Real-time monitoring method and system for communication condition of intelligent plant station equipment

Abstract

The invention relates to the technical field of power monitoring, and discloses a real-time monitoring method and system for the communication condition of intelligent plant station equipment, and the method comprises the steps: collecting the communication data of the plant station equipment, and carrying out the processing of the data; monitoring the communication state of the plant station equipment by using a heartbeat mechanism; analyzing the communication data collected in real time through a data analysis engine, and carrying out equipment alarm in combination with an analysis and evaluation result; and according to the analysis and evaluation result and the alarm report, diagnosing the communication abnormity of the equipment, generating a maintenance suggestion and performing visual display. The device state and operation information of the ground-level plant station are monitored in real time, and a heartbeat and double detection mechanism is adopted to ensure that the communication state is accurate and reliable. Through a data analysis engine and a real-time stream processing framework, a communication anomaly prediction model is established, second-level monitoring is realized, and real-time information is provided for operation and maintenance personnel. And in combination with historical data, diagnosis and targeted maintenance suggestions are provided for alarm, the maintenance efficiency is improved, and the cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power monitoring systems, and in particular to a real-time monitoring method and system for communication status of intelligent plant equipment. Background Art

[0002] In the power monitoring system, the communication status of the local plant and station equipment is crucial to the stable operation of the system. However, due to equipment failure, network problems and other reasons, equipment communication interruptions often occur. When the plant and station equipment has a communication interruption, the local master station personnel can only view the equipment interruption alarm by logging into the provincial master station, and cannot actively discover the plant and station communication interruption problem. There is a large risk of network security monitoring, and it is difficult to achieve real-time monitoring and rapid response. Therefore, it is of great practical application value to develop a system that can monitor the communication status of the device in real time, display it through graphical visualization, and provide technical solution suggestions when the communication is interrupted. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is: when communication interruption occurs in plant equipment, personnel at the local master station can only view the equipment interruption alarm by logging into the provincial master station, and cannot actively discover the plant communication interruption problem. There is a greater risk of network security monitoring, and it is difficult to achieve real-time monitoring and rapid response.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a real-time monitoring method for the communication status of intelligent plant and station equipment, comprising: collecting plant and station equipment communication data and processing the data; using a heartbeat mechanism to monitor the communication status of plant and station equipment; analyzing the real-time collected communication data through a data analysis engine, and issuing equipment alarms based on the analysis and evaluation results; diagnosing equipment communication anomalies based on the analysis and evaluation results and the alarm report, generating maintenance suggestions and displaying them visually.

[0006] As a preferred solution of the real-time monitoring method of the communication status of the intelligent plant and station equipment described in the present invention, before collecting the communication data of the plant and station equipment and processing the data, it also includes monitoring the communication data of the plant and station equipment and integrating the relevant historical data in the system, converting the format of the collected data and transmitting it to the system database; the relevant historical data includes: equipment status, data collection timestamp, device identification information, communication status information and system log information; the communication data includes protocol data, number of bytes and transmission speed.

[0007] As a preferred scheme of the real-time monitoring method of the communication status of the intelligent plant and station equipment described in the present invention, the method comprises: monitoring the communication status of the plant and station equipment by using the heartbeat mechanism includes regularly sending heartbeat request packets to the plant and station equipment and receiving response heartbeat packets from the target equipment, setting a response time threshold, and if the response data packet of the plant and station equipment is not received after exceeding the preset time threshold, the sequence data of the last response heartbeat packet received before exceeding the time threshold is input into the preset Markov chain model for analysis, determining the reasons affecting the communication status of the equipment and outputting the probability of the reasons affecting the communication status of the equipment.

[0008] As a preferred solution of the real-time monitoring method of the communication status of the intelligent plant and station equipment described in the present invention, the steps of building the preset Markov chain model include: collecting the response heartbeat packet sequence data sent by the plant and station equipment, formatting and standardizing the data based on the collected heartbeat packet sequence data samples, and sorting them in chronological order; defining the relevant equipment communication status according to the characteristics of the heartbeat packet sequence data; calculating the probability of transition between each state according to the heartbeat packet sequence data to obtain the state transition probability matrix, and performing state conversion and evolution according to the probability rules specified by the state transition probability matrix to construct a Markov chain model based on the state transition probability matrix.

[0009] As a preferred solution of the real-time monitoring method of the communication status of the intelligent plant and station equipment described in the present invention, the data analysis engine includes building a data analysis engine that uses real-time stream processing technology to perform data analysis, and deploying a preset communication anomaly prediction model in the real-time stream processing framework to predict the communication status of the plant and station equipment.

[0010] As a preferred solution of the real-time monitoring method of the communication status of intelligent plant equipment described in the present invention, the equipment alarm based on the analysis and evaluation results includes using the prediction results to compare with the preset alarm threshold, triggering an alarm when it is predicted that the communication status of the plant equipment is in an abnormal state, and combining the probability of the causes affecting the communication status of the equipment and comparing with the preset probability threshold. When the threshold is exceeded, an alarm is triggered, and the relevant information of the equipment that triggered the alarm is recorded.

[0011] As a preferred solution of the real-time monitoring method of the communication status of the intelligent plant equipment described in the present invention, the diagnosis of the communication anomaly of the equipment includes, based on the alarm report, using the correlation analysis algorithm to associate the relevant historical data in the database for deep fusion analysis, determining the specific cause of the equipment communication anomaly, and combining the successful maintenance experience in the historical database to generate and output targeted maintenance suggestions for the operation and maintenance personnel.

[0012] A real-time monitoring system for the communication status of intelligent plant and station equipment using any of the methods described in the present invention, wherein: a data acquisition module monitors the communication data of local plant and station equipment in real time and the relevant historical data in the integration system, converts the format of the acquired data and transmits it to the system database; a heartbeat detection module sends heartbeat request packets to plant and station equipment at regular intervals and receives response heartbeat packets from target equipment, and sets relevant response time thresholds for judging the network communication status of plant and station equipment; a real-time analysis and alarm module analyzes the real-time acquired communication data through a data analysis engine, compares the analysis results with preset alarm rules, and issues corresponding levels of alarms to equipment with problems in combination with the analysis and evaluation results; and an intelligent diagnosis module receives the alarm report of the real-time analysis and alarm module, diagnoses the communication anomaly of the equipment in combination with the relevant historical events in the database, and provides targeted maintenance suggestions to operation and maintenance personnel based on the diagnosis content and the alarm content.

[0013] A computer device comprises: a memory and a processor; the memory stores a computer program, comprising: the steps of implementing any one of the methods of the present invention when the processor executes the computer program.

[0014] A computer-readable storage medium stores a computer program, comprising: when the computer program is executed by a processor, the steps of implementing any one of the methods of the present invention are implemented.

[0015] Beneficial effects of the present invention: The present invention monitors the status and operation information of prefecture-level plant equipment in real time, and adopts heartbeat and dual detection mechanisms to ensure that the communication status is accurate and reliable. Through the data analysis engine and real-time stream processing framework, a communication anomaly prediction model is established to achieve second-level monitoring, provide real-time information for operation and maintenance personnel, and improve the online rate. Combined with historical data, diagnosis and targeted maintenance suggestions are provided for alarms to improve maintenance efficiency and reduce costs. Graphic visualization technology is used to intuitively display the communication status, improve operation and maintenance efficiency and decision-making accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0017] Figure 1 An overall flow chart of a method for real-time monitoring of communication status of intelligent plant equipment provided by one embodiment of the present invention;

[0018] Figure 2A flowchart of building a Markov chain model used in a heartbeat detection module of a method for real-time monitoring of communication status of intelligent plant equipment provided by an embodiment of the present invention;

[0019] Figure 3 A flow chart of building a communication anomaly detection model for a real-time monitoring method of communication status of intelligent plant equipment provided by an embodiment of the present invention;

[0020] Figure 4 A schematic diagram of a monitoring system for a real-time monitoring method of communication status of intelligent plant equipment provided in a second embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0022] Example 1, reference Figure 1-3 , is an embodiment of the present invention, and provides a real-time monitoring method for communication status of intelligent plant equipment, comprising:

[0023] S1: Collect plant equipment communication data and process the data.

[0024] Furthermore, the plant equipment is monitored in real time, the equipment communication data is collected and processed, and the relevant historical data is integrated to form a data set; the relevant historical data includes: equipment status, data collection timestamp, device identification information, communication status information and system log information; the communication data includes protocol data, number of bytes and transmission speed.

[0025] Specifically, the specific steps for the data acquisition module to collect the communication data of the plant station equipment are as follows:

[0026] Capture data packets in the plant network through Wireshark, select the network interface connected to the plant equipment, such as Ethernet interface or WIFI interface; set filters to capture communication data related to the plant equipment, and limit the captured data packets according to the IP address, port number or other network attributes of the plant equipment in the capture filter, such as setting the filter to "ip.addr == plant equipment ip" to only capture communication data packets with the device; when the filtering conditions need to be further refined, more complex filter expressions can be used for filtering, such as filtering based on port number or protocol type. Enable promiscuous mode to capture all data packets passing through the network interface. When only viewing the communication of a specific device or address, you can turn off the promiscuous mode; set other options as needed, including capture limit, capture buffer size, etc.

[0027] Actively interact with the device to obtain status information according to specific time intervals or event triggers through the protocol, and the protocol includes: Modbus protocol, Profinet protocol, SNMP protocol, etc.; for example, send a request to the plant equipment through the SNMP protocol at regular intervals to obtain device status information, and Wireshark continuously records all communication data in the current plant network. The module also parses the captured data packets and related device status-related information and clear status data collected through the protocol, and obtains accurate time through the module's clock function, and briefly records the time mark while collecting each piece of data to obtain data collection timestamp data.

[0028] During the data collection process, the data format is converted and error-checked, the data is continuously monitored and acquired, and the data is transmitted to the system real-time analysis and alarm module for subsequent processing.

[0029] S2: Use the heartbeat mechanism to monitor the communication status of plant equipment.

[0030] The heartbeat mechanism is used to monitor the communication status of the plant equipment and compare it with the preset time threshold. If the preset time threshold is exceeded and no response data packet of the plant equipment is received, the last response heartbeat packet sequence data received before the time threshold is exceeded is input into the preset Markov chain model for analysis to determine the reasons affecting the communication status of the equipment and output the probability of the reasons affecting the communication status of the equipment.

[0031] Specifically, the heartbeat detection module detects the connectivity of the plant equipment communication link and the online status of the equipment by periodically sending and receiving heartbeat packets. Based on the network connection handshake mechanism, according to the preset interval time, the module actively sends a heartbeat request packet to the plant equipment. After receiving the request, the equipment immediately responds to the relevant response heartbeat packet. If the response packet is successfully received within the preset time threshold, it is considered that the communication link is normal and the equipment is online. If the response heartbeat packet is not received within the preset time threshold, the module will determine that the equipment communication is abnormal, and input the last response heartbeat packet sent into the preset decision tree model to determine the type of communication abnormality.

[0032] The time threshold should be set according to the stability of the current plant equipment communication link and actual needs. Too short a time interval will cause unnecessary network burden and false alarms, while too long a time interval may not be able to detect communication anomalies of plant equipment in time. The heartbeat detection module relies on the network for communication, and it is necessary to ensure the stability and reliability of the network. In the case of network failure or instability, the heartbeat detection module may not work properly.

[0033] Furthermore, the preset Markov chain model is used to analyze the heartbeat packet sequence data, and predict the cause of the device communication status by the last received response heartbeat packet sequence data. The steps of building the preset Markov chain model include:

[0034] Collect the response heartbeat packet sequence data sent by the plant station equipment, format and standardize the data based on the collected heartbeat packet sequence data samples, and sort them in chronological order;

[0035] Define the relevant device communication status according to the characteristics of the heartbeat packet sequence data;

[0036] The probability of transition between each state is calculated according to the heartbeat packet sequence data to obtain the state transition probability matrix. The state transition and evolution are carried out according to the probability rules specified by the state transition probability matrix, and a Markov chain model based on the state transition probability matrix is ​​constructed.

[0037] Specifically, the response heartbeat packet sequence data sent by the plant equipment is collected, including normal response heartbeat packets and abnormal response heartbeat packets, and the data is preprocessed, including cleaning, conversion and feature extraction, so as to be converted into a form suitable for the Markov chain model; the corresponding state is defined according to the characteristics of the response heartbeat packet sequence data to represent the communication state of the plant equipment, and the comprehensiveness and non-overlapping of the state set are ensured.

[0038] Analyze the collected heartbeat packet sequence data to calculate the probability of transitioning from one state to another, and construct a state transition probability matrix. Each row of the matrix represents the current state, and each column represents the next state. The elements in the matrix represent the probability of transitioning from the current state to the next state. It is necessary to ensure that the state transition probability proof satisfies that the sum of the probabilities in each row is equal to 1, and the elements in the proof are non-negative numbers.

[0039] Specify an initial state distribution. The initial state distribution specifies the probability distribution of each state at the start and should be consistent with the state set and state transition probability matrix.

[0040] The Markov chain model is trained using the collected response heartbeat packet sequence data so that the model can learn the characteristics of the response heartbeat packet and the law of state transition; the cross-validation method is used to evaluate the prediction accuracy and generalization ability of the model.

[0041] When the plant equipment sends a response data packet beyond the preset time threshold, the last response heartbeat packet sequence data received before exceeding the time threshold is input into the Markov chain model to output the probability of the cause affecting the communication status of the equipment.

[0042] For example, the last response heartbeat packet sequence data of a generator set in the plant station shows "Gen1", the operating status is "offline", the working mode is unclear, and the timestamp is "2023-10-10-15:30". The response data packet sequence data is input into the preset Markov chain model. According to the model and previous data, there is a 30% probability that the transition from the online state to the offline state is due to communication failure, a 40% probability that the generator set is shut down, and a 30% probability that it is other unknown reasons. Based on the offline state of the last heartbeat packet, the probability of the cause caused by communication failure is predicted to be 30%, the probability of the cause caused by shutdown is 40%, and the probability of other reasons is 30%; a transformer, the last response heartbeat packet shows that the device identification is "Trans1", the operating status is "communication interruption", the working mode is not clear, and the timestamp is "2023-10-11-10:00". Through model analysis, the transition from the normal state to the communication interruption state has a 50% probability of communication line problems, a 30% probability of the transformer's own communication module failure, and a 20% probability of other factors. At this time, the predicted probability of the cause being a communication line problem is 50%, the probability of the cause being a transformer's own communication module failure is 30%, and the probability of the cause being other factors is 20%.

[0043] S3: Analyze the real-time collected communication data through the data analysis engine, and issue equipment alarms based on the analysis and evaluation results.

[0044] The data analysis engine is used to analyze the communication data collected in real time, and the analysis results are compared with the preset alarm rules. Combined with the analysis and evaluation results, the corresponding level of alarm is issued for the equipment with problems.

[0045] Furthermore, the data analysis engine is built using real-time stream processing technology, using the Flink real-time stream processing framework.

[0046] Specifically, install and configure the Flink real-time stream processing framework and its dependent components, and install and configure the corresponding data storage system. Select a suitable data storage system to store the integrated historical data and intermediate results, and use specific adapters or APIs as required to connect the communication data collected by the data acquisition module to the real-time stream processing system to ensure the real-time and integrity of the data.

[0047] Configure the data stream processing logic in the real-time stream processing framework, including data cleaning, conversion, aggregation, etc., and set appropriate parameters such as parallelism and window size to optimize processing performance.

[0048] The real-time analysis and alarm module is divided into a data analysis unit and an alarm unit;

[0049] The data analysis unit is used to predict the communication status of plant equipment by building a data analysis engine that uses real-time stream processing technology to perform data analysis and deploying a preset communication anomaly prediction model in the real-time stream processing framework;

[0050] Furthermore, the communication anomaly prediction model is used to analyze the data set monitored and processed in real time by the data acquisition module to predict the communication status of related plant equipment, and the communication anomaly prediction model adopts a random forest model.

[0051] Specifically, the steps to build a random forest model include:

[0052] Receive integrated plant equipment related historical data, encode and preprocess the data samples, including standardization and normalization, the relevant historical data includes: equipment status, data collection timestamp, device identification information, communication status information and system log information, select relevant features that affect the communication status of the plant equipment from the data, and use feature engineering technology to extract higher-level features;

[0053] The processed data set is divided into a training set and a test set. A certain number of data samples are randomly selected from the data set to construct multiple different training sets with replacement.

[0054] The decision tree model is constructed using the C4.5 algorithm. The information gain rate of each feature is calculated based on the selected features for each randomly sampled training set, and the feature with the largest information gain rate is selected as the decision node to recursively construct the decision tree.

[0055] In order to avoid overfitting of decision trees, pruning techniques are used to prune decision trees. Pruning can be achieved by limiting the depth of the decision tree or deleting some unimportant branches.

[0056] Integrate the constructed multiple decision trees into a random forest model and use the voting mechanism to make the final prediction;

[0057] Calculate the accuracy, recall, F1 value and other indicators of the random forest model to evaluate the performance of the model; optimize the model based on the evaluation results;

[0058] Save the trained model as a model library so that it can be loaded and used in Flink jobs. Write code in the Flink job, load the trained communication anomaly prediction model from the model library, write the logic of the Flink job, obtain communication data from the data acquisition module in real time, extract features, and use the loaded communication anomaly prediction model to judge and predict the communication status of the plant equipment.

[0059] When the collected real-time communication data of the plant equipment is input, the corresponding prediction results are output; the prediction results include: the communication success rate, packet loss rate and possible fault types in the future period of time.

[0060] The alarm unit is used to compare the preset alarm threshold according to the prediction result output by the data analysis unit, and trigger an alarm when the data analysis unit predicts that the communication status of the plant equipment is in an abnormal state. At the same time, it receives the analysis report output by the heartbeat detection module and compares it with the preset probability threshold. When the threshold is exceeded, an alarm is triggered and the relevant information of the device that triggered the alarm is recorded.

[0061] Further, the alarm unit is used to trigger an alarm mechanism when the prediction result and the analysis report output by the heartbeat detection module reach or exceed a preset alarm threshold, and the triggering of the alarm mechanism includes outputting an alarm report, and the alarm report includes: current communication status, prediction result, alarm time, alarm level and equipment operation information;

[0062] According to the alarm triggering frequency and processing effect, the alarm strategy is continuously optimized to improve the accuracy of the alarm, and at the same time, statistical information of regularly generated alarm reports is output, and the statistical information includes: alarm quantity, type, processing time, processing method, and processing result.

[0063] Specifically, analyze, collect and integrate relevant historical data, identify key indicators of the communication status of plant equipment, such as communication success rate, packet loss rate and communication delay, and set relevant alarm thresholds according to the communication status of the indicators in combination with communication requirements and industry standards; for example, the threshold for the communication success rate is set to below 95%, and an alarm is triggered when the communication success rate output by the data analysis unit is lower than the threshold; the packet loss rate is set to above 0.5%, and an alarm is triggered when the packet loss rate is higher than the threshold.

[0064] A corresponding probability threshold is set for the probability of the cause that affects the communication status of the device output by the heartbeat detection module. When the probability of a certain cause that affects the communication status of the device output exceeds the threshold, an alarm is triggered; for example, an alarm is triggered when the probability of a generator set shutdown reaches 50%, and an alarm is triggered when the probability of a communication line problem reaches 40%. According to the changing trend of equipment performance, the alarm threshold is dynamically adjusted to make the alarm more accurate and timely.

[0065] The alarm unit prioritizes the corresponding alarms according to their severity and impact range to determine different alarm levels. For example, a communication line failure is set as a level one alarm, and a device failure with a smaller impact range is set as a level two alarm.

[0066] After the alarm mechanism is triggered, the alarm report is output to the intelligent diagnosis module in real time; at the same time, the statistical information of the alarm report is generated and output regularly according to the requirements, so that the operation and maintenance personnel can formulate more reasonable and optimized plant operation and maintenance strategies according to the statistical reports.

[0067] S4: Based on the analysis and evaluation results and alarm reports, diagnose the communication anomalies of the equipment, generate maintenance suggestions and display them visually.

[0068] Receive alarm reports from the real-time analysis and alarm module and diagnose communication anomalies of the equipment in combination with relevant historical events in the database, and provide targeted maintenance suggestions to operation and maintenance personnel based on the diagnosis content and alarm content;

[0069] Furthermore, the intelligent diagnosis module is used to receive the output alarm report and use the correlation analysis algorithm to associate the relevant historical data in the database for deep fusion analysis to determine the specific cause of the equipment communication abnormality, and combine the successful maintenance experience in the historical database to generate targeted maintenance suggestions for the operation and maintenance personnel and output them.

[0070] Specifically, after receiving the output alarm report, the intelligent diagnosis module will use the relevant historical data to perform auxiliary diagnosis through the association algorithm, identify whether the current alarm is similar to a certain fault mode in the past through association analysis, and locate the cause of the fault. At the same time, it uses the historical maintenance information in the relevant historical data to select the solution to the fault mode most similar to the current alarm and provide targeted maintenance suggestions for the operation and maintenance personnel and output them. Maintenance suggestions include: replacing faulty equipment, optimizing network configuration, adding spare equipment, etc.

[0071] The maintenance recommendations will detail the maintenance steps, required tools and materials, expected results, etc., so that operation and maintenance personnel can perform maintenance quickly and accurately.

[0072] Furthermore, through the visualization module, the plant situation awareness device is visualized in combination with the above-mentioned corresponding analysis, alarm results, diagnosis content and maintenance suggestions.

[0073] Furthermore, the visualization display module is used to display the communication status monitoring screen of the plant equipment to the operation and maintenance personnel in real time in a graphical visualization manner, while receiving the communication status, heartbeat mechanism analysis results, communication anomaly prediction model prediction results, alarm information and corresponding maintenance suggestions, and using different colors and icons to represent relevant detailed information of the equipment.

[0074] Select a suitable visualization framework or tool, divide different areas to display the monitoring screen of plant communication status, various analysis results and equipment information, etc. Set a fixed position and size ratio for each area. Use image drawing technology to present the equipment in an intuitive form, and use specific icons to represent different equipment types.

[0075] Establish a data interface to receive the alarm results and maintenance suggestions output by the real-time analysis and alarm module and the intelligent diagnosis module in real time, and associate and match the data with the corresponding equipment. Define different colors to indicate different states of the equipment, such as green for normal communication, yellow for level 2 alarms, and red for level 1 alarms, so that operation and maintenance personnel can quickly identify alarm information.

[0076] The data displayed on the visual interface is continuously updated based on the data received in real time, so that the color, icon and related text description can reflect the latest status of the device in real time. At the same time, search, filtering and other functions are provided to facilitate the quick location of specific devices or information.

[0077] A data submission interface is provided for operation and maintenance personnel to upload the information after maintenance through the interface, which includes equipment failure information, maintenance methods and equipment identification, etc. The visual display module parses and organizes the received information and associates it with the corresponding equipment; the data related to the equipment in the update module is updated, such as adding a mark to the equipment icon or popping up a prompt box to display specific failure information and maintenance methods. The module is dynamically refreshed by regularly requesting data or using a push mechanism to display the latest maintenance information; at the same time, the maintenance information is stored as a historical record for subsequent query and analysis.

[0078] At the same time, the alarm priority setting is adjusted according to the frequency of occurrence of different fault types in the maintenance information, and the alarm level is increased for fault types that occur frequently and have a greater impact; combined with the maintenance information, the false alarms in the alarm unit are analyzed, the causes of the false alarms are found and corrected in the alarm unit to reduce the false alarm rate.

[0079] The visualization display module receives the statistical information of the regularly generated alarm reports output by the alarm unit and presents them in the form of charts, which is convenient for operation and maintenance personnel to provide data support for the periodic analysis of the communication status of plant and station equipment and optimize the operation and maintenance strategy of the communication status of plant and station equipment.

[0080] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0081] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0082] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0083] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0084] Embodiment 2. In an exemplary embodiment, a real-time monitoring system for the communication status of intelligent plant equipment is also provided, including a data acquisition module, a heartbeat detection module, a real-time analysis and alarm module, an intelligent diagnosis module and a visualization display module; the data acquisition module is respectively connected to the real-time analysis and alarm module and the visualization display module, the intelligent diagnosis module is respectively connected to the real-time analysis and alarm module and the visualization display module, and the real-time analysis and alarm module is respectively connected to the heartbeat detection module and the visualization display module.

[0085] The data acquisition module is used to monitor the communication data of the local plant equipment in real time and integrate the relevant historical data in the system, convert the format of the collected data and transmit it to the system database.

[0086] The heartbeat detection module is used to periodically send heartbeat request packets to the plant equipment and receive response heartbeat packets from the target device, and set relevant response time thresholds to determine the network communication status of the plant equipment.

[0087] The real-time analysis and alarm module is used to analyze the communication data collected in real time through the data analysis engine, compare the analysis results with the preset alarm rules, and issue an alarm of the corresponding level to the equipment with problems based on the analysis and evaluation results.

[0088] Furthermore, the real-time analysis and alarm module is divided into a data analysis unit and an alarm unit;

[0089] A data analysis unit is used to predict the communication status of plant equipment by building a data analysis engine that uses real-time stream processing technology to perform data analysis and deploying a preset communication anomaly prediction model in the real-time stream processing framework;

[0090] The alarm unit is used to compare the preset alarm threshold with the prediction result output by the data analysis unit. When the data analysis unit predicts that the communication status of the plant equipment is in an abnormal state, an alarm is triggered. At the same time, the analysis report output by the heartbeat detection module is received and compared with the preset probability threshold. When the threshold is exceeded, an alarm is triggered and relevant information of the device that triggered the alarm is recorded.

[0091] The intelligent diagnosis module is used to receive the alarm report of the real-time analysis and alarm module, diagnose the communication anomaly of the equipment in combination with the relevant historical events in the database, and provide targeted maintenance suggestions to the operation and maintenance personnel based on the diagnosis content and the alarm content.

[0092] The visualization display module is used to visualize the plant situation awareness device in combination with the above-mentioned corresponding analysis, alarm results, diagnosis content and maintenance suggestions.

[0093] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A real-time monitoring method for communication status of intelligent plant equipment, characterized in that: include: Collect plant and station equipment communication data and process the data; Use the heartbeat mechanism to monitor the communication status of plant and station equipment; The data analysis engine analyzes the real-time collected communication data and generates equipment alarms based on the analysis and evaluation results. Based on the analysis and evaluation results and alarm reports, the communication anomalies of the equipment are diagnosed, maintenance suggestions are generated and visualized.

2. The real-time monitoring method of the communication status of intelligent plant equipment according to claim 1 is characterized in that: Before collecting the plant station equipment communication data and processing the data, it also includes: Monitor the communication data of plant and station equipment and integrate relevant historical data in the system, convert the format of the collected data and transmit it to the system database; The relevant historical data includes: device status, data collection timestamp, device identification information, communication status information and system log information; The communication data includes protocol data, number of bytes and transmission speed.

3. The real-time monitoring method for communication status of intelligent plant equipment according to claim 2, characterized in that: The use of the heartbeat mechanism to monitor the communication status of the plant equipment includes: Send heartbeat request packets to the plant station equipment regularly and receive response heartbeat packets from the target equipment. Set a response time threshold. If the response data packet of the plant station equipment is not received within the preset time threshold, the last response heartbeat packet sequence data received before the time threshold is exceeded is input into the preset Markov chain model for analysis to determine the reasons affecting the communication status of the device and output the probability of the reasons affecting the communication status of the device.

4. The real-time monitoring method for communication status of intelligent plant equipment according to claim 3, characterized in that: The steps of building the preset Markov chain model include: Collect the response heartbeat packet sequence data sent by the plant station equipment, format and standardize the data based on the collected heartbeat packet sequence data samples, and sort them in chronological order; Define the relevant device communication status according to the characteristics of the heartbeat packet sequence data; The probability of transition between each state is calculated according to the heartbeat packet sequence data to obtain the state transition probability matrix. The state transition and evolution are carried out according to the probability rules specified by the state transition probability matrix, and a Markov chain model based on the state transition probability matrix is ​​constructed.

5. The real-time monitoring method for communication status of intelligent plant equipment according to claim 4, characterized in that: The data analysis engine includes building a data analysis engine that uses real-time stream processing technology to perform data analysis, and deploying a preset communication anomaly prediction model in the real-time stream processing framework to predict the communication status of plant equipment.

6. The real-time monitoring method for communication status of intelligent plant equipment according to claim 5, characterized in that: The device alarm based on the analysis and evaluation results includes using the prediction results to compare with the preset alarm threshold, triggering an alarm when it is predicted that the communication status of the plant equipment is in an abnormal state, and combining the probability of the cause affecting the communication status of the equipment and comparing with the preset probability threshold. When the threshold is exceeded, an alarm is triggered and the relevant information of the equipment that triggered the alarm is recorded.

7. The real-time monitoring method for communication status of intelligent plant equipment according to claim 6, characterized in that: The diagnosis of the communication anomaly of the equipment includes, based on the alarm report, using the correlation analysis algorithm to perform deep fusion analysis on relevant historical data in the correlation database, determining the specific cause of the equipment communication anomaly, and generating and outputting targeted maintenance suggestions for operation and maintenance personnel in combination with successful maintenance experience in the historical database.

8. A real-time monitoring system for the communication status of intelligent plant equipment using the method according to any one of claims 1 to 7, characterized in that: include, The data acquisition module monitors the communication data of the local plant equipment in real time and integrates the relevant historical data in the system, converts the format of the collected data and transmits it to the system database; The heartbeat detection module sends heartbeat request packets to the plant equipment at regular intervals and receives the response heartbeat packets from the target equipment, and sets the relevant response time threshold to determine the network communication status of the plant equipment; The real-time analysis and alarm module analyzes the real-time collected communication data through the data analysis engine, compares the analysis results with the preset alarm rules, and issues corresponding levels of alarms to the devices with problems based on the analysis and evaluation results; The intelligent diagnosis module receives the alarm reports from the real-time analysis and alarm modules and diagnoses the communication anomalies of the equipment in combination with the relevant historical events in the database, and provides targeted maintenance suggestions to the operation and maintenance personnel based on the diagnosis content and alarm content.

9. A computer device comprising: Memory and processor; The memory stores a computer program, which is characterized in that when the processor executes the computer program, the steps of the real-time monitoring method for the communication status of intelligent plant equipment as described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the real-time monitoring method of the communication status of intelligent plant equipment as described in any one of claims 1-7 are implemented.

Images