CN110830943A - Equipment state monitoring system based on edge calculation and big data analysis - Google Patents

Abstract

The invention relates to an equipment state monitoring system, in particular to an equipment state monitoring system based on edge calculation and big data analysis, which comprises a sensor layer, a terminal layer, a gateway layer and a platform layer, wherein the sensor layer senses a signal of an equipment running state and sends the signal to the terminal layer, the terminal layer analyzes and calculates the received signal and sends the data to the gateway layer, and the gateway layer cleans and integrates the data and then stores, analyzes and inquires the data in the platform layer. The edge computing capability provided by the invention on the terminal layer and the gateway layer prevents all real-time state monitoring data from being transmitted to the cloud platform for centralized processing, reduces the requirements on the transmission bandwidth of a communication line and the storage and computing capability of the server, is suitable for real-time state monitoring and intelligent operation and maintenance application of a large amount of equipment, and can ensure the real-time property and the continuity of the system monitoring data.

Description

Equipment state monitoring system based on edge calculation and big data analysis

Technical Field

The invention relates to the field of equipment state monitoring, in particular to an equipment state monitoring system based on edge calculation and big data analysis.

Background

Electromechanical devices such as motors and pumps are widely used in industrial production, and the devices need to be maintained regularly, some vulnerable parts are replaced, and some faults caused by long working time and application environment variation are avoided. At present, the maintenance of the pump is basically regular maintenance or repair and rush repair after a fault occurs. Therefore, on one hand, equipment failure can be caused due to insufficient experience of inspection personnel or untimely maintenance, so that production cannot be effectively guaranteed, and economic loss and even major accidents are caused; on the other hand, the well-operated equipment can be stopped for maintenance, which causes unnecessary production interruption and waste of maintenance cost.

The operation state of the electromechanical equipment is monitored on line by adopting an advanced sensor and an information technology, so that the reliability, the safety and the availability of the electromechanical equipment can be improved, and the maintenance cost of the equipment is effectively reduced. The sensors in the monitoring system collect real-time equipment state data, if all the data are transmitted to a background server or a cloud platform for storage and processing, when the data volume of monitoring signals is large (such as vibration signals) and the number of monitoring equipment is large, higher requirements on communication bandwidth and cloud platform storage and computing capacity are provided. Therefore, the distributed computing structure is a development direction of the equipment state monitoring system.

Disclosure of Invention

Aiming at the technical problems, the invention provides an equipment state monitoring system of a multi-stage fully-distributed processing architecture, which is based on an edge computing and big data analysis technology and consists of an intelligent terminal, an edge gateway and a cloud service platform.

The technical scheme adopted by the invention for solving the technical problems is as follows: the utility model provides an equipment state monitoring system based on edge calculation and big data analysis, includes sensor layer, terminal layer, gateway layer and platform layer, sensor layer response equipment running state's signal to with signal transmission to the terminal layer, this terminal layer carries out the analysis and calculation to the signal that receives, again with data transmission to the gateway layer, this gateway layer washs data, takes place after the integrated processing extremely the platform layer is saved, is analyzed, inquires.

Preferably, the terminal layer is a terminal layer with edge computing capability, and the gateway layer is a gateway layer with edge computing capability.

Preferably, the sensor layer comprises vibration, temperature, rotation speed, voltage, current, pressure and flow sensors, and the sensors are installed on equipment and send induction signals to the terminal layer.

Preferably, the terminal layer comprises an intelligent terminal, and the intelligent terminal collects signals sent by the sensor in real time, calculates characteristic values and sends calculation results to the gateway layer.

Preferably, the intelligent terminal performs time domain and frequency domain analysis and calculation on the sensor data acquired in real time to obtain a time domain characteristic value and a frequency domain characteristic value, establishes a physical fault model at the equipment terminal, and diagnoses and alarms in real time.

Preferably, the sensor is connected to an analog or digital acquisition channel of the intelligent terminal in a wired or wireless mode.

Preferably, the terminal layer further includes an OPC terminal, and the OPC terminal acquires the operating condition parameters from the control system of the device and sends the operating condition parameters to the gateway layer.

Preferably, the OPC terminal is connected to a programmable logic controller or an OPC server in a control system of the device via a field bus interface or a local area network, and exchanges data via a communication protocol or an OPC standard.

Preferably, the gateway layer includes an edge gateway, and the edge gateway receives the device state characteristic value and the operating condition parameter from the intelligent terminal and the OPC terminal in a wired or wireless communication manner, and performs cleaning and integrated processing on data according to the relationship between the start-stop state, the load state, the environmental change, and the device state characteristic value of the device.

Preferably, the platform layer comprises a cloud server and an application program, and the cloud server receives the device state data from the edge gateway to realize data storage, analysis and query; the application program establishes a unit personalized operation and maintenance model based on data drive by utilizing big data, cloud computing and artificial intelligence technologies.

According to the technical scheme, the fully-distributed computing architecture provided by the invention has the advantages that the fully-distributed computing architecture is suitable for real-time state monitoring and fault diagnosis analysis application of a large number of devices, and the real-time performance and the continuity of system monitoring data can be ensured. If the real-time sensor data of each device is transmitted to the server for centralized processing, when the number of the monitored devices is large, the requirements on the transmission bandwidth of a communication line and the storage and calculation capabilities of the server are high, and the effect of real-time analysis and diagnosis is difficult to achieve; in addition, if a server is down or a network fails, all equipment data is lost and the analysis and diagnosis service is interrupted. The intelligent terminal and the edge gateway in the system structure have computing capability, the data volume needing to be uploaded is greatly reduced after the intelligent terminal performs state characteristic computation, and the edge gateway performs preprocessing on the data, so that the computing pressure of a server can be reduced, and the system structure can be suitable for real-time state monitoring and fault diagnosis analysis application of a large number of devices. Meanwhile, the intelligent terminal and the edge gateway have storage capacity, when the communication line is abnormal, data can be stored locally for a period of time and uploaded when communication is recovered, and the continuity of system monitoring data is guaranteed.

Drawings

Fig. 1 is a block diagram of the present invention.

Detailed Description

The invention will now be described in detail with reference to fig. 1 and examples, wherein the exemplary embodiments and descriptions of the invention are provided to explain the invention, but not to limit the invention.

The invention provides an equipment state monitoring system based on edge calculation and big data analysis, which comprises a sensor layer 1, aterminal layer 2, a gateway layer 3 and aplatform layer 4, wherein the sensor layer senses signals of the running state ofequipment 5 and sends the signals to the terminal layer, the terminal layer analyzes and calculates the received signals and sends the data to the gateway layer, and the gateway layer cleans and integrates the data and then stores, analyzes and inquires the data in the platform layer. The device state monitoring system of the multilevel fully-distributed processing architecture of the sensor layer, the terminal layer, the gateway layer and the platform layer is formed, advanced sensors and information technology are adopted, the running state of the device can be monitored on line, and the reliability, the safety and the usability of the device are improved.

Preferably, the terminal layer is a terminal layer with edge computing capability, and the gateway layer is a gateway layer with edge computing capability. The monitoring system provided by the invention avoids the condition that the real-time monitoring data is completely transmitted to the cloud platform for centralized processing through the edge computing capability provided by the terminal layer and the gateway layer, reduces the requirements on the transmission bandwidth of a communication line and the storage and computing capability of the server, is suitable for real-time state monitoring and intelligent operation and maintenance application of a large amount of equipment, and can ensure the real-time property and continuity of the monitoring data of the system.

The sensor layer 1 comprises vibration, temperature, rotating speed, voltage, current, pressure andflow sensors 11, and the sensors are arranged 5 on equipment to realize signal conversion of the running state of the equipment and send induction signals to the terminal layer. Theterminal layer 2 comprises anintelligent terminal 21, anOPC terminal 22 and the like, and the OPC terminal acquires working condition parameters from a control system (DCS) 6 of the equipment and sends the working condition parameters to the gateway. The gateway layer 3 comprises anedge gateway 31, the edge gateway receives the state characteristic values uploaded by the intelligent terminal, performs comprehensive analysis together with the equipment working condition parameters, and then sends the state characteristic values to the platform for storage. Theplatform layer 4 includes acloud server 41 andvarious application programs 42, and the cloud server receives device status data from the gateway to implement functions such as data storage, analysis, and query. Various application programs can provide various WEB and mobile APP comprehensive application services.

Specifically, the sensor is connected to an analog or digital acquisition channel of the intelligent terminal in a wired or wireless mode, and the sensor data accessed to the equipment control system is obtained through communication between the OPC terminal and the control system. The intelligent terminal can analyze and calculate the time domain and the frequency domain of the sensor data acquired in real time, obtain time domain characteristic values (effective values, crest factors, kurtosis coefficients and the like of sensor signals) and frequency domain characteristic values (frequency spectrum components, current frequency spectrum components and the like related to frequency conversion), establish a physical fault model at a device end, and diagnose and alarm in real time. The OPC terminal is connected with a Programmable Logic Controller (PLC) or an OPC server in the equipment control system through a field bus interface or a local area network, and exchanges data through a communication protocol or an OPC standard.

The edge gateway of the invention adopts a wired or wireless communication mode to receive the equipment state characteristic value and the working condition parameter from the intelligent terminal and the OPC terminal, and carries out pretreatment such as cleaning, integrating and the like on data according to the relation between the start-stop state, the load state and the environmental change of the equipment and the equipment state characteristic value. When the number of terminals in the system is small and the scale is small, the edge gateway can be deployed on the server in the form of a service program. The application program of the platform layer establishes a unit personalized operation and maintenance model based on data drive by utilizing big data, cloud computing and artificial intelligence technology, provides automatic and intelligent cloud service for daily point inspection, health state assessment, maintenance scheme suggestion, maintenance effect assessment and energy efficiency optimization of equipment, and achieves the purposes of ensuring safe and reliable operation of the unit, improving operation efficiency and saving operation and maintenance cost.

Referring to fig. 1, the monitoring system of the present invention can be applied to a plurality of devices for monitoring at the same time, and the following embodiment is only an example of real-time monitoring and fault diagnosis of the operation state of the mill unit of the chemical plant, and is described in detail:

in this embodiment, a vibration sensor is mounted on a bearing cap of a motor, a fluid coupling, and a fan of each vertical mill fan unit, and a temperature sensor is mounted on a bearing cap of the motor and the fan. A motor, a speed reducer and a bearing cover and a gear box of a rocker arm of each vertical mill host machine set are provided with vibration sensors, a temperature sensor is arranged on the bearing cover of the motor, and a rotating speed sensor is arranged at a coupler. And a vibration sensor and a temperature sensor are arranged on a motor, a speed reducer bearing cover and a gear box of each powder selecting unit. All sensors are connected to the analog signal acquisition channel of the intelligent terminal through cables.

In this embodiment, the intelligent terminal is designed with 8-channel temperature, 8-channel vibration and 1-channel rotational speed sensor signal interfaces. The sampling frequency of a vibration signal channel is 40kHz, 8 channels are synchronously sampled, the effective value, the peak value, the crest factor and the warping degree coefficient of the signal are calculated in real time, FFT, resonance demodulation spectrum analysis and order spectrum analysis are carried out, and the calculation result is sent to an edge gateway by adopting Lora wireless communication. The intelligent terminal can carry out equipment fault diagnosis according to vibration signal time domain calculation and frequency domain analysis results, and can give an alarm for temperature abnormity.

In this embodiment, the OPC terminal communicates with the device control system PLC through a serial port to obtain the unit operating condition parameters, including voltage, current, winding temperature, ambient temperature, blower inlet/outlet pressure, and the like. And the OPC terminal sends the acquired data to the edge gateway through the Ethernet port. The edge gateway is provided with a Lora communication interface and an Ethernet interface, receives state characteristic data sent by the intelligent terminal and working condition parameters sent by the OPC terminal, performs data fusion and preprocessing, and transmits the data to the cloud service platform through the 4G communication module.

In this embodiment, the application software of the platform layer is developed based on JAVA, adopts a micro-service architecture, and can be flexibly deployed in various cloud environments. The application service provides panoramic state monitoring, trend and statistical analysis, state prediction and evaluation and intelligent operation and maintenance functional modules. The panoramic state monitoring function displays the running state and the fault condition of the equipment in a bird's-eye view mode, and the running state data of the equipment can be displayed by clicking the equipment. The trend and statistical analysis function provides a multi-state data time history trend curve of a single unit, the time history trends of the same state data of a plurality of units are compared, the start-stop times, the accumulated running time, the classification alarm times and the type statistics of the unit in a certain time period are carried out, and the maintenance level early warning threshold of the equipment state parameters are automatically generated or corrected according to the statistical result. The state prediction and evaluation function is based on the current operation state data, the working condition and environment data, the maintenance data and the historical data of the equipment, and an evaluation model and a total health index which comprehensively reflect the health state of the equipment are constructed hierarchically, so that the health state of the equipment is comprehensively, scientifically and automatically evaluated. The intelligent operation and maintenance function is based on a production plan, an equipment health state evaluation result and an energy efficiency analysis result, and performs capacity-health-energy efficiency multi-target collaborative optimization through health-capacity, capacity-energy efficiency and health-energy efficiency constraint association analysis, so as to provide intelligent operation and maintenance cloud services such as production scheduling optimization, maintenance plan generation and energy efficiency optimization suggestion. All services can be accessed and obtained through the Web and mobile APP.

Claims (10)

1. An equipment state monitoring system based on edge calculation and big data analysis is characterized in that: including sensor layer, terminal layer, gateway layer and platform layer, sensor layer responds to the signal of equipment running state to with signal transmission to the terminal layer, this terminal layer carries out the analysis and calculation to the signal of receiving, again with data transmission to the gateway layer, this gateway layer washs, integrated processing the data after taking place extremely the platform layer is saved, is analyzed, inquires.

2. The system for monitoring the state of equipment based on edge calculation and big data analysis according to claim 1, wherein: the terminal layer is a terminal layer with edge computing capability, and the gateway layer is a gateway layer with edge computing capability.

3. The system for monitoring the state of equipment based on edge calculation and big data analysis according to claim 2, wherein: the sensor layer includes vibration, temperature, rotational speed, voltage, electric current, pressure, flow sensor, and the sensor is installed on equipment to with sensing signal send to the terminal layer.

4. The system for monitoring the state of equipment based on edge calculation and big data analysis according to claim 3, wherein: the terminal layer comprises an intelligent terminal, and the intelligent terminal collects signals sent by the sensor in real time, calculates characteristic values and sends calculation results to the gateway layer.

5. The system for monitoring the state of equipment based on edge calculation and big data analysis according to claim 4, wherein: the intelligent terminal carries out time domain and frequency domain analysis and calculation on sensor data acquired in real time to obtain a time domain characteristic value and a frequency domain characteristic value, and establishes a physical fault model at an equipment terminal and carries out real-time diagnosis and alarm.

6. The system for monitoring the state of equipment based on edge calculation and big data analysis according to claim 4, wherein: the sensor is connected to an analog or digital acquisition channel of the intelligent terminal in a wired or wireless mode.

7. The system for monitoring the state of equipment based on edge calculation and big data analysis according to claim 4, wherein: the terminal layer also comprises an OPC terminal, and the OPC terminal acquires working condition parameters from a control system of the equipment and sends the working condition parameters to the gateway layer.

8. The system for monitoring the state of equipment based on edge calculation and big data analysis according to claim 7, wherein: the OPC terminal is connected with a programmable logic controller or an OPC server in a control system of the equipment through a field bus interface or a local area network, and exchanges data through a communication protocol or an OPC standard.

9. The system for monitoring the state of equipment based on edge calculation and big data analysis according to claim 7 or 8, wherein: the gateway layer comprises an edge gateway, the edge gateway receives the equipment state characteristic value and the working condition parameter from the intelligent terminal and the OPC terminal in a wired or wireless communication mode, and cleans and integrally processes data according to the relation between the start-stop state, the load state and the environmental change of the equipment and the equipment state characteristic value.

10. The system for monitoring the state of equipment based on edge calculation and big data analysis according to claim 9, wherein: the platform layer comprises a cloud server and an application program, the cloud server receives equipment state data from the edge gateway, and data storage, analysis and query are realized; the application program establishes a unit personalized operation and maintenance model based on data drive by utilizing big data, cloud computing and artificial intelligence technologies.

Images