CN114281052A - Mechanical equipment running state monitoring device, system and method - Google Patents
Mechanical equipment running state monitoring device, system and method Download PDFInfo
- Publication number
- CN114281052A CN114281052A CN202111656245.6A CN202111656245A CN114281052A CN 114281052 A CN114281052 A CN 114281052A CN 202111656245 A CN202111656245 A CN 202111656245A CN 114281052 A CN114281052 A CN 114281052A
- Authority
- CN
- China
- Prior art keywords
- equipment
- mechanical equipment
- model
- state
- diagnosis
- 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 26
- 238000012806 monitoring device Methods 0.000 title claims abstract description 22
- 238000003745 diagnosis Methods 0.000 claims abstract description 83
- 238000012544 monitoring process Methods 0.000 claims abstract description 58
- 238000003860 storage Methods 0.000 claims abstract description 21
- 230000001960 triggered effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 23
- 238000004458 analytical method Methods 0.000 description 16
- 238000004519 manufacturing process Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 9
- 238000013500 data storage Methods 0.000 description 8
- 238000006073 displacement reaction Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 238000009776 industrial production Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000009191 jumping Effects 0.000 description 4
- 230000036541 health Effects 0.000 description 3
- 238000003754 machining Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000012774 diagnostic algorithm Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003801 milling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a device, a method and a system for monitoring the running state of mechanical equipment, wherein the device comprises: the model storage device stores at least 2 trained models, and each model corresponds to one type of mechanical equipment; the equipment data module is used for receiving and storing the state parameters of the mechanical equipment; the state diagnosis module identifies the equipment type according to the corresponding equipment identification in the diagnosis instruction, calls the corresponding model to diagnose the running state and outputs a diagnosis result; when the model diagnoses the running state, reading the real-time characteristic data of the corresponding mechanical equipment from the equipment data module, and analyzing the real-time characteristic data; the model, the diagnostic instructions and the real-time characteristic data can be associated through equipment identification. The invention can diagnose the states of different types of mechanical equipment, realizes the state monitoring of a monitoring device on a plurality of types of mechanical equipment, can monitor the states of the mechanical equipment in time and improves the accuracy of the diagnosis result.
Description
Technical Field
The invention relates to the technical field of mechanical equipment monitoring, in particular to a device, a system and a method for monitoring the running state of mechanical equipment.
Background
Industrial equipment is an indispensable part in the industrial production and manufacturing process, and the types of industrial equipment are various, including assembly line machining equipment, production mechanical arms, various machine tools (lathes, milling machines, grinding machines and the like) and traditional non-digital machines. These machines support complex and delicate manufacturing activities for a manufacturing enterprise. The stability of the equipment and the health condition of the equipment are particularly critical to the processing quality and the production efficiency of enterprise products.
The management of the equipment by utilizing informatization and intellectualization becomes a normalization. The whole manufacturing industry presents the following characteristics along with the development of the industry:
(1) the automation level of enterprises is promoted to be higher and higher by informatization and intellectualization, and a plurality of automation functions gradually replace the traditional manual operation.
(2) Cloud computing evolves. The advent of cloud computing and widespread market adoption for rapid processing and integration of large volumes of data. And displaying the processing result to a needed object in real time.
(3) The internet of things is rapidly emerging. The Internet of things is developed rapidly, various sensors and data processing, acquisition and storage software and hardware are utilized to acquire state operation parameters and operation process data of the equipment in real time, and the state operation parameters and the operation process data are transmitted to a data analysis end to be calculated and analyzed, so that the real-time state condition of the equipment is obtained.
(4) Development and application of AI. The continuous rise of AI and the continuous promotion of the application degree in the actual production process, various new algorithms leap and leap, and the protection and navigation for the production and processing of enterprises are realized.
(5) A modern device management architecture. Enterprise informatization, cloud computing, the Internet of things and AI are integrated, so that the degree of standardization of enterprise management on production equipment is increased, the full life cycle of the equipment is tracked, and the equipment is effectively guaranteed in each life cycle.
Although the manufacturing industry as a whole is rapidly changing in iteration, the fault diagnosis of the equipment is still in a scattered and isolated state. The health state monitoring of the equipment is still deficient for most enterprises; at present, health state monitoring of equipment by a plurality of enterprises is mainly carried out by manually observing and evaluating an operation state of the equipment by depending on experience of people. The method has the disadvantages that the early fault state of the equipment cannot be evaluated, the fault degree of the equipment is increased, the maintenance cost of the subsequent equipment is greatly increased, and the production halt of enterprises is caused, so that the production plan and the economic benefit are influenced. Even if some enterprises adopt a computer system to monitor equipment, often one set of monitoring system monitors one equipment or a specific part of one equipment, if a plurality of equipment or a plurality of parts need to be monitored, the needed monitoring systems are various, in addition, the problem that the monitoring result is inaccurate due to equipment diversification exists in the current machining center mechanical equipment, the industrial production mechanical equipment is various, the reasons for the faults of each type of mechanical equipment are different, even if the same fault occurs, the running states of different types of equipment are possibly different, and therefore the state monitoring and the fault analysis of the plurality of mechanical equipment cannot be realized through one set of monitoring system.
Disclosure of Invention
The invention aims to provide a device for monitoring the running state of mechanical equipment, which solves the problem that the prior art can not realize the state monitoring and fault analysis of a plurality of pieces of mechanical equipment through a set of monitoring system and can timely and accurately obtain the states of the plurality of pieces of monitored mechanical equipment.
The invention is realized by the following technical scheme:
mechanical equipment running state monitoring device, including model storage device, equipment data module and state diagnosis module, wherein:
the model storage device is used for storing trained models, the model storage device can store at least 2 models, and each model corresponds to one type of mechanical equipment;
the equipment data module is used for receiving and storing state parameters of the mechanical equipment;
the state diagnosis module is used for identifying the equipment type according to the corresponding equipment identification in the diagnosis instruction, calling the corresponding model according to the equipment type to diagnose the running state and outputting a diagnosis result;
when the model diagnoses the running state, reading the real-time characteristic data of the corresponding mechanical equipment from the equipment data module, and analyzing the real-time characteristic data; the model, the diagnostic instructions and the real-time characteristic data can be associated through equipment identification.
In the scheme, the model storage device can store a plurality of different models which correspond to different types of mechanical equipment, so that the states of the different types of mechanical equipment can be diagnosed by operating the corresponding models, the states of the multiple types of mechanical equipment can be monitored by one monitoring device, and the states of the mechanical equipment can be monitored in time. In the device, the model only needs to call the corresponding mechanical equipment state parameters stored in the equipment data module during running and read real-time characteristic data in the state parameters, so that the state of the equipment can be accurately predicted, and if the equipment is found to be in a fault state, the model further outputs a fault grade, thereby not only avoiding manual monitoring, but also greatly improving the accuracy of a diagnosis result.
In some embodiments, as a further improvement of this solution, the device for monitoring the operating state of the mechanical equipment further includes a control module, which is configured to output a control instruction according to the diagnosis result and instruct the equipment to perform an emergency treatment measure, so that when the mechanical equipment of the machining center fails, the equipment is stopped in time, and further damage to the equipment and safety of workers are avoided.
Further, the mechanical equipment operation state monitoring device further comprises:
and the trigger condition judging module is used for outputting a diagnosis instruction when the diagnosis condition is triggered, wherein the diagnosis instruction comprises the equipment identifier of the mechanical equipment to be diagnosed.
Further, the device data module includes:
the data processing module is used for receiving the state parameters of the mechanical equipment and cleaning the state parameter data;
and the data storage module is used for storing the data cleaned by the data processing module.
In some embodiments, as a further improvement of the present solution, the device for monitoring the operating state of the mechanical equipment further includes:
the equipment selection module is used for judging whether the mechanical equipment is in the registration list or not when the diagnosis instruction is received, sending out prompt information if the mechanical equipment is not in the registration list, and selecting a model corresponding to the equipment if the mechanical equipment is in the registration list;
and the equipment management module is used for creating equipment according to an external instruction, receiving the uploaded new equipment model and storing the model to the model storage device.
In some embodiments, as a further improvement of the present disclosure, the device for monitoring an operating state of a mechanical apparatus further includes:
the cache module is used for caching the received model;
when the state diagnosis module calls the model, firstly, whether the model cache region has the model corresponding to the equipment type is searched according to the identified equipment type, if so, the model is issued to the model storage device, and the model is called after the model of the model cache region is deleted.
The invention further aims to provide a mechanical equipment running state monitoring method, which comprises the following steps:
s1, receiving and storing the state parameters of the mechanical equipment;
s2, when a diagnosis instruction is received, identifying the equipment type of the mechanical equipment to be diagnosed according to the equipment identification in the diagnosis instruction;
s3, calling a corresponding model according to the identified equipment type, reading the stored state parameters of the mechanical equipment to be diagnosed by the model to execute state diagnosis and outputting a diagnosis result;
and S4, generating a control command according to the state diagnosis result and sending the control command to the corresponding mechanical equipment.
Further, in step S3, it is also determined whether the mechanical device to be diagnosed in the identification state diagnosis condition is already in the registration list, and if not, a new device access prompt is issued.
Further, the method for monitoring the operating state of the mechanical equipment further comprises an equipment registration step: receiving a mechanical equipment creating request and an uploaded model of the mechanical equipment, adding the mechanical equipment into a registered list, storing the model, and binding the mechanical equipment and the model thereof; the device registration steps are not in sequence with steps S1-S3.
Further, there are model checking and updating steps before step S3:
and searching whether the model cache region has a model corresponding to the equipment type according to the identified equipment type, if so, releasing the model to a model storage device, deleting the model in the model cache region, then jumping to the step S3, and if not, directly jumping to the step S3.
Still another object of the present invention is to provide a system for monitoring an operation status of a mechanical device, comprising:
the data acquisition module is used for acquiring state parameters of the mechanical equipment;
the control device is used for receiving the state parameters, calling the correspondingly stored model by the state instruction to diagnose the state of the mechanical equipment, outputting a state diagnosis result, and sending a control instruction to the emergency control switch when the state diagnosis result indicates that a fault occurs; the control device adopts the mechanical equipment running state monitoring device in the scheme;
and the emergency control switch is used for receiving the control instruction of the control device and controlling the mechanical equipment according to the control instruction.
The system in the scheme integrates the whole process from data acquisition, analysis to output of a result and control of equipment, and realizes the logic closed loop from analysis of equipment state data, obtaining of equipment fault state grade to influence of equipment emergency treatment.
Furthermore, the system also comprises a data gateway, the data acquisition module sends the acquired state parameters to the control device through the data gateway, and the control device sends a control instruction to the emergency control switch through the data gateway.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the mechanical equipment running state monitoring device can diagnose the states of different types of mechanical equipment, realizes that one monitoring device monitors the states of a plurality of types of mechanical equipment, and can monitor the states of all the mechanical equipment in time.
2. The model of the mechanical equipment running state monitoring device is trained in an off-line or on-line mode in advance through a large number of corresponding mechanical equipment running state parameters and actual running state results (diagnosis results to be output), and the state of the equipment can be accurately predicted only by calling the corresponding mechanical equipment state parameters stored in the equipment data module during the running of the model, so that the manual monitoring is avoided, and the accuracy of the diagnosis results is greatly improved.
3. After the system is additionally provided with the control module, the control device sends an emergency instruction to the control module, and the control module enables the equipment to execute emergency treatment measures, so that the equipment is shut down in time when the mechanical equipment of the machining center breaks down, and further damage to the equipment and harm to the safety of workers are avoided.
4. The system integrates the whole process from data acquisition, analysis to output result and control of the equipment, and realizes the logical closed loop from analyzing the equipment state data, obtaining the equipment fault state grade to influencing the equipment emergency treatment.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and that for those skilled in the art, other related drawings can be obtained from these drawings without inventive effort. Further, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale. In the drawings:
fig. 1 is a schematic flowchart of a mechanical equipment operating state monitoring system for performing a mechanical equipment state diagnosis in embodiment 3;
fig. 2 is a schematic view of a work flow of a data acquisition module in embodiment 3;
fig. 3 is a schematic view of a processing flow of data by a data gateway and a device data module in embodiment 3;
FIG. 4 is a schematic view showing the operation of a state diagnosing module and a model storing means in embodiment 3;
fig. 5 is a schematic view of the working flow of the emergency control switch in embodiment 3.
Detailed Description
The inventor of the present application found in long-term research and practice that the following problems exist in the monitoring of the mechanical equipment of the machining center at present:
(1) the equipment is diversified, industrial production mechanical equipment is diversified, the failure reason of each type of mechanical equipment is different, and even if the same failure happens, one operation state of the equipment is possibly different.
(2) Many devices do not have a digital system and a monitoring instrument, and cannot acquire the operating state parameters of the devices and realize remote control on the devices.
(3) The difficulty of acquiring the running state data of the equipment is high, and the accuracy of the AI algorithm on fault diagnosis of the machining center is not high enough. The realization of the linkage control of the equipment by relying on the AI algorithm alone is not stable enough. The method is easy to be interfered by external environment factors, and the generated interference information can influence the judgment of the algorithm on the equipment state.
(4) When machining center mechanical equipment breaks down, equipment can't in time shut down, causes equipment further to damage, probably endangers workman's safety even.
In general, in a machining center, linkage control of machining equipment by analyzing fault conditions of the equipment is still blank. The inventor of the present invention has made an intensive study to provide a device, a system and a method for monitoring an operation state of a mechanical device, which aim to solve one or more of the above problems through one or more technical solutions.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: it is not necessary to employ these specific details to practice the present invention. In other instances, well-known structures, circuits, materials, or methods have not been described in detail so as not to obscure the present invention.
Throughout the specification, reference to "one embodiment," "an embodiment," "one example," or "an example" means: the particular features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the invention. Thus, the appearances of the phrases "one embodiment," "an embodiment," "one example" or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
[ example 1 ]
In the prior art, most enterprises check the safety of equipment and whether the equipment has obvious fault damage or not by adopting a regular point inspection and routing inspection mode for machining center mechanical equipment. However, manual point inspection consumes high resources, generates high cost, is not stable enough, can only detect obvious damaged points of equipment, is difficult to detect the damaged points hidden in the equipment by naked eyes, is not enough to prevent abnormity in the production and processing process, and cannot realize real-time monitoring.
An enterprise also adopts an equipment running state monitoring system, but many equipment running state monitoring systems in the current market collect the state data of temperature, current, displacement, humidity, noise, vibration and the like of equipment by using various sensors or state parameter monitoring interfaces carried by access equipment, and the state data are processed by data to visually show a running state of the equipment. However, most of these state monitoring systems only acquire the state parameters of the equipment, and after simple processing, the data are analyzed by professional technicians to give a manual diagnosis result. The mode is difficult to realize early warning in time, has high requirements on the professional level of an analyst and has no universality.
And part of systems also collect state data of specific equipment, and utilize AI algorithm to train the data of the specific equipment to predict the fault state of the specific equipment, simulate the life cycle change of the equipment and provide an equipment maintenance decision for enterprises. However, AI machine learning methods are directed at specific parts of specific devices, that is, one set of monitoring system is often used to monitor one device or one specific part, and if multiple devices and multiple parts are to be monitored, the required monitoring system is large and numerous, and the accuracy rate thereof is limited, because the machining center mechanical devices have the problem of inaccurate monitoring results due to device diversification, industrial production mechanical devices are diverse, the reasons for failures of each type of mechanical devices are different, and even if the same failure occurs, the operating states of different types of devices may be different, so that the state monitoring and failure analysis of multiple mechanical devices cannot be realized by one set of monitoring system.
Therefore, the current processing type enterprises lack a complete equipment state monitoring system, and in view of this, the present embodiment provides a mechanical equipment operation state monitoring apparatus, which can perform state monitoring and fault analysis of a plurality of mechanical equipment, and improve monitoring and judgment accuracy.
The mechanical equipment running state monitoring device in this embodiment includes a model storage device, a state diagnosis module, and an equipment data module, wherein:
the model storage device is used for storing the trained models and can store at least 2 models, and each model corresponds to one type of mechanical equipment;
the device data module is used for receiving and storing the state parameters of the mechanical device, and the state parameters comprise real-time characteristic data of the mechanical device;
the state diagnosis module is used for identifying the equipment type according to the corresponding equipment identifier in the diagnosis instruction, calling the corresponding model according to the equipment type to diagnose the running state and outputting a diagnosis result;
when the model is used for diagnosing the running state, reading the real-time characteristic data of the corresponding mechanical equipment from the equipment data module, and analyzing the real-time characteristic data;
the model, the diagnosis instruction and the real-time characteristic data in the embodiment can be associated through the equipment identifier.
In this embodiment, the model storage device can store a plurality of different models, and the models correspond to different types of mechanical devices, so that the state diagnosis of different types of mechanical devices can be performed by operating the corresponding models, thereby implementing the state monitoring of a plurality of types of mechanical devices by one monitoring device, and monitoring the state of each mechanical device in time. The model stored in the model storage device is trained in an off-line or on-line manner through a large number of corresponding operation state parameters of the mechanical equipment and actual operation state results (diagnosis results to be output, including the state of the equipment, the fault level of the equipment and control instructions to be output under each fault level), and the model after being trained by overlarge data can be used for judging the state according to the real-time state parameters of the mechanical equipment no matter whether the types of the mechanical equipment in industrial production are the same or not and whether the fault reasons are the same or not.
The inventors of the present application have also found that prior art monitoring systems are too isolated and have little means of controlling the devices in a coordinated manner. Therefore, in order to further solve the problem in this embodiment, the mechanical equipment operation state monitoring apparatus may be further improved, and a control module is further added for outputting a control command according to the diagnosis result. If an emergency shutdown switch for controlling the mechanical equipment is arranged on the mechanical equipment side of the machining center, the control instruction is linked with the switch, the equipment fault state diagnosis and identification can be linked with the mechanical equipment of the machining center, the equipment is shut down in time by using the emergency shutdown switch, and the integrated linkage control process from equipment data acquisition and analysis to output results and control of the equipment is realized.
In some embodiments, the apparatus of this embodiment may be further improved, and a trigger condition determining module, an equipment selecting module, and an equipment managing module are added, where:
the trigger condition judging module is used for outputting a diagnosis instruction when the diagnosis condition is triggered, wherein the diagnosis instruction comprises an equipment identifier of the mechanical equipment to be diagnosed;
the equipment selection module is used for judging whether the mechanical equipment is in the registration list or not when the diagnosis instruction is received, sending out prompt information if the mechanical equipment is not in the registration list, and selecting a model corresponding to the equipment if the mechanical equipment is in the registration list;
and the equipment management module is used for creating equipment according to an external instruction, receiving the uploaded new equipment model and storing the model to the model storage device.
The diagnosis condition received by the trigger condition judgment module is set as required, for example, the diagnosis condition may be set to a set time (i.e. timing inspection of mechanical equipment), a user instruction received through a human-computer interface (user selects to inspect mechanical equipment), a status parameter received from the mechanical equipment (data trigger inspection of mechanical equipment), and the like, the conditions can be one or more of the combination, the diagnosis conditions comprise the equipment identification of the mechanical equipment needing to be diagnosed, when the diagnosis instruction is generated, all the equipment parameters and control instructions also comprise the diagnosis instruction, the specified bit identification equipment is also arranged on all the equipment parameters and control instructions, each model also carries the equipment identification, therefore, the system can accurately identify each device in the whole process from data acquisition and analysis to output of results and control of the devices, and accurate acquisition and control are carried out.
In some embodiments, the present embodiment may be further improved, where the device data module includes a data processing module and a data storage module, where the data processing module is configured to receive state parameters of the mechanical device and clean the state parameter data; and the data storage module is used for storing the data cleaned by the data processing module. The data processing module carries out cleaning processing on the data and comprises the following steps: for waveform data such as noise signals or vibration signals, characteristics contained in the waveform data need to be extracted from the waveform data; the time domain signal needs to calculate the mean value, the root mean square, the variance and the like, the time domain signal is transformed into a frequency domain signal through Fourier transform or wavelet analysis, and the frequency domain characteristics contained in a spectrogram need to be extracted; as to how to extract the aforementioned features is well known in the prior art, the present embodiment does not describe the specific steps in detail. The data storage module stores the cleaned data according to different service requirements, and the data storage module is mainly divided into four types of real-time data, off-line data, picture video data and file data.
In some embodiments, the present embodiment may be further improved, and a cache module for caching the received model is additionally arranged in the mechanical equipment operation state monitoring device; when the state diagnosis module calls the model, firstly, whether the model cache region has the model corresponding to the equipment type is searched according to the identified equipment type, if so, the model is issued to the model storage device, and the model is called after the model of the model cache region is deleted.
Therefore, the mechanical equipment running state monitoring device can realize the rapid release of the model and automatically update the iterative model. For the model developed off-line, the model can start to work only by publishing the model to the mechanical equipment running state monitoring device and binding the model to the corresponding equipment. The mechanical equipment running state monitoring device checks the newly released model and carries out iterative updating on the model.
[ example 2 ]
The mechanical equipment running state monitoring method comprises the following steps:
s1, receiving and storing the state parameters of the mechanical equipment;
s2, when a diagnosis instruction is received, identifying the equipment type of the mechanical equipment to be diagnosed according to the equipment identification in the diagnosis instruction;
s3, calling a corresponding model according to the identified equipment type, reading the stored state parameters of the mechanical equipment to be diagnosed by the model to execute state diagnosis and outputting a diagnosis result;
and S4, generating a control command according to the state diagnosis result and sending the control command to the corresponding mechanical equipment.
In some embodiments, the present embodiment may be further modified, and in step S3, it is further determined whether the mechanical device to be diagnosed in the identification state diagnosis condition exists in the registration list, and if not, a new device access prompt is issued.
In some embodiments, the present embodiment may be further improved, and further includes an apparatus registration step: receiving a mechanical equipment creating request and an uploaded model of the mechanical equipment, adding the mechanical equipment into a registered list, storing the model, and binding the mechanical equipment and the model thereof; the device registration steps are not in sequence with steps S1-S3.
There is also a model checking and updating step before step S3:
and searching whether the model cache region has a model corresponding to the equipment type according to the identified equipment type, if so, releasing the model to a model storage device, deleting the model in the model cache region, then jumping to the step S3, and if not, directly jumping to the step S3.
[ example 3 ]
Mechanical equipment running state monitored control system includes:
the data acquisition module is used for acquiring state parameters of the mechanical equipment;
the control device is used for receiving the state parameters, calling the correspondingly stored model by the state instruction to diagnose the state of the mechanical equipment, outputting a state diagnosis result, and sending a control instruction to the emergency control switch when the state diagnosis result indicates that a fault occurs; the control device adopts the mechanical equipment running state monitoring device in embodiment 1;
the emergency control switch is used for receiving a control instruction of the control device and controlling the mechanical equipment according to the control instruction;
and the data gateway is used for sending the acquired state parameters to the control device through the data gateway, and the control device sends a control command to the emergency control switch through the data gateway.
The mechanical equipment running state monitoring system in the embodiment detects the fault state of mechanical equipment of a machining center based on AI and controls the mechanical equipment to be shut down through the linkage of an emergency switch. The core functions of the intelligent emergency control system are mainly divided into four parts, namely a data acquisition module, a data gateway, an emergency control switch and a control device. The four major workflows are shown in fig. 1:
the data acquisition module is responsible for acquiring various parameters (temperature, humidity, vibration, displacement and the like) from mechanical equipment of the machining center; and then sending the data to a data gateway, uniformly processing various transmitted data packets by the data gateway, sending the processed data packets to a data processing module through an MQTT (Message Queuing Telemetry Transport) instant messaging protocol, cleaning the data by the data processing module, and storing the cleaned data in a data storage module. The state diagnosis module reads the real-time data in the storage module in real time to analyze the state of the diagnosis equipment, and sends a control instruction to the data gateway according to the state result, and the data gateway forwards the instruction to an emergency control switch of the equipment, so that the emergency control of the equipment is realized. The following is a detailed description of the contents of each part:
1) data acquisition module
The data acquisition module includes one or more of a plurality of sensors, such as temperature sensors, humidity sensors, vibration sensors, displacement sensors, etc., mounted on or about the machining center machinery.
The data acquisition module can acquire various state parameters on the mechanical equipment through different protocol drivers (modbus, TCP, COAP and the like), and the protocol drivers are responsible for analyzing the acquired data to form corresponding data packets under various protocols and transmitting the data to the data gateway according to a transmission protocol.
As shown in fig. 2, the work flow of the data acquisition module is as follows: the method comprises the steps that after a corresponding state parameter data packet on the mechanical equipment is obtained by an acquisition module, a corresponding protocol driver is selected according to the type of a protocol, the state parameter data packet is analyzed by the protocol driver, a failure state prompt is returned when the analysis fails, the analyzed data packet is obtained after the analysis succeeds, and the analyzed data packet is transmitted to a gateway through a transmission protocol.
In this embodiment, the system supports multiple modes of deployment and multiple types of data transmission protocols, and the supported data protocols include data transmission protocols such as Modbus, TCP, Zigbee, and bluetooth.
2) Data gateway
As shown in fig. 3, after receiving the data, the data gateway parses the data packet, unifies the format of the parsed data packet, and then sends the data packet to the data processing module through MQTT.
3) Data processing module and data storage module
The data processing module receives data to clean the data, for waveform data such as noise signals or vibration signals, features contained in the waveform data need to be extracted from the waveform data, time domain signals need to calculate mean values, root mean square, variance and the like, the time domain signals are converted into frequency domain signals through Fourier transformation or wavelet analysis, and the frequency domain features contained in a spectrogram need to be extracted. The data after cleaning processing is stored in a data storage module according to different service requirements, and is mainly divided into four types of real-time data, off-line data, picture video data and file data.
4) State diagnosis module and model storage device
The model storage device stores a plurality of models, each model corresponds to one type of mechanical equipment, so that each type of equipment has the real-time running state and fault condition of the corresponding model diagnosis and analysis equipment, and the state diagnosis module can monitor the plurality of mechanical equipment at the same time. The models are pre-established models, and in this embodiment, the models are pre-trained offline by using big data of the devices corresponding to the models. The models include, but are not limited to, a device spindle bearing fault monitoring model (for diagnosing inner and outer ring faults and roller faults of a device spindle bearing), a device spindle wear state monitoring model (for monitoring the wear degree of a device spindle), a device guide rail wear state monitoring (for monitoring the wear degree of a device guide rail), and a device screw displacement monitoring (for monitoring the displacement degree of a device screw and diagnosing the machining precision change of the device). Model construction and model training for various types of mechanical equipment are well known in the art, and the present embodiment does not describe each model and the training method for the model in detail.
In this embodiment, the state diagnosis module further provides a human-computer interface for a user to perform operations such as device registration, uploading a model corresponding to the device, and selecting a device to view.
The working flow of the state diagnosing module and the model storing device is shown in fig. 4, after receiving the diagnosing instruction, the state diagnosing module firstly judges whether the device exists, that is, whether the device exists in the registration list, and if not, sends out the prompt message. The equipment which is registered on the state diagnosis module selects the model bound by the equipment and checks whether the model is updated iteratively, if a new model is released, the state diagnosis module automatically iterates the new model, then analyzes the real-time characteristic data of the equipment, outputs the fault state grade, and selects different control instructions to issue according to the fault state grade of the equipment.
If the new device is connected and registered to the state diagnosis module, the model suitable for the new device needs to be issued for binding. Each model has a fault level diagnostic algorithm that is independently adapted to the bound machining center mechanical equipment. The state diagnosis module diagnoses the fault level, and identifies a state of the equipment by analyzing state parameter data of the equipment, such as temperature, displacement, vibration intensity and the like of the equipment, and if the equipment is in fault, a corresponding equipment fault level is obtained according to a fault level diagnosis algorithm.
5) Emergency control switch
The emergency control switch can directly control the switch of the equipment, as shown in fig. 5, the data gateway receives the control command sent by the control module and forwards the control command to the emergency control switch, and the emergency control switch receives and executes the command to perform emergency treatment on the mechanical equipment.
The system of this embodiment is through installing sensors such as vibration signal, noise, temperature, humidity, displacement, current-voltage collection on production facility to register equipment on controlling means, the equipment data transmission who gathers the sensor in real time gives controlling means, controlling means passes through artificial intelligence and various mechanism data analysis, differentiates a fault condition level that present equipment is located, the safety problem that greatly reduced equipment produced in process of production also has certain degree of guarantee to workman's safety.
In this embodiment, one control apparatus may manage a plurality of devices at the same time, register a plurality of devices in the same control apparatus, and the control apparatus controls a plurality of devices.
The control device sends an emergency instruction to the equipment to enable the equipment to execute emergency treatment measures. Therefore, when the mechanical equipment of the machining center breaks down, the equipment is shut down in time, and further damage to the equipment and harm to safety of workers are avoided.
The system integrates the whole process from data acquisition, analysis to output result and control of the equipment, and realizes the purpose of analyzing the equipment state data by using an artificial intelligent algorithm to obtain the equipment fault state grade to a logic closed loop which influences the equipment emergency treatment.
The control device combines an artificial intelligence model and mechanism analysis, can accurately judge the level of a fault state where the equipment is positioned, and avoids the problems that the linkage control of the equipment is unstable, the equipment is easily interfered by external environmental factors and the judgment of the algorithm on the equipment state is influenced by independently depending on an AI algorithm.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. Mechanical equipment running state monitoring device, its characterized in that includes:
the model storage device is used for storing the trained models, the model storage device can store at least 2 models, and each model corresponds to one type of mechanical equipment;
the equipment data module is used for receiving and storing the state parameters of the mechanical equipment;
the state diagnosis module is used for identifying the equipment type according to the corresponding equipment identifier in the diagnosis instruction, calling the corresponding model according to the equipment type to diagnose the running state and outputting a diagnosis result;
when the model is used for diagnosing the running state, reading the real-time characteristic data of the corresponding mechanical equipment from the equipment data module, and analyzing the real-time characteristic data;
the model, the diagnostic instructions and the real-time characteristic data can be associated through equipment identification.
2. The mechanical equipment operation state monitoring device according to claim 1, further comprising:
and the control module is used for outputting a control instruction according to the diagnosis result.
3. The mechanical equipment operation state monitoring device according to claim 1, further comprising:
and the trigger condition judging module is used for outputting a diagnosis instruction when the diagnosis condition is triggered, wherein the diagnosis instruction comprises the equipment identifier of the mechanical equipment to be diagnosed.
4. The mechanical equipment operation state monitoring device according to any one of claims 1 to 4, characterized by further comprising:
the equipment selection module is used for judging whether the mechanical equipment is in the registration list or not when the diagnosis instruction is received, sending out prompt information if the mechanical equipment is not in the registration list, and selecting a model corresponding to the equipment if the mechanical equipment is in the registration list;
and the equipment management module is used for creating equipment according to an external instruction, receiving the uploaded new equipment model and storing the model to the model storage device.
5. The mechanical equipment running state monitoring method is characterized by comprising the following steps:
s1, receiving and storing the state parameters of the mechanical equipment;
s2, when a diagnosis instruction is received, identifying the equipment type of the mechanical equipment to be diagnosed according to the equipment identification in the diagnosis instruction;
and S3, calling a corresponding model according to the identified equipment type, reading the stored state parameters of the mechanical equipment to be diagnosed by the model to execute state diagnosis, and outputting a diagnosis result.
6. The mechanical equipment operation state monitoring method according to claim 5, characterized by further comprising the steps of:
and S4, generating a control command according to the state diagnosis result and sending the control command to the corresponding mechanical equipment.
7. The method for monitoring the operating status of mechanical equipment according to claim 5, wherein in step S3, it is further determined whether the mechanical equipment to be diagnosed in the identification status diagnosis condition exists in the registration list, and if not, a new equipment access prompt is issued.
8. The mechanical equipment operation state monitoring method according to claim 7, further comprising an equipment registration step of: receiving a mechanical equipment creating request and an uploaded model of the mechanical equipment, adding the mechanical equipment into a registered list, storing the model, and binding the mechanical equipment and the model thereof; the device registration steps are not in sequence with steps S1-S3.
9. Mechanical equipment running state monitored control system, its characterized in that includes:
the data acquisition module is used for acquiring state parameters of the mechanical equipment;
the control device is used for receiving the state parameters, calling the correspondingly stored model by the state instruction to diagnose the state of the mechanical equipment, outputting a state diagnosis result, and sending a control instruction to the emergency control switch when the state diagnosis result indicates that a fault occurs; the control device adopts the mechanical equipment operation state monitoring device of any one of claims 1 to 6;
and the emergency control switch is used for receiving the control instruction of the control device and controlling the mechanical equipment according to the control instruction.
10. The mechanical equipment running state monitoring system according to claim 9, further comprising a data gateway, wherein the data acquisition module transmits the acquired state parameters to the control device through the data gateway, and the control device transmits a control command to the emergency control switch through the data gateway.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111656245.6A CN114281052A (en) | 2021-12-30 | 2021-12-30 | Mechanical equipment running state monitoring device, system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111656245.6A CN114281052A (en) | 2021-12-30 | 2021-12-30 | Mechanical equipment running state monitoring device, system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114281052A true CN114281052A (en) | 2022-04-05 |
Family
ID=80878759
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111656245.6A Pending CN114281052A (en) | 2021-12-30 | 2021-12-30 | Mechanical equipment running state monitoring device, system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114281052A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114647234A (en) * | 2022-05-23 | 2022-06-21 | 医链数科医疗科技(江苏)有限公司 | Medical equipment monitoring method and device based on Internet of things and storage medium |
| CN115499273A (en) * | 2022-08-12 | 2022-12-20 | 上海航天精密机械研究所 | Edge computing soft gateway for numerical control equipment and implementation method thereof |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1910563A (en) * | 2004-01-07 | 2007-02-07 | 松下电器产业株式会社 | Device registration system, server, and terminal device |
| CN103556664A (en) * | 2013-11-13 | 2014-02-05 | 山推工程机械股份有限公司 | Automatic fault protection method and system for bulldozer |
| US20170214717A1 (en) * | 2016-01-22 | 2017-07-27 | Rockwell Automation Technologies, Inc. | Model-based security policy configuration and enforcement in an industrial automation system |
| CN110861123A (en) * | 2019-11-14 | 2020-03-06 | 华南智能机器人创新研究院 | Method and device for visually monitoring and evaluating running state of robot |
| CN111361444A (en) * | 2020-04-09 | 2020-07-03 | 重庆工业职业技术学院 | Pure electric vehicle charging fault diagnosis method and device |
| CN112383891A (en) * | 2020-10-02 | 2021-02-19 | 中盈优创资讯科技有限公司 | Equipment registration method and device based on object model automatic matching |
| CN112536819A (en) * | 2020-05-26 | 2021-03-23 | 深圳优地科技有限公司 | Fault processing method and device, robot and storage medium |
| CN113154897A (en) * | 2021-04-13 | 2021-07-23 | 上海电气斯必克工程技术有限公司 | Long-range fortune dimension system of thermal power plant air cooling system |
| CN113470475A (en) * | 2021-09-06 | 2021-10-01 | 深圳市信润富联数字科技有限公司 | Real-operation learning assessment method and system based on scene simulation and Internet of things |
| CN113556267A (en) * | 2021-07-20 | 2021-10-26 | 全球能源互联网研究院有限公司 | Terminal equipment state monitoring method and system and edge Internet of things proxy gateway |
| CN113656170A (en) * | 2021-07-27 | 2021-11-16 | 华南理工大学 | Intelligent equipment fault diagnosis method and system based on fog calculation |
| CN113821250A (en) * | 2021-09-23 | 2021-12-21 | 佛山技研智联科技有限公司 | Equipment management method, device, equipment and storage medium |
-
2021
- 2021-12-30 CN CN202111656245.6A patent/CN114281052A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1910563A (en) * | 2004-01-07 | 2007-02-07 | 松下电器产业株式会社 | Device registration system, server, and terminal device |
| CN103556664A (en) * | 2013-11-13 | 2014-02-05 | 山推工程机械股份有限公司 | Automatic fault protection method and system for bulldozer |
| US20170214717A1 (en) * | 2016-01-22 | 2017-07-27 | Rockwell Automation Technologies, Inc. | Model-based security policy configuration and enforcement in an industrial automation system |
| CN110861123A (en) * | 2019-11-14 | 2020-03-06 | 华南智能机器人创新研究院 | Method and device for visually monitoring and evaluating running state of robot |
| CN111361444A (en) * | 2020-04-09 | 2020-07-03 | 重庆工业职业技术学院 | Pure electric vehicle charging fault diagnosis method and device |
| CN112536819A (en) * | 2020-05-26 | 2021-03-23 | 深圳优地科技有限公司 | Fault processing method and device, robot and storage medium |
| CN112383891A (en) * | 2020-10-02 | 2021-02-19 | 中盈优创资讯科技有限公司 | Equipment registration method and device based on object model automatic matching |
| CN113154897A (en) * | 2021-04-13 | 2021-07-23 | 上海电气斯必克工程技术有限公司 | Long-range fortune dimension system of thermal power plant air cooling system |
| CN113556267A (en) * | 2021-07-20 | 2021-10-26 | 全球能源互联网研究院有限公司 | Terminal equipment state monitoring method and system and edge Internet of things proxy gateway |
| CN113656170A (en) * | 2021-07-27 | 2021-11-16 | 华南理工大学 | Intelligent equipment fault diagnosis method and system based on fog calculation |
| CN113470475A (en) * | 2021-09-06 | 2021-10-01 | 深圳市信润富联数字科技有限公司 | Real-operation learning assessment method and system based on scene simulation and Internet of things |
| CN113821250A (en) * | 2021-09-23 | 2021-12-21 | 佛山技研智联科技有限公司 | Equipment management method, device, equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114647234A (en) * | 2022-05-23 | 2022-06-21 | 医链数科医疗科技(江苏)有限公司 | Medical equipment monitoring method and device based on Internet of things and storage medium |
| CN115499273A (en) * | 2022-08-12 | 2022-12-20 | 上海航天精密机械研究所 | Edge computing soft gateway for numerical control equipment and implementation method thereof |
| CN115499273B (en) * | 2022-08-12 | 2023-11-10 | 上海航天精密机械研究所 | Edge computing soft gateway for numerical control equipment and implementation method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9996405B2 (en) | Embedded prognostics on PLC platforms for equipment condition monitoring, diagnosis and time-to-failure/service prediction | |
| US6694286B2 (en) | Method and system for monitoring the condition of an individual machine | |
| CN114281052A (en) | Mechanical equipment running state monitoring device, system and method | |
| CN110347124B (en) | Diagnostic service system and diagnostic method using network | |
| CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
| US7702401B2 (en) | System for preserving and displaying process control data associated with an abnormal situation | |
| CN108620950B (en) | Method and system for monitoring machining state of turning tool | |
| CN101939766A (en) | System and method of monitoring and quantifying performance of an automated manufacturing facility | |
| JPS6040043B2 (en) | Method and apparatus for performing monitoring and diagnostic operations on computer-controlled machine tools | |
| US11480941B2 (en) | Analysis device, analysis method, and non-transitory computer readable medium recording an analysis program | |
| CN111098463A (en) | Injection molding machine fault diagnosis system and diagnosis method | |
| CN113341879A (en) | Data acquisition and monitoring method and system for numerical control machine tool | |
| CN111627199A (en) | Hydropower station dam safety monitoring system and monitoring method | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN113420465A (en) | Hydraulic support full-life cycle management method based on digital twin model | |
| KR20210006832A (en) | Method and apparatus for machine fault diagnosis | |
| CN110765633A (en) | Intelligent management method and device for power device | |
| CN112329341B (en) | Fault diagnosis system and method based on AR and random forest model | |
| CN115660640A (en) | Intelligent automobile part fault diagnosis modeling method, electronic equipment and program product | |
| JP2003050617A (en) | Abnormality predicting and service life managing system | |
| CN111599033B (en) | Processing method for diagnosing cigarette machine fault | |
| CN114165430A (en) | Method, system, equipment and medium for monitoring health of pump based on edge calculation | |
| WO2021042233A1 (en) | Remote diagnosis system, apparatus and method for power tool | |
| KR20210059271A (en) | Management system of machine based on a vibration | |
| US20190369594A1 (en) | Diagnosis device, diagnosis method, and diagnosis program |
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 |