PIC module communication connection board

Abstract

The invention discloses a board for communication connection of all modules of a PIC, and relates to the technical field of PIC equipment, and the board comprises the following steps: starting a system to detect hardware connection and state, configuring operation modes of a master station and a slave station, and initializing parameters of a dynamic adaptive communication protocol and a fault prediction model; the system acquires load data and task remaining time of each module in real time every 10ms, and dynamically allocates communication priority and bandwidth through a weight calculation formula; acquiring operation data of the module per hour, and inputting a fault prediction model to calculate a fault probability; the system monitors the operation state of each module in real time, and dynamically optimizes the adjustment coefficient of the adaptive communication protocol and the weight of the fault prediction model according to historical data; when the system is closed, power supplies of all the modules are sequentially disconnected, and the aging module is replaced regularly according to a prediction result of the fault prediction model; according to the invention, efficient bandwidth allocation and communication optimization are realized through the dynamic adaptive communication protocol, and the data transmission efficiency between the PIC modules is remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of PIC devices, and particularly relates to a board for communication connection of each module of PIC. Background Art

[0002] In the existing fan control system, the connection between the PIC module and the communication connection board mainly relies on a data transmission mechanism with fixed priorities. This mechanism has many problems in practical applications. First of all, the fixed-priority mechanism cannot dynamically adjust the bandwidth allocation according to the real-time load, resulting in possible communication delays for critical tasks in the case of sudden loads, affecting the system response speed. Moreover, the existing system lacks effective fault prediction capabilities and usually relies on manual troubleshooting, which is not only inefficient but also may lead to a lag in fault response, increasing the risk of equipment downtime. The existing communication connection boards have poor compatibility and are difficult to adapt to the complex scenarios of multi-module dynamic cooperation, restricting the scalability and flexibility of the system. Therefore, we propose a board for communication connection of each module of PIC. Summary of the Invention

[0003] To solve the above technical problems, the present invention is realized through the following technical solutions:

[0004] The present invention is a board for communication connection of each module of PIC, including the following steps:

[0005] Step S1: Start the system to detect the hardware connection and status, configure the operation modes of the master station and slave stations, and initialize the parameters of the dynamic adaptive communication protocol and the fault prediction model;

[0006] Step S2: The system collects the load data and remaining task time of each module in real time every 10 ms, and dynamically allocates communication priorities and bandwidth through a weight calculation formula;

[0007] Step S3: Collect the operation data of the module every hour, input it into the fault prediction model to calculate the fault probability. If the fault probability exceeds the threshold, the system triggers an alarm and generates maintenance suggestions;

[0008] Step S4: The system monitors the operation status of each module in real time, dynamically optimizes the adjustment coefficients of the adaptive communication protocol and the weights of the fault prediction model according to historical data, and simultaneously records the operation log and generates an analysis report;

[0009] Step S5: When the system is shut down, disconnect the power supply of each module in sequence to ensure data integrity. According to the prediction results of the fault prediction model, replace the aging modules regularly and clean the radiator.

[0010] Furthermore, the following steps are included in the said Step S1:

[0011] Step S11: Connect the PIC communication connection board to the PIC module, power module, bus module, and I / O module through a standardized interface; detect whether the output voltage of the power module is within the rated range, detect whether the communication link of the bus module is normal, and detect whether the signal input and output of the I / O module are normal; for the modules detected with abnormalities, generate a detection report and mark the abnormal modules.

[0012] Step S12: Through the configuration interface of the master station, set the operating modes of the slave stations for distributed control, and initialize the adjustment coefficients of the adaptive communication protocol through historical data; load the FP-LSTM model weights through the embedded processor of the master station to initialize the fault prediction model.

[0013] Further, the step S2 includes the following steps:

[0014] Step S21: The system collects the load data L i and the remaining task time T i of each module every 10 ms. The load data includes CPU utilization rate, memory occupancy rate, and communication bandwidth occupancy rate, and the remaining task time is the specific remaining working duration that each module needs to execute.

[0015] Step S22: The master station dynamically adjusts the priority according to the real-time load and task urgency of each slave station, and the dynamic priority weight W i is calculated as follows:

[0016]

[0017] where L max is the maximum load capacity of the system, T critical is the task timeout threshold, and α and β are the adjustment coefficients optimized through historical data;

[0018] Step S23: Dynamically allocate bandwidth according to the weight W i to adjust the communication priority of the bus module; if the communication of a certain module is abnormal, the system automatically reduces its weight to 0 and triggers the fault prediction model for diagnosis.

[0019] Further, the step S3 includes the following steps:

[0020] Step S31: Collect the operation data of each module once an hour, including voltage fluctuation value, temperature change value, communication error rate, and historical fault records, normalize the data, and input it into the fault prediction model;

[0021] Step S32: Calculate the fault probability pf based on the fault prediction model;

[0022]

[0023] Wherein, Sigmoid converts the result of the linear combination into a probability value, and X t is the time series input data, and b is the bias term;

[0024] Step S33: If p f is greater than the threshold, the system triggers an alarm, notifies the maintenance personnel and provides maintenance suggestions.

[0025] Further, the step S4 includes the following steps:

[0026] Step S41: Monitor the operating status of each module through the master station, including the communication link status, load distribution, and fault warning information, and display the monitoring data in real time for the operator to view. The data is updated in real time through the bus protocol;

[0027] Step S42: Dynamically optimize the adjustment coefficient of the adaptive communication protocol according to the historical operation data, update the weights of the fault prediction model, record the system operation log, including communication exception events, fault prediction results, and maintenance operation records, and generate an analysis report regularly for system optimization. The log is stored in the SD card or the cloud, and the analysis report is generated through the data analysis tool.

[0028] Further, in the step S5, when the system is shut down, the power supplies of each module are disconnected in sequence, the system state is saved, and the aging modules are replaced regularly according to the prediction results of the fault prediction model, and the radiator is cleaned.

[0029] The present invention has the following beneficial effects:

[0030] 1. The present invention realizes efficient bandwidth allocation and communication optimization through the dynamic adaptive communication protocol, significantly improves the data transmission efficiency between PIC modules. The system calculates the priority weights of each module in real time every 10 ms, dynamically adjusts the communication priority to ensure that critical tasks are transmitted first, reduces the communication delay to within 5 ms, improves the bandwidth utilization rate, and the system can automatically handle communication exceptions to ensure stable operation in case of sudden load or module failure, greatly improving the response speed and reliability of the fan control system.

[0031] 2. The integrated fault prediction model of the present invention can predict potential faults in advance by collecting data such as voltage, temperature, and bit error rate in real time and performing time series analysis in combination with the LSTM network. When the fault probability exceeds the threshold, the system automatically triggers an alarm and provides maintenance suggestions to help the maintenance personnel take measures in advance to avoid unplanned shutdowns. This function significantly reduces the fault incidence rate during the operation of the fan, reduces the maintenance cost, prolongs the service life of the equipment, and improves the overall intelligence level of the system.

[0032] Of course, it is not necessary for any product implementing the present invention to achieve all the above advantages simultaneously. Brief Description of the Drawings

[0033] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0034] Figure 1 It is a schematic flow chart of the board for communication connection of each module of the PIC of the present invention. Detailed Embodiments

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0036] Please refer to Figure 1 As shown, the present invention is a board for communication connection of each module of the PIC, including the following steps:

[0037] Step S1: Start the system to detect the hardware connection and status, configure the operation modes of the master station and the slave station, and initialize the parameters of the dynamic adaptive communication protocol and the fault prediction model;

[0038] Step S2: The system collects the load data and the remaining task time of each module in real time every 10 ms, and dynamically allocates the communication priority and bandwidth through the weight calculation formula;

[0039] Step S3: Collect the operation data of the module every hour, input it into the fault prediction model to calculate the fault probability. If the fault probability exceeds the threshold, the system triggers an early warning and generates a maintenance suggestion;

[0040] Step S4: The system monitors the operation status of each module in real time, dynamically optimizes the adjustment coefficient of the adaptive communication protocol and the weight of the fault prediction model according to the historical data, and at the same time records the operation log and generates an analysis report;

[0041] Step S5: When the system is shut down, disconnect the power supply of each module in sequence to ensure data integrity. According to the prediction results of the fault prediction model, replace the aging modules regularly and clean the radiator.

[0042] Step S1 includes the following steps:

[0043] Step S11: Connect the PIC communication connection board to the PIC module, power module, bus module, and I / O module through a standardized interface; detect whether the output voltage of the power module is within the rated range, detect whether the communication link of the bus module is normal, and detect whether the signal input and output of the I / O module are normal; for the modules detected with abnormalities, generate a detection report and mark the abnormal modules.

[0044] Step S12: Through the configuration interface of the master station, set the operating modes of each slave station for distributed control, and initialize the adjustment coefficient of the adaptive communication protocol through historical data; load the FP-LSTM model weights through the embedded processor of the master station to initialize the fault prediction model.

[0045] Step S2 includes the following steps:

[0046] Step S21: The system collects the load data L i and the remaining task time T i of each module every 10 ms. The load data is the CPU utilization rate, memory occupancy rate, and communication bandwidth occupancy rate, and the remaining task time is the specific remaining working duration that each module needs to execute.

[0047] Step S22: The master station dynamically adjusts the priority according to the real-time load and task urgency of each slave station, and the dynamic priority weight W i is calculated as follows:

[0048]

[0049] where L max is the maximum load capacity of the system, T critical is the task timeout threshold, and α and β are the adjustment coefficients optimized through historical data;

[0050] Step S23: Dynamically allocate bandwidth according to the weight W i and adjust the communication priority of the bus module; if the communication of a certain module is abnormal, the system automatically reduces its weight to 0 and triggers the fault prediction model for diagnosis.

[0051] Step S3 includes the following steps:

[0052] Step S31: Collect the operation data of each module once an hour, including voltage fluctuation value, temperature change value, communication error rate, and historical fault records, normalize the data, and input it into the fault prediction model;

[0053] Step S32: Calculate the fault probability pf based on the fault prediction model;

[0054]

[0055] Wherein, Sigmoid converts the result of the linear combination into a probability value, and X t is the time series input data, and b is the bias term;

[0056] Step S33: If p f is greater than the threshold, the system triggers an alarm, notifies the maintenance personnel and provides maintenance suggestions.

[0057] Step S4 includes the following steps:

[0058] Step S41: Monitor the operating status of each module through the master station, including the communication link status, load distribution, and fault warning information, and display the monitoring data in real time for the operator to view. The data is updated in real time through the bus protocol;

[0059] Step S42: Dynamically optimize the adjustment coefficient of the adaptive communication protocol according to the historical operation data, update the weights of the fault prediction model, record the system operation log, including communication exception events, fault prediction results, and maintenance operation records, generate an analysis report regularly for system optimization, store the log in the SD card or the cloud, and generate the analysis report through the data analysis tool.

[0060] In Step S5, when the system is shut down, the power supply of each module is disconnected in sequence, the system state is saved, and the aging modules are replaced regularly according to the prediction results of the fault prediction model, and the radiator is cleaned.

[0061] A specific application of this embodiment is:

[0062] Scenario: A control system for a wind turbine generator;

[0063] Step 1: Initialization;

[0064] Connect the PIC communication connection board to the PIC module, configure the master station (MPC240) and the slave station (BS206), and initialize the dynamic adaptive communication protocol and the fault prediction model;

[0065] Step 2: Operation;

[0066] The system dynamically adjusts the communication priority every 10 ms and performs a fault prediction every hour. During a certain prediction, it is found that the bearing temperature is abnormal, pf = 0.85, and an alarm is triggered. The maintenance personnel replace the bearing in time to avoid unplanned shutdown;

[0067] Step 3: Optimization;

[0068] Optimize the adjustment coefficients of the dynamic adaptive communication protocol according to the historical data, α = 0.65, β = 0.35, to further improve the communication efficiency.

[0069] In the description of this specification, the descriptions referring to the terms "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0070] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. PIC module communication connection board, characterized by: The following steps are involved: Step S1: Start the system to detect the hardware connection and status, configure the operation mode of the master station and the slave station, and initialize the parameters of the dynamic adaptive communication protocol and the fault prediction model; Step S2: The system collects the load data and remaining task time of each module in real time every 10ms, and allocates communication priority and bandwidth through a dynamic priority weight calculation formula; Step S3: Collect the module's operating data every hour and input it into the fault prediction model to calculate the fault probability. If the fault probability exceeds the threshold, the system triggers an early warning and generates maintenance recommendations. Step S4: The system monitors the operating status of each module in real time, dynamically optimizes the adjustment coefficient of the adaptive communication protocol and the weight of the fault prediction model according to historical data, and records the operating log and generates an analysis report; Step S5: When the system is shut down, disconnect the power supply of each module in turn to ensure data integrity. According to the prediction results of the fault prediction model, replace the aged modules regularly and clean the radiator.

2. The PIC module communication connection board according to claim 1, characterized in that: The step S1 includes the following steps: Step S11, connecting the PIC communication connection board with the PIC module, the power module, the bus module and the I / O module through a standardized interface; detecting whether the output voltage of the power module is within the rated range, detecting whether the communication link of the bus module is normal, and detecting whether the signal input and output of the I / O module are normal; for the modules detected to be abnormal, generating a detection report and marking the abnormal modules; Step S12: Set the operation mode of each slave station through the configuration interface of the master station, perform distributed control, and initialize the adjustment coefficient of the adaptive communication protocol through historical data; load the FP-LSTM model weight through the embedded processor of the master station to initialize the fault prediction model.

3. The PIC module communication connection board according to claim 1, characterized in that: The step S2 includes the following steps: Step S21, the system collects the load data Li and task remaining time Ti of each module every 10ms, the load data is the CPU utilization, memory occupancy, communication bandwidth occupancy, and the task remaining time is the specific remaining working time that each module needs to execute; Step S22: The master station dynamically adjusts the priority of each slave station according to the real-time load and task urgency. The dynamic priority weight Wi is calculated as follows: Where Lmax is the maximum load capacity of the system, Tcritical is the task timeout threshold, and α and β are adjustment coefficients optimized through historical data; Step S23, dynamically allocate bandwidth according to weight Wi and adjust the communication priority of the bus module; if a module has communication abnormality, the system automatically reduces its weight to 0 and triggers the fault prediction model for diagnosis.

4. The PIC module communication connection board according to claim 1, characterized in that: The step S3 includes the following steps: Step S31, collect the operation data of each module once every hour, including voltage fluctuation value, temperature change value, communication bit error rate and historical fault records, normalize the data and input it into the fault prediction model; Step S32, calculating the failure probability pf based on the failure prediction model; In the formula, Sigmoid converts the linear combination result into a probability value, Xt is the time series input data, and b is the bias term; Step S33: If pf is greater than the threshold, the system triggers an early warning, notifies the maintenance personnel and provides maintenance suggestions.

5. The PIC module communication connection board according to claim 1, characterized in that: The step S4 includes the following steps: Step S41: Monitor the operation status of each module including communication link status, load distribution and fault warning information through the master station, and display the monitoring data in real time for operators to view. The data is updated in real time through the bus protocol; Step S42: According to the historical operation data, dynamically optimize the adjustment coefficient of the adaptive communication protocol, update the weight of the fault prediction model, record the system operation log, including communication abnormal events, fault prediction results and maintenance operation records, and regularly generate analysis reports for system optimization. The logs are stored in the SD card or cloud, and the analysis reports are generated by data analysis tools.

6. The PIC module communication connection board according to claim 1, characterized in that: In step S5, when the system is shut down, the power supply of each module is disconnected in turn, the system state is saved, and according to the prediction result of the fault prediction model, the aged module is replaced regularly and the radiator is cleaned.

Images