, but are not to be construed as limiting the application.
Unless defined otherwise, all technical and scientific terms used in the embodiments of the application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In describing embodiments of the present application, unless otherwise indicated and limited thereto, the term "connected" should be construed broadly, for example, it may be an electrical connection, or may be a communication between two elements, or may be a direct connection, or may be an indirect connection via an intermediate medium, and it will be understood by those skilled in the art that the specific meaning of the term may be interpreted according to circumstances.
It should be noted that, the term "first\second\third" related to the embodiment of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the application described herein may be practiced in sequences other than those illustrated or described herein.
It should be understood that an intelligent factory is a factory that utilizes advanced technology and digital means to achieve highly automated, intelligent and flexible production, by interconnecting physical devices, sensors, networks and data analysis technologies, to achieve collaboration between devices, real-time monitoring and analysis of data, and optimization and intelligent decision-making of production processes.
The main targets of the intelligent factory are to improve the production efficiency, reduce the production cost, improve the product quality and realize the flexibility and sustainable development of the production process. Key features and technical applications of intelligent factories include:
automated production, the intelligent factory utilizes automated technology to realize the automation operation and the control of production process. For example, the robot replaces manual work to carry out repeated and tedious work, and the production efficiency and the product quality are improved.
The intelligent factory connects equipment, sensors and a system together through the internet of things technology, and information communication and cooperative work among the equipment are realized. Thus, the state of the equipment can be monitored in real time, production data can be acquired, and data analysis and optimization can be performed.
Big data and analysis, intelligent factories can insight into potential problems and opportunities for improvement in the production process by collecting and analyzing large amounts of production data. Decision making and prediction models based on data analysis can help optimize production plans, predict equipment failures, and provide real-time production guidance.
Human-machine collaboration, intelligent factories encourage human-machine collaboration, i.e., close collaboration between personnel and automated equipment and systems. Personnel can interact with the intelligent system through the intelligent terminal, the wearable equipment and the like, so that monitoring, adjustment and optimization of the production process are realized.
Virtual simulation and digital twinning are utilized by the intelligent factory to model and simulate the production process in a digital environment. This helps predict production conditions, optimize production flows, and conduct fault diagnosis and preventive maintenance.
On the one hand, the intelligent factory can improve production efficiency, and the intelligent factory connects all equipment, working procedures and production lines through the technology of the Internet of things, so that cooperative work among the equipment is realized. Therefore, the production efficiency can be improved, the waste and the downtime in the production can be reduced, and the utilization rate of the production line can be improved.
On the one hand, the cost can be reduced, and the intelligent factory can realize the optimization and the fine management of the production process through an automation technology and data analysis. Therefore, the use of manpower resources can be reduced, and the production cost is reduced. Meanwhile, purchasing and inventory of raw materials can be accurately controlled through data analysis and prediction, and waste and excessive reserve of resources are avoided.
On the other hand, the quality can be improved, and the intelligent factory can monitor various indexes and key parameters in the production process in real time through data monitoring and analysis. Therefore, problems and anomalies can be found out in time, timely adjustment and correction can be performed, and the quality stability and consistency of products are improved.
On the other hand, the flexibility can be enhanced, and the smart factory can realize the rapid adjustment of the production line and the personalized customization of products through the digital technology and the design of the flexible production line. Therefore, the method can better adapt to the change of market demands, and improves the competitiveness and market response speed of enterprises.
That is, the intelligent factory collaborative management and control can help the enterprise to improve the production efficiency, reduce the cost, improve the quality and enhance the flexibility, and is very important for the competitive power and sustainable development of the enterprise. In one embodiment of the present application, fig. 1 is a block diagram of an intelligent factory collaboration management and control system provided in an embodiment of the present application. As shown in fig. 1, an intelligent factory cooperative control system 100 according to an embodiment of the application includes: a data acquisition module 110, configured to acquire power values of a monitored device acquired by a device sensor at a plurality of predetermined time points in a predetermined time period, and vibration signals of the monitored device in the predetermined time period; the data interaction analysis module 120 is configured to perform collaborative association analysis on the power values at the plurality of predetermined time points and the vibration signal to obtain a power-amplitude interaction characteristic; and a monitoring device status detection module 130, configured to determine whether the operation status of the monitoring device is normal based on the power-amplitude interaction characteristic.
In the data acquisition module 110, accuracy and reliability of the device sensor are ensured to obtain an accurate power value and a vibration signal, and meanwhile, selection of a frequency and a time point of data acquisition is considered to meet real-time monitoring requirements on the state of the device. By acquiring the power value and the vibration signal of the equipment, the running condition and the performance of the equipment can be known in real time. This provides the underlying data for subsequent data analysis and status monitoring.
In the data interaction analysis module 120, when performing the correlation analysis of the power-amplitude interaction characteristics, accuracy and integrity of data need to be considered, and meanwhile, an appropriate data analysis algorithm and model need to be selected to extract effective interaction characteristics. By performing collaborative correlation analysis on the power value and the vibration signal, the relation between the running state of the equipment and the power and vibration can be revealed. This helps to discover the early warning of equipment abnormality and trouble, improves reliability and stability of equipment.
In the monitoring device state detection module 130, when determining whether the device operation state is normal based on the power-amplitude interaction characteristic, a proper state detection model and algorithm need to be established, and at the same time, reasonable thresholds and rules need to be set to determine the abnormal situation of the device state. By detecting the state of the monitoring equipment, the abnormal and fault conditions of the equipment can be found in time, and the predictive maintenance and repair of the equipment are realized. This helps to reduce equipment downtime and line interruptions, improving production efficiency and quality stability.
The data acquisition module, the data interaction analysis module and the monitoring equipment state detection module in the intelligent factory cooperative management and control system have important attention points and beneficial effects in the aspects of data acquisition, data analysis and equipment state monitoring respectively, and the data acquisition module, the data interaction analysis module and the monitoring equipment state detection module cooperate together to provide support and guarantee for the operation of the intelligent factory.
Specifically, the data acquisition module 110 is configured to acquire power values of a monitored device acquired by a device sensor at a plurality of predetermined time points in a predetermined time period, and vibration signals of the monitored device in the predetermined time period.
Aiming at the technical problems, the technical conception of the application is that the device sensor and the monitoring system are connected to carry out cooperative control so as to input the sensor data of the device into the monitoring system to carry out data cooperative analysis processing after the sensor data of the device are acquired by the device sensor, so that the intelligent factory cooperative control system can monitor the running state and performance index of the device in real time to judge whether the running state of the monitoring device is normal or not. Thus, the method can help the factory to discover the abnormal condition of the equipment in time and take corresponding measures in time so as to reduce the downtime and the production loss.
Specifically, in the technical scheme of the application, firstly, power values of a monitored device in a plurality of preset time points in a preset time period acquired by a device sensor are acquired, and vibration signals of the monitored device in the preset time period are acquired.
The power value of the monitoring device can provide information about the energy consumption condition and the workload of the device, whether the device operates normally can be judged by monitoring the power value of the device, and if the power value of the device is abnormally higher or lower, the problem that the device has faults or low efficiency can be possibly indicated. Therefore, the power value may be one of important indicators for judging the operation state of the apparatus.
The vibration signal may provide information about the structure and operating condition of the device, and the device may generate a specific vibration pattern during operation, and by monitoring the vibration signal of the device, it may be detected whether an abnormal vibration or shock exists in the device. Abnormal vibrations may be indicative of loosening, wear, or malfunction of equipment components, so that the vibration signal may help determine whether the operational state of the equipment is normal.
The power value and the vibration signal are all important parameters for determining whether the operation state of the monitoring equipment is normal or not, faults or anomalies of the equipment can be found in time through monitoring and analyzing the parameters, and corresponding maintenance measures are taken, so that the reliability and the production efficiency of the equipment are improved.
Specifically, the data interaction analysis module 120 is configured to perform collaborative association analysis on the power values at the plurality of predetermined time points and the vibration signal to obtain a power-amplitude interaction characteristic. Fig. 2 is a block diagram of the data interaction analysis module in the intelligent factory cooperative control system according to an embodiment of the present application, as shown in fig. 2, the data interaction analysis module 120 includes: a power timing change feature extraction unit 121, configured to perform timing correlation feature extraction on the power values at the plurality of predetermined time points to obtain a power timing feature vector; a vibration amplitude timing variation feature extraction unit 122, configured to perform timing analysis on the vibration signal to obtain a vibration amplitude timing feature vector; and a power-amplitude feature interaction fusion unit 123 for fusing the power timing feature vector and the vibration amplitude timing feature vector to obtain a power-amplitude interaction feature vector as the power-amplitude interaction feature.
Further, by extracting time sequence correlation characteristics from power values at a plurality of preset time points, power time sequence characteristic vectors can be obtained, and the time sequence characteristic vectors can reflect the time change trend of the power of the equipment and comprise information such as fluctuation, peak value, average value and the like of the power. By analyzing the power time sequence characteristics, abnormal conditions of the running state of the equipment, such as abrupt power change, overlarge fluctuation and the like, can be identified, so that measures can be taken in time to carry out fault diagnosis and predictive maintenance.
By carrying out time sequence analysis on the vibration signals, time sequence eigenvectors of vibration amplitude can be obtained, and the time sequence eigenvectors can reflect information such as the intensity, frequency, period and the like of equipment vibration. By analyzing the vibration amplitude time sequence characteristics, whether the vibration state of the equipment is normal or not can be detected, for example, whether the problems of abnormal vibration, resonance and the like exist or not, and the loosening, abrasion or faults of the equipment structure can be found in time, so that the equipment is prevented from being further damaged or potential safety hazards are avoided.
And fusing the power time sequence feature vector and the vibration amplitude time sequence feature vector to obtain a power-amplitude interaction feature vector, and revealing the association relation between power and vibration by fusing the two feature vectors. For example, it can be found whether a change in power would result in a change in vibration, or whether a change in vibration would affect the stability of power. Such interactive features facilitate a more comprehensive understanding of the operational status of the device, providing more accurate fault diagnosis and predictive maintenance.
That is, the design and the function of the power time sequence change feature extraction unit, the vibration amplitude time sequence change feature extraction unit and the power-amplitude feature interaction fusion unit of the data interaction analysis module can provide comprehensive equipment state analysis, and help to realize the cooperative control target of the intelligent factory.
For the power timing variation feature extraction unit 121, it includes: a power timing distribution subunit, configured to arrange power values of the plurality of predetermined time points into a power timing input vector according to a time dimension; and a power timing correlation encoding subunit, configured to pass the power timing input vector through a power timing feature extractor based on a one-dimensional convolutional neural network model to obtain the power timing feature vector.
Next, it is considered that the power values at the plurality of predetermined time points have a timing correlation in the time dimension due to a dynamic change rule of the power values in the time dimension. Therefore, in the technical scheme of the application, the power values at the plurality of preset time points are further arranged into power time sequence input vectors according to the time dimension, so that after the distribution information of the power values on the time sequence is integrated, the power time sequence input vectors are subjected to feature mining in a power time sequence feature extractor based on a one-dimensional convolutional neural network model, so that the time sequence associated feature distribution information of the power values on the time dimension is extracted, and then the power time sequence feature vectors are obtained. By analyzing the power time sequence change characteristics of the equipment, the characteristic information about the energy consumption, the working state and the like of the equipment can be captured, and the detection of the abnormal operation of the equipment is facilitated.
The power values of a plurality of preset time points are arranged into power time sequence input vectors according to time dimensions, so that time sequence representation of equipment power change is realized, the extraction of rules and trends in time sequence data is facilitated, and a foundation is provided for subsequent feature extraction and analysis.
The power timing input vector is converted into a power timing feature vector by a power timing feature extractor based on a one-dimensional convolutional neural network model. Higher-level abstract features can be extracted from the time sequence data, so that the system is helped to better understand the running state and performance of the equipment.
By analyzing the power time sequence data and extracting the characteristics, the system can accurately judge whether the equipment has faults or abnormal conditions. For example, when the power time sequence feature vector has an abnormal mode or an abnormal change trend, the system can give an alarm in time and take corresponding measures to avoid the loss of production caused by equipment faults.
By historical analysis and modeling of the power time sequence data, the system can predict the future performance and service life of the equipment, is favorable for making a reasonable maintenance plan, maintains and replaces key components in advance, and avoids shutdown and production delay caused by equipment sudden faults.
The vibration amplitude timing variation feature extraction unit 122 includes: the vibration amplitude time sequence arrangement subunit is used for performing discrete sampling on the vibration signal to obtain a plurality of vibration sample points, and arranging the plurality of vibration sample points into vibration amplitude discrete time sequence input vectors according to a time dimension; and the vibration amplitude time sequence correlation subunit is used for enabling the vibration amplitude discrete time sequence input vector to pass through a vibration amplitude time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain the vibration amplitude time sequence feature vector.
Further, considering that the vibration signal of the equipment can reflect more important information in the working state of the equipment, whether the equipment has abnormal vibration or resonance phenomenon can be detected, the abnormal conditions can reflect the fault precursors of the equipment, the equipment can be prevented from being broken down by timely finding and processing the abnormal conditions, and the reliability and the service life of the equipment are improved. Therefore, in the technical scheme of the application, the vibration signal is further subjected to discrete sampling to obtain a plurality of vibration sample points, and the plurality of vibration sample points are arranged into vibration amplitude discrete time sequence input vectors according to the time dimension, so that the time sequence distribution information of the vibration sample points is integrated, and the time sequence distribution information of the discrete sample points is reserved during the subsequent vibration characteristic extraction. By discrete sampling, a series of discrete vibration sample points can be obtained from the continuous vibration signal, so that the vibration signal can be processed and analyzed later, and useful equipment state characteristic information can be extracted.
The discrete sampling refers to sampling a continuous signal at intervals in time, converting the continuous signal into discrete sample points, and sampling the continuous vibration signal in a certain time interval in the discrete sampling of the vibration signal to obtain a series of discrete vibration sample points. The process of discrete sampling may be implemented by an analog-to-digital converter (ADC) that samples and converts the continuous vibration signal to a digital signal for processing and analysis by a computer or other digital device.
In the vibration amplitude time sequence arrangement subunit, discrete sampling is used for sampling vibration signals to obtain a plurality of vibration sample points. The time interval of sampling may be adjusted as desired, typically at fixed intervals, such as every 1 millisecond or every 10 milliseconds. By discrete sampling, the continuous vibration signal is converted into a series of discrete vibration sample points that can be used for subsequent vibration analysis, feature extraction, and fault diagnosis. The discrete sampling process is an important step in digitizing the vibration signal, providing a basis for subsequent data processing and analysis.
And then, carrying out feature mining on the vibration amplitude discrete time sequence input vector in a vibration amplitude time sequence feature extractor based on a one-dimensional convolutional neural network model so as to extract time sequence related feature distribution information of the vibration amplitude of the monitored equipment in a time dimension, thereby obtaining a vibration amplitude time sequence feature vector. By describing the time sequence change characteristics of the vibration amplitude of the monitored equipment, the method is beneficial to detecting the more important and deep abnormal operation state of the monitored equipment, so that the abnormal conditions can be timely found and processed.
Further, a plurality of vibration sample points are obtained by carrying out discrete sampling on the vibration signals, and the vibration sample points are arranged into vibration amplitude discrete time sequence input vectors according to the time dimension, so that continuous vibration signals can be converted into discrete time sequence data, and the subsequent feature extraction and analysis are convenient.
The vibration amplitude discrete time sequence input vector is converted into the vibration amplitude time sequence feature vector through the vibration amplitude time sequence feature extractor based on the one-dimensional convolutional neural network model, so that the feature mode and the change trend of the vibration signal are extracted from time sequence data, and useful information is provided for subsequent fault diagnosis and predictive maintenance.
The vibration signal is an important index for judging the running state and the health condition of the equipment, and the system can accurately detect whether the equipment has vibration abnormality or fault through analysis and feature extraction of vibration amplitude time sequence data. For example, when the vibration amplitude time sequence feature vector shows an abnormal mode or an abnormal change trend, the system can give an alarm in time and take corresponding measures to avoid the loss of production caused by equipment faults.
By historical analysis and modeling of vibration amplitude time sequence data, the system can predict future vibration behaviors and health states of equipment, is favorable for making a reasonable maintenance plan, maintains and replaces key components in advance, and avoids shutdown and production delay caused by equipment sudden faults.
For the interactive fusion unit 123, it is configured to: feature interactions between the power timing feature vector and the vibration amplitude timing feature vector are performed using a cascading function to obtain the power-amplitude interaction feature vector.
It will be appreciated that both the power and vibration signals of the device contain important information about the operating state of the device, but their respective timing characteristics alone may not be sufficient to convey the operating state of the device, i.e. to reduce the accuracy of the detection of the operating state of the device. Therefore, in the technical scheme of the application, the cascading function is further used for carrying out characteristic interaction between the power time sequence characteristic vector and the vibration amplitude time sequence characteristic vector to obtain a power-amplitude interaction characteristic vector, so that the time sequence change characteristic information of the power and the vibration signal is fused by carrying out the interaction of the power and the vibration time sequence characteristic of the monitored equipment, and the richer and more comprehensive working state characteristic information related to the monitored equipment is extracted.
Specifically, the monitoring device status detection module 130 is configured to determine whether the operation status of the monitoring device is normal based on the power-amplitude interaction characteristic. Further used for: and the power-amplitude interaction characteristic vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state of the monitoring equipment is normal or not.
And then, the power-amplitude interaction feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state of the monitoring equipment is normal or not. That is, the operation state detection of the device is comprehensively performed by the power time sequence variation characteristic information and the vibration amplitude time sequence variation characteristic information of the device, so as to judge whether the operation state of the monitoring device is normal or not. Thus, the method can help the factory to discover the abnormal condition of the equipment in time and take corresponding measures in time so as to reduce the downtime and the production loss.
The intelligent factory cooperative control system further comprises a training module for training the power time sequence feature extractor based on the one-dimensional convolutional neural network model, the vibration amplitude time sequence feature extractor based on the one-dimensional convolutional neural network model and the classifier. Fig. 3 is a block diagram of the training module in the intelligent factory cooperative control system according to the embodiment of the present application, and as shown in fig. 3, the training module 140 includes: a training data acquisition unit 141, configured to acquire training data, where the training data includes training power values of a monitored device at a plurality of predetermined time points within a predetermined time period, a training vibration signal of the monitored device during the predetermined time period, and a true value of whether an operation state of the monitored device is normal; a training power timing arrangement unit 142, configured to arrange the training power values at the plurality of predetermined time points into training power timing input vectors according to a time dimension; a training vibration amplitude timing sequence arrangement unit 143, configured to perform discrete sampling on the training vibration signal to obtain a plurality of training vibration sample points, and arrange the plurality of training vibration sample points into training vibration amplitude discrete timing sequence input vectors according to a time dimension; a training power time sequence change feature extraction unit 144, configured to pass the training power time sequence input vector through the power time sequence feature extractor based on the one-dimensional convolutional neural network model to obtain a training power time sequence feature vector; a training vibration amplitude timing variation feature extraction unit 145, configured to pass the training vibration amplitude discrete timing input vector through the vibration amplitude timing feature extractor based on the one-dimensional convolutional neural network model to obtain a training vibration amplitude timing feature vector; a training feature fusion unit 146, configured to perform feature interaction between the training power timing feature vector and the training vibration amplitude timing feature vector by using a cascading function to obtain a training power-amplitude interaction feature vector; a classification loss unit 147 for passing the training power-amplitude interaction feature vector through the classifier to obtain a classification loss function value; and a model training unit 148 for training the one-dimensional convolutional neural network model-based power timing feature extractor, the one-dimensional convolutional neural network model-based vibration amplitude timing feature extractor, and the classifier based on the classification loss function value and traveling in the gradient descent direction, wherein in each round of iteration of the training, feature transfer optimization based on feature distribution cross-domain attention is performed on a weight matrix of the classifier.
In particular, in the technical scheme of the application, the power time sequence feature vector and the vibration amplitude time sequence feature vector respectively express local time sequence association features of power values and vibration amplitudes, and after feature interaction between the power time sequence feature vector and the vibration amplitude time sequence feature vector is performed by using a cascading function, the power-amplitude interaction feature vector contains interaction features of the power features and the vibration amplitude features in a time sequence dimension while retaining the local time sequence association features of the power values and the vibration amplitudes, so that the power-amplitude interaction feature vector has diversified feature distribution.
Thus, when the power-amplitude interaction feature vector is classified by a classifier, the distribution transferability difference of the diversified feature distribution in the domain transfer process of classification is considered, for example, when the weight matrix of the classifier is adapted relative to the single-sample time-series correlation feature representation, the power-amplitude interaction feature vector has better distribution transferability than the time-series interaction correlation feature among samples, and vice versa. Therefore, the power-amplitude interaction feature vector needs to be adaptively optimized for the weight matrix of the classifier, so as to improve the training effect of the power-amplitude interaction feature vector in classification training through the classifier, namely, improve the classification speed and the accuracy of the obtained classification result.
Therefore, in the iterative process of the weight matrix of each classifier, the applicant of the application performs feature transfer optimization based on feature distribution cross-domain attention on the weight matrix M, which is specifically expressed as follows: in each iteration of the training, performing feature transfer optimization based on feature distribution cross-domain attention on a weight matrix of the classifier according to the following optimization formula; wherein, the optimization formula is:
wherein M is the weight matrix of the classifier, and the scale of M is M multiplied by M, V 1 To V m Is the M row vectors of the weight matrix M, I.I 2 Representing the two norms of the feature vector (Σ) j m i,j Is a row vector obtained by arranging the summation value of each row vector of the weight matrix M, and cov 1 (. Cndot.) and cov 2 (. Cndot.) all represent a single-layer convolution operation,representing matrix multiplication, M' represents the weight matrix of the classifier after iteration.
Here, the feature transfer optimization based on feature distribution cross-domain attention is directed to different representations of feature distribution of the power-amplitude interaction feature vector existing in a feature space domain and a classification target domain, based on cross-domain diversity feature representation of a weight matrix M of the classifier relative to the power-amplitude interaction feature vector to be classified, the transferability of cross-domain gaps of good transfer feature distribution in a diversified feature distribution is enhanced by giving attention to spatial structured feature distribution of the weight matrix M through convolution operation, while negative transfer (negotivetransfer) of bad transfer feature distribution is suppressed, so as to realize unsupervised domain transfer adaptive optimization of the weight matrix M based on a distribution structure of the weight matrix M itself relative to the power-amplitude interaction feature vector to be classified, thereby improving training effect of classification training of the power-amplitude interaction feature vector by the classifier. Therefore, the intelligent factory can be cooperatively controlled through the equipment sensor and the monitoring system, so that the running state and the performance index of the equipment are monitored in real time, the equipment in an abnormal state is correspondingly processed, the reliability and the production efficiency of the equipment are improved, and the downtime and the production loss are reduced.
In summary, the intelligent factory cooperative control system 100 according to the embodiment of the application is illustrated, and performs cooperative control by connecting the device sensor and the monitoring system, so that after the device sensor collects the sensing data of the device, the sensing data is input into the monitoring system for data cooperative analysis processing, so that the intelligent factory cooperative control system can monitor the running state and performance index of the device in real time, so as to determine whether the running state of the monitored device is normal. Thus, the method can help the factory to discover the abnormal condition of the equipment in time and take corresponding measures in time so as to reduce the downtime and the production loss.
As described above, the intelligent factory cooperation management system 100 according to the embodiment of the application can be implemented in various terminal devices, such as a server for intelligent factory cooperation management, etc. In one example, the intelligent factory co-management system 100 according to embodiments of the application may be integrated into a terminal device as a software module and/or hardware module. For example, the intelligent factory co-management system 100 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the intelligent factory cooperative control system 100 can also be one of many hardware modules of the terminal device.
Alternatively, in another example, the intelligent factory co-administration system 100 and the terminal device may be separate devices, and the intelligent factory co-administration system 100 may be connected to the terminal device through a wired and/or wireless network and transmit interaction information in a agreed data format.
FIG. 4 is a flowchart of a smart factory collaborative management and control method according to an embodiment of the present application. Fig. 5 is a schematic diagram of a system architecture of an intelligent factory cooperation control method according to an embodiment of the application. As shown in fig. 4 and 5, an intelligent factory collaborative management and control method includes: 210, acquiring power values of a monitored device acquired by a device sensor at a plurality of preset time points in a preset time period, and vibration signals of the monitored device in the preset time period; 220, performing collaborative correlation analysis on the power values of the plurality of preset time points and the vibration signal to obtain power-amplitude interaction characteristics; and, 230, determining whether the operating state of the monitoring device is normal based on the power-amplitude interaction characteristic.
It will be appreciated by those skilled in the art that the specific operation of each step in the above-described intelligent factory cooperation management method has been described in detail in the above description of the intelligent factory cooperation management system with reference to fig. 1 to 3, and thus, a repetitive description thereof will be omitted.
FIG. 6 is a diagram of an intelligent factory collaborative management and control system according to an embodiment of the present application. As shown in fig. 6, in this application scenario, first, power values (e.g., C1 as illustrated in fig. 6) of a monitored device acquired by a device sensor at a plurality of predetermined time points within a predetermined period of time are acquired, and a vibration signal (e.g., C2 as illustrated in fig. 6) of the monitored device at the predetermined period of time; the acquired power values and vibration signals are then input to a server (e.g., S as illustrated in fig. 6) deployed with a smart factory cooperative control algorithm, wherein the server is capable of processing the power values and vibration signals based on the smart factory cooperative control algorithm to determine whether the operating state of the monitoring device is normal.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (10)
1. An intelligent factory cooperative control system, comprising:
the data acquisition module is used for acquiring power values of the monitored equipment in a plurality of preset time points in a preset time period acquired by the equipment sensor and vibration signals of the monitored equipment in the preset time period;
the data interaction analysis module is used for carrying out collaborative association analysis on the power values of the plurality of preset time points and the vibration signal to obtain power-amplitude interaction characteristics; and
and the monitoring equipment state detection module is used for determining whether the operation state of the monitoring equipment is normal or not based on the power-amplitude interaction characteristics.
2. The intelligent plant collaborative management system according to claim 1, wherein the data interaction analysis module comprises:
the power time sequence change feature extraction unit is used for extracting time sequence association features of the power values of the plurality of preset time points to obtain a power time sequence feature vector;
the vibration amplitude time sequence change feature extraction unit is used for performing time sequence analysis on the vibration signal to obtain a vibration amplitude time sequence feature vector; and
and the power-amplitude characteristic interaction fusion unit is used for fusing the power time sequence characteristic vector and the vibration amplitude time sequence characteristic vector to obtain a power-amplitude interaction characteristic vector as the power-amplitude interaction characteristic.
3. The intelligent factory cooperative control system according to claim 2, wherein the power timing variation feature extraction unit comprises:
a power timing distribution subunit, configured to arrange power values of the plurality of predetermined time points into a power timing input vector according to a time dimension; and
and the power time sequence associated coding subunit is used for enabling the power time sequence input vector to pass through a power time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain the power time sequence feature vector.
4. The intelligent factory cooperative control system according to claim 3, wherein the vibration amplitude timing variation feature extraction unit comprises:
the vibration amplitude time sequence arrangement subunit is used for performing discrete sampling on the vibration signal to obtain a plurality of vibration sample points, and arranging the plurality of vibration sample points into vibration amplitude discrete time sequence input vectors according to a time dimension;
and the vibration amplitude time sequence correlation subunit is used for enabling the vibration amplitude discrete time sequence input vector to pass through a vibration amplitude time sequence feature extractor based on a one-dimensional convolutional neural network model to obtain the vibration amplitude time sequence feature vector.
5. The intelligent plant cooperative control system of claim 4, wherein the power-amplitude feature interactive fusion unit is configured to: feature interactions between the power timing feature vector and the vibration amplitude timing feature vector are performed using a cascading function to obtain the power-amplitude interaction feature vector.
6. The intelligent factory cooperative control system according to claim 5, wherein the monitoring device status detection module is configured to: and the power-amplitude interaction characteristic vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state of the monitoring equipment is normal or not.
7. The intelligent plant collaborative management and control system according to claim 6, further comprising a training module for training the one-dimensional convolutional neural network model-based power timing feature extractor, the one-dimensional convolutional neural network model-based vibration amplitude timing feature extractor, and the classifier.
8. The intelligent factory cooperative control system of claim 7, wherein the training module comprises:
the system comprises a training data acquisition unit, a monitoring unit and a control unit, wherein the training data acquisition unit is used for acquiring training data, the training data comprises training power values of monitored equipment at a plurality of preset time points in a preset time period, training vibration signals of the monitored equipment in the preset time period and a true value of whether the running state of the monitoring equipment is normal or not;
the training power time sequence arrangement unit is used for arranging the training power values of the plurality of preset time points into training power time sequence input vectors according to the time dimension;
the training vibration amplitude time sequence arrangement unit is used for performing discrete sampling on the training vibration signal to obtain a plurality of training vibration sample points, and arranging the plurality of training vibration sample points into training vibration amplitude discrete time sequence input vectors according to a time dimension;
the training power time sequence change feature extraction unit is used for enabling the training power time sequence input vector to pass through the power time sequence feature extractor based on the one-dimensional convolutional neural network model so as to obtain a training power time sequence feature vector;
the training vibration amplitude time sequence change feature extraction unit is used for enabling the training vibration amplitude discrete time sequence input vector to pass through the vibration amplitude time sequence feature extractor based on the one-dimensional convolutional neural network model so as to obtain a training vibration amplitude time sequence feature vector;
the training feature fusion unit is used for performing feature interaction between the training power time sequence feature vector and the training vibration amplitude time sequence feature vector by using a cascading function so as to obtain a training power-amplitude interaction feature vector;
the classification loss unit is used for passing the training power-amplitude interaction feature vector through the classifier to obtain a classification loss function value; and
the model training unit is used for training the power time sequence feature extractor based on the one-dimensional convolutional neural network model, the vibration amplitude time sequence feature extractor based on the one-dimensional convolutional neural network model and the classifier based on the classification loss function value and through gradient descent direction propagation, wherein in each round of iteration of the training, feature transfer optimization based on feature distribution cross-domain attention is carried out on a weight matrix of the classifier.
9. The intelligent factory cooperative control system according to claim 8, wherein in each iteration of the training, feature transfer optimization based on feature distribution cross-domain attention is performed on the weight matrix of the classifier with the following optimization formula;
wherein, the optimization formula is:
wherein M is the weight matrix of the classifier, and the scale of M is M multiplied by M, V 1 To V m Is the M row vectors of the weight matrix M, I.I 2 Representing the two norms of the feature vector (Σ) j m i,j Is a row vector obtained by arranging the summation value of each row vector of the weight matrix M, and cov 1 (. Cndot.) and cov 2 (. Cndot.) all represent a single-layer convolution operation,representing matrix multiplication, M' represents the weight matrix of the classifier after iteration.
10. An intelligent factory cooperative control method is characterized by comprising the following steps:
acquiring power values of a monitored device acquired by a device sensor at a plurality of preset time points in a preset time period, and vibrating signals of the monitored device in the preset time period;
performing collaborative correlation analysis on the power values of the plurality of preset time points and the vibration signal to obtain power-amplitude interaction characteristics; and
based on the power-amplitude interaction characteristics, it is determined whether the operating state of the monitoring device is normal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310936330.0A CN116880402A (en) | 2023-07-28 | 2023-07-28 | Intelligent factory cooperative control system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310936330.0A CN116880402A (en) | 2023-07-28 | 2023-07-28 | Intelligent factory cooperative control system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116880402A true CN116880402A (en) | 2023-10-13 |
Family
ID=88254819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310936330.0A Pending CN116880402A (en) | 2023-07-28 | 2023-07-28 | Intelligent factory cooperative control system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116880402A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117388893A (en) * | 2023-12-11 | 2024-01-12 | 深圳市移联通信技术有限责任公司 | Multi-device positioning system based on GPS |
-
2023
- 2023-07-28 CN CN202310936330.0A patent/CN116880402A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117388893A (en) * | 2023-12-11 | 2024-01-12 | 深圳市移联通信技术有限责任公司 | Multi-device positioning system based on GPS |
| CN117388893B (en) * | 2023-12-11 | 2024-03-12 | 深圳市移联通信技术有限责任公司 | Multi-device positioning system based on GPS |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102521604B (en) | Device and method for estimating performance degradation of equipment based on inspection system | |
| Xu et al. | Quantile regression neural network‐based fault detection scheme for wind turbines with application to monitoring a bearing | |
| KR20190013017A (en) | Method and device for equipment health monitoring based on sensor clustering | |
| Mathew et al. | Regression kernel for prognostics with support vector machines | |
| CN116880402A (en) | Intelligent factory cooperative control system and method thereof | |
| CN112173636B (en) | Method for detecting faults of belt conveyor carrier roller by inspection robot | |
| US20220414526A1 (en) | Intelligent fault detection system | |
| CN110709789A (en) | Method and apparatus for monitoring the condition of a subsystem within a renewable power generation device or microgrid | |
| CN117118781A (en) | Intelligent industrial gateway design method and device | |
| CN116629627A (en) | Intelligent detection system of power transmission on-line monitoring device | |
| CN112734977B (en) | Equipment risk early warning system and algorithm based on Internet of things | |
| CN110456732B (en) | Punch press fault monitoring system with learning function | |
| CN117375237A (en) | Substation operation and maintenance method and system based on digital twin technology | |
| CN116704729A (en) | Industrial kiln early warning system and method based on big data analysis | |
| CN117060353A (en) | Fault diagnosis method and system for high-voltage direct-current transmission system based on feedforward neural network | |
| CN116961215A (en) | Rapid fault response processing method for power system | |
| CN115905348A (en) | Industrial electricity utilization abnormity early warning method and system of multi-source heterogeneous data | |
| Papa et al. | Cyber physical system based proactive collaborative maintenance | |
| Geetha et al. | The Smart Development of the Large Scale Sensing Techniques in Intelligent Industrial Automation | |
| Suzuki et al. | An anomaly detection system for advanced maintenance services | |
| CN114414938B (en) | Dynamic response method and system for power distribution network faults | |
| Vanitha et al. | An Innovation Development of Neuro Controller for Condition Monitoring and Smart Industrial Instrumentation | |
| CN112654060B (en) | Device abnormity detection method and system | |
| CN117252435B (en) | Factory production safety monitoring and early warning method and system based on industrial Internet | |
| CN117272844B (en) | Method and system for predicting service life of distribution board |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |