WO2019062833A1

WO2019062833A1 - Intelligent diagnosis system and method

Info

Publication number: WO2019062833A1
Application number: PCT/CN2018/108250
Authority: WO
Inventors: 聂仕华; 叶浩
Original assignee: 上海微电子装备（集团）股份有限公司
Priority date: 2017-09-28
Filing date: 2018-09-28
Publication date: 2019-04-04
Also published as: TW201925942A; CN109581995A; CN109581995B

Abstract

Disclosed are an intelligent diagnosis system and method. The system comprises a main system (100), a subsystem (200), and a diagnosis prediction card (300). The main system (100) comprises a master control card (1) of the main system (100), a main hub card (2), and multiple main data cards (3). The main hub card (2) is connected to a sensor corresponding to the main system (100), and is used for receiving measurement data of the sensor and sending the measurement data to the main data cards (3) of the main system (100) for computing. The subsystem (200) comprises a master control card (1) of the subsystem (200), a sub hub card (6), and multiple sub data cards (3). The sub hub card (6) is connected to a sensor corresponding to the subsystem (200), and is used for receiving measurement data of the sensor and sending the measurement data to the sub data cards (3) of the subsystem (200) for computing. The diagnosis prediction card (300) is connected to the master control card (1) of the main system (100) and the master control card (1) of the subsystem (200), and is used for regularly obtaining intermediate operating data of the main data cards (3) or the sub data cards (3), and performing fault prediction according to the received intermediate operating data, and feeding back the prediction result to the master control card (1) of the main system (100) or the master control card (1) of the subsystem (200). Real-time memory operations can be performed on data measured by the sensors, and time-consuming frequency-IO operations on batch data can be avoided.

Description

Intelligent diagnosis system and method

Technical field

The present invention relates to the field of equipment fault diagnosis technology, and in particular, to an intelligent diagnosis system and method.

Background technique

With the advancement of technology and the development of computer science, various devices have begun to evolve into integration, complexity, and intelligence, making machines or devices closer to or satisfying natural people's operating habits and functional requirements. However, the intelligence of machines and equipment is premised on the complexity of machine design, manufacturing, and operation. Intelligent equipment is often accompanied by a variety of problems. The appearance of the problem often has "lag", that is, once the machine shows the problems that people can find, the machine is already "disease-ridden". At this time, the problem location, repair, maintenance, etc. are relatively very cumbersome, usually relying on the experience of engineers to solve the problem. Troubleshoot, unable to quickly locate problems, quickly restore the device to work properly, and can not complete the inheritance of technology.

The common method used by the industry to solve the above problems is to increase various sensing devices, and to detect the temperature, humidity, pressure, current and other factors inside the device in real time. Because the occurrence of faults has the characteristics of “randomness” and “accidentality”, The detected data needs to be stored in real time, which greatly increases the storage time and increases the storage space, that is, the space complexity and time complexity will increase linearly, even exponentially; and when the failure occurs, often only The data of the first few seconds or the first few minutes before the failure occurs, a large amount of data is garbage or redundant data, which not only takes up a lot of hardware space, but also increases the hardware cost, and also greatly increases the high frequency I/O operation of the computer. The running time affects the overall performance of the device.

In addition, the industry's fault detection and processing is generally after the failure occurs, the shutdown process, no fault prediction mechanism is adopted, to avoid the occurrence of simple or repeated faults, although the fault problem can be finally solved, but it will lead to MTTR (Mean Time To Repair, the average time before recovery is large, affecting the production schedule and reducing the productivity of the equipment.

Summary of the invention

The present invention provides an intelligent diagnostic system and method for realizing fault pre-judging and fault pre-processing, accelerating production progress, and improving equipment yield, in view of the problems existing in the prior art.

In order to solve the above technical problem, the present invention provides an intelligent diagnosis system, including:

The main system includes a main system main control board, a main pivot board, and a plurality of main data boards, and the main hub board is connected to a sensor corresponding to the main system, and is configured to receive measurement data of the sensor, and Sending to each of the main data boards of the main system for calculation;

The sub-system includes a sub-system main control board, a slave hub board and a plurality of slave data board cards, wherein the slave hub board is connected with a sensor corresponding to the subsystem, for receiving measurement data of the sensor, and transmitting Calculating to each of the slave data boards of the subsystem;

a diagnostic prediction board, connected to the main system main control board and the sub-system main control board, for periodically acquiring intermediate operation data of the main data board or the slave data board and receiving according to The intermediate running data performs fault prediction, and feeds back the predicted result to the main system main control board or the sub-system main control board.

Further, the main system further includes a data bus and a control bus connected to the main system main control board, the main pivot board, and the main data board; the sub-system further includes a data bus and a control bus connected to the system main control board, the slave hub board, and the slave data board.

Further, the main system main control board and the sub-system main control board adopt a PowerPC board.

Further, the diagnostic prediction board uses a host computer or a PowerPC board.

Further, the diagnostic prediction board includes a fault prediction module, a database, and a fault receiving and processing module.

Further, the diagnostic prediction board is further connected to the main hub card and the slave hub card through a HSSL fiber transmission bus and a serial port connection bus.

Further, the main system and the sub-system further comprise a fault diagnosis board, wherein the fault diagnosis board is connected to the data bus and the control bus, and the fault diagnosis board and the diagnostic prediction board are It is connected through a HSSL optical fiber transmission bus and a serial port connection bus.

The present invention also provides a diagnostic method using the intelligent diagnostic system as described above, comprising the steps of:

S1: the main hub board and the slave board obtain real-time detection data of the corresponding sensor, and send the detection data to the main data board and calculate from the data board;

S2: periodically acquiring intermediate operation data of the main data board or the slave data board, and transmitting the data to the diagnostic prediction board;

S3: The diagnosis prediction board performs fault prediction according to the received intermediate operation data, and feeds back the prediction result to the main system main control board or the sub-system main control board.

Further, in the step S2, the intermediate operation data is periodically acquired by the main hub card and the slave hub card, and the intermediate operation data is transmitted to the diagnosis prediction board.

Further, in the step S2, the intermediate operation data is periodically acquired by the fault diagnosis board, fault prediction is performed, and the prediction information and the intermediate operation data are transmitted to the diagnosis prediction board.

Further, in the step S2, the fault prediction includes the following steps:

S21: The fault diagnosis board periodically acquires the intermediate running data according to the time parameter and the interest data in the configuration file, and puts the intermediate running data into the memory buffer;

S22: The fault diagnosis board performs real-time monitoring on the acquired intermediate operation data, and determines whether the data value is in a security range set by the configuration file;

S23: When the data value exceeds the range of the security range between 0 and m%, the warning information is reported to the fault prediction board, and is fed back to the main system main control board or the sub-system main control board in real time. Drive components, adjust accordingly to avoid deterioration of operating conditions;

S24: When the data value exceeds the security range by more than m%, the fault information is reported to the fault prediction board for processing, and directly fed back to the main system main control board or the driving component in the sub-system main control board. , the initialization operation, where m is a real number, set by the configuration file.

Further, in the step S24, when the magnitude of the data value exceeds the safe range is greater than m%, the fault diagnosis board encodes the fault type, and triggers the serialization interrupt to notify the diagnostic prediction board.

Further, the step S3 further includes: after the diagnosis prediction board receives the fault information, first sending an instruction to suspend all the sub-system actions, and processing the fault, determining the fault mechanism, whether to run the action retry, if allowed , then send a "retry" command to the sub-system participating in the action, retry the action, if the retry fails the same, report it to the server; if not, send a "system error" message to the server, waiting for the manual Intervention.

Further, the step S3 includes the following steps:

S31: The diagnostic prediction board is configured according to sampling time and data of interest in the configuration file;

S32: The diagnostic prediction board samples the data of the fault diagnosis board every n servo cycles and stores it in a database, where n is a natural number and is set by a configuration file;

S33: The fault prediction module in the diagnostic prediction board comprehensively processes the data sampled in this time and the historical data in the database, fits the data change curve, and searches for a corresponding rule in the database to obtain fault prediction information;

S34: The diagnostic prediction board feeds the fault prediction information to the corresponding sub-system through the main hub card in the main system, and performs corresponding adjustment and operation by the sub-system main control board in the sub-system.

Further, in the step S33, the rules are saved in the form of a fault tree.

Further, in the step S33, if no rule is found, the fault prediction module performs fault training and stores it as a new rule.

Further, in the step S33, the data variation curve is fitted by a method of least squares or averaging trend.

Further, the method further includes the step S4 of performing fault injection on the diagnostic prediction board or the main system main control board or the sub-system main control board to verify the diagnostic effect of the intelligent diagnosis system.

The intelligent diagnosis system and method provided by the invention have the following advantages over the prior art:

(1) Real-time memory operation on the data detected by the sensor, avoiding the time-consuming operation of the frequency I/O of the batch data;

(2) Adopting a configurable data acquisition mode of interest to avoid processing a large amount of redundant data;

(3) Perform “online” processing and analysis on the running intermediate data of the data board in the device to predict the fault;

(4) Intelligent fault judgment and online processing, avoiding equipment shutdown and waiting for manual intervention, speeding up production schedule and improving equipment yield;

(5) Adopting the “interrupt trigger” and “pause” modes to avoid the expansion of faults and easy fault location;

(6) Using distributed fault diagnosis and processing models, the faults of the primary system and the subsystem can be processed quickly and timely;

(7) Coexist with “failure training” and “rule processing” methods to predict the occurrence of faults and deal with faults quickly, in real time and accurately.

(8) Simulate the occurrence of faults through fault injection, test the fault handling capability of the system, and improve system reliability.

DRAWINGS

1 is a schematic structural diagram of an intelligent diagnosis system according to Embodiment 1 of the present invention;

2 is a schematic structural view of a diagnostic prediction board in Embodiment 1 of the present invention;

3 is a schematic structural view of a diagnostic prediction board in Embodiment 2 of the present invention;

4 is a schematic diagram of determining three states of a fault diagnosis board in Embodiment 2 of the present invention.

The figure shows: 100, main system; 200, sub-system; 300, diagnostic prediction board; 400, server end; 1, system main control board; 2. main hub board; 3. data board; Data bus; 5, control bus; 6, from the hub board; 7, Ethernet bus; 8, HSSL fiber transmission bus; 9, serial port connection bus; 10, fault prediction module; 11, database; 12, fault reception and processing Module; 13, fault diagnosis board.

Detailed ways

The invention will now be described in detail in conjunction with the drawings.

Example 1

As shown in FIG. 1, the present invention provides an intelligent diagnosis system, including:

The main system 100 includes a system main control board 1, a main hub board (MHB) 2, and a plurality of data boards 3, and a main control board 1 and a main hub board. 2 Data bus 4 and control bus 5 connected to data board 3. The main hub card 2 is connected to a sensor corresponding to the main system 100 for receiving measurement data of the sensor and is sent to each data card 3 of the main system 100 for calculation.

The sub-system 200 includes a system main control board 1, a slave hub board 6 and a plurality of data board 3, and the system main control board 1, the slave board 6 and the data board 3 The connected data bus 4 and the control bus 5 are connected to the sensor corresponding to the sub-system 200 for receiving the measurement data of the sensor and transmitting the data to the data card 3 of the sub-system 200. Calculation.

The system main control board 1 adopts a PowerPC (Performance Optimization With Enhanced RISC-Performance Computing), which is also called a PPC board, and is mainly responsible for receiving commands for diagnosing and predicting the board 300. The command is interpreted and sent to other boards in the system. Specifically, the system main control board 1 receives the command issued by the diagnostic prediction board 300 (such as initialization, machine parameter delivery, running firmware allocation, etc.) through the Ethernet bus 7, and interprets the command through the data bus 4 The command is sent to each board in the system. For example, the system main control board 1 in the main system 100 is used to send commands to the main hub board 2 and the data board in the main system 100 through the data bus 4. The card 3, the system main control board 1 in the sub-system 200 is used to send commands to the slave hub board 6 and the data board card 3 in the sub-system 200 via the data bus 4. The data bus 4 can adopt SRIO, SDB, MDB, PCIe, etc.; during the operation of the system, some other auxiliary information (such as Trace) will be sent to the PPC board through the control bus 5 to complete the processing or storage of the information. The control bus 5 is a VME64x or VPX bus, or Ethernet. At the same time, the driver of the system runs on the PPC board, and the data board 3 is subjected to parameter delivery and control through the control bus 5.

The data board 3 is mainly used to control the implementation of the algorithm and the operation and processing of the data in the control process. After the system is initialized, the data board 3 is in a ready state at a time, waiting for the sensor to detect the arrival of data; when data arrives, the data is quickly moved to the RAM of the data board, and the calculation is completed at the fastest speed. The calculation result is broadcasted through the data bus 4 according to the pre-agreed sequence, and all the cards in the system can obtain the calculation result from the data bus 4 and store it, thereby realizing the interaction between the data between the boards; during the data processing The intermediate running data can be written to the external storage of the data card 3 or the DPRAM according to the configuration requirements, and provided to the main hub card 2 or captured from the hub board 6 to avoid directly discarding data after the execution of the operation is completed.

The Master Diagnosis Trigger Board (MDT) 300 is connected to the system main control board 1 through the Ethernet bus 7 by using a host computer or a PowerPC board, and the diagnostic prediction board 300 is also connected to the main hub. The board 2 is connected from the hub board 6 via the HSSL fiber optic transmission bus 8 and the serial port connection bus 9. The serial bus 5 can be RS232, RS485, USB, IEEE1394, etc. As shown in FIG. 2, the diagnostic prediction board 300 includes a fault prediction module 10, a database 11 and a fault receiving and processing module 12, wherein the fault prediction module 10 The fault processing is performed in two ways: "rule processing" and "fault training", and the fault rules of the database 11 are improved in real time; the database 11 is mainly used to store processing rules, and the rules are saved in the form of "fault tree", that is, The data trend corresponds to a fault type; the fault receiving and processing module 12 is mainly responsible for fault handling. Specifically, the main hub board 2 periodically captures data written by the data board card 3 into the external memory or the DPRAM from the hub board 6, and every n servo cycles, n is a natural number, which is set by the configuration file. The operation data of the current servo cycle is uploaded to the diagnostic prediction board 300 through the HSSL optical fiber transmission bus 8, and the diagnostic prediction board 300 is received and stored in the database 11; the fault prediction module 10 will capture the current running data and the database 11. The historical data is comprehensively processed, the data change curve is fitted, and the corresponding rules in the database 11 are searched for the fault prediction information, and the main pivot card 2 in the main system 100 is fed back to the corresponding sub-system 200, and the sub-system The system main control board 1 in 200 performs corresponding adjustment and operation; if no rules are found, "fault training" is performed and stored as a new rule.

There are two ways to fit the parameter data:

Least squares method: due to the current, voltage, temperature and other parameter values, it should be kept as stable as possible during the operation of the equipment, and its growth trend is slow. It can be set as a one-way regression linear equation y _i =f(t _i )=at _i +b+ ξ _i (for different parameter data, different function terms are set, such as velocity and acceleration, etc., which are multi-order polynomials), according to f(y _i , t _i )=∑[y _i -at _i -b] ² , f(y _i , t _i ) finds the partial derivative to obtain the values of a and b, thereby determining the relational function. In the above equation, t is the time sampled value, y is the sampled value of the current, voltage, temperature and other parameter values, a and b are the linearization coefficients of the one-way regression linear equation to be fitted, and ξ is the true value and the fitted value. The difference (ie the error value), i represents the sampling point.

MA method: To find the average trend, set the function to y _i =f(t _i )=at _i +b, and gradually determine and repair the formula by the average between the two points, and predict the fault trend by the formula.

The method for diagnosing the above intelligent diagnosis system is further provided in the embodiment, and includes the following steps:

S1: The main hub card 2 and the detection data of the sensor are acquired in real time from the hub card 6, and the detection data is sent to the data board 3 for calculation, and the data running of the data board 3 in the middle of the data processing may be Write to its external memory or DPRAM according to configuration requirements.

S2: the main hub card 2 and the intermediate operation data of the data board card 3 are periodically acquired from the hub board 6 and transmitted to the diagnostic prediction board 300; specifically, the main hub board 2 or slave The hub board 6 periodically captures the data written by the data board 3 to the external memory or DPRAM, and every n servo cycles, n is a natural number, and is set by the configuration file, and the servo is uploaded through the HSSL optical fiber transmission bus 8. The periodic operational data is sent to the diagnostic prediction board 300, and the diagnostic prediction board 300 is stored and stored in the database 11.

S3: The diagnosis prediction board 300 performs fault prediction according to the received intermediate operation data, and feeds back the prediction result to the system main control board 1. Specifically, the fault prediction module 10 comprehensively processes the current running data and the historical data in the database 11, fits the data change curve, and searches for the corresponding rule in the database 11, obtains the fault prediction information, and passes the main system. The main hub card 2 in the 100 is fed back to the corresponding sub-system 200, and the system main control board 1 in the sub-system 200 performs corresponding adjustment and operation; if the rule is not found, the "fault training" is performed and stored as New rules.

S4: Perform fault injection on the diagnostic prediction board 300 or the system main control board 1 to check the diagnostic effect of the system. That is, the fault injection may be injected by the diagnostic prediction board 300, and the diagnostic prediction board 300 packages the fault information to the main system 100 and the sub-system 200, and processes the corresponding faults of the main system 100 and the sub-system 200 in real time; or for the main system. The system main control board 1 of the 100 or sub-system 200 is separately injected, and the diagnostic prediction board 300 receives and processes the failures of the main system 100 and the sub-system 200.

Example 2

As shown in FIG. 3, unlike the first embodiment, the main system 100 and the sub-system 200 in the embodiment further include a Slave Diagnosis Trigger Board (SDT) 13, and the fault diagnosis board 13 is provided. Connected to the data bus 4 and the control bus 5, the fault diagnostic board 13 and the diagnostic predictive board 300 are connected by a HSSL optical fiber transmission bus 8 and a serial port connection bus 9.

The functions of the fault diagnosis board 13 mainly include the following aspects:

1. The configurability of time and data can be configured according to the time parameter of the configuration file DTS.cfg and the data of interest. If it is a motion subsystem, the data can take the voltage or current data of the motor; if it is a lighting subsystem, The data can take parameters such as laser light intensity and laser dose; if it is an environmental subsystem, the data can take parameters such as temperature, pressure and humidity. Of course, it is not limited to the above parameters, and the specific parameters are defined by the actual scene or the engineer.

2. At each certain time, go to the DPRAM or external memory of each data board 3 to capture the running data in the middle, and put into the fault diagnosis board 13 for the memory buffer opened by each data board 3; The number of servo cycles is in units. The initialization time is read from the configuration file DTS.cfg. This parameter can also be set in real time by the user interface. Since the probability of failure is often the highest at initialization and machine startup, the time at this time The interval is as small as possible, and can be set to 1 servo cycle; when the device is stable, it can be adjusted in real time according to the needs or actual conditions;

3. Real-time monitoring of the intermediate running data to determine whether the data value is in the safe range. The security range is set by the configuration file DTS.cfg; as shown in Figure 4, the security range can be set to three states: health, fault, and Sub-health; health status corresponds to data within a safe range; sub-health status corresponds to data within m% of the safety threshold; fault status corresponds to data exceeding m% above the safety threshold, where m is a real number, by configuration file set up;

4. When the monitored parameter value exceeds the safe range between 0 and m%, that is, the system is in a sub-health state, the fault diagnosis board 13 reports a warning message to the fault prediction board 300 through the serial connection bus 9. And feedback to the drive components in the system main control board 1 in real time, and make corresponding adjustments to avoid deterioration of operating conditions;

5. When the monitored parameter value exceeds the range of the safety range ≧m%, the system is defined as the fault state at this time, and the fault diagnosis board 13 first encodes the fault type, and reports the fault information to the serial connection bus 9. The fault prediction board 300 processes and directly feeds back to the driving component in the system main control board 1 to perform an initialization operation to avoid the fault waiting state, and facilitates the upper layer to send a “Retry” or other request, where m is a real number and is configured by a configuration file. set up.

Correspondingly, after receiving the fault information of the system, the fault receiving and processing module 12 in the diagnostic prediction board 300 first sends an event to suspend all the sub-systems 200, processes the fault, determines the fault mechanism, and operates the action. Retry, if allowed, send a "Retry" command to the sub-system 200 participating in the action, retry the action; if not, send a "system error" to the server, waiting for manual intervention.

The method for diagnosing the intelligent diagnosis system described in this embodiment includes the following steps:

S1: The main hub card 2 and the detection data of the sensor are acquired in real time from the hub card 6, and the detection data is sent to the data board 3 for calculation; the data running of the data board 3 in the middle of the data processing may be Write to its external memory or DPRAM according to configuration requirements.

S2: The fault diagnosis board 13 periodically acquires the intermediate operation data of the data board 3, performs fault prediction, and transmits the predicted information and the intermediate operation data to the diagnostic prediction board 300. The fault prediction includes the following steps:

S21: The fault diagnosis board 13 periodically captures the intermediate running data of the data board 3 according to the time parameter and the interest data in the configuration file DTS.cfg, and may also actively acquire and put into the memory buffer. It should be noted that if it is a motion subsystem, the data of interest can take the voltage or current data of the motor; if it is a lighting subsystem, the data can take parameters such as laser intensity and laser dose; if it is an environmental subsystem, then the sense Interest data can take parameters such as temperature, pressure, and humidity. The above parameters are examples and are not limited to the above parameters. The specific parameters are defined by the actual scenario or by the engineer.

S22: The fault diagnosis board 300 performs real-time monitoring on the acquired intermediate operation data to determine whether the data value is in the security range set by the configuration file; the security range is set by the configuration file DTS.cfg; the security range can be set to three Status: health, fault, and sub-health; health status corresponds to data within a safe range; sub-health status corresponds to data within m% of the safety threshold; and fault status corresponds to data above the safety threshold m%, where m Real number, set by configuration file;

S23: When the data value exceeds the safe range between 0 and m%, the fault diagnosis board 13 reports the warning information to the fault prediction board 300 through the serial connection bus 9, and feeds back to the system main control board 1 in real time. In the drive components, adjust accordingly to avoid deterioration of operating conditions;

S24: When the magnitude of the data value exceeds the safe range is greater than m%, the system is defined as a fault state at this time, and the fault diagnosis board 13 first encodes the fault type, and triggers the serialization interrupt to notify the diagnostic prediction board 300. At the same time, directly feedback to the drive component in the system main control board 1 for initialization operation, where m is a real number and is set by the configuration file.

S3: The diagnosis prediction board 300 performs fault prediction according to the received intermediate operation data, and feeds back the prediction result to the system main control board 1. Includes the following steps:

S31: The diagnostic prediction board 300 is configured according to sampling time and data of interest in the configuration file;

S32: The diagnostic prediction board 300 fixes n servo cycles to sample (actively acquire, or passively accept) the data of the fault diagnosis board 13 and stores it in the database 11, where n is a natural number and is set by a configuration file;

S33: The fault prediction module 10 in the diagnostic prediction board 300 comprehensively processes the data sampled in this time and the historical data in the database 11, fits the data change curve, and searches for the corresponding rule in the database 11, and obtains a fault prediction. information;

S34: The diagnostic prediction board 300 feeds the fault prediction information to the corresponding subsystem 200 through the main hub card 1 in the main system 100, and performs corresponding adjustment and operation by the system main control board 1 of the sub-system 200. .

In addition, after the diagnostic prediction board 300 receives the fault information of the fault diagnosis board 13, first sends an instruction to suspend all the sub-systems 200, and processes the fault, determines the fault mechanism, and whether the operation retry is performed, if allowed, Then send a "retry" command to the sub-system participating in the action, retry the action, if the retry fails the same, report it to the server 400, wait for manual intervention; if not, send "system error" to the server 400, waiting for manual intervention.

Compared with the first embodiment, in the technical solution provided in the embodiment, the fault diagnosis board 13 is added, and the distributed fault diagnosis and processing model is adopted to implement pre-detection and online processing of faults in the main system 100 and the sub-system 200, thereby further improving. The efficiency.

In summary, the intelligent diagnosis system and method provided by the present invention have the following advantages over the prior art:

(3) Perform “online” processing and analysis on the running intermediate data of the data board 3 in the device to predict the fault;

(4) Intelligent fault judgment and online processing, avoiding equipment shutdown and waiting for manual intervention, saving time and improving efficiency;

(6) Using the distributed fault diagnosis and processing model, the faults of the main system 100 and the sub-system 200 can be quickly and timely processed;

Although the embodiments of the present invention have been described in the specification, these embodiments are merely illustrative and are not intended to limit the scope of the invention. Various omissions, substitutions, and changes may be made without departing from the scope of the invention.

Claims

An intelligent diagnosis system, comprising:

The main system includes a main system main control board, a main pivot board, and a plurality of main data boards, and the main hub board is connected to a sensor corresponding to the main system, and is configured to receive measurement data of the sensor, and Sending to each of the main data boards of the main system for calculation;

The sub-system includes a sub-system main control board, a slave hub board and a plurality of slave data board cards, wherein the slave hub board is connected with a sensor corresponding to the subsystem, for receiving measurement data of the sensor, and transmitting Calculating to each of the slave data boards of the subsystem;

a diagnostic prediction board, connected to the main system main control board and the sub-system main control board, for periodically acquiring intermediate operation data of the main data board or the slave data board and receiving according to The intermediate running data performs fault prediction, and feeds back the predicted result to the main system main control board or the sub-system main control board.
The intelligent diagnosis system according to claim 1, wherein the main system further comprises a data bus and a control connected to the main system main control board, the main pivot board, and the main data board. The sub-system further includes a data bus and a control bus connected to the sub-system main control board, the slave hub board, and the slave data board.
The intelligent diagnosis system according to claim 1, wherein the main system main control board and the sub-system main control board adopt a PowerPC board.
The intelligent diagnosis system according to claim 1, wherein the diagnostic prediction board uses a host computer or a PowerPC board.
The intelligent diagnostic system of claim 1 wherein said diagnostic predictive board comprises a fault prediction module, a database, and a fault receiving and processing module.
The intelligent diagnosis system according to claim 1, wherein the diagnostic prediction board is further connected to the main hub card and the slave hub card through a HSSL fiber transmission bus and a serial port connection bus.
The intelligent diagnostic system according to claim 2, wherein

The main system and the sub-system further include a fault diagnosis board, the fault diagnosis board is connected to the data bus and the control bus, and the fault diagnosis board and the diagnostic prediction board pass the HSSL The optical fiber transmission bus is connected to the serial port connection bus.
A diagnostic method using the intelligent diagnostic system according to claim 1, comprising the steps of:

S1: the main hub board and the slave board obtain real-time detection data of the corresponding sensor, and send the detection data to the main data board card and calculate from the data board card;

S2: periodically acquiring intermediate operation data of the main data board or the slave data board, and transmitting the data to the diagnostic prediction board;

S3: The diagnosis prediction board performs fault prediction according to the received intermediate operation data, and feeds back the prediction result to the main system main control board or the sub-system main control board.
The intelligent diagnosis method according to claim 8, wherein in the step S2, the intermediate operation data is periodically acquired by the main hub card and the slave hub card, and the intermediate operation data is transmitted. To the diagnostic prediction board.
The intelligent diagnosis method according to claim 8, wherein in the step S2, the intermediate operation data is periodically acquired by the fault diagnosis board, fault prediction is performed, and the prediction information and the intermediate operation data are transmitted to the location. The diagnosis predicts the board.
The intelligent diagnosis method according to claim 10, wherein in the step S2, the fault prediction comprises the following steps:

S21: The fault diagnosis board periodically acquires the intermediate running data according to the time parameter and the interest data in the configuration file, and puts the intermediate running data into the memory buffer;

S22: The fault diagnosis board performs real-time monitoring on the acquired intermediate operation data, and determines whether the data value is in a security range set by the configuration file;

S23: When the data value exceeds the range of the security range between 0 and m%, the warning information is reported to the fault prediction board, and is fed back to the main system main control board or the sub-system main control board in real time. Drive components, adjust accordingly to avoid deterioration of operating conditions;

S24: When the data value exceeds the security range by more than m%, the fault information is reported to the fault prediction board for processing, and directly fed back to the main system main control board or the driving component in the sub-system main control board. , the initialization operation, where m is a real number, set by the configuration file.
The intelligent diagnosis method according to claim 11, wherein in the step S24, when the magnitude of the data value exceeds the safe range is greater than m%, the fault diagnosis board encodes the fault type and serializes The interrupt triggers, notifying the diagnostic prediction board.
The intelligent diagnosis method according to claim 12, wherein the step S3 further comprises: after the diagnosis prediction board receives the failure information, first sending an instruction to suspend all the sub-system actions, and processing the failure, Determine the failure mechanism, whether to run the action retry, if allowed, send a "retry" command to the sub-system participating in the action, retry the action, if the retry fails the same, report it to the server; if not, then Send a "system error" message to the server side, waiting for manual intervention.
The intelligent diagnosis method according to claim 10, wherein the step S3 comprises the following steps:

S31: The diagnostic prediction board is configured according to sampling time and data of interest in the configuration file;

S32: The diagnostic prediction board samples the data of the fault diagnosis board every n servo cycles and stores it in a database, where n is a natural number and is set by a configuration file;

S33: The fault prediction module in the diagnostic prediction board comprehensively processes the data sampled in this time and the historical data in the database, fits the data change curve, and searches for a corresponding rule in the database to obtain fault prediction information;

S34: The diagnostic prediction board feeds the fault prediction information to the corresponding sub-system through the main hub card in the main system, and performs corresponding adjustment and operation by the sub-system main control board in the sub-system.
The intelligent diagnosis method according to claim 12, wherein in the step S33, the rules are saved in the form of a fault tree.
The intelligent diagnosis method according to claim 12, wherein in the step S33, if the rule is not found, the fault prediction module performs fault training and stores it as a new rule.
The intelligent diagnosis method according to claim 12, wherein in the step S33, the data change curve is fitted by a least square method or a method of averaging the trend.
The intelligent diagnosis method according to claim 8, further comprising a step S4, performing fault injection on the diagnosis prediction board or the main system main control board or the sub-system main control board, Verify the diagnostic results of the intelligent diagnostic system.