CN112650166A - Production line condition big data system based on wireless network and diagnosis method thereof - Google Patents

本发明公开了一种基于无线网络的生产线状况大数据系统，其特征在于：包括设备端和云端，设备端包括无线数据交互协议模块，无线采集模块，子网网络模块，中心节点模块，PLC控制网络模块；所述云端包括输送线故障应急通知模块，服务端故障决策模块，输送线健康状况分析模块，设备数据存储模块，服务端数据接收模块；本发明能够及时、快速找到输送线中发生问题的故障设备，减少人工劳力的花费。

The invention discloses a production line condition big data system based on a wireless network, which is characterized in that it includes a device end and a cloud, and the device end includes a wireless data interaction protocol module, a wireless acquisition module, a subnet network module, a central node module, and a PLC control module. network module; the cloud includes a transmission line fault emergency notification module, a server-side fault decision-making module, a transmission line health status analysis module, an equipment data storage module, and a server-side data receiving module; the present invention can timely and quickly find problems in the transmission line of faulty equipment, reducing labor costs.

Production line condition big data system based on wireless network and diagnosis method thereof

Technical Field

The invention relates to the technical field of intelligent control, in particular to a production line condition big data system based on a wireless network and a diagnosis method thereof.

Background

With the continuous progress of advanced automation technology, the manufacturing technology is rapidly developed day by day, and particularly in automatic systems such as logistics, express delivery and the like, a large number of conveying mechanical devices and systems exist, so that the whole production process needs to be operated stably and continuously for a long time under heavy load. However, the fine design of the system and the complex and severe working environment are the biggest defects of the service life of the equipment, and the failure rate of the fine equipment is high due to the severe working environment.

Whether the equipment system can be safely and effectively put into operation for a long time in a special environment or not is very high in daily maintenance and repair cost of the equipment; in fast paced, high intensity advanced industrial systems, traditional maintenance and repair procedures have not kept pace with the wear pace of equipment. From the whole industry, under a fast-paced and high-precision working system of industrial production, the development of a system maintenance technology based on real-time monitoring of working equipment becomes a key point of attention of related industries.

In the conveying line production equipment, special equipment such as a motor, a speed reducer, a roller way or a belt conveyor and the like are used in a large quantity and are in long-term uninterrupted work, even high-reliability equipment can generate abrasion in long-term operation and gradually damage to lose normal functions. Through a large amount of researches, the damage of the equipment is not an emergent condition but a long-term continuous deterioration process; scientific research shows that main state parameters representing the health condition of machine equipment before the machine equipment is damaged, including key data such as vibration quantity of the equipment, surface temperature of a main shafting abrasion point, vibration quantity of a speed reducer set and the like can show regular changes, faults of conveying line production equipment can be predicted in advance and reported through continuously monitoring changes of the data, measures are taken before major faults occur, and great waste of production cost after the faults occur is reduced.

The intelligent operation maintenance of the equipment unit is carried out by combining a large amount of monitoring data of the production line motor unit and constructing a production line big data platform, and the development trend of the industry is reached. The production line big data has the characteristics of large data size, complex data structure, high data generation speed, data coupling redundancy, low value density, strong data time variation and the like.

In order to efficiently transmit a large amount of data between field acquisition equipment (lower computer) and an upper computer for fault identification and prediction, the existing emerging cloud computing technology can be used. The traditional single computer computing mode limits the mining efficiency of the big data of the production line, the big data system can realize the quick real-time analysis of the big data of the production line with high throughput based on the distributed cluster parallel computing mode, and the expandability of the nodes is realized, so that the problem of insufficient traditional computing resources is solved.

Relatively speaking, the change of the key state parameters of the production equipment of the conveying line is a very long process, if the regular inspection and detection are carried out by equipment maintenance personnel, a large amount of labor hour needs to be consumed, the more complex the production process is, the larger the scale of the production line is, the larger the labor hour needed by the work is, the state parameter data obtained by manual statistics cannot directly reflect the health condition of a machine, and equipment with hidden troubles of faults can be found in advance only by long-term continuous data analysis and interpretation. If an equipment defect point with hidden danger is to be found in mass data, the equipment defect point is almost unlikely to be found, even if the equipment fails, a great deal of maintenance man-hours are required to be consumed for accurately finding the fault point and performing maintenance treatment, and indirect loss caused by equipment halt and production halt in the maintenance process is inevitable.

The problem is particularly obvious in the industries of express delivery, logistics and the like which operate efficiently and fully automatically, economic loss and production time consumption caused by faults are large hidden cost which cannot be ignored, and further, maintenance and after-sales technicians configured for guaranteeing production and operation of equipment feel high in cost and low in efficiency due to high human cost.

Disclosure of Invention

The invention aims to provide a production line health condition fault big data diagnosis method based on a wireless network, and solves the problem that the health condition of a machine cannot be directly found and obtained due to large labor input of manual regular inspection equipment.

In order to solve the technical problems, the invention adopts the following technical scheme:

a production line condition big data system based on a wireless network comprises an equipment end and a cloud end, wherein the equipment end comprises a wireless data interaction protocol module, a wireless acquisition module, a subnet network module, a central node module and a PLC control network module; the cloud end comprises a transmission line fault emergency notification module, a server end fault decision module, a transmission line health condition analysis module, an equipment data storage module and a server end data receiving module; the wireless acquisition module is arranged on field equipment and is connected with the subnet network module, the subnet network module is connected with the central node module, the central node module is connected with the PLC control network module, the PLC control network module is connected with the server data receiving module through the wireless data interaction protocol module, the server data receiving module is connected with the equipment data storage module, the equipment data storage module is connected with the conveyor line health condition analysis module, the conveyor line health condition analysis module is connected with the server fault decision module, the server fault decision module is connected with the conveyor line fault emergency notification module, and the conveyor line fault emergency notification module feeds back to the PLC control network module.

Furthermore, the wireless acquisition module is responsible for monitoring, acquiring and preprocessing key health data of the field equipment; the sub-network module is arranged on the production line site, assists in wirelessly networking each on-site wireless acquisition module, and collects all health data of all equipment in the corresponding sub-network segment; the central node module is arranged on a plurality of sites and is responsible for wirelessly networking each site subnet network module to form a local area network and collecting all health data corresponding to equipment corresponding to all subnet sections in the local area network; the PLC control network module is responsible for accessing all field central node modules into the original transmission line control system, and the data is transmitted to a higher-level big data analysis center from a control network in a centralized manner by virtue of the PLC control network module; the wireless data interaction protocol module assists in packaging and sending all data to a cloud end; the server data receiving module is responsible for receiving a data packet sent by the wireless data interaction protocol module in an auxiliary manner of packaging all data; the device data storage module is responsible for the data packet received by the storage end data receiving module; the transmission line health condition analysis module is responsible for taking out and analyzing health data of the equipment in a data packet in the equipment data storage module; the server fault decision module is responsible for making a decision according to a conclusion obtained by analysis of the transmission line health condition analysis module; and the transmission line fault emergency notification module is responsible for feeding back the decision made by the server fault decision module to the PLC control network module and other monitoring modules.

Further, the wireless acquisition module comprises a sensor module, a data processing and control module, a wireless communication module and an energy supply module which are electrically connected in sequence, the sensor module comprises a sensor and an A/D converter, the sensor is installed on equipment needing monitoring, the A/D converter is electrically connected with the sensor and connected to the data processing and control module, the data processing and control module comprises a processor and a memory, the processor is connected with the wireless communication module, and the energy supply module is respectively connected with the sensor module, the data processing and control module and the wireless communication module.

Furthermore, 10-20 wireless acquisition modules are networked through a wireless network to form a subnet network module.

Further, networking the 5-8 sub-network modules to form a central node module.

Further, the 6-10 central node modules are connected to the PLC control network module of the original equipment.

Further, the data that wireless acquisition module gathered include the vibration data of motor, the surface temperature of key position point, proximity sensor's output state, and the vibration data includes time domain monitoring characteristic index and frequency domain monitoring characteristic index.

Further, the method for diagnosing the production line condition big data system based on the wireless network comprises the following steps;

1) constructing a big data diagnosis system;

2) obtaining diagnosis parameters through a diagnosis system, wherein the diagnosis parameters comprise vibration data of a motor, the surface temperature of a key position point and the output state of a proximity sensor, and the vibration data comprise a time domain monitoring characteristic index and a frequency domain monitoring characteristic index; in the process of obtaining the diagnosis, firstly, an original PLC control network module records original key parameters to form normal data comparison, and then a wireless acquisition module acquires the diagnosis data in real time to form a data stream;

3) summarizing and analyzing the data;

4) making a decision according to the summarized and analyzed information;

5) and classifying the decision-making information for feedback.

Compared with the prior art, the invention has the beneficial effects that:

the trouble equipment that takes place the problem in the transfer chain can be timely, quick found, the cost of artifical labour is reduced.

Drawings

FIG. 1 is a block diagram showing the overall structure of the system of the present invention.

Fig. 2 is a hierarchical diagram of the control network of the system of the present invention.

Fig. 3 is a structure diagram of the on-site wireless acquisition module of the present invention.

Fig. 4 is a diagram of a subnet network architecture of the present invention.

Fig. 5 is a diagram of a wireless center node structure according to the present invention.

Fig. 6 is a diagram illustrating a PLC network connection structure according to the present invention.

Fig. 7 is a schematic diagram of a data transmission protocol structure.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Example 1:

as shown in the figure, the production line condition big data system based on the wireless network comprises an equipment end and a cloud end, wherein in order to form a mature big system for collecting data; the equipment end comprises a wireless data interaction protocol module, a wireless acquisition module, a subnet network module, a central node module and a PLC control network module; the cloud end comprises a transmission line fault emergency notification module, a server end fault decision module, a transmission line health condition analysis module, an equipment data storage module and a server end data receiving module. Specifically, the wireless acquisition module is arranged on the field device and is connected with the subnet network module, the subnet network module is connected with the central node module, the central node module is connected with the PLC control network module, the PLC control network module is connected with the server data receiving module through the wireless data interaction protocol module, the server data receiving module is connected with the device data storage module, the device data storage module is connected with the conveyor line health condition analysis module, the conveyor line health condition analysis module is connected with the server fault decision module, the server fault decision module is connected with the conveyor line fault emergency notification module, and the conveyor line fault emergency notification module feeds back to the PLC control network module.

Example 2:

on the basis of the above embodiments, in this embodiment, each component of the system is specifically responsible for the following functional implementation:

the wireless acquisition module is responsible for monitoring, acquiring and preprocessing key health data of the field equipment; the sub-network module is arranged on the production line site, assists in wirelessly networking each on-site wireless acquisition module, and collects all health data of all equipment in the corresponding sub-network segment; the central node module is arranged on a plurality of sites and is responsible for wirelessly networking each site subnet network module to form a local area network and collecting all health data corresponding to equipment corresponding to all subnet sections in the local area network; the PLC control network module is responsible for accessing all field central node modules into the original transmission line control system, and the data is transmitted to a higher-level big data analysis center from a control network in a centralized manner by virtue of the PLC control network module; the wireless data interaction protocol module assists in packaging and sending all data to a cloud end; the server data receiving module is responsible for receiving a data packet sent by the wireless data interaction protocol module in an auxiliary manner of packaging all data; the device data storage module is responsible for the data packet received by the storage end data receiving module; the transmission line health condition analysis module is responsible for taking out and analyzing health data of the equipment in a data packet in the equipment data storage module; the server fault decision module is responsible for making a decision according to a conclusion obtained by analysis of the transmission line health condition analysis module; and the transmission line fault emergency notification module is responsible for feeding back the decision made by the server fault decision module to the PLC control network module and other monitoring modules.

Example 3:

on the basis of the foregoing embodiment, in this embodiment, the wireless acquisition module is a final end node of the whole big data wireless network health condition online fault prediction system, and is designed mainly by using a wireless sensor network technology, as shown in fig. 3, the system includes four parts, namely, a sensor module, a data processing and control module, a wireless communication module, and an energy supply module, specifically, the sensor module includes a sensor and an a/D converter, the sensor is installed on a device to be monitored, the a/D converter is electrically connected to the sensor and connected to the data processing and control module, the data processing and control module includes a processor and a memory, the processor is connected to the wireless communication module, and the energy supply module is respectively connected to the sensor module, the data processing and control module, and the wireless communication module. The wireless acquisition module can convert the acquired original signals into recognizable equipment state data. When the sensor receives an external signal, the A/D converter converts the data and then transmits the data to the data processing control module for signal processing, the processed original signal is converted into a signal which can be identified, the signal is transmitted and exchanged to a previous layer of network through wireless network communication, and the energy supply module continuously provides stable electric energy for the sensor.

Example 4:

on the basis of the above embodiments, in this embodiment, the subnet network control module is a wireless acquisition module installed at a proper position on each device, and then each field wireless acquisition module is connected to the network to form a wireless sensor subnet network, as shown in fig. 4. Each subnet network control module automatically forms a wireless network with each wireless acquisition module through a wireless link, regularly collects the equipment parameter data acquired by each wireless acquisition module in real time, the parameters comprise vibration data of each equipment, surface temperature of a key position point, output state of a proximity sensor and other key data information for representing the running health condition of the equipment, and the data quantity required to be acquired and transmitted by each field equipment is 3 words. In consideration of the transmission delay of wireless network data and the requirement of rapidity of data polling, each subnet network control module can at least simultaneously control 20 wireless acquisition modules in a networking manner, that is, each subnet network control module can at least simultaneously control 20 field devices in a networking manner.

Example 5:

on the basis of the above-described embodiment, in the present embodiment, in order to manage the respective subnets, a central node module of a wireless network is installed at an appropriate position of a production line, as shown in fig. 5. And each subnet network control module is connected to the upper-level PLC control network module. Each subnet network control module can at least simultaneously control 20 field devices in a networking way, and each wireless network center node module can at least simultaneously form a network with 8 field subnet network control modules according to design requirements. In this way, each wireless network central node module can manage 8 × 20=160 field devices simultaneously.

The wireless network center node module and the field subnet network control module form a wireless acquisition network in a wireless ad hoc network mode.

The effective data quantity that each wireless network central node module can gather is 160 × 60 words =9600 words.

Example 6:

on the basis of the above embodiment, in this embodiment, in the original PLC control network module, the ProfiBus-DP fieldbus technology is used, the central node module of each wireless network is accessed to the original PLC control system, and all pieces of field device data are collected in a centralized manner by the PLC fieldbus network. In the system design, at least 6 wireless network center node modules are supported to access the ProfiBus-DP field bus network, and each wireless network center node module can manage 8 × 20=160 field devices, so that the whole system supports 6 × 8 × 20=720 field device data in total.

The total effective data quantity acquired by the whole system is 6 x 9600 words =57600 words. Therefore, the finally obtained effective data collection quantity of the whole system is large, the data transmission rate of each subsystem can be obviously reduced through the wireless sensor network layering technology, the difficulty of system design is reduced, and the workload of system field installation and debugging is reduced.

Example 7:

on the basis of the above embodiment, in this embodiment, in order to better facilitate interaction of data on a control network, a wireless data interaction protocol on the uppermost layer in fig. 7 is provided, in order to improve data transmission and data reliability, the format of data transmitted by each sensor at a time is one byte, where the first 2 bits are used for identifying a version, so that the version number of data sent by the current sensor can be distinguished, different collectors can be conveniently replaced, the data interaction consistency of data between collectors of different generations is ensured, the immediately following 4 bits are used for verification, and 2 bits are left. The effective data amount is 3 words (2 bytes).

Example 8:

on the basis of the above embodiment, in this embodiment, the application method corresponding to the system includes the following steps:

1) constructing a big data diagnosis system;

2) obtaining diagnosis parameters through a diagnosis system, wherein the diagnosis parameters comprise vibration data of a motor, the surface temperature of a key position point and the output state of a proximity sensor, and the vibration data comprise a time domain monitoring characteristic index and a frequency domain monitoring characteristic index; in the process of acquiring the diagnosis, the vibration data is the primary data, and the surface temperature and the output state of the proximity sensor are only used as auxiliary data, such as: when the temperature data at a certain position is far beyond normal, the abnormal fault of the detection electricity of the equipment is necessary. When parameters are obtained, firstly, original key parameters are recorded through an original PLC control network module to form normal data comparison, and then, diagnostic data are collected in real time through a wireless collector to form a data stream;

3) summarizing and analyzing the data;

4) making a decision according to the summarized and analyzed information;

5) and classifying the decision-making information for feedback.

The collected data are processed at the cloud end, the data are not limited by the operation processing capacity of a certain computer, the capacity of data storage is not limited by the storage space of a single computer any more, and statistical analysis of mass data in a long time process can be realized by means of rapidly developed computers and network technologies, so that the fault hidden danger of a fault device can be predicted rapidly and accurately, early warning is made on the device fault in advance, and the production loss caused by device fault shutdown is reduced. The server side of the invention at least comprises the following five modules according to the receiving sequence of the data:

1) the server data receiving module is used for receiving field acquired equipment data, is used as an interface for field acquisition and background service processing, and has the functions of data storage routing and data log storage besides providing data receiving cache;

2) the device data storage module is used for storing the acquired device data, the format is not limited to texts and databases, and the data storage performance and indexes can meet the parallel data storage of the 720 collectors at least;

3) the transmission line health condition analysis module is a place which needs attention, collected field data are time sequence data, and the most important motor data on a production line at present are vibration data.

Vibration is a very important operating condition characteristic. The healthy motor can generate regular vibration more or less during working, mainly because of the coupling of electromagnetic force and mechanical force and the structure of a rotor, energy is transmitted to the surface of the motor layer by layer during the running process of the motor to generate vibration response, and the abnormal vibration of the motor is the external representation of the internal defect of the motor, so that the fault diagnosis of the motor can be carried out by measuring and analyzing the vibration of the motor. The technology for extracting the running health index based on the vibration monitoring data of the equipment mainly comprises 1) time domain monitoring characteristic index extraction and 2) frequency domain monitoring characteristic index extraction.

The time domain monitoring characteristic index is mainly used for researching the time domain distribution rule of the vibration monitoring data by adopting a mathematical statistics related theoretical method; the frequency domain monitoring characteristic indexes are mainly used for carrying out spectrum analysis on signals, such as an effective value amplitude spectrum, a power spectrum, an envelope spectrum and the like, and carrying out effective monitoring and trend analysis by combining with the fault characteristic frequency of the motor.

The module provides time domain and frequency domain data analysis methods, and integrates different data analysis methods of data in a plug-in mode.

The time sequence analysis is a method for predicting the target which can be achieved in the future time domain by analyzing the development process, direction and trend of the time sequence. The method applies the time sequence analysis principle and technology in probability statistics, and utilizes the data correlation of a time sequence system to establish a corresponding mathematical model and describe the time sequence state of the system so as to predict the future.

The method comprises the following basic steps:

based on the data of the related historical data, the different time dynamics such as irregular variation, cyclic variation, seasonal variation and the like, particularly the continuous long-term dynamics, are distinguished, and a statistical chart is arranged;

starting from the system principle, comprehensively analyzing the time sequence, reflecting all causal connections and influences which occur once, and analyzing the comprehensive action of various acting forces;

and (III) calculating each predicted value of the time sequence and the future time states by using a mathematical model, such as a moving average method, a seasonal coefficient method and an exponential smoothing method.

The time sequence analysis is suitable for a time sequence system for data quantization, and mainly adopts a random system which is changed along with time through probability statistical analysis. By utilizing probability statistics, the past data are sorted, the change rule of the past data is analyzed, particularly the continuous long-term action is mastered, and the future state of the equipment phenomenon changing along with time can be predicted. The frequency domain analysis method is an engineering method for researching a control system. The signals in the control system may be represented as a composite of sinusoidal signals of different frequencies. A mathematical model describing the relationship between the steady state output and input signals of the control system when a sinusoidal function of different frequencies is applied is called the frequency characteristic, which reflects the behavior of the system response under the action of the sinusoidal signal. The frequency domain analysis method is a graphical method for studying linear systems by applying frequency characteristics. The frequency characteristic, like the transfer function, can be used to represent the dynamic behavior of a linear system or a link. The frequency domain method of the analysis control system established on the basis of the frequency characteristics makes up for the defects in the time domain analysis method.

The frequency characteristic is the complex ratio of the frequency response of the system to the sinusoidal input signal. And the frequency response refers to the steady-state component of the linear system output under the action of the sinusoidal input signal.

The frequency domain analysis is to decompose a signal into sine waves and synthesize the signal with the sine waves. The decomposition or analysis is to calculate the proportion of sine waves of various frequencies in the signal, and the synthesis or integration is to synthesize the signal according to sine waves of different proportions. The decomposed signal can be processed as follows: and reserving part of sine wave components with larger amplitude for future signal recovery.

4) The server-side fault decision module integrates the multiple monitoring quantities into corresponding multiple monitoring predicted values by adopting a deep learning method, and performs production line equipment health state monitoring and fault early warning by taking a reconstruction error between a model predicted value and an actual value as a monitoring index;

5) the transmission line fault emergency notification module outputs the final information to be processed;

the method combines time domain analysis and frequency domain analysis, and finally, the temperature and the like of the key point position are monitored, and other systems such as storage control system software (WCS) and the like are timely notified according to the fault and decision information processed by 3) and 4), so that corresponding measures can be taken for the fault or the fault which is about to occur most timely.

The title provides a real-time, rapid, remote and accurate method for monitoring the state of transmission line equipment and diagnosing faults.

The collector provided by the invention has the advantages of low cost, expandability and easiness in deployment.

The network layering technology can greatly simplify the functions of a field wireless collector to be installed on each device, and aims to reduce the cost of the collector so as to avoid installation and purchase of a large number of collectors and matched sensors, which causes the total price of the online fault prediction system for the health condition of the transmission line to rise, and the cost performance of system reconstruction to be low, so that users are reluctant to implement system reconstruction and upgrade.

Moreover, after the network layering technology is adopted, the original production line control system does not need to be stopped in the technology transformation process, and transformation can be implemented when the original system is normally produced. The loss of production benefits brought to users due to the fact that equipment is completely shut down in the reconstruction construction process is avoided, and therefore the reconstruction cost of the users is indirectly reduced.

The whole system has large effective data acquisition amount, and the data transmission rate of each subsystem can be obviously reduced, the difficulty of system design is reduced, and the workload of system field installation and debugging is reduced by the wireless sensor network layering technology.

Through the implementation of the technology, the technology such as cloud computing, edge computing, intelligent sensors and machine learning can be combined to enable all production lines to be developed into automatic intelligent production lines based on a big data cloud platform. The intelligent network monitoring of the running equipment of all production sites by the online monitoring system distributed in different regions and different cities is realized.

The specific embodiment is as follows:

building a big data system, and for a transmission line comprising 120 sets of field equipment, according to the spatial arrangement relation of each equipment, installing a set of acquisition terminal on each equipment, and needing 120 sets of field wireless acquisition modules; every 10 sets of equipment form an acquisition sub-network, and 12 sets of field sub-network modules are needed; and each 3 sub-networks are independently accessed to the original PLC field bus ProfiBus-DP control network, 4 sets of wireless network center node modules are needed, and finally, the center node modules are connected to the original PLC control network modules to form an equipment end system which is accessed to a cloud end system.

In the system, in the cloud system, the vibration quantization value under the normal operation condition is recorded as N, the vibration quantization offset N is set as M, and corresponding health levels can be set according to the vibration deviation condition Δ = N-M between the two, and the health state is set as "normal, warning and serious" and is divided into three levels. "Normal" is D1+ epsilon, and the threshold value can be measured by frequency domain analysis and time domain analysis according to the vibration state of different equipment, the measured value is derived from the original empirical value of the system, wherein epsilon is a smaller adjustment value, and epsilon is set to be 0.5-1% of the threshold value according to historical analysis. "Warning" is D2+ ε, and "Severe" is D3+ ε. Recording deviation value delta through a window within a time observation t, if the recorded value continuously appears D2 or D3, the state of the equipment is in an unhealthy state, and otherwise, the state is in a normal state.

In particular, the classification of the vibration abnormality state is not limited to the above-mentioned 3 levels, and may be subdivided according to the management granularity, and the determination of the health state, i.e., the deviation value Δ = D1, is generally obtained by observing the same-level equipment according to a mathematical statistical method and averaging the normal operation by measuring a plurality of times.

The feedback method mainly includes two methods, one is to directly communicate with a WCS (warehouse control system), and the WCS controls the conveying line to take corresponding measures, for example, if the health status is warning, the speed of the conveying line is reduced or if the health status is serious, the operation of the conveying line is stopped. Note that the implementation of this measure depends on the division of the health level, and different reactive measures can be taken, which are divided according to the situation of the field device. And the other method is that data interaction is directly carried out with an upper-layer platform information system, and further analysis is carried out through the upper-layer information system to make a decision. The priorities of these two feedback methods also depend on the determination of the health state, and can be set in advance. Finally, the health condition of the equipment is obtained and corresponding treatment is carried out.

Reference throughout this specification to "one embodiment," "another embodiment," "an embodiment," "a preferred embodiment," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment described generally in this application. The appearances of the same phrase in various places in the specification are not necessarily all referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with any embodiment, it is submitted that it is within the scope of the invention to effect such feature, structure, or characteristic in connection with other embodiments.

Although the invention has been described herein with reference to a number of illustrative embodiments thereof, it should be understood that numerous other modifications and embodiments can be devised by those skilled in the art that will fall within the spirit and scope of the principles of this disclosure. More specifically, various variations and modifications are possible in the component parts and/or arrangements of the subject combination arrangement within the scope of the disclosure, the drawings and the appended claims. In addition to variations and modifications in the component parts and/or arrangements, other uses will also be apparent to those skilled in the art.