Operation monitoring method, device and equipment applied to gas turbine

Abstract

The embodiment of the invention discloses an operation monitoring method, device and equipment applied to a gas turbine. A specific embodiment of the method comprises the following steps: generating an overtemperature control instruction according to the outlet pressure of the gas compressor and the obtained exhaust temperature of each thermocouple; generating an overspeed control instruction according to a preset voting condition, the first rotor rotating speed set and the second rotor rotating speed set; generating a flameout control instruction according to each flame state signal and the working state of the gas turbine; generating a vibration control instruction according to the vibration signal of each part of the gas turbine; generating a combustion control instruction according to each temperature value and the allowable dispersity threshold value; and in response to the received overtemperature control instruction, overspeed control instruction, flameout control instruction, vibration control instruction or combustion control instruction, controlling the gas turbine to execute interruption operation. According to the implementation mode, the time consumed for monitoring the operation of the gas turbine is shortened, and consumed computing resources are reduced.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer and gas turbine cross-technology, and more specifically to methods, apparatus and equipment for monitoring the operation of gas turbines. Background Technology

[0002] When the operating parameters of a gas turbine (e.g., exhaust temperature, rotor speed, vibration amplitude, etc.) exceed critical values ​​or the control equipment malfunctions, the gas turbine can be shut down by quickly cutting off the fuel supply to protect the equipment from damage. Currently, the common method for monitoring the operation of gas turbines is as follows: a single control system centrally acquires all operating parameters, performs threshold judgment and logical processing uniformly, and executes shutdown operations based on the judgment results.

[0003] However, in practice, the following technical problems often arise when using the above methods to monitor the operation of gas turbines: Because the judgment logic of all protection functions is centrally processed in the same control system, and the judgment logic of various protections is coupled with each other, when monitoring the operation of the gas turbine, all operating parameters need to be acquired uniformly and voted on according to their respective judgment logics. This increases the complexity and computational burden of the system, resulting in a long time consumption and a large amount of computing resources for monitoring the operation of the gas turbine, thus causing poor real-time performance and reliability of the monitoring of the gas turbine operation.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion later. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure provide methods, apparatus, electronic devices, and computer-readable media for monitoring the operation of gas turbines to address one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide a method for monitoring the operation of a gas turbine. The method includes: generating an over-temperature control command based on the compressor outlet pressure and the exhaust temperatures of various thermocouples; generating an overspeed control command based on preset voting conditions, a first set of rotor speeds, and a second set of rotor speeds; generating a flameout control command based on various flame state signals and the gas turbine's operating state; generating a vibration control command based on vibration signals corresponding to various parts of the gas turbine; generating a combustion control command based on the temperature values ​​of various turbine exhaust thermocouples and an allowable dispersion threshold; and controlling the gas turbine to perform a shutdown operation in response to receiving the over-temperature control command, the overspeed control command, the flameout control command, the vibration control command, or the combustion control command.

[0008] Secondly, some embodiments of this disclosure provide an operation monitoring device for a gas turbine, comprising: a first generating unit configured to generate an over-temperature control command based on the compressor outlet pressure and the exhaust temperatures of various thermocouples; a second generating unit configured to generate an overspeed control command based on preset voting conditions and a set of first and second rotor speeds; a third generating unit configured to generate a flameout control command based on various flame state signals and the operating state of the gas turbine; a fourth generating unit configured to generate a vibration control command based on vibration signals corresponding to various parts of the gas turbine; a fifth generating unit configured to generate a combustion control command based on the temperature values ​​of various turbine exhaust thermocouples and an allowable dispersion threshold; and a control unit configured to control the gas turbine to perform a shutdown operation in response to receiving the over-temperature control command, the overspeed control command, the flameout control command, the vibration control command, or the combustion control command.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any of the implementations of the first or second aspect.

[0011] The above-described embodiments of this disclosure have the following beneficial effects: Through the gas turbine operation monitoring method of some embodiments of this disclosure, the time spent monitoring the operation of a gas turbine can be shortened, the computational resources consumed can be reduced, thereby improving the real-time performance and reliability of gas turbine operation monitoring. The reason for the long monitoring time, high computational resource consumption, and poor real-time performance and reliability of gas turbine operation monitoring is that: since the judgment logic of all protection functions is centrally processed in the same control system, and the judgment logic between various protections is coupled, when monitoring the operation of a gas turbine, all operating parameters need to be uniformly acquired and voted on according to their respective judgment logics, increasing the complexity and computational burden of the system, resulting in a long monitoring time and high computational resource consumption, thus causing poor real-time performance and reliability of gas turbine operation monitoring. Based on this, the gas turbine operation monitoring method of some embodiments of this disclosure first generates an over-temperature control command based on the compressor outlet pressure and the acquired exhaust temperatures of various thermocouples. Therefore, an over-temperature control command for the corresponding gas turbine can be obtained. Then, based on preset voting conditions and the acquired first and second rotor speed sets, an overspeed control command is generated. Next, a flameout control command is generated based on the acquired flame state signals and the gas turbine's operating state. Then, a vibration control command is generated based on the acquired vibration signals corresponding to various parts of the gas turbine. Next, a combustion control command is generated based on the acquired temperature values ​​and allowable dispersion thresholds of the turbine exhaust thermocouples. Finally, in response to receiving the over-temperature control command, the overspeed control command, the flameout control command, the vibration control command, or the combustion control command, the gas turbine is controlled to perform a shutdown operation. Because the judgment logic for all protection functions is not centralized in a single control system, but rather over-temperature protection, over-speed protection, flameout protection, vibration protection, and combustion monitoring protection are each independently judged by corresponding dedicated hardware or subsystems, resulting in judgment results for different protection functions, the gas turbine operation is monitored and protected in a differentiated manner. Finally, the judgment results are sent as control commands to a unified execution entity, which responds by controlling the gas turbine to perform a shutdown operation upon receiving any control command. Therefore, the time spent monitoring the gas turbine operation can be shortened, the computational resources consumed can be reduced, and the real-time performance and reliability of gas turbine operation monitoring can be improved. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 This is a flowchart of some embodiments of the operation monitoring method for gas turbines according to the present disclosure; Figure 2 These are schematic diagrams illustrating the structure of some embodiments of the operation monitoring device for gas turbines according to this disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0017] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0018] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0019] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1A flow 100 of some embodiments of a gas turbine operation monitoring method according to the present disclosure is shown. The gas turbine operation monitoring method includes the following steps: Step 101: Generate an over-temperature control command based on the exhaust temperature of each thermocouple and the compressor outlet pressure obtained.

[0021] In some embodiments, the execution entity (e.g., a computing device) of the gas turbine operation monitoring method can generate an over-temperature control command based on the compressor outlet pressure and the acquired exhaust temperatures of each thermocouple. The exhaust temperature of each thermocouple can characterize the temperature of the gas gas at the turbine outlet of the gas turbine. The compressor outlet pressure can characterize the pressure value at the compressor outlet of the gas turbine. The over-temperature control command can characterize a command to control the gas turbine to perform a shutdown operation due to excessively high exhaust temperature.

[0022] In some optional implementations of certain embodiments, the aforementioned execution entity can generate an over-temperature control command based on the compressor outlet pressure and the exhaust temperatures of the various thermocouples obtained through the following steps: The first step is to average the exhaust temperatures of each thermocouple to obtain an average exhaust temperature. This average exhaust temperature represents the average exhaust temperature of each thermocouple. In practice, the executing entity first calculates the average and standard deviation of the exhaust temperatures of each thermocouple. Then, temperature values ​​deviating from the average by more than a preset multiple of the standard deviation are removed, resulting in updated exhaust temperatures for each thermocouple. This preset multiple can be 3. Finally, the updated exhaust temperatures of each thermocouple are averaged using an arithmetic mean to obtain the average exhaust temperature.

[0023] The second step is to generate the permissible protection temperature value based on the compressor outlet pressure. This permissible protection temperature value represents the dynamically calculated limit of the exhaust temperature allowed at the turbine outlet under the current operating conditions. In practice, the executing entity can use a lookup table to retrieve the temperature value corresponding to the compressor outlet pressure from the target temperature and pressure table as the permissible protection temperature value. The target temperature and pressure table represents the correspondence between the compressor outlet pressure and the permissible protection temperature value. For example, the target temperature and pressure correspondence table could be "..., compressor outlet pressure: 10, permissible protection temperature value: 540,...".

[0024] The third step involves generating a temperature comparison result based on the average exhaust temperature and the permissible protection temperature value. This temperature comparison result represents the comparison between the average exhaust temperature and the permissible protection temperature value. The temperature comparison result can be either a first comparison result or a second result. A first comparison result indicates that the average exhaust temperature is greater than the permissible protection temperature value. A second comparison result indicates that the average exhaust temperature is less than the permissible protection temperature value. In practice, the executing entity can use a programmable logic controller (PLC) to compare the average exhaust temperature and the permissible protection temperature value to obtain the temperature comparison result.

[0025] The fourth step involves generating an over-temperature control command in response to the detection that the temperature comparison result is the first comparison result. In practice, the executing entity can first output a high-level signal through a comparator. Then, this high-level signal is identified as the over-temperature control command.

[0026] In addressing the technical problems mentioned above, and considering the application scenario—specifically, combustion monitoring of gas turbines in high-altitude regions (e.g., Qinghai) using a mixture of high- and low-calorific-value gases (e.g., coalbed methane and natural gas)—often presents a second technical problem: The large diurnal temperature range in high-altitude areas and the drastic fluctuations in the calorific value of the high- and low-calorific-value mixture result in unsuitable methods. Relying solely on compressor outlet pressure for table lookup is insufficient to accommodate the dynamic factors of significant ambient temperature changes, rapid fluctuations in fuel calorific value, and thermal channel performance degradation. This leads to a severe mismatch between the generated allowable protection temperature value and actual operating conditions, requiring repeated corrections and frequent offline calibration, which is time-consuming and compromises the real-time performance and accuracy of high-temperature protection. Consequently, monitoring gas turbine operation is time-consuming and lacks real-time performance and reliability. To address the specific requirements of this application scenario—adaptability to large diurnal temperature ranges, drastic fluctuations in the calorific value of the high- and low-calorific-value mixture, and rapid degradation of thermal channel performance—we have decided to adopt the following solution: In some optional implementations of certain embodiments, the aforementioned execution entity may generate an allowable protection temperature value based on the compressor outlet pressure, and control the gas turbine to perform a shutdown operation based on the allowable protection temperature value, through the following steps: The first step is to obtain the multi-source operating parameters of the gas turbine. These multi-source operating parameters characterize parameters related to the operation of the gas turbine. They may include gas turbine power, ambient temperature, ambient humidity, fuel calorific value, and gas turbine operating hours. The gas turbine power characterizes the active power output of the gas turbine at the current moment. The ambient temperature characterizes the ambient temperature of the gas turbine intake air. The ambient humidity characterizes the ambient humidity of the gas turbine intake air. The fuel calorific value characterizes the heat contained per unit mass or unit volume of fuel in the combustion chamber of the gas turbine. The gas turbine operating hours characterize the total accumulated operating time of the gas turbine from its initial operation to the current moment. In practice, the executing entity can directly obtain these multi-source operating parameters using power sensors, temperature sensors, humidity sensors, calorific value analyzers, and timers. Here, no specific type of power sensor, temperature sensor, humidity sensor and calorimeter is limited. For example, the power sensor can be a Hall effect sensor, the temperature sensor can be a thermocouple, the humidity sensor can be a resistive humidity sensor, and the calorimeter can be a calorimeter.

[0027] The second step involves generating inlet guide vane temperature control values, pressure ratio temperature control values, and power temperature control values ​​based on the compressor outlet pressure and gas turbine power. The inlet guide vane temperature control value represents the temperature corresponding to the opening degree of the gas turbine inlet guide vanes. The pressure ratio temperature control value represents the temperature corresponding to the compressor outlet pressure. The power temperature control value represents the temperature corresponding to the gas turbine power. In practice, the executing entity can use a lookup table method to retrieve the pressure ratio temperature control value from a preset pressure ratio temperature control table, the power temperature control value from a preset power temperature control table, and the inlet guide vane temperature control value from a preset inlet guide vane temperature control table. The preset pressure ratio temperature control table represents the pre-set correspondence between the compressor outlet pressure and the pressure ratio temperature control value. The preset power temperature control table represents the pre-set correspondence between the gas turbine power and the power temperature control value. The aforementioned preset inlet guide vane temperature control table can represent the correspondence between the preset inlet guide vane opening and the preset inlet guide vane temperature control value. For example, the preset pressure ratio temperature control table can be "..., compressor outlet pressure: 8.0; pressure ratio temperature control value: 580,...". The preset power temperature control table can be "..., gas turbine power: 50, power temperature control value: 590,...". The preset inlet guide vane temperature control table can be "..., inlet guide vane opening: 34, inlet guide vane temperature control value: 600,...".

[0028] The third step involves generating a temperature control reference value based on the aforementioned inlet guide vane temperature control value, pressure ratio temperature control value, power temperature control value, and isothermal constant. The isothermal constant characterizes the maximum permissible exhaust temperature of the gas turbine. It should be noted that the isothermal constant is a fixed constant, and its specific value can be set according to actual needs. The temperature control reference value represents the setpoint exhaust temperature obtained after minimum value selection under the current operating conditions. In practice, firstly, the actuator can use a minimum value selector to filter the inlet guide vane temperature control value, pressure ratio temperature control value, power temperature control value, and isothermal constant to obtain the minimum value. Then, the obtained minimum value is determined as the temperature control reference value.

[0029] The fourth step involves correcting the aforementioned temperature control reference value based on the ambient temperature, ambient humidity, and fuel calorific value to obtain a corrected temperature control reference value. This corrected temperature control reference value characterizes the temperature value obtained after correcting the aforementioned temperature control reference value. In practice, the executing entity can use polynomial fitting to correct the aforementioned temperature control reference value, ambient temperature, ambient humidity, and fuel calorific value to obtain the corrected temperature control reference value.

[0030] The fifth step involves generating a thermal channel performance degradation coefficient based on the aforementioned corrected temperature control benchmark value and the aforementioned gas turbine operating hours. This thermal channel performance degradation coefficient characterizes the degree to which the thermal channel performance of the gas turbine degrades with the operating time of the gas turbine. In practice, the executing entity can recursively calculate the thermal channel performance degradation coefficient using an exponentially weighted moving average method, applying the corrected temperature control benchmark value and the aforementioned gas turbine operating hours.

[0031] Step 6: Based on the aforementioned thermal channel performance attenuation coefficient, update the aforementioned corrected temperature control reference value to obtain an attenuation-compensated temperature control reference value. The attenuation-compensated temperature control reference value characterizes the temperature value obtained after updating the aforementioned corrected temperature control reference value. In practice, the executing entity can reduce the corrected temperature control reference value using a preset compensation rule to obtain the attenuation-compensated temperature control reference value. The preset compensation rule characterizes the relationship between the reduction magnitude of the aforementioned corrected temperature control reference value and the magnitude of the thermal channel performance attenuation coefficient. For example, the preset compensation rule could be: in response to determining that the thermal channel performance attenuation coefficient is greater than a first preset threshold, reduce the aforementioned corrected temperature control reference value by a first preset magnitude to obtain the attenuation-compensated temperature control reference value; in response to determining that the thermal channel performance attenuation coefficient is greater than a second preset threshold and less than or equal to the first preset threshold, reduce the aforementioned corrected temperature control reference value by a second preset magnitude to obtain the attenuation-compensated temperature control reference value. It should be noted that the aforementioned first preset threshold is greater than the aforementioned second preset threshold, and the aforementioned first preset magnitude is greater than the aforementioned second preset magnitude. Here, the specific values ​​of the first preset threshold, the second preset threshold, the first preset amplitude, and the second preset amplitude are not limited. For example, the first preset threshold can be 0.05, the second preset threshold can be 0.02, the first preset amplitude can be 5%, and the second preset amplitude can be 2%.

[0032] Step 7: Generate the base temperature value based on the compressor outlet pressure and preset temperature pressure table mentioned above. The preset temperature pressure table represents the correspondence between the compressor outlet pressure and the base temperature value. For example, the preset temperature pressure correspondence table could be "..., compressor outlet pressure: 10, base temperature value: 540,...". The base temperature value represents the temperature value corresponding to the compressor outlet pressure obtained from the initial table lookup. In practice, the executing entity can use the table lookup method to retrieve the base temperature value corresponding to the compressor outlet pressure from the preset temperature pressure table.

[0033] Step 8: Based on the aforementioned attenuation compensation temperature control reference value, the aforementioned base temperature value is corrected to obtain the allowable protection temperature value. In practice, the aforementioned executing entity can subtract the aforementioned attenuation compensation temperature control reference value from the aforementioned base temperature value to correct the aforementioned base temperature value and obtain the allowable protection temperature value. It should be noted that the specific implementation steps for controlling the aforementioned gas turbine to perform the shutdown operation based on the aforementioned allowable protection temperature value can be referred to steps 101 and 106, and will not be repeated here.

[0034] The above-described technical solution, as an inventive point of this disclosure, solves technical problem two: "the monitoring of gas turbine operation is time-consuming, and the real-time performance and reliability of the monitoring are poor." The reasons for the long monitoring time and poor real-time performance and reliability of gas turbine operation are as follows: In high-altitude areas, the diurnal temperature range is large, and the calorific value of the high-calorific-value and low-calorific-value mixture fluctuates drastically. Using only the compressor outlet pressure as a reference for table lookup is insufficient to adapt to multiple dynamic factors such as large changes in ambient temperature, rapid fluctuations in fuel calorific value, and the degradation of thermal channel performance. This results in a severe mismatch between the generated allowable protection temperature value and the actual operating conditions, requiring repeated corrections and frequent offline calibration, which consumes a significant amount of time and makes it difficult to guarantee the real-time performance and accuracy of high-temperature protection. Therefore, the monitoring of gas turbine operation is time-consuming, and the real-time performance and reliability of the monitoring are poor. Solving these factors can shorten the monitoring time of gas turbine operation and improve the real-time performance and reliability of the monitoring. To achieve this effect, the disclosed method for monitoring the operation of gas turbines collects multi-source operating parameters of the gas turbine and, combined with the compressor outlet pressure, generates inlet guide vane temperature control values, pressure ratio temperature control values, and power temperature control values. Then, a temperature control reference value is generated by selecting the minimum value to initially establish a basic temperature control reference. Furthermore, the temperature control reference value is corrected based on ambient temperature, ambient humidity, and fuel calorific value to adapt to the impact of large diurnal temperature differences at high altitudes and drastic fluctuations in fuel calorific value on the temperature control reference. In addition, a thermal channel performance attenuation coefficient is generated based on the corrected temperature control reference value and the number of gas turbine operating hours. This coefficient is then used to compensate for the attenuation of the corrected temperature control reference value, adapting to the dynamic changes in thermal channel performance over operating time. Finally, a base temperature value is retrieved from a preset temperature and pressure table based on the compressor outlet pressure, and then corrected based on the attenuated and compensated temperature control reference value to obtain the allowable protection temperature value. This allows for the real-time output of over-temperature protection limits that match the current operating conditions, thereby shortening the time required for monitoring the gas turbine's operation and improving the real-time performance and reliability of the monitoring.

[0035] Step 102: Generate an overspeed control command based on preset voting conditions, the obtained first rotor speed set, and the second rotor speed set.

[0036] In some embodiments, the executing entity can generate an overspeed control command based on preset voting conditions and the acquired first rotor speed set and second rotor speed set. The first rotor speed in the first rotor speed set can represent the rotor speed obtained from the first overspeed protection entity set. The second rotor speed in the second rotor speed set can represent the rotor speed obtained from the second overspeed protection entity set. The first overspeed protection entity set can represent a preset number of overspeed protection cards for receiving the first rotor speed set. The preset number can be three. The second overspeed protection entity set can represent a preset number of overspeed protection devices for receiving the second rotor speed set. Here, the specific types of the overspeed protection cards and overspeed protection devices are not limited; for example, the overspeed protection card can be a Keyuan Smart KM533A speed measurement and overspeed protection card, and the overspeed protection device can be a Keyuan Smart SY3701 speed monitoring module. The preset voting conditions can be a two-out-of-three voting logic. The aforementioned two-out-of-three voting logic can characterize a situation where at least two of the first overspeed protection entities in the first overspeed protection entity set determine that the speed sensor is overspeeding, or at least two of the second overspeed protection entities in the second overspeed protection entity set determine that the speed sensor is overspeeding. The aforementioned overspeed control command can characterize a command to control the gas turbine to perform a shutdown operation due to excessively high speed of the speed sensor included in the gas turbine. Here, the specific type of the speed sensor is not limited; for example, the speed sensor can be a magnetoelectric speed probe.

[0037] In some optional implementations of certain embodiments, the aforementioned execution entity can generate an overspeed control command based on preset voting conditions, the obtained first rotor speed set, and the second rotor speed set through the following steps: The first step is to generate a first overspeed voting result based on the aforementioned first rotor speed set and the aforementioned preset voting conditions. This first overspeed voting result characterizes the overspeed judgment result of the speed sensor corresponding to the aforementioned first rotor speed set. In practice, the executing entity can directly obtain the first overspeed voting result obtained by the overspeed protection card based on the aforementioned preset voting conditions for overspeed judgment of the aforementioned first rotor speed set.

[0038] The second step involves generating a second overspeed voting result based on the aforementioned second rotor speed set and the aforementioned preset voting conditions. This second overspeed voting result characterizes the overspeed judgment result of the speed sensor corresponding to the aforementioned second rotor speed set. In practice, the executing entity can directly obtain the second overspeed voting result obtained by the overspeed protection device from the overspeed judgment of the aforementioned second rotor speed set based on the aforementioned preset voting conditions.

[0039] The third step involves generating an overspeed control command in response to determining that the first overspeed voting result meets the preset overspeed condition, or in response to determining that the second overspeed voting result meets the preset overspeed condition. The preset overspeed condition can be either the speed sensor corresponding to the first overspeed voting result or the speed sensor corresponding to the second overspeed voting result exceeding its speed limit. In practice, firstly, the executing entity can output a high-level signal using a comparator. Then, this high-level signal is identified as the overspeed control command.

[0040] Step 103: Generate a flameout control command based on the acquired flame status signals and gas turbine operating status.

[0041] In some embodiments, the aforementioned executing entity can generate a flameout control command based on the acquired flame state signals and the gas turbine operating state. Each of the aforementioned flame state signals can represent the detection result output by the flame detector included in the gas turbine. The flame state signals can represent a flame-on state or a flame-off state. A flame-on state indicates that a flame exists in the combustion chamber of the gas turbine. A flame-off state indicates that no flame exists in the combustion chamber of the gas turbine. The gas turbine operating state can represent the operating state of the gas turbine at the current moment. The gas turbine operating state can be a start-up state or a running state. A start-up state indicates that the gas turbine is currently performing a start-up operation. A running state indicates that the gas turbine has completed the start-up operation and is currently operating normally. The flameout control command can represent a command to control the gas turbine to perform a shutdown operation due to ignition failure or flameout during operation.

[0042] In some optional implementations of certain embodiments, the aforementioned execution entity can generate a flameout control command based on the acquired flame state signals and the gas turbine operating state through the following steps: The first step is to perform the following steps based on each of the flame status signals mentioned above: First, in response to detecting that the gas turbine is in a start-up state, the ignition detection result is determined based on the flame state signal. The ignition detection result can indicate successful or failed ignition. Successful ignition indicates that the combustion chamber of the gas turbine has been ignited. Failed ignition indicates that the combustion chamber of the gas turbine has not been ignited. In practice, in response to determining that the flame state signal indicates a flame-on state, the actuator can determine that the ignition detection result is successful; in response to determining that the flame state signal indicates a flame-off state, the actuator can determine that the ignition detection result is failed.

[0043] Then, in response to detecting that the gas turbine is in operation, the flameout detection result is determined based on the flame status signal. The flameout detection result can represent either flameout or flameout-free. Flameout can represent flameout within the combustion chamber of the gas turbine. Flameout-free can represent flameout-free within the combustion chamber of the gas turbine. In practice, in response to determining that the flame status signal indicates a flame-on state, the actuator can determine that the flameout detection result is flameout-free; in response to determining that the flame status signal indicates a flame-off state, the flameout detection result is determined to be flameout-free.

[0044] The second step is to determine the obtained ignition detection results as the ignition detection result set and the obtained flameout detection results as the flameout detection result set.

[0045] The third step involves generating a flameout control command in response to either the detection that the set of ignition detection results meets a preset ignition determination condition, or the detection that the set of flameout detection results meets a preset flameout determination condition. The preset ignition determination condition can be a case where the ignition detection result in the set of ignition detection results indicates an ignition failure. The preset flameout determination condition can be a case where the flameout detection result in the set of flameout detection results indicates flameout. In practice, firstly, the executing entity can output a high-level signal using a comparator. Then, this high-level signal is identified as the flameout control command.

[0046] Step 104: Generate vibration control commands based on the acquired vibration signals of various parts of the corresponding gas turbine.

[0047] In some embodiments, the aforementioned execution entity can generate vibration control commands based on the acquired vibration signals corresponding to various parts of the gas turbine. The vibration signals of these parts can characterize electrical signals reflecting the vibration of the gas turbine, acquired through vibration probes. These vibration probes can include bearing vibration probes and shaft vibration probes. The vibration probes can be installed on the compressor, turbine, load end, excitation end, and turbine end bearing housings of the gas turbine. The specific type of the vibration signal is not limited here; for example, the vibration signal can be a voltage. The vibration control commands can characterize commands to control the gas turbine to perform a shutdown operation due to excessive vibration.

[0048] In some optional implementations of certain embodiments, the aforementioned execution entity can generate vibration control commands based on the acquired vibration signals corresponding to various parts of the gas turbine through the following steps: The first step is to amplify the vibration signals from the aforementioned locations to obtain amplified vibration signals. Each of these amplified vibration signals can represent the electrical signal obtained after amplifying the original vibration signal. In practice, the aforementioned actuator can acquire the amplified vibration signals obtained by amplifying the vibration signals from the aforementioned locations using a preamplifier.

[0049] The second step involves extracting and processing the amplified vibration signals to obtain individual vibration amplitudes. Each vibration amplitude represents a physical quantity indicating the vibration intensity of a corresponding part of the gas turbine. In practice, the actuator can acquire the vibration amplitudes extracted from the amplified vibration signals via the TSI system.

[0050] The third step involves generating various vibration judgment results based on the aforementioned vibration amplitudes and shutdown setting values. The shutdown setting value represents a pre-set threshold for triggering vibration protection. The specific value of the shutdown setting value is not limited and can be adjusted according to actual needs. Each vibration judgment result represents whether the aforementioned vibration amplitude exceeds the aforementioned shutdown setting value. The vibration judgment result can represent either a first judgment result or a second judgment result. The first judgment result indicates that the vibration amplitude exceeds the aforementioned shutdown setting value, i.e., the vibration probe corresponding to the aforementioned vibration amplitude is out of limit. The second judgment result indicates that the vibration amplitude does not exceed the aforementioned shutdown setting value, i.e., the vibration probe corresponding to the aforementioned vibration amplitude is not out of limit. In practice, the executing entity can obtain the various vibration judgment results obtained by comparing the aforementioned vibration amplitudes and the aforementioned shutdown setting values ​​using a comparator.

[0051] The fourth step involves generating a vibration control command in response to the detection of a vibration judgment result among the aforementioned vibration judgment results that meets the preset vibration judgment conditions. The preset vibration judgment conditions can be determined using a two-out-of-three voting logic or a two-out-of-two voting logic based on the installation area. The installation area can represent the location where the vibration probes are installed in the gas turbine. The installation area can be the compressor, the turbine, the load end, the excitation end, or the turbine end bearing housing. The two-out-of-three voting logic indicates that, in response to determining that the installation area is equipped with three vibration probes, and at least two vibration probes exceed their limits, the preset vibration judgment conditions are met. The two-out-of-two voting logic indicates that, in response to determining that the installation area is equipped with two vibration probes, and both vibration probes exceed their limits, the preset vibration judgment conditions are met. In practice, firstly, the executing entity can output a high-level signal through a comparator. Then, the high-level signal is determined as the vibration control command.

[0052] Step 105: Generate combustion control commands based on the obtained temperature values ​​and allowable dispersion thresholds of each turbine exhaust thermocouple.

[0053] In some embodiments, the aforementioned execution entity can generate combustion control commands based on the acquired temperature values ​​of each turbine exhaust thermocouple and the permissible dispersion threshold. The aforementioned turbine exhaust thermocouples can represent multiple temperature sensors circumferentially installed in the exhaust duct of the turbine. Here, the specific type of the temperature sensors is not limited; for example, the temperature sensor can be a thermocouple. The temperature values ​​of each turbine exhaust thermocouple can represent the temperature of the gas at the turbine outlet, acquired in real time by each turbine exhaust thermocouple. The permissible dispersion threshold can represent the limit of the allowable exhaust temperature dispersion under the current operating conditions. The aforementioned combustion control commands can represent commands to control the gas turbine to perform a shutdown operation due to combustion anomalies. For example, a combustion anomaly can be uneven combustion.

[0054] In some optional implementations of certain embodiments, the aforementioned execution entity can generate combustion control commands based on the obtained temperature values ​​of each turbine exhaust thermocouple and the permissible dispersion threshold through the following steps: The first step is to determine the set of temperature values ​​based on the temperature values ​​of the various turbine exhaust thermocouples mentioned above.

[0055] The second step is to sort the temperature values ​​in the aforementioned temperature value set in descending order, resulting in a sorted temperature value set. Each sorted temperature value in this set represents a temperature value arranged from highest to lowest. In practice, the executing entity can use bubble sort to sort the temperature values ​​in the aforementioned temperature value set in descending order to obtain the sorted temperature value set.

[0056] The third step involves calculating the dispersion of the sorted temperature value set to obtain the maximum dispersion, the second-highest dispersion, and the third-highest dispersion. The maximum dispersion represents the difference between the highest and lowest temperature values ​​in the sorted temperature value set. The second-highest dispersion represents the difference between the highest and second-lowest temperature values ​​in the sorted temperature value set. The third-highest dispersion represents the difference between the highest and second-lowest temperature values ​​in the sorted temperature value set. The highest temperature value represents the first temperature value in the sorted temperature value set. The lowest temperature value represents the last temperature value in the sorted temperature value set. The second-lowest temperature value represents the second-to-last temperature value in the sorted temperature value set. The second-to-last temperature value represents the third-to-last temperature value in the sorted temperature value set. In practice, the executing entity can first calculate the differences between the highest and lowest temperature values, the second-lowest temperature value, and the second-to-last lowest temperature value in the sorted temperature value set using arithmetic operations to obtain the first difference, the second difference, and the third difference. Then, the first difference is determined as the maximum dispersion, the second difference is determined as the second highest dispersion, and the third difference is determined as the third highest dispersion.

[0057] The fourth step is to generate combustion control commands based on the above-mentioned maximum dispersion, the above-mentioned second highest dispersion, the above-mentioned third highest dispersion, the lowest temperature value, the second lowest temperature value, and the second lowest temperature value.

[0058] In some optional implementations of certain embodiments, the aforementioned executing entity may generate combustion control commands based on the maximum dispersion, the second highest dispersion, the third highest dispersion, the lowest temperature value, the second lowest temperature value, and the second lowest temperature value through the following steps: The first step involves generating a combustion control command in response to the detection that both the maximum and second-highest dispersion values ​​are above the allowable dispersion threshold, and that the thermocouples corresponding to the lowest and second-lowest temperature values ​​are adjacent. In practice, the executing entity can first output a high-level signal via a comparator. Then, this high-level signal is identified as the combustion control command.

[0059] The second step involves generating a combustion control command in response to the detection that both the second-highest and third-highest dispersion values ​​are above the allowable dispersion threshold, and that the thermocouples corresponding to the second-lowest and second-lowest temperature values ​​are adjacent. In practice, the executing entity can first output a high-level signal via a comparator. Then, this high-level signal is identified as the combustion control command.

[0060] The third step involves generating a combustion control command in response to the detection that the third highest dispersion exceeds the allowable dispersion threshold. In practice, firstly, the executing entity can output a high-level signal via a comparator. Then, this high-level signal is identified as the combustion control command.

[0061] In addressing the technical problems mentioned above, and considering the application scenario, when using aged thermocouples to collect temperature data during the combustion of fuels with fluctuating hydrogen blending ratios, the following technical problem often arises: Due to the rapid combustion rate of hydrogen, high-frequency oscillating combustion and combustion pulsation occur when gas turbines use fuels with fluctuating hydrogen blending ratios. Simultaneously, aged thermocouples exhibit slow response and are prone to signal jumps, resulting in distorted temperature values ​​with time phase misalignment, high-frequency noise superposition, and abnormal jumps. Multiple filtering and repeated alignment are required to obtain relatively reliable temperature values, which not only consumes significant computational resources and time but also makes it difficult to guarantee the real-time performance and accuracy of the processing results. This leads to lengthy monitoring times, high computational resource consumption, and poor real-time performance for gas turbine operation. To meet the following requirements for this application scenario: adaptability to collaborative processing of multi-source interference, adaptability to dynamic combustion characteristics caused by fluctuations in hydrogen blending ratios, and adaptability to high real-time requirements, we have decided to adopt the following solution: In some optional implementations of certain embodiments, the aforementioned execution entity may determine a set of temperature values ​​based on the temperature values ​​of the respective turbine exhaust thermocouples through the following steps, and control the gas turbine to perform a shutdown operation based on the set of temperature values: The first step is to construct an initial temperature matrix based on the temperature values ​​of the various turbine exhaust thermocouples. This initial temperature matrix can be represented as a two-dimensional array consisting of the temperature values ​​of each thermocouple at different sampling times. The sampling times represent the points in time when the temperature values ​​of each thermocouple were collected. The rows of the initial temperature matrix correspond to the individual thermocouples, and the columns correspond to different sampling times. In practice, the execution entity can construct the initial temperature matrix based on the thermocouple numbers and the order of the sampling times.

[0062] The second step involves performing wavelet packet decomposition on each row of the original temperature matrix to obtain the various high-frequency coefficients. Each of these high-frequency coefficients represents a high-frequency component obtained after wavelet packet decomposition of each row of the original temperature matrix. In practice, the execution entity can use a preset wavelet basis function and decomposition level to perform wavelet packet decomposition on each row of the original temperature matrix, extracting the high-frequency coefficients of each row to obtain the various high-frequency coefficients. For example, the wavelet basis function can be the db4 wavelet, and the decomposition level can be 3 levels.

[0063] The third step involves denoising the aforementioned high-frequency coefficients based on an adaptive threshold to obtain effective feature components. The adaptive threshold represents a threshold value dynamically calculated based on the signal-to-noise level. The effective feature components represent the signal features retained after denoising the aforementioned high-frequency coefficients. In practice, firstly, the executing entity can calculate the noise standard deviation of the aforementioned high-frequency coefficients using the median absolute deviation method. Then, for each of the aforementioned high-frequency coefficients, an adaptive threshold is calculated using a general threshold formula. Finally, components with absolute values ​​lower than their corresponding adaptive thresholds are set to zero, while components with absolute values ​​higher than their corresponding adaptive thresholds are retained. These components with absolute values ​​higher than the adaptive thresholds are then used as effective feature components to denoise the aforementioned high-frequency coefficients, obtaining each effective feature component. It should be noted that there is a one-to-one correspondence between the aforementioned high-frequency coefficients and the aforementioned adaptive thresholds.

[0064] The fourth step involves performing wavelet packet reconstruction on each of the aforementioned effective feature components to obtain a denoised temperature matrix. This denoised temperature matrix characterizes the matrix obtained after denoising the original temperature matrix. In practice, the executing entity can use the `idwt` function to perform inverse wavelet packet transform on each of the aforementioned effective feature components to obtain the denoised temperature matrix.

[0065] The fifth step involves performing dynamic time warping on the denoised temperature matrix to obtain the aligned temperature matrix. This aligned temperature matrix represents the matrix obtained after eliminating the time and phase differences between the thermocouples. In practice, the executing entity can use a dynamic time warping algorithm to perform dynamic time warping on the denoised temperature matrix, synchronizing the temperature sequences of the thermocouples on the time axis and arranging them according to the structure of the denoised temperature matrix to obtain the aligned temperature matrix.

[0066] Step 6: Based on the thermocouple position information set and the aforementioned aligned temperature matrix, construct a spatiotemporal feature tensor and a spatial feature matrix. The thermocouple position information in the thermocouple position information set represents the installation position of each thermocouple in the circumferential direction of the turbine exhaust channel. The spatiotemporal feature tensor represents a three-dimensional data structure that integrates various temperature values, first-order rates of change, second-order rates of change, and adjacent temperature difference features. The various temperature values ​​represent the temperature value of each thermocouple at the current moment. The first-order rate of change represents the rate of change of the temperature value of each thermocouple over time. The second-order rate of change represents the rate of change of the first-order rate of change over time. The adjacent temperature difference feature represents the temperature difference between each thermocouple and its adjacent thermocouples at the same moment. The spatial feature matrix represents the temperature gradient relationship between each thermocouple and its adjacent thermocouples. In practice, firstly, the executing entity can extract data from the aligned temperature matrix using direct indexing to obtain the temperature value of each thermocouple at different sampling times. Then, using a difference calculation method, the temperature sequence of each thermocouple in the aligned temperature matrix is ​​processed to obtain the first-order rate of change and the second-order rate of change. It should be noted that each row in the aligned temperature matrix corresponds to the temperature sequence of one thermocouple. The first-order rate of change can be calculated from the difference between adjacent sampling points, and the second-order rate of change can be obtained by calculating the difference again from the first-order rate of change. Next, the temperature difference between each thermocouple and its adjacent thermocouples at the same sampling time is calculated as the adjacent temperature difference feature. Then, the temperature values ​​of each thermocouple, the first-order rate of change, the second-order rate of change, and the adjacent temperature difference feature are organized according to three dimensions: thermocouple number, sampling time, and feature type, to construct a spatiotemporal feature tensor. The feature type can characterize four different feature dimensions: the temperature values, the first-order rate of change, the second-order rate of change, and the adjacent temperature difference feature. Furthermore, based on the aforementioned thermocouple position information set, the adjacency relationship of each thermocouple in the circumferential direction of the turbine exhaust channel is determined, and the temperature difference gradient between each thermocouple and its adjacent thermocouples is calculated to obtain the spatial feature matrix.

[0067] Step 7: Based on the aforementioned spatiotemporal feature tensor and historical operating data, generate the desired temperature vector and the anomaly candidate marker vector. The aforementioned historical operating data represents the temperature values ​​acquired by each thermocouple within a preset time interval prior to the current moment. For example, the preset time interval can be 24 hours. The aforementioned desired temperature vector represents the desired temperature value of each thermocouple at the current moment. The aforementioned desired temperature value represents the target temperature that each thermocouple should achieve under the current operating conditions. The specific value of the aforementioned desired temperature value is not limited and can be set according to actual needs. The aforementioned anomaly candidate marker vector represents a Boolean vector composed of the anomaly candidate states of each thermocouple. The aforementioned anomaly candidate state represents that the deviation between the measured temperature value and the desired temperature value of each thermocouple at the current moment is greater than a preset threshold. The aforementioned measured temperature value represents the temperature values ​​actually measured by each thermocouple. The aforementioned preset threshold represents a pre-set temperature value. For example, the preset threshold can be 5℃. In practice, firstly, the aforementioned executing entity can pre-train a preset Long Short-Term Memory (LSTM) network using the aforementioned historical operational data to obtain the LSM network. Here, the specific type of the preset LSM network is not limited; for example, the preset LSM network can be an LSTM. Then, the aforementioned spatiotemporal feature tensor is input into the LSM network to obtain the expected temperature value of each thermocouple at the current time. Next, the deviation between the measured temperature value and the expected temperature value is calculated. In response to determining that the deviation is greater than the aforementioned preset threshold, the thermocouple corresponding to the deviation is marked as an abnormal candidate state, resulting in an abnormal candidate label vector.

[0068] Step 8: Based on the aforementioned denoised temperature matrix, spatial feature matrix, expected temperature vector, and anomaly candidate marker vector, the final fusion weights are generated. These final fusion weights can represent a vector composed of the weight coefficients of each thermocouple in the weighted data fusion. In practice, firstly, the executing entity can calculate the deviation between the measured temperature value and the expected temperature value of each thermocouple based on the denoised temperature matrix and the expected temperature vector. Then, using an inverse proportional function, the deviation is mapped to a first weight vector. Next, based on the aforementioned spatial feature matrix, the temperature gradient between each thermocouple and its neighboring thermocouples is calculated. Secondly, using an inverse proportional function, the temperature gradient is mapped to a second weight vector. Then, using evidence theory, the first weight vector and the second weight vector are fused to obtain a fused weight vector. Finally, based on the anomaly candidate marker vector, the weight values ​​of thermocouples corresponding to anomaly candidate states in the fused weight vector are reduced to a preset minimum value to obtain the final fused weight vector. For example, the preset minimum value can be 0.1. The first weight vector described above represents the weight of each thermocouple determined by the deviation between the measured temperature value and the desired temperature value. The second weight vector described above represents the weight of each thermocouple determined by the temperature gradient between each thermocouple and its neighboring thermocouples. The fused weight vector described above represents the weight obtained by fusing the first weight vector and the second weight vector.

[0069] Step nine involves performing a weighted average of the denoised temperature matrix based on the final fusion weights to obtain each optimized temperature value. Each optimized temperature value represents the temperature obtained after optimizing the temperature values ​​of the turbine exhaust thermocouples. In practice, the executing entity can use a weighted average method, based on the final fusion weights, to perform a weighted average of the denoised temperature matrix to obtain each optimized temperature value.

[0070] Step 10: Determine the optimized temperature values ​​mentioned above as the temperature values ​​of each turbine exhaust thermocouple. It should be noted that the specific implementation steps for controlling the gas turbine to perform the shutdown operation based on the above set of temperature values ​​can be found in steps 105 and 106, and will not be repeated here.

[0071] The above-described technical solution, as an inventive point of this disclosure, solves technical problem three: "The monitoring of gas turbine operation is time-consuming, computationally resource-intensive, and lacks real-time performance." The reasons for this are as follows: Due to the rapid combustion rate of hydrogen, when a gas turbine uses fuel with a large fluctuation in hydrogen blending ratio, high-frequency oscillating combustion and combustion pulsation occur. Simultaneously, aging thermocouples exhibit slow response and are prone to signal jumps. The collected temperature values ​​suffer from distortions such as time phase misalignment, high-frequency noise superposition, and abnormal jumps, requiring multiple filtering and repeated alignment to obtain relatively reliable temperature values. This not only consumes significant computational resources and time but also makes it difficult to guarantee the real-time performance and accuracy of the processing results. Therefore, monitoring gas turbine operation is time-consuming, computationally resource-intensive, and lacks real-time performance. Solving these factors can shorten the monitoring time of gas turbine operation, reduce computational resource consumption, and improve real-time performance. To achieve this effect, the disclosed method for monitoring the operation of gas turbines denoises the temperature values ​​of each turbine exhaust thermocouple using wavelet packet decomposition and adaptive threshold denoising, thereby effectively suppressing high-frequency noise and anomalous jumps. Time warping aligns the time axes of the denoised temperature values ​​to eliminate temporal phase misalignment caused by combustion pulsations. Furthermore, based on the thermocouple position information set and the aligned temperature matrix, a spatiotemporal feature tensor and a spatial feature matrix are constructed, which can fuse multi-dimensional features and characterize the spatial distribution of the temperature field. Finally, by combining the anomaly candidate label vector, a final fusion weight is generated, and a weighted average of the denoised temperature matrix is ​​performed based on the final fusion weight to obtain the optimized temperature values ​​of each turbine exhaust thermocouple. This reduces the time required to monitor the operation of gas turbines, decreases computational resource consumption, and improves the real-time performance of monitoring.

[0072] Step 106: In response to receiving an over-temperature control command, over-speed control command, flameout control command, vibration control command, or combustion control command, control the gas turbine to perform a shutdown operation.

[0073] In some embodiments, in response to receiving the above-mentioned over-temperature control command, the above-mentioned overspeed control command, the above-mentioned flameout control command, the above-mentioned vibration control command, or the above-mentioned combustion control command, the above-mentioned execution entity can control the gas turbine to perform a shutdown operation.

[0074] The above-described embodiments of this disclosure have the following beneficial effects: Through the gas turbine operation monitoring method of some embodiments of this disclosure, the time spent monitoring the operation of a gas turbine can be shortened, the computational resources consumed can be reduced, thereby improving the real-time performance and reliability of gas turbine operation monitoring. The reason for the long monitoring time, high computational resource consumption, and poor real-time performance and reliability of gas turbine operation monitoring is that: since the judgment logic of all protection functions is centrally processed in the same control system, and the judgment logic between various protections is coupled, when monitoring the operation of a gas turbine, all operating parameters need to be uniformly acquired and voted on according to their respective judgment logics, increasing the complexity and computational burden of the system, resulting in a long monitoring time and high computational resource consumption, thus causing poor real-time performance and reliability of gas turbine operation monitoring. Based on this, the gas turbine operation monitoring method of some embodiments of this disclosure first generates an over-temperature control command based on the compressor outlet pressure and the acquired exhaust temperatures of various thermocouples. Therefore, an over-temperature control command for the corresponding gas turbine can be obtained. Then, based on preset voting conditions and the acquired first and second rotor speed sets, an overspeed control command is generated. Next, a flameout control command is generated based on the acquired flame state signals and the gas turbine's operating state. Then, a vibration control command is generated based on the acquired vibration signals corresponding to various parts of the gas turbine. Next, a combustion control command is generated based on the acquired temperature values ​​and allowable dispersion thresholds of the turbine exhaust thermocouples. Finally, in response to receiving the over-temperature control command, the overspeed control command, the flameout control command, the vibration control command, or the combustion control command, the gas turbine is controlled to perform a shutdown operation. Because the judgment logic for all protection functions is not centralized in a single control system, but rather over-temperature protection, over-speed protection, flameout protection, vibration protection, and combustion monitoring protection are each independently judged by corresponding dedicated hardware or subsystems, resulting in judgment results for different protection functions, the gas turbine operation is monitored and protected in a differentiated manner. Finally, the judgment results are sent as control commands to a unified execution entity, which responds by controlling the gas turbine to perform a shutdown operation upon receiving any control command. Therefore, the time spent monitoring the gas turbine operation can be shortened, the computational resources consumed can be reduced, and the real-time performance and reliability of gas turbine operation monitoring can be improved.

[0075] Further reference Figure 2As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a method for monitoring the operation of a gas turbine. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0076] like Figure 2 As shown, some embodiments of the gas turbine operation monitoring device 200 include: a first generation unit 201, a second generation unit 202, a third generation unit 203, a fourth generation unit 204, a fifth generation unit 205, and a control unit 206. The first generation unit 201 is configured to generate an over-temperature control command based on the compressor outlet pressure and the exhaust temperatures of the various thermocouples. The second generation unit 202 is configured to generate an overspeed control command based on preset voting conditions and the acquired first and second rotor speed sets. The third generation unit 203 is configured to generate a flameout control command based on the acquired flame state signals and the gas turbine operating state. The fourth generation unit 204 is configured to generate a vibration control command based on the acquired vibration signals corresponding to various parts of the gas turbine. The fifth generation unit 205 is configured to generate a combustion control command based on the acquired temperature values ​​of the turbine exhaust thermocouples and the allowable dispersion threshold. The control unit 206 is configured to control the gas turbine to perform a shutdown operation in response to receiving the over-temperature control command, the overspeed control command, the flameout control command, the vibration control command, or the combustion control command.

[0077] It is understandable that the units and references described in the gas turbine operation monitoring device 200 are similar. Figure 1 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method are also applicable to the operation monitoring device 200 applied to the gas turbine and the units contained therein, and will not be repeated here.

[0078] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0079] like Figure 3As shown, the electronic device 300 may include a processing unit 301 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0080] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0081] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0082] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0083] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0084] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently without being assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: generate an over-temperature control command based on the compressor outlet pressure and the exhaust temperatures of the various thermocouples; generate an overspeed control command based on preset voting conditions and the acquired first and second rotor speed sets; generate a flameout control command based on the acquired flame state signals and the gas turbine operating state; generate a vibration control command based on the acquired vibration signals corresponding to various parts of the gas turbine; generate a combustion control command based on the acquired temperature values ​​and permissible dispersion thresholds of the various turbine exhaust thermocouples; and, in response to receiving the aforementioned over-temperature control command, overspeed control command, flameout control command, vibration control command, or combustion control command, control the gas turbine to perform a shutdown operation.

[0085] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0086] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0087] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including a first generation unit, a second generation unit, a third generation unit, a fourth generation unit, a fifth generation unit, and a control unit. The names of these units do not necessarily limit the specific unit; for example, the first generation unit may also be described as "a unit that generates over-temperature control commands based on the compressor outlet pressure and the exhaust temperatures of the various thermocouples."

[0088] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0089] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for monitoring the operation of a gas turbine, comprising: Based on the compressor outlet pressure and the exhaust temperature of each thermocouple, an over-temperature control command is generated. Based on the preset voting conditions and the obtained first rotor speed set and second rotor speed set, an overspeed control command is generated; Based on the acquired flame status signals and gas turbine operating status, a flameout control command is generated; Based on the acquired vibration signals corresponding to various parts of the gas turbine, vibration control commands are generated; Based on the temperature values ​​and allowable dispersion thresholds of each turbine exhaust thermocouple, combustion control commands are generated. In response to receiving the over-temperature control command, the overspeed control command, the flameout control command, the vibration control command, or the combustion control command, the gas turbine is controlled to perform a shutdown operation.

2. The method according to claim 1, wherein, The process of generating an over-temperature control command based on the compressor outlet pressure and the obtained exhaust temperatures of each thermocouple includes: The exhaust temperature of each thermocouple is averaged to obtain the average exhaust temperature. Based on the compressor outlet pressure, an allowable protection temperature value is generated; A temperature comparison result is generated based on the average exhaust temperature and the allowable protection temperature value; In response to detecting that the temperature comparison result is the first comparison result, an over-temperature control command is generated.

3. The method according to claim 1, wherein, The process of generating an overspeed control command based on preset voting conditions, the acquired first rotor speed set, and the second rotor speed set includes: Based on the first set of rotor speeds and the preset voting conditions, a first overspeed voting result is generated; Based on the second rotor speed set and the preset voting conditions, a second overspeed voting result is generated; In response to determining that the first overspeed voting result meets the preset overspeed conditions, or in response to determining that the second overspeed voting result meets the preset overspeed conditions, an overspeed control command is generated.

4. The method according to claim 1, wherein, The step of generating a flameout control command based on the acquired flame state signals and gas turbine operating status includes: Based on each of the flame state signals, perform the following steps: In response to detecting that the gas turbine is in a start-up state, the ignition detection result is determined based on the flame state signal; In response to detecting that the gas turbine is in an operating state, the flameout detection result is determined based on the flame state signal; The obtained ignition detection results are defined as the ignition detection result set, and the obtained flameout detection results are defined as the flameout detection result set. In response to detecting that the ignition detection result set meets the preset ignition determination condition, or in response to detecting that the flameout detection result set meets the preset flameout determination condition, a flameout control command is generated.

5. The method according to claim 1, wherein, The step of generating vibration control commands based on the acquired vibration signals corresponding to various parts of the gas turbine includes: The vibration signals of each part are amplified to obtain amplified vibration signals. Each amplified vibration signal is extracted and processed to obtain its vibration amplitude. Based on the vibration amplitude and shutdown setting value, generate each vibration judgment result; In response to the detection that there is a vibration judgment result that meets the preset vibration judgment conditions among the various vibration judgment results, a vibration control command is generated.

6. The method according to claim 1, wherein, The step of generating combustion control commands based on the acquired temperature values ​​and allowable dispersion thresholds of each turbine exhaust thermocouple includes: Based on the temperature values ​​of each turbine exhaust thermocouple, a set of temperature values ​​is determined; The temperature values ​​in the set of temperature values ​​are sorted in descending order to obtain a sorted set of temperature values. The dispersion of the sorted temperature value set is calculated to obtain the maximum dispersion, the second highest dispersion, and the third highest dispersion. Combustion control commands are generated based on the maximum dispersion, the second highest dispersion, the third highest dispersion, the lowest temperature value, the second lowest temperature value, and the second lowest temperature value.

7. An operation monitoring device for a gas turbine, comprising: The first generation unit is configured to generate an over-temperature control command based on the compressor outlet pressure and the exhaust temperature of each thermocouple. The second generation unit is configured to generate an overspeed control command based on preset voting conditions, the first set of rotor speeds and the second set of rotor speeds. The third generation unit is configured to generate a flameout control command based on the acquired flame status signals and the gas turbine operating status. The fourth generation unit is configured to generate vibration control commands based on the acquired vibration signals corresponding to various parts of the gas turbine. The fifth generation unit is configured to generate combustion control commands based on the temperature values ​​and permissible dispersion thresholds of the various turbine exhaust thermocouples. The control unit is configured to control the gas turbine to perform a shutdown operation in response to receiving the over-temperature control command, the overspeed control command, the flameout control command, the vibration control command, or the combustion control command.

8. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6.

9. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

Images