A gas turbine startup process monitoring system based on Siemens SFC

Abstract

The present invention provides a gas turbine startup process monitoring system based on Siemens SFC, belonging to the technical field of process monitoring. The system includes: an acquisition module: acquiring the integration of the control part of the Siemens SFC system and obtaining the relative control methods between the control integrations; a collection module: collecting the status data of Siemens SFC, excitation, TCS, and all auxiliary devices according to the relative control methods between the control integrations; a generation module: transmitting all the status data into a self-developed screen, obtaining the analog and digital quantities of all devices in the Siemens SFC during the startup sequence control, and generating a real-time dynamic control screen; a monitoring module: configuring a touch-based human-machine interaction interface mode based on the dynamic control screens of all devices to monitor the entire process of the instructions received and feedback sent during the startup process, as well as the status of each switch opening and closing during the startup process. It solves the problems of time, economic waste caused by the cumbersome startup process, and the timeliness of being able to quickly start when encountering problems.

Description

Technical Field

[0001] The present invention relates to the technical field of process monitoring, and particularly to a gas turbine startup process monitoring system based on Siemens SFC. Background Art

[0002] At present, there is no process monitoring for the Siemens SFC startup in gas turbine power plants. Previously, to find the faults in the Siemens SFC startup of gas turbines, engineers needed to measure or analyze each operation link before they could locate the specific faults in the Siemens SFC sequential control. The process was extremely cumbersome, wasting a large amount of time and money. At the same time, in the operation of its own sequential control process, the internal control of Siemens SFC runs in a "black box" mode. When encountering specific faults, it is impossible to quickly locate the fault source. Professional engineers from the equipment manufacturer need to connect special equipment to specifically query the fault codes to determine the root cause of the faults, and it is impossible to meet the timeliness requirements of the quick startup of the power plant units when problems occur.

[0003] Therefore, the present invention proposes a gas turbine startup process monitoring system based on Siemens SFC. Summary of the Invention

[0004] The present invention provides a gas turbine startup process monitoring system based on Siemens SFC. By obtaining the integration of the control part of the Siemens SFC system and obtaining the relative control methods between the control integrations, the state data of all devices are collected according to the relative control methods between the control integrations, and all the state data are transmitted into a self-developed screen. The analog quantities and switch quantities of all devices in the Siemens SFC startup sequential control are obtained, and a real-time dynamic control screen is generated. Based on the dynamic control screen of all devices, a touch-based human-computer interaction interface method is configured to monitor the whole process of the instructions received and feedback sent during the SFC startup process, as well as the on-off states of each switch during the startup process, solving the problems of wasting time and money caused by the cumbersome process in the background art and the timeliness of quick startup when problems occur.

[0005] The present invention proposes a gas turbine startup process monitoring system based on Siemens SFC, and the system includes:

[0006] An acquisition module: obtaining the integration of the control part of the Siemens SFC system and obtaining the relative control methods between the control integrations;

[0007] A collection module: collecting the state data of Siemens SFC, excitation, TCS, and all auxiliary devices according to the relative control methods between the control integrations;

[0008] A generation module: transmitting all the state data into a self-developed screen, obtaining the analog quantities and switch quantities of all devices in the Siemens SFC startup sequential control, and generating a real-time dynamic control screen;

[0009] Monitoring module: Based on the dynamic control screens of all devices, a touch-based human-machine interaction interface method is configured to monitor the whole process of the instructions received and feedback sent during the SFC startup process, as well as the on / off states of each switch during the startup process.

[0010] Preferably, the acquisition module includes:

[0011] The first acquisition unit: According to the components of the Siemens SFC system and combined with the function selection control of each part, the integration of the control part is obtained.

[0012] The first determination unit: Based on the integration and the preset working mode of the Siemens SFC system, the startup trigger conditions between the control integrations are determined.

[0013] The second determination unit: Based on the startup trigger conditions between the control integrations, the relative control modes between the control integrations are determined.

[0014] Preferably, the acquisition module includes:

[0015] The third determination unit: Determine the current states of the Siemens SFC, excitation, TCS, and all auxiliary devices during the operation of each control integration.

[0016] The fourth determination unit: Based on the current state, determine the data acquisition conditions for each acquisition device.

[0017] The configuration unit: Based on the data acquisition conditions of each acquisition device and the relative control modes between the control integrations, configure the acquisition environments of the Siemens SFC, excitation, TCS, and all auxiliary devices respectively.

[0018] The acquisition unit: Acquire the state data of the Siemens SFC, excitation, TCS, and all auxiliary devices in the acquisition environments of the Siemens SFC, excitation, TCS, and all auxiliary devices.

[0019] Preferably, it further includes:

[0020] The classification unit: Classify the state data of the Siemens SFC, excitation, TCS, and all auxiliary devices according to the data type.

[0021] The formulation unit: Based on the classification results, determine the data characteristics in the classified data, and formulate data labels according to the data characteristics.

[0022] The association unit: Package the classification results into multiple data sets according to the data labels and associate them with the data labels.

[0023] Preferably, the formulation unit includes:

[0024] The first determination subunit: Based on the classification result, determine the general data attributes of the classified data in each type of data;

[0025] The second determination subunit: Determine multiple mapping labels for each type of data according to the general data attributes;

[0026] The acquisition subunit: Acquire the label mapping domain of each mapping label of each type of data, and determine the matching degree between the label mapping domain and each type of data;

[0027] The selection subunit: Select the target mapping label with the maximum matching degree of each type of data as the data label of this type of data.

[0028] Preferably, the generation module includes:

[0029] The conversion unit: Convert all status data into analog signals and transmit the analog signals into the self-developed screen;

[0030] The fifth determination unit: Determine the analog quantities and switch quantities of all devices in the Siemens SFC during the start-up sequence control according to the state variables of the self-developed screen;

[0031] The first generation unit: Acquire the control parameters of all devices in the Siemens SFC during the start-up sequence control, and generate the control quantity of each device according to the control parameters;

[0032] The second generation unit: Generate a real-time dynamic control screen based on the control quantity of each device and the analog quantity and switch quantity of this device.

[0033] Preferably, the monitoring module includes:

[0034] The second acquisition unit: Determine the best interaction method based on the dynamic control screens of all devices, and acquire the interaction parameters of the best interaction method;

[0035] The receiving unit: Configure the touch-based human-computer interaction interface method according to the interaction parameters, and remotely receive the instructions received and the feedback sent during the SFC start-up process;

[0036] The monitoring unit: Monitor the whole process of the on-off state of each switch according to the instructions received and the feedback sent during the SFC start-up process.

[0037] Preferably, it further includes:

[0038] The third acquisition unit: Perform redundancy and dimensionality reduction processing on the device data, and acquire the processed device data;

[0039] The fourth acquisition unit: Perform feature extraction on the processed device data, and acquire the initial feature set of the device data according to the extraction result;

[0040] Integration unit: Retrieve key features related to the status from the initial feature set and integrate them into a subset of key features;

[0041] Fifth acquisition unit: Acquire the topological structure information and preset operation mode information of the Siemens SFC, as well as the node attributes of each control node of the Siemens SFC;

[0042] Sixth determination unit: Determine the control topology weight value of each control node according to the node attributes of each control node, the topological structure information, and the preset operation mode information;

[0043] Seventh determination unit: Determine the base value of each control quantity in the device data based on the control topology weight value of each control node;

[0044] Sixth acquisition unit: Acquire the timing feature information corresponding to the device data;

[0045] Extraction unit: Extract the time series data of each control quantity from the device data according to the timing feature information;

[0046] Eighth determination unit: Determine the control feature information of each control quantity based on the time series data of each control quantity;

[0047] Seventh acquisition unit: Use the time series data and base value of each control quantity as model input samples, and use the control feature information of each control quantity as model output samples to train a preset network model to obtain an identification model for each control quantity;

[0048] Eighth acquisition unit: Use the identification model of each control quantity to obtain the target control features corresponding to the target time series data of each key feature in the subset of key features;

[0049] Ninth acquisition unit: Obtain the first operation feature of each control quantity according to the target control feature of each key feature;

[0050] Ninth determination unit: Obtain the change situation of the target control feature of each control quantity in the device data, and determine the control change rule of each control quantity according to the change situation;

[0051] Confirmation unit: Confirm the control quantities with a control change rule similarity greater than or equal to a preset threshold as the same type of control, and confirm the second target operation feature of any control quantity in each type of control as the final operation feature of the type of control.

[0052] Other features and advantages of the present invention will be described in the subsequent specification, and part of them will become obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification, claims, and drawings.

[0053] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Description of the Drawings

[0054] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the accompanying drawings:

[0055] Figure 1 is a structural diagram of a gas turbine startup process monitoring system based on Siemens SFC in an embodiment of the present invention;

[0056] Figure 2 is a structural diagram of the acquisition module in an embodiment of the present invention;

[0057] Figure 3 is a network diagram of the control part of adding a touch-type human-machine interaction interface device to Siemens SFC;

[0058] Figure 4 is a schematic diagram showing the states of TCS commands, SFC status, and related switches indicated by different colors in the touch-type human-machine interaction interface device;

[0059] Figure 5 is a schematic diagram of the screen display during the process of the Siemens SFC in the stop state and the SFC running state dragging the unit. Detailed Embodiments

[0060] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0061] Embodiment 1:

[0062] The present invention provides a gas turbine startup process monitoring system based on Siemens SFC, as Figure 1 shown. The system includes:

[0063] An acquisition module: acquires the integration of the control part of the Siemens SFC system and obtains the relative control methods between the control integrations;

[0064] A collection module: collects the status data of Siemens SFC, excitation, TCS, and all auxiliary devices according to the relative control methods between the control integrations;

[0065] A generation module: transmits all the status data into a self-developed screen, obtains the analog and digital quantities of all devices in the Siemens SFC during the startup sequence control, and generates a real-time dynamic control screen;

[0066] Monitoring Module: Based on the dynamic control screens of all devices, a touch-based human-machine interaction interface method is configured to monitor the entire process of the instructions received and feedback sent during the SFC startup process, as well as the on / off status of each switch during the startup process.

[0067] In this embodiment, the relative control method means that the control part of the Siemens SFC system consists of an S7-300 series PLC and a CU320, and Profibus DP communication is used between the two. The signals between the TCS and the SFC, as well as between the excitation and the SFC, are in hardwired mode, including the TCS sending commands to the SFC and the SFC sending status feedback to the TCS, and the SFC sending commands to the excitation and the excitation sending status feedback to the SFC.

[0068] In this embodiment, the self-developed screen refers to a self-developed screen that can display analog and digital quantities during the startup process of the Siemens SFC.

[0069] In this embodiment, the status data refers to the data of all devices in different states, where the different states include: high-speed operation state, low-speed operation state, and fault state. For example, in the fault state, the power on the excitation system is 0.

[0070] In this embodiment, the dynamic control screen refers to a screen that can display the on / off status of each digital quantity, as well as the instructions received and feedback sent during the SFC startup process.

[0071] In this embodiment, the human-machine interaction interface refers to the communication medium or means between a human and a computer system, and is a platform for two-way information exchange of various symbols and actions between a human and a computer.

[0072] The beneficial effects of the above technical solution are: By obtaining the control method between the Siemens SFC integrations, collecting the status data of all devices, and transmitting the status data to the self-developed screen to generate a real-time dynamic control screen, and configuring a touch-based human-machine interaction interface method, it is possible to quickly locate problems that occur during device operation, and can also greatly shorten the fault analysis time, which greatly improves the economy and reliability of operation.

[0073] Embodiment 2:

[0074] The present invention provides a gas turbine startup process monitoring system based on Siemens SFC, as Figure 2 shown, the acquisition module includes:

[0075] The first acquisition unit: According to the components of the Siemens SFC system and combined with the functions of each part for selection and control, obtain the integration of the control part;

[0076] The first determination unit: Determine the start trigger conditions between each control integration according to the preset working mode based on the Siemens SFC system;

[0077] The second determination unit: Based on the start trigger conditions between each control integration, determine the relative control mode between each control integration.

[0078] In this embodiment, the function selection control may include: control function, communication function, diagnostic function, and processing speed.

[0079] In this embodiment, the preset working modes include: centralized operation, independent operation.

[0080] In this embodiment, the start trigger condition is, for example, that when the generator is running with an allowed load, the excitation system should be able to supply the corresponding excitation current, or when a fault occurs inside the generator, the excitation system should be able to quickly de-energize the field.

[0081] In this embodiment, the relative control mode means that the control part of the Siemens SFC system consists of an S7-300 series PLC and a CU320, and Profibus DP communication is used between the two. The signals between the TCS and the SFC and between the excitation and the SFC adopt a hard-wired connection method, including the TCS sending commands to the SFC and the SFC sending status feedback to the TCS, and the SFC sending commands to the excitation and the excitation sending status feedback to the SFC.

[0082] The beneficial effects of the above technical solutions are: By obtaining the integration of each control part of the Siemens SFC, based on the preset working mode of the Siemens SFC, determining the start trigger conditions between each inheritance, and determining the relative control mode between each integration, it provides a prerequisite for subsequent collection of all device data.

[0083] Embodiment 3:

[0084] The present invention provides a gas turbine startup process monitoring system based on Siemens SFC, and the acquisition module includes:

[0085] The third determination unit: Determine the current states of the Siemens SFC, excitation, TCS, and all auxiliary devices respectively when each control integration is running;

[0086] The fourth determination unit: Based on the current state, determine the data acquisition conditions for each acquisition device;

[0087] The configuration unit: Based on the data acquisition conditions of each acquisition device and the relative control mode between each control integration, configure the acquisition environments of the Siemens SFC, excitation, TCS, and all auxiliary devices respectively;

[0088] Collection unit: Collect the status data of Siemens SFC, excitation, TCS and all auxiliary devices in the collection environment of Siemens SFC, excitation, TCS and all auxiliary devices.

[0089] In this embodiment, the current status includes: operating status, stopped operating status, closed or open status of the switch corresponding to the device, recording status, stopped recording status.

[0090] In this embodiment, the data collection condition refers to the current status of all devices corresponding to the collection device when collecting data. For example, when collecting real-time data of the excitation system, the excitation system should be in the powered-on state.

[0091] In this embodiment, the status data refers to the data of all devices in different states.

[0092] The beneficial effects of the above technical solution are: By determining the current status of all devices and determining the collection conditions of each collection device, the collection environment of all devices is configured, and the status data of all devices is collected in the collection environment, which can make the collected data more accurate.

[0093] Embodiment 4:

[0094] The present invention provides a gas turbine startup process monitoring system based on Siemens SFC, further including:

[0095] Classification unit: Classify the status data of Siemens SFC, excitation, TCS and all auxiliary devices according to the data type;

[0096] Formulation unit: Based on the classification result, determine the data characteristics in the classified data, and formulate data labels according to the data characteristics;

[0097] Association unit: Package the classification result into multiple data sets according to the data label and associate it with the data label.

[0098] In this embodiment, the data type includes numeric type, such as data representing the magnitude of current;

[0099] Alphabetic type, such as model parameters representing various devices.

[0100] In this embodiment, the data characteristic refers to the unique feature of the data, such as the speed of obtaining the data, the variability of the data, the authenticity of the data.

[0101] In this embodiment, the data label refers to an additional information added to the data during the data processing process, which can help better understand and analyze the data.

[0102] In this embodiment, the data tags can include: large current, constant current, etc. Data with the same tags are packaged into multiple data sets.

[0103] The beneficial effects of the above technical solution are as follows: Classify the data of all devices according to the data type, determine the characteristics of each type of data, formulate data tags, and package the data into multiple data sets according to the data tags, which can classify the data more accurately and facilitate observation.

[0104] Embodiment 5:

[0105] The present invention provides a gas turbine startup process monitoring system based on Siemens SFC. The formulation unit includes:

[0106] The first determination subunit: Based on the classification result, determine the common data attributes of the classified data in each type of data;

[0107] The second determination subunit: Determine multiple mapping tags for each type of data according to the common data attributes;

[0108] The acquisition subunit: Acquire the label mapping domain of each mapping tag of each type of data, and determine the matching degree between the label mapping domain and each type of data;

[0109] The selection subunit: Select the target mapping tag with the maximum matching degree of each type of data as the data tag of this type of data.

[0110] In this embodiment, the data attributes may include: It may be a Boolean attribute, which is a nominal attribute with only two states: 0 or 1. It may be a numerical attribute, a quantitative measurement, represented by an integer or a real value. It may also be a continuous attribute, with the attribute value being a real number, generally represented by a floating-point variable, such as temperature.

[0111] In this embodiment, the mapping tag is multiple functional tags mapped by each type of data.

[0112] In this embodiment, the label mapping domain is the industrial field involved in each functional tag.

[0113] In this embodiment, the matching degree is the data generation matching degree between each industrial field and each type of data.

[0114] The beneficial effects of the above technical solution are as follows: According to the classification result, determine the common data attributes of each type of data, thereby determining multiple mapping tags for each type of data, acquire the label mapping domain, determine the matching degree between the label mapping domain and each type of data, which can accurately perform data tagging on the data and facilitate the later search for data.

[0115] Embodiment 6:

[0116] The present invention provides a monitoring system for the starting process of a gas turbine based on Siemens SFC. The generating module includes:

[0117] Conversion unit: Convert all status data into analog signals and transmit the analog signals into the self-developed screen.

[0118] Fifth determination unit: Determine the analog quantities and digital quantities of all devices in the Siemens SFC during the starting sequence control according to the status variables of the self-developed screen.

[0119] First generating unit: Obtain the control parameters of all devices in the Siemens SFC during the starting sequence control, and generate the control quantity of each device according to the control parameters.

[0120] Second generating unit: Generate a real-time dynamic control screen based on the control quantity of each device and the analog quantity and digital quantity of the device.

[0121] In this embodiment, the analog signal refers to the information represented by a continuously changing physical quantity, and the amplitude, frequency, or phase of its signal changes continuously with time, or within a continuous time interval, the characteristic quantity representing the information can present any value at any instant. For example, voltage, current signal, pressure signal, temperature signal.

[0122] In this embodiment, the analog quantity refers to a quantity whose variable changes continuously within a certain range, that is, it can take any value within a certain range (domain of definition).

[0123] In this embodiment, the digital quantity is a signal similar to the on / off of a switch, either on or off.

[0124] In this embodiment, the control parameter is some physical parameters that affect the evolution characteristics of the system status variables. These parameters change slowly and can often be treated as constants in the system mathematical model and can be adjusted by people from outside the system.

[0125] In this embodiment, the dynamic control screen refers to a screen that can display the on / off states of each digital quantity and the instructions received and feedback sent during the starting process of the Siemens SFC.

[0126] The beneficial effects of the above technical solution are: By converting the status data into analog signals and transmitting them into the self-developed screen, determining the analog quantities and digital quantities of all devices in the Siemens SFC, and obtaining the control parameters of all devices in the Siemens SFC, a dynamic control screen is generated, which is convenient for analyzing the starting process and troubleshooting, and can realize real-time recording and storage of signals.

[0127] Embodiment 7:

[0128] The present invention provides a monitoring system for the starting process of a gas turbine based on Siemens SFC, and a monitoring module, including:

[0129] A second acquisition unit: determining the optimal interaction mode based on the dynamic control screens of all devices, and acquiring the interaction parameters of the optimal interaction mode;

[0130] A receiving unit: configuring a touch-based human-machine interaction interface mode according to the interaction parameters, and remotely receiving the instructions received and the feedback sent during the SFC starting process;

[0131] A monitoring unit: monitoring the whole process of the on-off state of each switch according to the instructions received and the feedback sent during the SFC starting process.

[0132] In this embodiment, the interaction modes include: voice interaction, touch screen interaction, text interaction, and visual interaction.

[0133] In this embodiment, the optimal interaction mode is touch screen interaction.

[0134] In this embodiment, if the interaction parameter is voice interaction, for example, relevant parameters need to be determined, such as the voice volume, speech rate, and voice clarity.

[0135] In this embodiment, the instructions may include enabling power supply to the excitation system, igniting the gas turbine, and entering the water washing mode.

[0136] The beneficial effects of the above technical solutions are: by determining the interaction parameters of the optimal interaction mode, configuring a touch-based human-machine interaction interface mode, remotely receiving the instructions received and the feedback sent during the Siemens SFC starting process, and thus monitoring the whole process of the on-off state of each switch, it is possible to quickly locate the problems occurring in the equipment operation, and can also greatly shorten the fault analysis time, which greatly improves the economy and reliability of the operation.

[0137] Embodiment 8:

[0138] The present invention provides a monitoring system for the starting process of a gas turbine based on Siemens SFC, further including:

[0139] A third acquisition unit: performing redundancy and dimensionality reduction processing on the device data to obtain the processed device data;

[0140] A fourth acquisition unit: extracting features from the processed device data, and obtaining an initial feature set of the device data according to the extraction results;

[0141] An integration unit: retrieving the key features related to the state from the initial feature set and integrating them into a key feature subset;

[0142] The fifth acquisition unit: acquires the topological structure information and preset operation mode information of the Siemens SFC, as well as the node attributes of each control node of the Siemens SFC;

[0143] The sixth determination unit: determines the control topology weight value of each control node according to the node attributes of each control node, the topological structure information, and the preset operation mode information;

[0144] The seventh determination unit: determines the base value of each control quantity in the device data based on the control topology weight value of each control node;

[0145] The sixth acquisition unit: acquires the timing characteristic information corresponding to the device data;

[0146] The extraction unit: extracts the timing sequence data of each control quantity from the device data according to the timing characteristic information;

[0147] The eighth determination unit: determines the control characteristic information of each control quantity based on the timing sequence data of each control quantity;

[0148] The seventh acquisition unit: uses the timing sequence data and the base value of each control quantity as model input samples, and at the same time uses the control characteristic information of each control quantity as model output samples to train a preset network model to obtain an identification model for each control quantity;

[0149] The eighth acquisition unit: uses the identification model of each control quantity to obtain the target control characteristics corresponding to the target timing sequence data of each key feature in the key feature subset;

[0150] The ninth acquisition unit: obtains the first operation characteristics of each control quantity according to the target control characteristics of each key feature;

[0151] The ninth determination unit: obtains the change situation of the target control characteristics of each control quantity in the device data, and determines the control change rule of each control quantity according to the change situation;

[0152] The confirmation unit: confirms the control quantities with a control change rule similarity greater than or equal to a preset threshold as the same type of control, and determines the final operation characteristics of the same type of control as the second target operation characteristics of any control quantity in each type of control.

[0153] In this embodiment, dimensionality reduction processing means that dimensionality reduction is a preprocessing method for high-dimensional feature data. Dimensionality reduction is to retain some important features of the high-dimensional data, remove noise and unimportant features, so as to achieve the purpose of improving the data processing speed.

[0154] In this embodiment, detect the distribution of useless data in the device data;

[0155] Determine the attribute value of each piece of useless data according to the distribution of the useless data;

[0156] Calculate the influence factor of the useless data in the device data based on the attribute value of each piece of useless data:

[0157]

[0158] where, W k represents the influence factor of the useless data in the k-th device data, N represents the total number of useless data in all device data, Nk represents the number of useless data in the k-th device data, y represents the y-th piece of useless data, L y represents the attribute value of the y-th piece of useless data, L represents the reference attribute value of the normal data, γ y represents the conflict factor between the y-th piece of useless data and other useful data in the device data, represents the interference factor of the y-th piece of useless data on other useful data in the device data, e represents the natural constant, with a value of 2.72, μ k represents the data integrity of the k-th device data, with a value range of (0, 1); a1 represents a constant, with a value of 0.8;

[0159] Confirm whether the influence factor of the useless data in the device data is greater than or equal to the preset threshold. If so, confirm that there is bad data in the device data. If not, confirm that there is no bad data in the device data;

[0160] Eliminate the bad data in the device data according to the confirmation result.

[0161] In this embodiment, feature extraction is to extract the features of the data, such as the capacity, type, and variability of the data.

[0162] In this embodiment, the initial feature set of the device data is represented as the set of the performance features of the data composition items of the device data. For example, the data represents the serial number, device model, and measurement data of the device..

[0163] In this embodiment, the key features related to the state are represented as the feature data features corresponding to the data composition items related to the device state evaluation. For example, if the upper power is 0, it means that the excitation system is in the off state.

[0164] In this embodiment, the preset operation mode information is represented as the preset operation line information of the Siemens SFC and the control information on each line.

[0165] In this embodiment, the key feature subset is to integrate all the key features into a data subset.

[0166] In this embodiment, the topology structure information is the physical layout information of the interconnections between various devices in the Siemens SFC system.

[0167] In this embodiment, the node attributes include: the name of the node, for example, the name of an element node is the same as the tag name, the value of the node, for example, the node value of an element node is undefined or null, and the type of the node.

[0168] In this embodiment, the control topology weight value is the control weight of each control node for device control, which is determined according to the number of devices controlled by each control node and the control parameters for each controlled device.

[0169] Among them, each control node corresponds to a control topology weight value. According to the node attributes, multiple control topology weight values of each control node for each control quantity are obtained, and a preset base value is determined according to the multiple control topology weight values.

[0170] In this embodiment, the base value refers to the value that the control quantity cannot exceed, which is the minimum working value of each control quantity of each controlled device under the control of the control node. For example, when using a switch to control the power on, where the control quantity is the real-time speed of electricity, such as 1 J / s.

[0171] In this embodiment, the time series feature information refers to the feature information extracted from the time series data that is meaningful for the research problem, which is mainly divided into time domain features and frequency domain features.

[0172] In this embodiment, the time series data is the sequence data of the state vectors of each control quantity changing with time, which describes the measured values of the measured subject at each time point within a time range.

[0173] In this embodiment, the control change rule means that, for example, when the gas turbine is in the ignition mode, then the water washing mode should stop working.

[0174] In this embodiment, the control change rule similarity means that, for example, when entering the gas turbine ignition, then the water washing mode and the purging mode should stop working. However, when the excitation system enters the power-on mode, then the water washing mode stops working, but the purging mode can continue to work. Then the control change rule similarity between the water washing mode and the purging mode is 50%.

[0175] In this embodiment, the first operation feature can be that the operation speed is too fast or the operation is stable.

[0176] In this embodiment, the preset threshold can be 0.51.

[0177] In this embodiment, the time series feature information corresponding to the device data is expressed as the statistical feature information of the device data in each time period.

[0178] In this embodiment, the second target operating characteristic means that if the washing mode and the purging mode are of the same type of control, for example, the operating characteristic of the washing mode can be selected as the final operating characteristic, such as operating once every 10 minutes.

[0179] In this embodiment, the control characteristic information is represented as the control frequency and control intensity information corresponding to each control quantity.

[0180] The beneficial effects of the above technical solution are as follows: By obtaining the initial feature set of the device data, the sub-data in the device data can be quickly subjected to feature normalization processing, so that the data features of each dimension can be statistically obtained, laying the foundation for the subsequent determination of the operating characteristics of the control quantity. Further, by constructing the recognition model of each control quantity, the target control characteristics corresponding to the target time series data of each key feature in the key feature subset can be quickly obtained, and then the operating characteristics of the control quantity can be accurately determined, improving the data acquisition efficiency and accuracy.

[0181] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and its equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A gas turbine startup process monitoring system based on Siemens SFC, characterized in that, The system includes: An acquisition module: acquiring the integration of the control part of the Siemens SFC system, and acquiring the relative control modes between the control integrations; A collection module: collecting the status data of the Siemens SFC, excitation, TCS, and all auxiliary devices according to the relative control modes between the control integrations; A generation module: transmitting all the status data into the self-developed screen, acquiring the analog quantities and digital quantities of all devices in the Siemens SFC during the start-up sequence control, and generating a real-time dynamic control screen; A monitoring module: configuring a touch-based human-computer interaction interface mode based on the dynamic control screens of all devices, and monitoring the whole process of the instructions received and feedback sent during the SFC start-up process, as well as the on-off states of each switch during the start-up process; Among them, it also includes: A classification unit: classifying the status data of the Siemens SFC, excitation, TCS, and all auxiliary devices according to the data type; A formulation unit: determining the data characteristics in the classified data based on the classification result, and formulating data labels according to the data characteristics; An association unit: packaging the classification result into multiple data sets according to the data labels and associating them with the data labels; Among them, the formulation unit includes: A first determination subunit: determining the common data attributes of the classified data in each type of data based on the classification result; A second determination subunit: determining multiple mapping labels for each type of data according to the common data attributes; An acquisition subunit: acquiring the label mapping domain of each mapping label of each type of data, and determining the matching degree between the label mapping domain and each type of data; A selection subunit: selecting the target mapping label with the maximum matching degree of each type of data as the data label of that type of data.

2. The monitoring system for the gas turbine startup process based on Siemens SFC according to claim 1, characterized in that, The acquisition module includes: A first acquisition unit: acquiring the integration of the control part according to the components of the Siemens SFC system and combining the functions of each part for control selection; A first determination unit: determining the start trigger conditions between the control integrations based on the integration and the preset working mode of the Siemens SFC system; A second determination unit: determining the relative control modes between the control integrations based on the start trigger conditions between the control integrations.

3. The monitoring system for the gas turbine starting process based on Siemens SFC according to claim 1, wherein The collection module includes: A third determination unit: determining the current states of the Siemens SFC, excitation, TCS, and all auxiliary devices respectively when each control integration is running; A fourth determination unit: determining the data collection conditions of each collection device based on the current state; A configuration unit: respectively configuring the collection environments of the Siemens SFC, excitation, TCS, and all auxiliary devices based on the data collection conditions of each collection device and the relative control modes between the control integrations; A collection unit: collecting the status data of the Siemens SFC, excitation, TCS, and all auxiliary devices in the collection environments of the Siemens SFC, excitation, TCS, and all auxiliary devices.

4. The monitoring system for the gas turbine startup process based on Siemens SFC according to claim 1, characterized in that The generation module includes: A conversion unit: converting all the status data into analog signals and transmitting the analog signals into the self-developed screen; A fifth determination unit: determining the analog quantities and digital quantities of all devices in the Siemens SFC during the start-up sequence control according to the status variables of the self-developed screen; The first generation unit: Obtain the control parameters of all devices in the Siemens SFC during the start-up sequence control, and generate the control quantity of each device according to the control parameters; The second generation unit: Generate a real-time dynamic control screen based on the control quantity of each device and the analog quantity and switch quantity of the device.

5. The monitoring system for the gas turbine startup process based on Siemens SFC according to claim 1, wherein The monitoring module includes: The second acquisition unit: Determine the optimal interaction method based on the dynamic control screens of all devices, and obtain the interaction parameters of the optimal interaction method; The receiving unit: Configure the touch-based human-machine interaction interface method according to the interaction parameters, and remotely receive the instructions and feedback sent during the SFC start-up process; The monitoring unit: Monitor the entire process of the on / off state of each switch according to the instructions received and feedback sent during the SFC start-up process.

6. The monitoring system for the gas turbine startup process based on Siemens SFC according to claim 1, wherein It also includes: The third acquisition unit: Perform redundancy and dimensionality reduction processing on the data of the auxiliary device, and obtain the processed device data; The fourth acquisition unit: Extract features from the processed device data, and obtain the initial feature set of the device data according to the extraction results; The integration unit: Retrieve the key features related to the state from the initial feature set and integrate them into a key feature subset; The fifth acquisition unit: Obtain the topology structure information and preset operation mode information of the Siemens SFC and the node attributes of each control node of the Siemens SFC; The sixth determination unit: Determine the control topology weight value of each control node according to the node attributes of each control node, the topology structure information, and the preset operation mode information; The seventh determination unit: Determine the base value of each control quantity in the device data based on the control topology weight value of each control node; The sixth acquisition unit: Obtain the time-series feature information corresponding to the device data; The extraction unit: Extract the time-series data of each control quantity from the device data according to the time-series feature information; The eighth determination unit: Determine the control feature information of each control quantity based on the time-series data of each control quantity; The seventh acquisition unit: Use the time-series data and base value of each control quantity as the model input samples, and use the control feature information of each control quantity as the model output samples to train the preset network model to obtain the recognition model of each control quantity; The eighth acquisition unit: Use the recognition model of each control quantity to obtain the target control features corresponding to the target time-series data of each key feature in the key feature subset; The ninth acquisition unit: Obtain the first operation feature of each control quantity according to the target control feature of each key feature; The ninth determination unit: Obtain the change situation of the target control feature of each control quantity in the device data, and determine the control change rule of each control quantity according to the change situation; The confirmation unit: Confirm the control quantities with a control change rule similarity greater than or equal to the preset threshold as the same type of control, and confirm the second target operation feature of any control quantity in each type of control as the final operation feature of the type of control.

Images