Generator set performance real-time online monitoring device

Abstract

The invention relates to the technical field of generator set performance monitoring, and particularly discloses a generator set performance real-time on-line monitoring device, which comprises a calibration module for setting a pressure range and a temperature range; under the condition that the pressure is kept unchanged, the temperature of the water is adjusted within the temperature range, and after the temperature of the water is adjusted every time, the specific enthalpy of the water is calculated; specific enthalpies of water under different pressures and temperatures are obtained, and a specific enthalpy change curve of the water is obtained; a specific enthalpy change curve of air is obtained; the data determination module is used for determining the specific enthalpy of water on each time node in the acquisition period; the specific enthalpy of air on each time node is obtained; calculating boiler efficiency, steam turbine heat consumption rate, pipeline efficiency and station service power consumption rate; and the evaluation module is used for calculating power generation coal consumption and power supply coal consumption and judging the performance of the generator set. The corresponding secondary data can be obtained in real time according to the detected parameters, the performance of the generator set is judged according to the secondary data, the reliability is high, and the real-time performance is good.

Description

Technical Field

[0001] The present invention relates to the technical field of generator set performance monitoring, and in particular to a real-time online monitoring device for generator set performance. Background Art

[0002] A DCS system is designed during the design phase of the generator set, and the original primary measurement data reflecting the operating status of the unit, such as the pressure and temperature of the medium, are concentrated in the DCS system. However, due to functional positioning considerations, most DCS systems on the market currently do not have all the functions to calculate secondary data. Secondary data, such as boiler efficiency, is calculated based on the original primary data using complex algorithms. Some DCS system manufacturers have tried to carry out related developments, such as the SIS system based on the original DCS system, but they have not been satisfactory and the results have not been very good.

[0003] Accurate secondary data is very important, especially before and after the generator set is repaired. Secondary data can not only verify the effect of the repair, but also has great value in guiding operation optimization, early fault warning, and unit health diagnosis. In the existing technology, most of the accurate secondary data are obtained by entrusting a third-party agency to conduct performance tests on the unit. However, traditional unit performance tests can only select a few typical operating conditions for testing, which cannot reflect the overall operation of the unit. In addition, the test time is long and requires exiting the normal production sequence to meet the test requirements alone. Therefore, there are defects such as the performance test data not fully reflecting the operating conditions and affecting normal production. In addition, this method cannot monitor the performance of the generator set in real time. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time online monitoring device for the performance of a generator set to solve the above technical problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A real-time online monitoring device for generator set performance, comprising:

[0007] Calibration module: set pressure range [Pmin, Pmax] and temperature range [Tmin, Tmax];

[0008] While keeping the pressure P constant, the temperature T of the water is adjusted within the temperature range, and after each adjustment of the water temperature, the specific enthalpy of the water is calculated;

[0009] Repeat the above steps to obtain the specific enthalpy of water at different pressures and temperatures, generate corresponding data points in the coordinate system, and fit the data points to obtain the specific enthalpy change curve of water fbh (P, T);

[0010] Repeat the above steps to obtain the specific enthalpy change curve of air gbh(P, T);

[0011] Data determination module: setting a collection period, and setting a number of time nodes at preset time intervals within the collection period;

[0012] The pressure and temperature of water are collected at each time node, and substituted into the specific enthalpy change curve of water fbh (P, T) to obtain the specific enthalpy of water at each time node;

[0013] Repeat the above steps to obtain the specific enthalpy of air at each time node;

[0014] Calculate boiler efficiency, turbine heat rate, pipeline efficiency and plant power rate at each time node;

[0015] Evaluation module: calculates the power generation coal consumption and the power supply coal consumption at each time node, and judges the performance of the generator set based on the power generation coal consumption and the power supply coal consumption.

[0016] As a further solution of the present invention: in the evaluation module, the specific steps of calculating the power generation coal consumption and the power supply coal consumption include:

[0017] Calculate the power generation coal consumption FD = THR / BE / GE, where THR represents the turbine heat rate, BE represents the boiler efficiency, and GE represents the pipeline efficiency;

[0018] Calculate the power supply coal consumption GD = THR / BE / GE / (1-CYD), where CYD represents the plant power consumption rate.

[0019] As a further solution of the present invention: the process of judging the performance of the generator set according to the power generation coal consumption and the power supply coal consumption specifically includes:

[0020] Counting the ratio BFD of the power generation coal consumption FD≥FD', where FD' is a preset power generation coal consumption threshold;

[0021] Counting the ratio BGD of the power supply coal consumption GD≥GD', where GD' is a preset power supply coal consumption threshold;

[0022] When the ratio BFD≥BFD' and the ratio BGD≥BGD', it is determined that the performance of the generator set is poor, BFD' is a preset power generation coal consumption ratio threshold, and BGD' is a preset power supply coal consumption ratio threshold;

[0023] When the ratio BFD<BFD' and the ratio BGD<BGD', it is determined that the performance of the generator set is poor;

[0024] When the ratio BFD<BFD' and the ratio BGD≥BGD', executing a preset judgment step;

[0025] When the ratio BFD≥BFD′ and the ratio BGD<BGD′, the preset judgment step is performed.

[0026] As a further solution of the present invention: the judging step specifically includes:

[0027] Step 1: Obtain the power generation coal consumption A and the corresponding water temperature AST and pressure ASP, and obtain the air temperature AKT and pressure AKP corresponding to the power generation coal consumption A, and generate a mapping (AST, ASP, AKT, AKP)→A;

[0028] Repeat the above steps to obtain m mappings, where m is a preset value, and store the mappings in a database;

[0029] Step 2: Establish a power generation coal consumption prediction model through a deep learning model, train and verify the power generation coal consumption prediction model through a database, input the predicted water temperature, predicted water pressure, predicted air temperature and predicted air pressure into the power generation coal consumption prediction model, and output the predicted power generation coal consumption;

[0030] Repeat the above steps to obtain the predicted power supply coal consumption;

[0031] Step 3: Starting from the end of the collection period, continuously obtain n predicted power generation coal consumptions, and obtain the predicted power generation coal consumption greater than or equal to FD', and use it as the power generation coal consumption within the collection period;

[0032] Recalculate the proportion B of the power generation coal consumption FD≥FD' during the collection period, and when the proportion B is greater than or equal to BFD', determine that the performance of the power generation unit is poor;

[0033] Step 4: In step 3, when the ratio is less than BFD', step 3 is repeated to count the ratio C of coal consumption for power supply during the acquisition period, and when the ratio C is greater than or equal to BGD', it is determined that the performance of the generator set is poor.

[0034] As a further solution of the present invention: in the step 2, the process of obtaining the predicted temperature of the water specifically includes:

[0035] The temperature of the water during the collection period is obtained, and the water temperature change curve h(t) is obtained by fitting it, and T+Δt is substituted into h(t) to obtain the predicted temperature of the water at T+Δt, where T represents the time node at the end of the collection period, and Δt represents the time interval between two adjacent time nodes.

[0036] As a further solution of the present invention: the evaluation module further comprises the following steps:

[0037] When it is determined that the performance of the generator set is poor, the optimal operating parameters of the generator set are determined through a quadratic programming optimization algorithm with the goal of minimizing the coal consumption for power generation and power supply. The operating parameters are parameters that affect the performance of the generator set when the generator set is running.

[0038] Beneficial effects of the present invention: The present invention is applicable to a generator set that burns fossil energy and uses water as a working medium; in the present invention, a calibration process is first performed, that is, determining the specific enthalpy of water at different pressures and temperatures, and determining the specific enthalpy of air at different pressures and temperatures; it should be noted that the calculation of the physical parameters (i.e., specific enthalpy) of water and air is the basis of the entire secondary calculation process. Only by ensuring the accuracy of the calculation of the basic parameters can the subsequent calculation have a solid foundation to support it and continue, otherwise it will be a castle in the air. The present invention adopts the latest international standard IAPWS-IF97 for the calculation of the above-mentioned physical parameters, and fully reproduces it in the present invention. Compared with the standard, the error is 0 (equal to 8 decimal places), thereby improving the accuracy of subsequent judgments on the performance of the generator set; then, the pressure and temperature of the water are obtained in real time during the acquisition period to obtain the specific enthalpy of the water, and the specific enthalpy of the air is obtained. The pressure and temperature of the gas are used to obtain the specific enthalpy of the air, and the corresponding boiler efficiency, turbine heat rate, pipeline efficiency and plant power consumption rate are calculated; finally, the performance of the generator set is judged according to the power generation coal consumption and the power supply coal consumption; it is worth noting that in actual situations, the performance of the generator set at a certain time node may be poor due to various reasons such as measurement errors (i.e., the power generation coal consumption and / or power supply coal consumption are greater than the preset threshold value). However, if the performance of the generator set is directly judged to be poor at this time, it may lead to misjudgment and may affect the normal use of the generator set. Therefore, the performance of the generator set is judged from the overall performance within the acquisition period to improve the accuracy of the judgment. The length of the acquisition period is 5s, and the interval between two adjacent time nodes is 300ms to prevent the acquisition period from being too long, resulting in hysteresis in the final judgment of the performance of the generator set, affecting the normal operation of the generator set. The present invention can obtain the corresponding secondary data in real time according to the detected parameters, and judge the performance of the generator set according to the secondary data, with high reliability and good real-time performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The present invention will be further described below in conjunction with the accompanying drawings.

[0040] Figure 1 The present invention is a flow chart of a real-time online monitoring device for the performance of a generator set. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] See also Figure 1 As shown, the present invention is a real-time online monitoring device for the performance of a generator set, comprising:

[0043] Calibration module: set pressure range [Pmin, Pmax] and temperature range [Tmin, Tmax];

[0044] While keeping the pressure P constant, the temperature T of the water is adjusted within the temperature range, and after each adjustment of the water temperature, the specific enthalpy of the water is calculated;

[0045] Repeat the above steps to obtain the specific enthalpy of water at different pressures and temperatures, generate corresponding data points in the coordinate system, and fit the data points to obtain the specific enthalpy change curve of water fbh (P, T);

[0046] Repeat the above steps to obtain the specific enthalpy change curve of air gbh(P, T);

[0047] Data determination module: setting a collection period, and setting a number of time nodes at preset time intervals within the collection period;

[0048] The pressure and temperature of water are collected at each time node, and substituted into the specific enthalpy change curve of water fbh (P, T) to obtain the specific enthalpy of water at each time node;

[0049] Repeat the above steps to obtain the specific enthalpy of air at each time node;

[0050] Calculate boiler efficiency, turbine heat rate, pipeline efficiency and plant power rate at each time node;

[0051] Evaluation module: calculates the power generation coal consumption and the power supply coal consumption at each time node, and judges the performance of the generator set based on the power generation coal consumption and the power supply coal consumption.

[0052] It should be noted that the present invention is applicable to a generator set that burns fossil energy and uses water as a working medium; in the present invention, a calibration process is first performed, that is, determining the specific enthalpy of water at different pressures and temperatures, and determining the specific enthalpy of air at different pressures and temperatures; it should be noted that the calculation of the physical parameters (i.e., specific enthalpy) of water and air is the basis of the entire secondary calculation process. Only by ensuring the accuracy of the calculation of the basic parameters can the subsequent calculation have a solid foundation to support it and continue, otherwise it will be a castle in the air. The present invention adopts the latest international standard IAPWS-IF97 for the calculation of the above-mentioned physical parameters, and fully reproduces it in the present invention. Compared with the standard, the error is 0 (equal to 8 decimal places), thereby improving the accuracy of subsequent judgment of the performance of the generator set; then, the pressure and temperature of the water are obtained in real time during the acquisition period to obtain the specific enthalpy of the water, and the specific enthalpy of the air is obtained. The pressure and temperature are used to obtain the specific enthalpy of air, and the corresponding boiler efficiency, turbine heat rate, pipeline efficiency and plant power consumption rate are calculated; finally, the performance of the generator set is judged according to the power generation coal consumption and the power supply coal consumption; it is worth noting that in actual situations, various reasons such as measurement errors may cause the performance of the generator set at a certain time node to be poor (that is, the power generation coal consumption and / or power supply coal consumption is greater than the preset threshold). However, if the performance of the generator set is directly judged to be poor at this time, it may lead to misjudgment and may affect the normal use of the generator set. Therefore, the performance of the generator set is judged from the overall performance within the collection period to improve the accuracy of the judgment. The length of the collection period is 5s, and the interval between two adjacent time nodes is 300ms to prevent the collection period from being too long, resulting in a lag in the final judgment of the performance of the generator set, affecting the normal operation of the generator set.

[0053] In another preferred implementation of the present invention, in the evaluation module, the specific steps of calculating the power generation coal consumption and the power supply coal consumption include:

[0054] Calculate the power generation coal consumption FD = THR / BE / GE, where THR represents the turbine heat rate, BE represents the boiler efficiency, and GE represents the pipeline efficiency;

[0055] Calculate the power supply coal consumption GD = THR / BE / GE / (1-CYD), where CYD represents the plant power consumption rate.

[0056] In another preferred implementation of the present invention, the process of judging the performance of the generator set according to the power generation coal consumption and the power supply coal consumption specifically includes:

[0057] Counting the ratio BFD of the power generation coal consumption FD≥FD', where FD' is a preset power generation coal consumption threshold;

[0058] Counting the ratio BGD of the power supply coal consumption GD≥GD', where GD' is a preset power supply coal consumption threshold;

[0059] When the ratio BFD≥BFD' and the ratio BGD≥BGD', it is determined that the performance of the generator set is poor, BFD' is a preset power generation coal consumption ratio threshold, and BGD' is a preset power supply coal consumption ratio threshold;

[0060] When the ratio BFD<BFD' and the ratio BGD<BGD', it is determined that the performance of the generator set is poor;

[0061] When the ratio BFD<BFD' and the ratio BGD≥BGD', executing a preset judgment step;

[0062] When the ratio BFD≥BFD′ and the ratio BGD<BGD′, the preset judgment step is performed.

[0063] It is understandable that the performance of the generator set is judged by the overall performance of the generator set during the acquisition period to prevent misjudgment caused by accidental errors.

[0064] In another preferred implementation of the present invention, the judging step specifically includes:

[0065] Step 1: Obtain the power generation coal consumption A and the corresponding water temperature AST and pressure ASP, and obtain the air temperature AKT and pressure AKP corresponding to the power generation coal consumption A, and generate a mapping (AST, ASP, AKT, AKP)→A;

[0066] Repeat the above steps to obtain m mappings, where m is a preset value, and store the mappings in a database;

[0067] Step 2: Establish a power generation coal consumption prediction model through a deep learning model, train and verify the power generation coal consumption prediction model through a database, input the predicted water temperature, predicted water pressure, predicted air temperature and predicted air pressure into the power generation coal consumption prediction model, and output the predicted power generation coal consumption;

[0068] Repeat the above steps to obtain the predicted power supply coal consumption;

[0069] Step 3: Starting from the end of the collection period, continuously obtain n predicted power generation coal consumptions, and obtain the predicted power generation coal consumption greater than or equal to FD', and use it as the power generation coal consumption within the collection period;

[0070] Recalculate the proportion B of the power generation coal consumption FD≥FD' during the collection period, and when the proportion B is greater than or equal to BFD', determine that the performance of the power generation unit is poor;

[0071] Step 4: In step 3, when the ratio is less than BFD', step 3 is repeated to count the ratio C of coal consumption for power supply during the acquisition period, and when the ratio C is greater than or equal to BGD', it is determined that the performance of the generator set is poor.

[0072] It should be noted that by predicting future coal consumption for power generation and power supply and judging the performance of the generator set, it is possible to discover in advance the situation of poor performance of the generator set and deal with it in time; the introduction of deep learning models makes the monitoring and judgment processes more intelligent and automated, reducing human errors; deep learning models are a type of machine learning model, which are composed of multi-layer neural networks and can automatically learn features and patterns from large amounts of data. In the present invention, a long short-term memory network (LSTM) is selected. LSTM is a variant of RNN (recurrent neural network) and is good at processing and predicting time series-based data. It is suitable for processing time series data in the operation of generator sets.

[0073] In another preferred implementation of the present invention, in step 2, the process of obtaining the predicted temperature of the water specifically includes:

[0074] The temperature of the water during the collection period is obtained, and the water temperature change curve h(t) is obtained by fitting it, and T+Δt is substituted into h(t) to obtain the predicted temperature of the water at T+Δt, where T represents the time node at the end of the collection period, and Δt represents the time interval between two adjacent time nodes.

[0075] It should be noted that the predicted water pressure, the predicted air temperature and the predicted air pressure can be obtained in the same manner as the predicted water temperature, and therefore will not be described in detail.

[0076] In another preferred implementation of the present invention, the evaluation module further includes the following steps:

[0077] When it is determined that the performance of the generator set is poor, the optimal operating parameters of the generator set are determined through a quadratic programming optimization algorithm with the goal of minimizing the coal consumption for power generation and power supply. The operating parameters are parameters that affect the performance of the generator set when the generator set is running.

[0078] It can be understood that operating parameters such as parameters on the boiler side: coal moisture content, coal ash content and exhaust gas temperature, parameters of the turbine: high-pressure cylinder efficiency, medium-pressure cylinder efficiency and low-pressure cylinder efficiency, etc.; in the present invention, the goal is to minimize the coal consumption for power generation and power supply, so we need to construct an objective function related to coal consumption, and determine constraints such as the upper and lower limits of the high-pressure cylinder efficiency, and solve the objective function through the quadratic programming algorithm to determine the optimal operating parameters of the generator set; it should be noted that the actual values ​​of the operating parameters are taken from the primary measurement values ​​of the DCS system. Some actual values ​​cannot be directly measured and need to be obtained through existing primary measurement values. Secondary calculations are used to obtain data, such as the efficiency of high, medium and low pressure cylinders. Some advanced algorithms used in the secondary calculations need to run in real time at the bottom layer, which requires the bottom layer real-time system to have good real-time and portability. The real-time performance ensures that the indirect measurement values ​​obtained by the secondary calculations are the same as the direct measurement values ​​obtained once. The portability ensures that the algorithms generated by the MATLAB / Simulink development platform can run stably and reliably in the bottom layer real-time system. The bottom layer real-time system of the device of the present invention adopts the CoDeSys soft PLC real-time system, which has rich communication functions and code transplantation capabilities, ensuring the ability of the device of the present invention to develop and apply advanced functions.

[0079] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A real-time online monitoring device for generator set performance, characterized in that: include: Calibration module: set pressure range [Pmin, Pmax] and temperature range [Tmin, Tmax]; While keeping the pressure P constant, the temperature T of the water is adjusted within the temperature range, and after each adjustment of the water temperature, the specific enthalpy of the water is calculated; Repeat the above steps to obtain the specific enthalpy of water at different pressures and temperatures, generate corresponding data points in the coordinate system, and fit the data points to obtain the specific enthalpy change curve of water fbh (P, T); Repeat the above steps to obtain the specific enthalpy change curve of air gbh(P, T); Data determination module: setting a collection period, and setting a number of time nodes at preset time intervals within the collection period; The pressure and temperature of water are collected at each time node, and substituted into the specific enthalpy change curve of water fbh (P, T) to obtain the specific enthalpy of water at each time node; Repeat the above steps to obtain the specific enthalpy of air at each time node; Calculate boiler efficiency, turbine heat rate, pipeline efficiency and plant power rate at each time node; Evaluation module: calculates the power generation coal consumption and the power supply coal consumption at each time node, and judges the performance of the generator set based on the power generation coal consumption and the power supply coal consumption.

2. A real-time online monitoring device for generator set performance according to claim 1, characterized in that: In the evaluation module, the specific steps of calculating the power generation coal consumption and the power supply coal consumption include: Calculate the power generation coal consumption FD = THR / BE / GE, where THR represents the turbine heat rate, BE represents the boiler efficiency, and GE represents the pipeline efficiency; Calculate the power supply coal consumption GD = THR / BE / GE / (1-CYD), where CYD represents the plant power consumption rate.

3. A real-time online monitoring device for generator set performance according to claim 2, characterized in that: The process of judging the performance of the generator set according to the power generation coal consumption and the power supply coal consumption specifically includes: Counting the ratio BFD of the power generation coal consumption FD≥FD', where FD' is a preset power generation coal consumption threshold; Counting the ratio BGD of the power supply coal consumption GD≥GD', where GD' is a preset power supply coal consumption threshold; When the ratio BFD≥BFD' and the ratio BGD≥BGD', it is determined that the performance of the generator set is poor, BFD' is a preset power generation coal consumption ratio threshold, and BGD' is a preset power supply coal consumption ratio threshold; When the ratio BFD<BFD' and the ratio BGD<BGD', it is determined that the performance of the generator set is poor; When the ratio BFD<BFD' and the ratio BGD≥BGD', executing a preset judgment step; When the ratio BFD≥BFD′ and the ratio BGD<BGD′, the preset judgment step is performed.

4. A real-time online monitoring device for generator set performance according to claim 3, characterized in that: The judging step specifically includes: Step 1: Obtain the power generation coal consumption A and the corresponding water temperature AST and pressure ASP, and obtain the air temperature AKT and pressure AKP corresponding to the power generation coal consumption A, and generate a mapping (AST, ASP, AKT, AKP)→A; Repeat the above steps to obtain m mappings, where m is a preset value, and store the mappings in a database; Step 2: Establish a power generation coal consumption prediction model through a deep learning model, train and verify the power generation coal consumption prediction model through a database, input the predicted water temperature, predicted water pressure, predicted air temperature and predicted air pressure into the power generation coal consumption prediction model, and output the predicted power generation coal consumption; Repeat the above steps to obtain the predicted power supply coal consumption; Step 3: Starting from the end of the collection period, continuously obtain n predicted power generation coal consumptions, and obtain the predicted power generation coal consumption greater than or equal to FD', and use it as the power generation coal consumption within the collection period; Recalculate the proportion B of the power generation coal consumption FD≥FD' during the collection period, and when the proportion B is greater than or equal to BFD', determine that the performance of the power generation unit is poor; Step 4: In step 3, when the ratio is less than BFD', step 3 is repeated to count the ratio C of coal consumption for power supply during the acquisition period, and when the ratio C is greater than or equal to BGD', it is determined that the performance of the generator set is poor.

5. A real-time online monitoring device for generator set performance according to claim 4, characterized in that: In the step 2, the process of obtaining the predicted water temperature specifically includes: The temperature of the water during the collection period is obtained, and the water temperature change curve h(t) is obtained by fitting it, and T+Δt is substituted into h(t) to obtain the predicted temperature of the water at T+Δt, where T represents the time node at the end of the collection period, and Δt represents the time interval between two adjacent time nodes.

6. A real-time online monitoring device for generator set performance according to claim 5, characterized in that: The evaluation module further includes the following steps: When it is determined that the performance of the generator set is poor, the optimal operating parameters of the generator set are determined through a quadratic programming optimization algorithm with the goal of minimizing the coal consumption for power generation and power supply. The operating parameters are parameters that affect the performance of the generator set when the generator set is running.

Images