Method and system for diesel engine efficiency optimization and emission control

Abstract

The present application provides a diesel generator energy efficiency optimization and emission control method and system, relates to the technical field of data processing, and the method comprises the following steps: constructing a spatial topological configuration with three stress collection sites as end points, and performing section calculation on the spatial topological configuration to obtain a shape coefficient; correcting the corrected operation index according to the shape coefficient to obtain a final operation index; calculating the fuel consumption, nitrogen oxide emission and particulate matter emission according to process parameters to obtain energy consumption indexes and environmental protection indexes; calculating the final operation index, the energy consumption index and the environmental protection index to obtain an energy efficiency value; performing multi-objective optimization according to the energy efficiency value to obtain a target scheme; and adjusting the power and voltage frequency according to the target scheme. The present application improves the stability and adaptability of unit energy efficiency and emission control, and helps to balance the unit operation efficiency, environmental protection performance and structural safety.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for optimizing the energy efficiency and controlling emissions of diesel generators. Background Technology

[0002] In the application scenario of diesel generator sets for communication base stations, the units are usually used as backup power sources and are often in standby mode for extended periods, typically starting only when the mains power is interrupted. However, during actual operation, they are often under low load conditions and experience frequent start-stop cycles. Existing energy efficiency optimization and emission control methods typically focus on real-time monitoring and adjustment of conventional operating parameters such as speed, power output, and fuel consumption rate, improving the combustion process through optimized fuel injection strategies and intake management. However, in actual operation, key load-bearing components of the diesel generator set (such as crankshafts and connecting rods) sometimes gradually experience fatigue under repeated dynamic loads. The cumulative effect of fatigue damage can, in some cases, lead to slow changes in the microstructure of components, thereby affecting the stability of combustion chamber boundary conditions. Under such conditions, even if the operating parameters are within the normal optimization range, fuel atomization quality and combustion efficiency may still deviate to some extent, making it difficult to maintain good consistency between the actual energy consumption and emission levels of the unit and the optimization model established based on instantaneous operating parameters. In existing technologies, the correlation between fatigue damage state and operation control needs to be further established, and the adaptability of energy efficiency optimization strategies often has room for improvement when the unit's structural performance undergoes potential changes. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for optimizing the energy efficiency and controlling the emissions of diesel generators, which improves the stability and adaptability of the unit's energy efficiency and emission control, and helps to balance the unit's operating efficiency, environmental performance and structural safety.

[0004] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows: Firstly, a method for optimizing the energy efficiency and controlling emissions of diesel generators, the method comprising: Step 1: Collect analog parameters, switch status values, and pulse values ​​of the diesel generator set during operation as process parameters; Step 2: Based on process parameters, extract dynamic stress data of key load-bearing components, and obtain the cumulative fatigue damage amount through cycle counting and cumulative damage calculation; according to process parameters, extract speed values, power output values ​​and fuel consumption rate values ​​to obtain operating indicators, and correct the operating indicators based on the cumulative fatigue damage amount to obtain the corrected operating indicators; set three stress acquisition points on the key load-bearing components, construct a spatial topology configuration with the three stress acquisition points as endpoints, and perform subdivision calculation on the spatial topology configuration to obtain the shape coefficient; Step 3: Correct the modified operating indicators based on the morphological coefficient to obtain the final operating indicators; calculate the fuel consumption, nitrogen oxide emissions and particulate matter emissions based on the process parameters to obtain the energy consumption indicators and environmental protection indicators; calculate the final operating indicators, energy consumption indicators and environmental protection indicators to obtain the energy efficiency value. Step 4: Based on the energy efficiency value, perform multi-objective optimization to obtain the target scheme; based on the target scheme, adjust the power and voltage frequency.

[0005] Secondly, the diesel generator energy efficiency optimization and emission control system includes: The parameter acquisition module is used to collect analog parameters, switch status values ​​and pulse values ​​of the diesel generator set as process parameters during operation. The calculation module is used to extract dynamic stress data of key load-bearing components based on process parameters, and obtain the cumulative fatigue damage through cycle counting and cumulative damage calculation; according to process parameters, it extracts speed values, power output values ​​and fuel consumption rate values ​​to obtain operating indicators, and corrects the operating indicators based on the cumulative fatigue damage to obtain the corrected operating indicators; three stress acquisition points are set on the key load-bearing components, and a spatial topology is constructed with the three stress acquisition points as endpoints, and the spatial topology is partitioned and calculated to obtain the shape coefficient; The correction module is used to correct the modified operating indicators based on the morphological coefficient to obtain the final operating indicators; based on the process parameters, it calculates the fuel consumption, nitrogen oxide emissions and particulate matter emissions respectively to obtain the energy consumption indicators and environmental protection indicators; and calculates the final operating indicators, energy consumption indicators and environmental protection indicators to obtain the energy efficiency value. The adjustment module is used to perform multi-objective optimization based on the energy efficiency value to obtain the target scheme; and to adjust the power and voltage frequency according to the target scheme.

[0006] Thirdly, a computing device, comprising: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method.

[0007] Fourthly, a computer-readable storage medium storing a program that, when executed by a processor, implements the method.

[0008] The above-described solution of the present invention has at least the following beneficial effects: By incorporating the cumulative fatigue damage of key load-bearing components into the operational indicator correction system, the unit's energy efficiency optimization and structural health status are coordinated and managed. This avoids problems such as decreased combustion efficiency, excessive energy consumption and emissions due to component fatigue damage, ensuring the long-term stable operation of the unit. Through the calculation of spatial topology configuration and morphological coefficients, the impact of the structural characteristics of key load-bearing components on operational indicators is quantified. Combined with the secondary correction of operational indicators based on fatigue damage, the accuracy of the final operational indicators and energy efficiency values ​​is improved, effectively reducing the deviation between the optimization model and the actual operating state. Attached Figure Description

[0009] Figure 1 This is a schematic diagram of the process for optimizing the energy efficiency and controlling emissions of a diesel generator provided in an embodiment of the present invention.

[0010] Figure 2 This is a schematic diagram of a diesel generator energy efficiency optimization and emission control system provided in an embodiment of the present invention. Detailed Implementation

[0011] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0012] like Figure 1 As shown, embodiments of the present invention propose a method for optimizing the energy efficiency and controlling emissions of diesel generators, the method comprising the following steps: Step 1: Collect analog parameters, switch status values, and pulse values ​​of the diesel generator set during operation as process parameters; Step 2: Based on process parameters, extract dynamic stress data of key load-bearing components, and obtain the cumulative fatigue damage amount through cycle counting and cumulative damage calculation; according to process parameters, extract speed values, power output values ​​and fuel consumption rate values ​​to obtain operating indicators, and correct the operating indicators based on the cumulative fatigue damage amount to obtain the corrected operating indicators; set three stress acquisition points on the key load-bearing components, construct a spatial topology configuration with the three stress acquisition points as endpoints, and perform subdivision calculation on the spatial topology configuration to obtain the shape coefficient; Step 3: Correct the modified operating indicators based on the morphological coefficient to obtain the final operating indicators; calculate the fuel consumption, nitrogen oxide emissions and particulate matter emissions based on the process parameters to obtain the energy consumption indicators and environmental protection indicators; calculate the final operating indicators, energy consumption indicators and environmental protection indicators to obtain the energy efficiency value. Step 4: Based on the energy efficiency value, perform multi-objective optimization to obtain the target scheme; based on the target scheme, adjust the power and voltage frequency.

[0013] In this embodiment of the invention, the cumulative fatigue damage of key load-bearing components is incorporated into the operational indicator correction system, realizing the coordinated management and control of unit energy efficiency optimization and structural health status. This avoids problems such as decreased combustion efficiency, excessive energy consumption and emissions due to component fatigue damage, ensuring long-term stable operation of the unit. By calculating the spatial topology configuration and morphological coefficients, the impact of the structural characteristics of key load-bearing components on operational indicators is quantified. Combined with the secondary correction of operational indicators by fatigue damage, the accuracy of the final operational indicators and energy efficiency values ​​is improved, effectively reducing the deviation between the optimization model and the actual operating state.

[0014] In a preferred embodiment of the present invention, step 1, collecting analog parameters, switch status values, and pulse values ​​of the diesel generator set during operation as process parameters, may include: Step 101: Collect continuously changing physical quantities of the diesel generator set during operation to obtain analog signals; perform analog-to-digital conversion on the analog signals to obtain digitized analog parameters; collect on / off status signals of each device in the diesel generator set to obtain switching signals; perform level state identification and filtering on the switching signals to obtain switching status values; collect the rotational speed pulse signals of rotating parts in the diesel generator set to obtain the original pulse sequence; perform period measurement and frequency calculation on the original pulse sequence to obtain pulse value. Specifically, this includes: deploying corresponding sensors to collect continuously changing physical quantities during the operation of the diesel generator set, including the engine oil temperature, considering the long standby, low load operation, and frequent start-stop characteristics of diesel generator sets used in communication base stations. The system collects and transmits continuously changing physical quantities, including cooling water temperature, cooling water pressure, intake pressure, exhaust pressure, fuel flow rate in the fuel supply line, voltage and current signals at the unit output, and strain signals of key load-bearing components. These quantities are converted into transmitable analog signals. The analog signals are then converted to digital values ​​(ADCs) to obtain digitized analog parameters. Specifically, the acquired analog signals are transmitted to a data acquisition device, where the ADC circuitry completes the conversion. The analog signal range and ADC bit depth are set. The range is set to 0 to 10 volts, and the bit depth is set to 16 bits. The quantization interval is calculated using the formula: the maximum value minus the minimum value of the range, divided by 2 raised to the power of the ADC bit depth. ,in This represents the maximum value of the measurement range. The value represents the minimum range, and n represents the number of conversion bits. Substituting these values, the result is calculated. The volt is calculated by dividing the actual voltage value of the analog signal by the quantization interval to obtain the corresponding digital value. During the conversion process, it is ensured that the digital signal can accurately correspond to the range and pattern of change of the analog signal, avoiding parameter distortion due to conversion deviation, and finally obtaining the digitized analog parameter.

[0015] The on / off status signals of various devices in the diesel generator set are collected to obtain switch signals. Specifically, the on / off status of various devices such as the fuel pump, starting relay, cooling fan, and excitation switch is collected. The on / off status of these devices directly reflects the operating status of the generator set. During the acquisition process, the timeliness of signal acquisition is ensured to avoid errors in device status judgment due to signal delay. The collected on / off status is converted into switch signals. The switch signals are then subjected to level state identification and filtering to obtain switch status values. Specifically, the collected switch signals are first identified by level state identification to distinguish the on / off status of devices corresponding to high and low levels. High level corresponds to the device being on, and low level corresponds to the device being off. The identified switch signals are then filtered to remove noise and interference signals generated during signal transmission to avoid misjudgment of device status due to noise signals. After level identification and filtering, switch status values ​​that accurately reflect the on / off status of the devices are obtained.

[0016] The original pulse sequence is obtained by collecting the rotational speed pulse signals of rotating components in the diesel generator set. Specifically, pulse sensors are deployed on rotating components such as the crankshaft and flywheel of the unit. When the rotating components rotate, the pulse sensors generate corresponding pulse signals according to the rotational frequency of the rotating components. These pulse signals are continuously collected to form the original pulse sequence. During the collection process, it is ensured that the collection frequency of the pulse signals can meet the accuracy requirements of speed calculation and adapt to the characteristic of small speed fluctuations when the unit is running at low load. The pulse quantity value is obtained by period measurement and frequency calculation of the original pulse sequence. Specifically, the time interval between two adjacent pulses in the original pulse sequence is first measured, that is, the pulse period. Then, the pulse frequency is calculated based on the pulse period. The pulse frequency is obtained by dividing 1 by the pulse period. The pulse frequency is directly related to the rotational speed of the rotating components. The rotational speed-related value of the rotating components is further calculated based on the pulse frequency, and finally the pulse quantity value is obtained.

[0017] Step 102 involves fusing and synchronizing the digitized analog parameters, switch status values, and pulse values ​​to obtain process parameters. Specifically, considering that the acquisition time of various parameters may deviate during the operation of the diesel generator set used in the communication base station, and that the acquisition frequencies of different types of parameters are also different (analog parameters acquisition frequency 10Hz to 100Hz, switch status values ​​acquisition frequency 1Hz to 10Hz, pulse values ​​acquisition frequency 100Hz to 1000Hz), directly using these parameters for subsequent calculations would lead to deviations in the calculation results. Therefore, it is necessary to first process the three types of parameters... Time synchronization is performed by adjusting the timestamps of the other two types of parameters based on the acquisition time of one type of parameter, ensuring that the three types of parameters correspond in the same time dimension and eliminating timing deviations. Data fusion is then performed by integrating the time-synchronized digital analog parameters, switch status values, and pulse values ​​into a single dataset. During the integration process, the validity of each type of parameter is verified, and invalid and abnormal data are removed, such as analog parameters that are outside the normal range, and frequently fluctuating switch status values ​​and pulse values. This ensures that the integrated dataset can comprehensively and accurately reflect the operating status of the unit, ultimately yielding the process parameters.

[0018] This embodiment eliminates interference and timing deviations in the parameter acquisition process through preprocessing, data fusion, and time synchronization, obtaining unified and reliable process parameters, and solving the problem of incomplete parameter acquisition and data asynchrony leading to subsequent calculation deviations.

[0019] In a preferred embodiment of the present invention, step 2 involves extracting dynamic stress data of key load-bearing components based on process parameters, and obtaining the cumulative fatigue damage amount through cycle counting and cumulative damage calculation; extracting operating indicators based on process parameters, including rotational speed, power output, and fuel consumption rate, and correcting the operating indicators based on the cumulative fatigue damage amount; setting three stress acquisition points on the key load-bearing components, constructing a spatial topology configuration using the three stress acquisition points as endpoints, and performing a subdivision calculation on the spatial topology configuration to obtain morphological coefficients, which may include: Step 201: Based on the process parameters, extract the strain response signals collected from the key load-bearing components to obtain the raw strain time series data; preprocess the raw strain time series data to obtain the preprocessed strain time series data; obtain the elastic modulus parameters based on the material properties of the key load-bearing components, specifically including: selecting the strain signals corresponding to the key load-bearing components from the process parameters. The key load-bearing components of the diesel generator set for communication base stations mainly include crankshafts, connecting rods, etc. These components are subjected to repeated dynamic loads during low-load operation and frequent start-stop processes of the unit. The strain signals (value range -2000) By 2000 It can reflect the stress state of the component and arrange the selected strain signals in chronological order to form the original strain time series data.

[0020] The raw strain time series data is preprocessed to obtain preprocessed strain time series data. Specifically, the raw strain time series data is first denoised to filter out environmental interference signals and equipment interference signals generated during signal acquisition and transmission. The denoising process ensures that the original variation patterns of the strain time series data are not destroyed. Then, the denoised time series data is interpolated to fill in missing data. The interpolation operation uses linear interpolation. First, the denoised time series data is checked point by point to locate the missing data points and their durations. For a single isolated missing point, the strain value of the missing point is calculated based on the strain change trend between the two adjacent valid data points, using the difference in strain between the two points as a reference. That is, the strain change rate per unit time is obtained by dividing the strain difference between the two adjacent points by the time interval. The calculation formula is v = Where v is the rate of change of strain. The strain value of the previous valid data point before the missing point. The strain value of the next valid data point after the missing point. The timestamp of the previous valid data point. The timestamp of the next valid data point is used; then, the strain value of the previous valid data point is added to the product of the rate of change and the time interval between the missing point and the previous valid data point to obtain the interpolation result of the missing point. The calculation formula is as follows: ,in The interpolated strain value for the missing point. The timestamps of the missing points are used. For multiple consecutive missing points, the strain value of each missing point is calculated sequentially using the same method to ensure that the interpolated time series data has the same trend as the original valid data, without abrupt deviations, making the time series data more continuous. Trend correction is performed on the interpolated time series data to eliminate time series data deviations caused by sensor drift. After denoising, interpolation, and trend correction processing, the preprocessed strain time series data is obtained (value range -1800). up to 1800 The elastic modulus parameters are obtained based on the material properties of key load-bearing components. Specifically, the material of the key load-bearing components is determined. For example, crankshafts are usually made of alloy steel, and connecting rods are usually made of high-strength aluminum alloy. The elastic modulus parameters of these materials are obtained under different operating conditions such as normal temperature and unit operating temperature. The elastic modulus parameter of alloy steel ranges from 200GPa to 210GPa, and the elastic modulus parameter of high-strength aluminum alloy ranges from 70GPa to 75GPa.

[0021] Step 202: Calculate the preprocessed strain time series data and elastic modulus parameters to obtain dynamic stress time series data; detect the dynamic stress time series data to obtain a stress extremum sequence; extract each stress cycle from the stress extremum sequence to obtain a stress cycle set, specifically including: based on the principles of mechanics of materials, namely, that stress and strain are directly proportional within the elastic deformation range of key load-bearing components, this relationship is the core basis for dynamic stress calculation; multiply each strain value in the preprocessed strain time series data by the corresponding elastic modulus parameter, and calculate according to the formula... ,in Here, E represents the dynamic stress value, and E is the elastic modulus parameter. The strain values ​​after pretreatment are given, each strain value (-1800). up to 1800 Each strain value corresponds to an elastic modulus parameter (200GPa to 210GPa for alloy steel, 70GPa to 75GPa for aluminum alloy). Multiplying the two values ​​yields the dynamic stress value at each time point. The dynamic stress value ranges from -126MPa to 378MPa. The dynamic stress values ​​at all time points are arranged in chronological order to form dynamic stress time series data. During the calculation process, it is ensured that the correspondence between each strain value and the elastic modulus parameter is accurate to avoid distortion of the dynamic stress data due to incorrect correspondence.

[0022] The stress extremum sequence is obtained by detecting dynamic stress time series data. Specifically, the dynamic stress time series data is detected point by point, and the maximum and minimum stress values ​​within each stress change cycle are selected. Among them, the maximum stress value within each cycle is... (0MPa to 378MPa) represents the peak stress and minimum stress value within this cycle. (-126MPa to 0MPa) is the valley value of stress within this cycle, covering all cycles. and Arranged chronologically to form a stress extreme value sequence, the detection process ensures that no stress change cycle is missed, accurately capturing the stress extreme value of each cycle, thus providing a basis for subsequent stress cycle extraction.

[0023] The stress cycle set is obtained by extracting each stress cycle from the stress extremum sequence, specifically by selecting the adjacent maximum stress values ​​in the stress extremum sequence. (0MPa to 378MPa) and minimum stress value (-126MPa to 0MPa) are combined, each Adjacent to it A complete stress cycle is formed by sequentially extracting all stress cycles in the stress extremum sequence and integrating these stress cycles together to form a stress cycle set.

[0024] Step 203: Calculate the amplitude and mean of each stress cycle in the stress cycle set to obtain the data on the relationship between stress and cycle number of the key load-bearing component material, thus obtaining the material stress cycle characteristic data; based on the amplitude of each stress cycle and the material stress cycle characteristic data, determine the cycle number limit, specifically including: for each stress cycle in the stress cycle set, using the maximum stress value of that stress cycle... (0MPa to 378MPa) minus the minimum stress value (-126MPa to 0MPa), the amplitude of this stress cycle is obtained. The calculation formula is: Amplitude The value ranges from 0 MPa to 378 MPa, reflecting the stress variation range of this stress cycle; then the maximum stress value of this stress cycle is used. Add minimum stress value Then divide by two to obtain the mean value of the stress cycle. The calculation formula is: mean The value ranges from -63MPa to 189MPa, reflecting the average stress level of the stress cycle. The amplitude of each stress cycle is calculated sequentially. and mean .

[0025] By obtaining data on the relationship between stress and cycle number of key load-bearing component materials, material stress-cycle characteristic data is obtained. Specifically, this is achieved through material testing, which simulates stress changes during unit operation by applying different amplitudes to the material samples. Stress cycles (amplitude from 0 MPa to 378 MPa) were recorded, and each stress amplitude was recorded. The corresponding number of cycles when the sample fails due to fatigue ( to (times), different stress amplitudes The data are compiled and integrated with the corresponding number of cycles to form material stress cycle characteristic data.

[0026] Amplitude for each stress cycle (0MPa to 378MPa), find the number of cycles corresponding to this amplitude in the material stress cycle characteristic data. This number of cycles is the cycle limit corresponding to this stress cycle. to (times), loop count limit This indicates the maximum number of cycles a critical load-bearing component can withstand under this stress amplitude. Exceeding this number will cause fatigue damage to the component. During the search process, ensure the accurate correspondence between the amplitude and the number of cycles. If the stress cycle amplitude... Since there is no directly corresponding value in the material stress cyclic characteristics data, the corresponding cycle number limit is calculated using linear interpolation. Specifically, it means finding the amplitude. Two adjacent known amplitudes , (in < < ) and the corresponding number of loops , First, calculate the change in the number of cycles, k, corresponding to a unit amplitude. The formula is k = Then multiply this change k by the difference between the target amplitude and the smaller known amplitude. Add the number of cycles corresponding to the smaller known amplitude The limit of the number of iterations corresponding to the target amplitude is obtained. The calculation formula is: = Ensure that each stress cycle has a corresponding cycle count limit, and that all cycle count limits are within [the specified limits]. to Within this range.

[0027] Step 204: Calculate the damage contribution value of each stress cycle based on its amplitude, mean, and cycle number limit. Summate the damage contribution values ​​of each stress cycle to obtain the cumulative fatigue damage. Specifically, for each stress cycle, first determine the damage coefficient corresponding to that stress cycle based on its amplitude (0 MPa to 378 MPa) and mean (-63 MPa to 189 MPa), combined with the material's fatigue characteristics. The material's fatigue characteristics specifically refer to the fatigue resistance of the key load-bearing component material under different stress amplitudes and mean values. The core reference is the material's stress cycle characteristic data and fatigue strength limit. The damage coefficient is determined by the ratio of the amplitude / mean to the material's fatigue strength limit. The damage coefficient ranges from 0.001 to 0.999, reflecting the degree of influence of the stress cycle on the component's fatigue damage. Then, divide the damage coefficient by the cycle number limit of that stress cycle (…). to The damage contribution value of this stress cycle is obtained by (times). to The damage contribution value of each stress cycle represents the degree to which that cycle contributes to the cumulative fatigue damage of the component. During the calculation, the damage coefficient is ensured to be accurately determined and closely reflect the actual fatigue characteristics of the material. The cumulative fatigue damage is obtained by summing the damage contribution values ​​of each stress cycle. Specifically, this involves summing the damage contribution values ​​of all stress cycles (…). to The sum of all damage contribution values ​​is the cumulative fatigue damage of the key load-bearing component, ranging from 0 to 1.

[0028] Step 205: Based on the process parameters, extract the rotational speed pulse signals of the rotating components of the diesel generator set to obtain raw rotational speed data; perform period measurement and frequency calculation on the raw rotational speed data to obtain the rotational speed value; based on the process parameters, extract the voltage and current signals at the output terminal of the diesel generator set and calculate the power output value; based on the process parameters, extract the flow rate signal on the fuel supply pipeline of the diesel generator set to obtain raw fuel flow rate data; calculate the fuel consumption rate value based on the raw fuel flow rate data, specifically including: selecting the rotational speed pulse signals corresponding to the rotating components from the process parameters obtained in step 102. The rotating components mainly include the crankshaft, flywheel, etc., and the rotational speed of these components directly reflects the operating status of the unit. The selected rotational speed pulse signals are used as the raw rotational speed data; perform period measurement and frequency calculation on the raw rotational speed data to obtain the rotational speed value. Specifically, first measure the time interval between two adjacent pulses in the raw rotational speed data, i.e., the pulse period T (0.001s to 0.01s), and then divide the unit time by the pulse period to calculate the pulse frequency f. The calculation formula is as follows: The pulse frequency f (100Hz to 1000Hz) is obtained; the pulse frequency is proportional to the rotational speed of the rotating component, and the rotational speed is calculated by combining the number of teeth z (12 to 36 teeth) of the rotating component. The calculation formula is: = The speed value is measured in revolutions per minute (rpm), with a range of 1500 r / min ± 50 r / min. The voltage signal U (single-phase 220V ± 10%, three-phase 380V ± 10%) and current signal I (0A to 100A) at the unit's output are selected from the process parameters. These signals reflect the unit's output capacity. For single-phase output, the power output value P is calculated using the following formula: The value ranges from 0kW to 22kW; for three-phase output, the power output value P is calculated using the following formula: The value ranges from 0kW to 38kW.

[0029] Fuel flow signals from the fuel supply pipeline are selected from process parameters. These signals reflect the fuel supply rate. During the selection process, the continuity of the flow signals is ensured to avoid data loss. The selected flow signals are used as the raw fuel flow data, with a range of 10L / h to 50L / h, providing a basis for subsequent fuel consumption rate calculations. The fuel consumption rate is calculated from the raw fuel flow data by first summing the total fuel flow per unit time to obtain the fuel consumption per unit time m (10g / h to 50000g / h), and then dividing the fuel consumption per unit time by the unit's power output P (0kW to 38kW) to obtain the fuel consumption rate. The calculation formula is: The fuel consumption rate is expressed in grams per kilowatt-hour, ranging from 200 g / (kW·h) to 350 g / (kW·h).

[0030] Step 206: Combine the speed, power output, and fuel consumption rate values ​​to obtain the operating indicators; calculate the correction coefficient based on the accumulated fatigue damage to obtain the operating indicator correction coefficient; calculate the operating indicators and the operating indicator correction coefficient to obtain the corrected operating indicators. Specifically, this includes: integrating the speed, power output, and fuel consumption rate values ​​to form the unit's operating indicators, where the speed reflects the unit's operating speed, the power output reflects the unit's output capacity, and the fuel consumption rate reflects the unit's fuel utilization efficiency; and calculating the correction coefficient based on the accumulated fatigue damage to obtain the operating indicator correction coefficient, specifically by first setting a baseline value for the accumulated fatigue damage. The baseline value is the cumulative amount when the critical load-bearing components have not experienced fatigue damage, i.e. Then, divide the cumulative fatigue damage D (0 to 1) by the sum of the baseline value and the cumulative fatigue damage to obtain the correction factor. The calculation formula is: = The correction factor ranges from 0.1 to 0.99. The greater the cumulative fatigue damage, the smaller the correction factor, and vice versa. During the calculation process, it is ensured that the benchmark value is set reasonably and conforms to the actual fatigue characteristics of the key load-bearing components to avoid errors in the calculation of the correction factor due to the deviation of the benchmark value. The correction factor of the operating index can reflect the degree of impact of fatigue damage on the unit's operating index.

[0031] The corrected operating indicators are obtained by calculating the operating indicators and the operating indicator correction factor. Specifically, each parameter value in the operating indicators is multiplied by the operating indicator correction factor (0.1 to 0.99). The formula for calculating the corrected speed value is: the corrected speed value is equal to the original speed value multiplied by the correction factor (value range 0 r / min to 1550 r / min). The formula for calculating the corrected power output value is: the corrected power output value is equal to the original power output value multiplied by the correction factor (value range 0 kW to 38 kW). The formula for calculating the corrected fuel consumption rate value is: the corrected fuel consumption rate value is equal to the original fuel consumption rate value multiplied by the correction factor (value range 0 g / (kW·h) to 350 g / (kW·h)). The corrected operating indicators are obtained by integrating the three parameter values.

[0032] Step 207: Set three stress acquisition points on the key load-bearing component. These three points are located at the center of the main load-bearing area, the transition zone between the main load-bearing area and the auxiliary support structure, and the end constraint zone furthest from the main load-bearing area. Dynamic stress data is collected from these three points to obtain first, second, and third stress time-series data. Specifically, this involves setting three stress acquisition points on the key load-bearing component. These points are located at the center of the main load-bearing area, the transition zone between the main load-bearing area and the auxiliary support structure, and the end constraint zone furthest from the main load-bearing area. The specific locations are: the center point of the main load-bearing area, the transition zone between the main load-bearing area and the auxiliary support structure, and the end constraint zone furthest from the main load-bearing area on the crankshaft. The crank arm is located in the middle section between the main journal and the main journal, and on the connecting rod, it is located in the core stress area of ​​the middle section of the rod body; the connection and transition zone between the main load-bearing area and the auxiliary support structure is located at the connection between the main journal and the crank arm on the crankshaft, and at the transition fillet between the big end of the connecting rod and the rod body on the connecting rod; the end constraint zone is located at the free end of the crankshaft, and at the end where the small end of the connecting rod connects to the piston pin on the connecting rod. Combining the structural characteristics and stress conditions of the key load-bearing components, the center of the main load-bearing area is the area where the component bears the largest load, and the stress change in this area best reflects the overall stress state of the component; the connection and transition zone between the main load-bearing area and the auxiliary support structure is a stress concentration area, which is prone to fatigue damage; and the end constraint zone is the area where the component bears the least stress.

[0033] Dynamic stress data was collected from three stress acquisition points to obtain the first, second, and third stress time series data. Specifically, a corresponding stress sensor was deployed at each stress acquisition point to continuously collect dynamic stress signals at each point. The dynamic stress signals (-180MPa to 378MPa) collected at the center of the main load-bearing area (middle part of crankshaft crank arm and middle section of connecting rod body) were arranged in chronological order to form the first stress time series data. The dynamic stress signals (-150MPa to 350MPa) collected at the connection transition area (connection between crankshaft main journal and crank arm, and transition fillet between connecting rod big end and rod body) were arranged in chronological order to form the second stress time series data. The dynamic stress signals (-50MPa to 100MPa) collected at the end constraint area (free end of crankshaft and small end of connecting rod) were arranged in chronological order to form the third stress time series data.

[0034] Step 208: Construct a spatial topology configuration using the three stress acquisition points as endpoints, and map the three stress time series data to the corresponding endpoints of the spatial topology configuration to obtain the stress-related spatial topology configuration. Specifically, this includes: determining the three-dimensional coordinates (unit: mm) of each stress acquisition point based on its actual spatial location on the key load-bearing component. The three-dimensional coordinates of the center of the main load-bearing area consist of X-axis coordinates, Y-axis coordinates, and Z-axis coordinates, where the X-axis coordinate ranges from 50 to 100 mm, the Y-axis coordinate ranges from 50 to 100 mm, and the Z-axis coordinate ranges from 50 mm to 100 mm. The three-dimensional coordinates of the connecting transition zone consist of X-axis, Y-axis, and Z-axis coordinates, with the X-axis coordinate ranging from 30 to 80 mm, the Y-axis coordinate ranging from 30 to 80 mm, and the Z-axis coordinate ranging from 30 to 80 mm. The three-dimensional coordinates of the end constraint zone consist of X-axis, Y-axis, and Z-axis coordinates, with the X-axis coordinate ranging from 10 to 50 mm, the Y-axis coordinate ranging from 10 to 50 mm, and the Z-axis coordinate ranging from 10 to 50 mm. Using the three-dimensional coordinates of the three points as endpoints, a spatial topological configuration of a triangle is constructed.

[0035] Three stress time series data points are mapped to corresponding endpoints of a spatial topology to obtain a stress-associated spatial topology. Specifically, the stress value at each time point in the first stress time series data (ranging from -180MPa to 378MPa) is mapped to the endpoint of the center of the main load-bearing zone in the spatial topology; the stress value at each time point in the second stress time series data (ranging from -150MPa to 350MPa) is mapped to the endpoint of the connecting transition zone in the spatial topology; and the stress value at each time point in the third stress time series data (ranging from -50MPa to 100MPa) is mapped to the endpoint of the end constraint zone in the spatial topology. During the mapping process, it is necessary to ensure that the three stress values ​​at each time point correspond one-to-one with the three endpoints, and that the time dimension of the three stress time series data points remains consistent, i.e., all are within the same time range from the start time to the end time of data acquisition. Through mapping, the spatial topology is associated with the stress data, forming a stress-associated spatial topology.

[0036] Based on the stress-related spatial topology, an algorithm for calculating the intersection area of ​​convex polygons is added to further quantify the spatial characteristics of the configuration, providing a precise basis for subsequent subdivision and stress gradient calculation; specifically, the triangular region of the stress-related spatial topology is used as the reference convex polygon. Its vertex coordinates are the projections of the three-dimensional coordinates of the three stress acquisition points onto a two-dimensional plane. , ), ( ), ( , Based on the actual structural contour of the corresponding area of ​​the key load-bearing component, construct an auxiliary convex polygon that adapts to the shape of the component. Its vertex coordinates are determined by measuring the actual contour of the component. The solution for two convex polygons is obtained using an algorithm for calculating the intersection area of ​​convex polygons. and The intersection area H is calculated using the following algorithm: first, extract the intersection area H of the two convex polygons. , The coordinates of all vertices are sorted clockwise, and then calculated using the cross product of vectors. Remove collinear redundant vertices (if the cross product is 0, determine that the vertices are collinear and remove them); then use the vector cross product to determine the position of each vertex relative to the other convex polygon, and determine the set of vertices at the intersection of the two convex polygons. ; e represents the total number of vertices in the intersection vertex set, that is, the number of vertices in the polygon formed by the intersection of two convex polygons; the area of ​​the polygon formed by the intersection vertices is calculated using the Shoelace formula, the formula is as follows: The intersection area H of the convex polygons is obtained (unit: ), where H [100,5000] .

[0037] Step 209 involves subdividing the stress-related spatial topology into multiple spatial elements. Based on the stress values ​​at each endpoint within each spatial element, the stress gradient is calculated to obtain the element stress gradient set. Specifically, this includes: using a uniform mesh subdivision method, with the overlapping region corresponding to the intersection area of ​​convex polygons as the core, uniformly subdividing the stress-related spatial topology. The subdivision algorithm involves extracting the boundary vertex coordinates of the intersection area of ​​the convex polygons, determining the X-axis and Y-axis coordinate range of the two-dimensional plane containing the intersection area, combining the three-dimensional coordinates of the spatial topology, projecting the three-dimensional space onto the two-dimensional plane, and simultaneously determining the boundary range of the projected configuration; determining the subdivision based on the size of the intersection area. The number of elements is determined, ranging from 10 to 50. The theoretical area of ​​a single element is calculated, which is equal to the intersection area divided by the number of elements. Uniform grid lines are then drawn along the X and Y axes of the intersection area. The spacing between the grid lines is determined based on the theoretical area of ​​a single element, ensuring that the area of ​​the grid element formed after the grid lines intersect in the X and Y axes is consistent with the theoretical area. The portion of the grid lines that exceeds the intersection area of ​​the convex polygon is removed, and the grid elements within the intersection area are retained, which are the independent spatial elements obtained after partitioning. Each spatial element contains a portion of three stress acquisition points, and its vertex coordinates are generated step by step by the partitioning algorithm described above.

[0038] For each spatial cell, the stress values ​​of each endpoint within that cell at the same time point are extracted. Two adjacent endpoints within the cell are considered as two different acquisition endpoints, with their stress values ​​representing the stress data at the same time point for each endpoint. First, the stress difference between the two endpoints is calculated, with the stress difference ranging from 0 MPa to 328 MPa. Then, the spatial distance between the two endpoints is calculated using the three-dimensional coordinate calculation formula: the spatial distance equals the square root of the sum of the squares of the differences in the X-axis, Y-axis, and Z-axis coordinates of the two endpoints, with the spatial distance ranging from 10 mm to 100 mm. The stress difference is divided by the spatial distance to obtain the stress gradient in that direction, with the stress gradient ranging from 0.1 MPa / mm to 32.8 MPa / mm. Multiple stress gradients are calculated for each spatial cell, with at least two directions. The average of these stress gradients is taken as the stress gradient of that spatial cell. The stress gradients of each spatial cell are calculated sequentially, and the stress gradients of all spatial cells are integrated to form a set of cell stress gradients.

[0039] Step 210: Based on the element stress gradient set, calculate the uniformity of stress gradient distribution for all spatial elements in the stress-correlated spatial topology to obtain the stress field uniformity coefficient. Also, based on the element stress gradient set, calculate the dispersion of stress gradient distribution for all spatial elements in the stress-correlated spatial topology to obtain the stress concentration characteristic value. Combine the stress field uniformity coefficient and the stress concentration characteristic value to obtain the shape coefficient. Specifically, this includes calculating the average value of all stress gradients in the element stress gradient set (from 0.1 MPa / mm to 32.8 MPa / mm), and using the stress gradient of all spatial elements... The average value is obtained by dividing the sum of the stress gradients by the number of spatial elements (10 to 50). Then, the difference between the stress gradient of each spatial element and the average value is calculated. The absolute values ​​of all the differences are added together to get the total difference. The total difference is divided by the number of spatial elements, and then the result is subtracted by one to obtain the stress field uniformity coefficient, which ranges from 0.1 to 0.99. The stress field uniformity coefficient is between zero and one. The closer the coefficient is to one, the more uniform the stress gradient distribution is, and vice versa. During the calculation process, it is important to ensure that the calculation of each step is accurate to avoid the distortion of the coefficient due to errors in the calculation of the difference or the average value.

[0040] The stress concentration characteristic value is obtained by calculating the dispersion of stress gradient distribution of all spatial elements in the stress-related spatial topology based on the element stress gradient set. Specifically, the average value of all stress gradients in the element stress gradient set (0.1 MPa / mm to 32.8 MPa / mm) is first calculated. The average value is obtained by dividing the sum of stress gradients of all spatial elements by the number of spatial elements (10 to 50). Then, the square of the difference between the stress gradient of each spatial element and the average value is calculated. All squares are added together to obtain the sum of squares. The variance is obtained by dividing the sum of squares by the number of spatial elements. The square root of the variance is the standard deviation. The stress concentration characteristic value is obtained by dividing the standard deviation by the average value, with a value range of 0.01 to 0.95. The shape coefficient is obtained by calculating the stress field homogeneity coefficient and the stress concentration characteristic value. Specifically, the shape coefficient is obtained by multiplying the stress field homogeneity coefficient (0.1 to 0.99) by the difference between the stress concentration characteristic value (0.01 to 0.95) and the stress field homogeneity coefficient (0.1 to 0.99), with a value range of 0.005 to 0.98.

[0041] This embodiment eliminates the impact of fatigue damage on operating indicators by calculating a correction coefficient based on the cumulative amount of fatigue damage, enabling the operating indicators to truly reflect the actual operating status of the unit and solving the problem that the operating indicators do not take into account structural fatigue and have a large deviation from the actual operating status.

[0042] In a preferred embodiment of the present invention, step 3 involves correcting the modified operating indicators based on the morphological coefficient to obtain the final operating indicators; calculating fuel consumption, nitrogen oxide emissions, and particulate matter emissions based on process parameters to obtain energy consumption indicators and environmental protection indicators; and calculating the final operating indicators, energy consumption indicators, and environmental protection indicators to obtain the energy efficiency value, which may include: Step 301: Calculate the compensation coefficient for the operating indicators based on the morphological coefficient to obtain the morphological compensation coefficient. Then, calculate the final operating indicators by combining the corrected operating indicators with the morphological compensation coefficient. Specifically, this involves: first, clarifying the value characteristics of the morphological coefficient, which reflects the influence of the structural morphology of key load-bearing components on stress distribution, with a value range between 0 and 1; second, calculating the morphological compensation coefficient based on the numerical variation law of this coefficient, combined with the characteristics of the unit's operating indicators, namely the correlation between the numerical changes in speed, power output, and fuel consumption rate and the structural morphology. The specific calculation method is to subtract the morphological coefficient from one and add the preset basic compensation coefficient. The basic compensation coefficient is set based on the rated operating parameters of the diesel generator set. The values ​​of parameters such as speed, power output, and fuel consumption rate included in the corrected operating indicators are extracted. The accuracy of each parameter value is confirmed one by one to ensure that it is consistent with the corrected operating indicator values ​​calculated in step 206. Each parameter value is multiplied by the morphological compensation coefficient. The speed value is multiplied by the morphological compensation coefficient to obtain the corrected speed, the power output value is multiplied by the morphological compensation coefficient to obtain the corrected power output, and the fuel consumption rate value is multiplied by the morphological compensation coefficient to obtain the corrected fuel consumption rate. Finally, the corrected parameter values ​​are integrated to form the complete final operating indicators.

[0043] Step 302: Based on the process parameters, extract fuel consumption rate data and runtime data, calculate fuel consumption, and obtain energy consumption indicators; based on the process parameters, extract exhaust temperature data, air-fuel ratio data, and combustion pressure data, calculate nitrogen oxide generation, and obtain nitrogen oxide emissions; based on the process parameters, extract exhaust smoke opacity data and particulate matter concentration data, and calculate particulate matter emissions; weightedly fuse nitrogen oxide emissions and particulate matter emissions to obtain environmental protection indicators, specifically including: extracting fuel consumption rate data and runtime data from the process parameters, where fuel consumption rate data is the amount of fuel consumed by the diesel generator set per unit time, and runtime data is the length of time the unit operates continuously; multiplying the fuel consumption rate value by the runtime value, i.e., fuel consumption rate multiplied by runtime, the result is fuel consumption, and this fuel consumption is used as the energy consumption indicator.

[0044] Environmental indicators are calculated, primarily including nitrogen oxide (NOx) emissions and particulate matter (PM) emissions. A comprehensive environmental indicator is obtained by integrating the emissions of these two pollutants. Specifically, NOx emission calculation involves extracting exhaust temperature, air-fuel ratio, and combustion pressure data from process parameters. First, the NOx formation impact factors corresponding to these three data points are calculated separately. Higher exhaust temperature results in a larger NOx formation impact factor, while the impact factor is minimized when the air-fuel ratio is within a reasonable range. Higher combustion pressure results in a larger impact factor. The calculation method is as follows: exhaust temperature data is divided by the unit's rated exhaust temperature to obtain the exhaust temperature impact factor; the absolute value of the difference between the air-fuel ratio data and the rated air-fuel ratio is divided by the rated air-fuel ratio to obtain the air-fuel ratio impact factor; and combustion pressure... The combustion pressure influence factor is obtained by dividing the force data by the rated combustion pressure. Then, each influence factor is multiplied by its corresponding preset weight. The preset weight of the exhaust temperature influence factor ranges from 0.5 to 0.7, the air-fuel ratio influence factor ranges from 0.2 to 0.3, and the combustion pressure influence factor ranges from 0.1 to 0.2. The sum of the three preset weights is one, with the exhaust temperature influence factor having the highest weight, followed by the air-fuel ratio influence factor, and the combustion pressure influence factor having the lowest weight. The three weighted influence factors are added together to obtain the total influence factor. The total influence factor is then multiplied by the unit's rated nitrogen oxide emissions to obtain the nitrogen oxide generation, which is used as the nitrogen oxide emissions.

[0045] The calculation of particulate matter emissions specifically involves extracting exhaust smoke opacity data and particulate matter concentration data from process parameters. Exhaust smoke opacity data reflects the concentration of smoke in the exhaust, while particulate matter concentration data reflects the content of particulate matter in the exhaust. The exhaust smoke opacity value and the particulate matter concentration value are multiplied together to obtain the particulate matter emission amount. The integration of environmental indicators specifically involves weighting and integrating nitrogen oxide emissions and particulate matter emissions according to a preset weighting rule. This preset weighting rule assigns corresponding weight coefficients based on the degree of impact of the two pollutants on the unit's operating environment and component wear. This is combined with the operating characteristics of the diesel generator set, considering the impact of nitrogen oxides on the unit's exhaust gas treatment system and surrounding environment. The impact of particulate matter on the surrounding environment is greater than that on nitrogen oxides. Therefore, nitrogen oxide emissions have a higher weight than particulate matter emissions. The preset weight for nitrogen oxide emissions ranges from 0.6 to 0.8, and the preset weight for particulate matter emissions ranges from 0.2 to 0.4. The sum of the two preset weights is one. The core of the weight allocation rule is to prioritize pollutants that have a greater impact on unit operation, ensuring that the environmental indicators can accurately reflect the comprehensive impact of the unit's pollutant emissions on itself and the surrounding environment. First, nitrogen oxide emissions are multiplied by their corresponding preset weight coefficients, and then particulate matter emissions are multiplied by their corresponding preset weight coefficients. The results of the two multiplications are then added together. The environmental indicators are obtained through this weighted fusion method.

[0046] Step 303: Normalize the final operating indicators, energy consumption indicators, and environmental protection indicators to obtain normalized operating indicators, normalized energy consumption indicators, and normalized environmental protection indicators. Based on preset weighting coefficients, weighted summation of the normalized operating indicators, normalized energy consumption indicators, and normalized environmental protection indicators yields the energy efficiency value. Specifically, this includes: determining the numerical range of the three types of indicators; clarifying the numerical ranges of the final operating indicators, energy consumption indicators, and environmental protection indicators by analyzing historical operating data and rated operating parameters of the diesel generator set; and determining the numerical range of the final operating indicators based on the corrected value range of the operating indicators combined with morphological compensation correction results. If the results are determined, the numerical range of energy consumption indicators is determined based on the fuel consumption range under different loads of the unit, and the numerical range of environmental protection indicators is determined based on the unit's preset emission control threshold and the unit's actual emission data. The specific calculation method for normalization is as follows: subtract the minimum value of the corresponding indicator's value range from the actual value of each indicator to obtain the indicator deviation value, and then divide the deviation value by the difference between the maximum and minimum values ​​of the corresponding indicator's value range to obtain the normalized indicator value. Through this calculation method, the values ​​of the three types of indicators are uniformly converted to the range of 0 to 1, respectively, to obtain the normalized operation indicators, normalized energy consumption indicators, and normalized environmental protection indicators.

[0047] The preset weighting coefficients for normalized operation indicators, normalized energy consumption indicators, and normalized environmental protection indicators are determined. The preset weighting allocation rule specifically refers to assigning weighting coefficients based on the degree of impact of the three types of indicators on the overall operating efficiency of the diesel generator set. Unit operating stability is the core requirement; therefore, the normalized operation indicators have the greatest impact, followed by environmental performance, while energy consumption level has a relatively smallest impact. The weights are allocated accordingly, with the normalized operation indicators having the highest preset weight, ranging from 0.4 to 0.6; the normalized environmental protection indicators having the second highest preset weight, ranging from 0.25 to 0.35; and the normalized energy consumption indicators having the lowest preset weight. The value ranges from 0.1 to 0.2. The sum of the preset weight coefficients of the three types of indicators is one. The weight allocation rules are set in line with the unit operation priority, giving priority to ensuring operational stability while taking into account environmental protection and energy conservation requirements. The calculation process is as follows: multiply the value of the normalized operation indicator by its corresponding preset weight coefficient to obtain the weighted value of the operation indicator; multiply the value of the normalized energy consumption indicator by its corresponding preset weight coefficient to obtain the weighted value of the energy consumption indicator; multiply the value of the normalized environmental protection indicator by its corresponding preset weight coefficient to obtain the weighted value of the environmental protection indicator; and then add the three weighted values ​​together to obtain the energy efficiency value.

[0048] This embodiment compensates and corrects the operating indicators through morphological coefficients, so that the final operating indicators can fit the actual structural state of the key load-bearing components of the diesel generator set, eliminating the interference of structural morphology on the operating indicators. At the same time, based on process parameters, energy consumption and environmental protection indicators are accurately calculated, and energy efficiency values ​​are generated through normalization and weighted summation, realizing a comprehensive quantitative evaluation of the unit's operation, energy consumption and environmental performance.

[0049] In a preferred embodiment of the present invention, step 4, performing multi-objective optimization based on the energy efficiency value to obtain a target scheme; and adjusting the power and voltage frequency based on the target scheme, may include: Step 401: Based on the energy efficiency value, and combined with the final operating indicators, energy consumption indicators, and environmental protection indicators, determine the objective function and constraints to obtain a multi-objective solution model. Calculate the multi-objective solution model to generate a candidate solution set. Select one solution from the candidate solution set to obtain the target solution. Specifically, this includes: determining the objective function and clarifying the optimization direction of the objective function. The objective function takes maximizing energy efficiency value as its core optimization objective, while also considering the stability of the final operating indicators, the reasonable controllability of energy consumption indicators, and the compliance of environmental protection indicators. Integrate these optimization objectives to determine the core content of the objective function. The construction process of the objective function is as follows: using the energy efficiency value as the core variable, and using the fluctuation values ​​of the final operating indicators, energy consumption indicators, and environmental protection indicators as auxiliary variables, construct a multi-variable objective function, whose expression is maxF=Q- × - ×C- ×L, where F is the objective function value and Q is the energy efficiency value. The final operational indicator fluctuation values ​​are: C represents the energy consumption indicator value, and L represents the environmental protection indicator value. The weighting coefficient for the final operating index fluctuation value. The weighting coefficient for energy consumption index values. The three weighting factors are used to assign weights to the environmental indicators, with the sum of the three weighting factors equal to one. The default value range is 0.2 to 0.3. The default value range is 0.1 to 0.2. The preset value range is 0.25 to 0.35, ensuring that the objective function can simultaneously take into account multiple optimization directions and match the unit's operating priority.

[0050] The constraints are defined, covering the operating parameter range of the diesel generator set, component mechanical performance limitations, pollutant emission control thresholds, power output adjustment range, and rated voltage and frequency fluctuation range. All constraints are based on the actual operating specifications and hardware performance of the diesel generator set. Specifically, these include speed constraints: the speed must be maintained within the allowable fluctuation range of the rated speed, preset to ±1% to ±2% of the rated speed; the actual speed of the unit must fluctuate within this range and must not exceed the upper or lower limits of the rated speed fluctuation range; power constraints: the power output must be within the rated power range of the unit, ranging from 20% to 100% of the rated power; the actual power output of the unit must not be lower than 20% of the rated power or exceed 100% of the rated power; and voltage constraints: the output voltage must be within the rated... Within the permissible voltage fluctuation range, which is preset to ±0.5% to ±1% of the rated voltage, the actual output voltage of the unit must be controlled within this fluctuation range to ensure stable voltage output. Frequency constraints apply, meaning the output frequency must be maintained within the permissible fluctuation range of the rated frequency, preset to ±0.2% to ±0.5% of the rated frequency. The actual output frequency of the unit must meet this fluctuation requirement to ensure power supply quality. Mechanical constraints stipulate that the actual stress value of key load-bearing components must not exceed the rated stress limit. The rated stress limit is determined based on the component material and structural strength, with a range of 150MPa to 250MPa, to prevent component damage due to excessive stress. Emission constraints further stipulate that nitrogen oxide emissions and particulate matter emissions must not exceed the unit's preset emission control thresholds, with the preset nitrogen oxide emission threshold ranging from 50mg / m³. 3 Up to 100 mg / m 3 The preset emission control threshold for particulate matter is set at 10 mg / m³. 3 Up to 20 mg / m 3 The actual emissions of both types of pollutants must be controlled within the corresponding thresholds. All constraints are clearly defined in the form of inequalities to ensure that the model calculation process does not exceed the safe and compliant range of unit operation.

[0051] By integrating the objective function and constraints, a multi-objective solution model is constructed. The model construction process must consider the operating characteristics of the diesel generator set, employing a multi-objective optimization calculation method adapted to the unit's operating scenario as the core solution algorithm. The objective function serves as the optimization core, and all constraints are used as boundary conditions for the model calculation. The model's input and output variables are clearly defined. Input variables include final operating indicators, energy consumption indicators, environmental indicators, and various constraint parameters; output variables are the adapted parameter combinations (including preset values ​​for power, voltage, and frequency) that meet the constraints. The model training process involves collecting operating data from the diesel generator set over the past 6 to 12 months, covering different load conditions such as light, medium, and heavy loads. This includes final operating indicators, energy consumption indicators, environmental indicators, energy efficiency values, and corresponding constraint parameters under different loads. At least 1000 sets of valid data are collected. The data is divided into training and testing sets in a 7:3 ratio. The training set is used for model parameter calibration, and the testing set is used for model performance verification. During training, the model parameters are initialized first, and the iteration step size is set to 0.01 to 0.05, and the number of iterations is 100 to 200. By adjusting the weight parameters in the model, the deviation between the energy efficiency value calculated by the model and the actual operating energy efficiency value is minimized. The calibration is repeated iteratively until the model calculation error is controlled within the preset range. The preset error threshold range is ±3% to ±5%, that is, the deviation between the energy efficiency value calculated by the model and the actual operating energy efficiency value of the unit does not exceed ±3% to ±5%. The model training is then completed. The trained model can accurately adapt to the operating characteristics of the unit and ensure the accuracy of the calculation results. The accuracy rate of the test set verification must reach more than 95%, that is, the proportion of the number of samples in the test set whose calculation results meet the requirements is not less than 95% of the total number of samples in the test set.

[0052] The trained multi-objective solution model is calculated by iterating through all parameter combinations that meet all constraints. Each parameter combination corresponds to a set of final operating indicators, energy consumption indicators, and environmental protection indicators. The objective function value corresponding to each parameter combination is calculated using the objective function expression. The meaning of each parameter is the same as before. Based on the magnitude of the objective function value, multiple sets of parameter combinations that meet the requirements are selected, i.e., the objective function value is close to the maximum value and all parameters meet the constraints. The number of selections is preset to 10 to 20 sets, forming a candidate solution set. From the candidate solution set, the parameter combination whose objective function value best matches the expectation is selected, and the corresponding parameter combination is the target solution.

[0053] Step 402: Extract the desired power output value, desired voltage output value, and desired frequency output value according to the target scheme to obtain the desired operating state vector. Collect the position and attitude of the current speed regulation component and excitation component of the diesel generator set to obtain the current operating state vector. Establish a mapping relationship from control quantity to operating state based on the desired operating state vector and the current operating state vector to obtain the kinematic model. Specifically, this includes: constructing the operating state vector, extracting the desired power output value, desired voltage output value, and desired frequency output value from the target scheme, verifying the accuracy of the three values ​​one by one to ensure consistency with the parameters in the target scheme, and integrating the three values ​​in a preset order of power, voltage, and frequency to form the desired operating state vector. This vector can accurately represent the ideal operating state that the diesel generator set needs to achieve. Each element in the vector corresponds to a core operating parameter, which is convenient for subsequent model calculation and state comparison.

[0054] The current position and attitude data of the speed regulating component and excitation component of the diesel generator set are collected. Position sensors and attitude sensors deployed on the two types of components are used to collect the current position and attitude data of the components in real time. The sampling frequency is preset to 10Hz to 20Hz. The position data includes the adjustment stroke of the speed regulating component and the excitation angle of the excitation component. The attitude data includes the tilt angle of the speed regulating component and the installation attitude of the excitation component. The collected data is processed and abnormal data that deviates from the normal range by more than ±10% are removed. The data is then integrated in the order corresponding to the expected operating state vector to form the current operating state vector. This vector can accurately reflect the current actual operating state of the unit and provide basic data for subsequent model solving and control quantity calculation.

[0055] A mapping relationship from control variables to operating states was established, and a kinematic model was constructed to clarify the logical relationship between control variables and operating states. Control variables mainly include speed control component adjustment (unit: °) and excitation component adjustment (unit: A). The speed control component adjustment mainly affects the unit's power output and speed, while the excitation component adjustment mainly affects the unit's voltage output and frequency. Operating states mainly include power output, voltage output, and frequency output. Through unit operation tests, different control variable values ​​were changed. The speed control component adjustment ranged from 0° to 10°, and the excitation component adjustment ranged from 5A to 20A, with adjustment steps of 0.5° and 1A respectively. Corresponding operating state change data were recorded, collecting no fewer than 500 sets of test data. The influence of changes in each control variable on the operating state was analyzed to clarify the one-to-one correspondence between them. For example, increasing the speed control component adjustment will correspondingly increase power output and speed, while increasing the excitation component adjustment will correspondingly adjust voltage output and frequency.

[0056] Based on this mapping relationship, a kinematic model is constructed. The model uses the control quantity as input and the operating state as output. Combining experimental correlation data, a linear correlation equation between the control quantity and the operating state is established, clarifying the proportional relationship between changes in the control quantity and changes in the operating state. The specific expression is as follows: The correlation equation between the power change and the speed regulation component adjustment is ΔP = The equation relating the voltage change to the excitation component adjustment is ΔU = ×Δθ. The correlation equation between the frequency change and the adjustment of the excitation components is Δf = ×ΔI. The equation relating the change in rotational speed to the adjustment amount of the speed regulating component is Δn = ×ΔI. ×Δθ; where ΔP is the power change and Δθ is the adjustment amount of the speed regulating component. Here, ΔU represents the correlation coefficient between power and the adjustment amount of the speed control component, ΔI represents the voltage change, and ΔI represents the adjustment amount of the excitation component. Δf is the correlation coefficient between voltage and the adjustment amount of the excitation component, and Δf is the frequency change. Here, Δn is the correlation coefficient between frequency and the adjustment amount of the excitation component, and Δn is the change in rotational speed. This is the correlation coefficient between the rotational speed and the adjustment amount of the speed regulating component. , , , All values ​​were obtained by fitting experimental data, ranging from 0.8 to 1.2. The model incorporates the unit's mechanical characteristic parameters, including moment of inertia and damping coefficient, with the moment of inertia preset to a range of 10 kg·m. 2 Up to 20 kg·m 2 The damping coefficient is preset to a range of 0.5 N·s / m to 1.5 N·s / m to ensure that the model can accurately describe the mathematical relationship between changes in control quantities and changes in unit operating status. The model training process involves dividing 500 sets of experimental data on control quantities and corresponding operating states into a training set and a validation set in a 6:4 ratio. The training set data is input into the model, and the correlation coefficient in the model is iteratively adjusted to minimize the deviation between the model output operating status value and the actual experimental data. The deviation threshold is preset to ±2%. The accuracy of the model is verified using validation set data. If the deviation exceeds the preset range, the correlation coefficient is adjusted again, and the process is repeated until the model output deviation is controlled within a reasonable range, thus completing the model training.

[0057] Step 403: The kinematic model is solved in reverse to obtain initial values ​​of the analytical control variables; these initial values ​​are then used as the starting point for iteration to obtain iterative control variables; the iterative control variables are input into the kinematic model for calculation to obtain forward calculation results; the deviation between the forward calculation results and the desired running state vector is used to determine whether the convergence condition is met. If not, the iterative control variables are further modified until the convergence condition is met, resulting in a set of control variables. Specifically, this includes: solving the kinematic model in reverse to obtain initial values ​​of the analytical control variables. The core of the inverse solution is to determine the initial values ​​of the analytical control variables based on the deviation between the desired running state and the desired running state vector. The deviation of the current operating state is used to derive the control quantity values ​​that can eliminate the deviation. Specifically, the desired operating state vector and the current operating state vector are input into the kinematic model, and the deviation values ​​between the two are calculated, including power deviation, voltage deviation, and frequency deviation. Combining the correlation of the model, the initial values ​​of the analytical control quantities that can make the unit approach the desired state from the current state are derived in reverse. These include the initial values ​​of the speed regulation component adjustment and the excitation component adjustment. These initial values ​​serve as the initial values ​​for iterative calculations and can initially make the unit approach the desired state, but there is still a certain deviation, which needs to be further corrected.

[0058] The iterative control quantity is obtained by correcting the initial value of the analytical control quantity as the starting point of the iteration. Specifically, the initial value is adjusted based on a preset correction rule. The correction rule is formulated according to the operating characteristics of the unit and mainly combines the sensitivity of the influence of the control quantity change on the operating state. The higher the sensitivity, the smaller the correction amplitude, so as to avoid the unit operation being unstable due to excessive adjustment of the control quantity. The preset value range of the correction coefficient is 0.1 to 0.3. The correction process is as follows: first, the initial value of the analytical control quantity is input into the trained kinematic model to calculate the corresponding predicted value of the operating state. The predicted value is compared with the expected operating state vector to obtain the prediction deviation. According to the magnitude and direction of the prediction deviation, the initial value of the analytical control quantity is adjusted. The adjusted value is the iterative control quantity.

[0059] The iterative control input is used to perform forward calculations on the trained kinematic model, yielding the forward calculation results, which are the unit's operating state values ​​under the influence of the iterative control input, including power output, voltage output, and frequency output. After the calculation, the forward calculation results are compared with the desired operating state vector to determine if the convergence condition is met. The convergence condition is set based on the unit's operational stability requirements. Specifically, it involves calculating the differences between the forward calculation results and the parameters of the desired operating state, including power deviation, voltage deviation, and frequency deviation. The absolute values ​​of all differences are summed to obtain the total deviation value, which is then compared with a preset convergence threshold. The convergence threshold is based on the unit's rated operating fluctuation range. The range is set to 0.05 to 0.1 to ensure stable unit operation. If the total deviation value is greater than the convergence threshold, it means that the current iterative control quantity has not met the requirements and needs to be corrected. When correcting, the correction range is adjusted according to the size of the total deviation value. The larger the total deviation value, the larger the correction range. The correction coefficient can be dynamically adjusted within the range of 0.1 to 0.3. The steps of control quantity correction, model forward calculation and deviation judgment are repeated. After each correction, the forward calculation result and the total deviation value are recalculated. The number of iterations is set to 5 to 10 times until the total deviation value is less than or equal to the convergence threshold and the convergence condition is met. The iterative control quantity obtained at this time is the set of control quantities that meets the requirements.

[0060] Step 404: Based on the control quantity set, extract the control quantity corresponding to power regulation to obtain a power regulation command and transmit it to the speed control component of the diesel generator set for power regulation; based on the control quantity set, extract the control quantity corresponding to voltage regulation and the control quantity corresponding to frequency regulation to obtain a voltage regulation command and a frequency regulation command and transmit them to the excitation component of the diesel generator set for voltage and frequency regulation. Specifically, this includes: generating and executing the power regulation command; extracting the speed control component adjustment value corresponding to power regulation from the control quantity set, with the adjustment accuracy preset to 0.1°; generating a power regulation command based on the value; clarifying the adjustment direction and amplitude of the speed control component; transmitting the command to the speed control component through the generator set control bus, with the transmission rate preset to 9600bps; after receiving the command, the speed control component executes the adjustment action according to the command requirements, adjusting the fuel supply, with the adjustment step size preset to 0.01L / min, thereby adjusting the generator set power output; monitoring power changes in real time until the desired power output value is reached; and controlling the power regulation error within ±1%.

[0061] The system generates and executes voltage and frequency regulation commands. It extracts the corresponding excitation component adjustment values ​​from the control quantity set, with a preset adjustment accuracy of 0.1A. Based on the voltage adjustment value, it generates a voltage regulation command, specifying the excitation voltage adjustment range for the excitation component. Similarly, based on the frequency regulation value, it generates a frequency regulation command, specifying the excitation frequency adjustment range for the excitation component. Both commands are synchronously transmitted to the excitation component via the control bus. Upon receiving the commands, the excitation component synchronously executes the voltage and frequency regulation actions, adjusting the excitation current and excitation frequency. The preset excitation current adjustment step size is 0.05A, and the preset excitation frequency adjustment step size is 0.1Hz, thereby adjusting the unit's output voltage. The system monitors the changes in both voltage and frequency in real time until the desired values ​​are reached. The voltage regulation error is controlled within ±0.5%, and the frequency regulation error is controlled within ±0.2%. Throughout the adjustment process, the system collects the unit's operating status data in real time, with the sampling frequency maintained between 10Hz and 20Hz. The system compares the current operating status with the desired operating status. If the deviation exceeds the preset thresholds (power ±1%, voltage ±0.5%, frequency ±0.2%), the system promptly adjusts the control quantity set and adjustment commands to ensure that the diesel generator set's operating status eventually approaches the desired state corresponding to the target scheme. This achieves precise regulation of power, voltage, and frequency, ensuring that the unit operates in a state of good energy efficiency, compliance with emission standards, and stable operation.

[0062] In this embodiment, by establishing a kinematic model and completing inverse solving and iterative correction, a precise set of control quantities is obtained, and finally, corresponding adjustment commands are generated and power, voltage and frequency adjustments are executed. The whole process fully considers the constraints of unit operation and the needs of multi-objective optimization.

[0063] like Figure 2 As shown, embodiments of the present invention also provide a diesel generator energy efficiency optimization and emission control system, including: The parameter acquisition module is used to collect analog parameters, switch status values ​​and pulse values ​​of the diesel generator set as process parameters during operation. The calculation module is used to extract dynamic stress data of key load-bearing components based on process parameters, and obtain the cumulative fatigue damage through cycle counting and cumulative damage calculation; according to process parameters, it extracts speed values, power output values ​​and fuel consumption rate values ​​to obtain operating indicators, and corrects the operating indicators based on the cumulative fatigue damage to obtain the corrected operating indicators; three stress acquisition points are set on the key load-bearing components, and a spatial topology is constructed with the three stress acquisition points as endpoints, and the spatial topology is partitioned and calculated to obtain the shape coefficient; The correction module is used to correct the modified operating indicators based on the morphological coefficient to obtain the final operating indicators; based on the process parameters, it calculates the fuel consumption, nitrogen oxide emissions and particulate matter emissions respectively to obtain the energy consumption indicators and environmental protection indicators; and calculates the final operating indicators, energy consumption indicators and environmental protection indicators to obtain the energy efficiency value. The adjustment module is used to perform multi-objective optimization based on the energy efficiency value to obtain the target scheme; and to adjust the power and voltage frequency according to the target scheme.

[0064] It should be noted that this system is a system corresponding to the above method. All implementation methods in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.

[0065] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0066] Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0067] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for optimizing the energy efficiency and controlling emissions of diesel generators, applied to the control of diesel engines, characterized in that, The method includes: Step 1: Collect analog parameters, switch status values, and pulse values ​​of the diesel generator set during operation as process parameters; Step 2: Based on process parameters, extract dynamic stress data of key load-bearing components, and obtain the cumulative fatigue damage amount through cycle counting and cumulative damage calculation; according to process parameters, extract speed values, power output values ​​and fuel consumption rate values ​​to obtain operating indicators, and correct the operating indicators based on the cumulative fatigue damage amount to obtain the corrected operating indicators; set three stress acquisition points on the key load-bearing components, construct a spatial topology configuration with the three stress acquisition points as endpoints, and perform subdivision calculation on the spatial topology configuration to obtain the shape coefficient; Step 3: Correct the modified operating indicators based on the morphological coefficient to obtain the final operating indicators; calculate the fuel consumption, nitrogen oxide emissions and particulate matter emissions based on the process parameters to obtain the energy consumption indicators and environmental protection indicators; calculate the final operating indicators, energy consumption indicators and environmental protection indicators to obtain the energy efficiency value. Step 4: Based on the energy efficiency value, perform multi-objective optimization to obtain the target scheme; based on the target scheme, adjust the power and voltage frequency.

2. The method for optimizing the energy efficiency and controlling emissions of a diesel generator according to claim 1, characterized in that, The analog parameters, switch status values, and pulse values ​​of the diesel generator set during operation are collected as process parameters, including: The system collects continuously changing physical quantities of the diesel generator set during operation to obtain analog signals; performs analog-to-digital conversion on the analog signals to obtain digitized analog parameters; collects on / off status signals of various devices in the diesel generator set to obtain switch signals; performs level status identification and filtering on the switch signals to obtain switch status values; collects rotational speed pulse signals of rotating parts in the diesel generator set to obtain the original pulse sequence; and performs period measurement and frequency calculation on the original pulse sequence to obtain pulse quantity values. The process parameters are obtained by fusing and synchronizing the digitized analog parameters, switch status values, and pulse values.

3. The method for optimizing the energy efficiency and controlling emissions of a diesel generator according to claim 2, characterized in that, Based on process parameters, dynamic stress data of key load-bearing components are extracted. Through cycle counting and cumulative damage calculation, the cumulative fatigue damage is obtained, including: Based on the process parameters, the strain response signals collected on the key load-bearing components are extracted to obtain the original strain time series data; the original strain time series data is preprocessed to obtain the preprocessed strain time series data; and the elastic modulus parameters are obtained based on the material properties of the key load-bearing components. The preprocessed strain time series data and elastic modulus parameters are used to calculate dynamic stress time series data; the dynamic stress time series data are detected to obtain stress extremum sequence; each stress cycle is extracted from the stress extremum sequence to obtain stress cycle set; Calculate the amplitude and mean of each stress cycle in the stress cycle set, obtain the data on the relationship between stress and cycle number of key load-bearing component materials, and obtain material stress cycle characteristic data; determine the cycle number limit based on the amplitude of each stress cycle and the material stress cycle characteristic data; Based on the amplitude and mean of each stress cycle and the cycle number limit, the damage contribution value of each stress cycle is calculated; the damage contribution values ​​of each stress cycle are summed to obtain the cumulative fatigue damage.

4. The method for optimizing the energy efficiency and controlling emissions of a diesel generator according to claim 3, characterized in that, Based on process parameters, operating indicators are obtained by extracting speed, power output, and fuel consumption rate values. These operating indicators are then corrected based on accumulated fatigue damage, resulting in revised operating indicators, including: Based on the process parameters, the rotational speed pulse signals of the rotating parts of the diesel generator set are extracted to obtain the raw rotational speed data; the raw rotational speed data is then subjected to periodic measurement and frequency calculation to obtain the rotational speed value; based on the process parameters, the voltage and current signals at the output terminals of the diesel generator set are extracted, and the power output value is calculated; based on the process parameters, the flow rate signal on the fuel supply pipeline of the diesel generator set is extracted to obtain the raw fuel flow rate data; the raw fuel flow rate data is then calculated to obtain the fuel consumption rate value. The operating index is obtained by combining the speed value, power output value and fuel consumption rate value; the correction coefficient is calculated based on the cumulative fatigue damage, and the operating index correction coefficient is obtained; the operating index and the operating index correction coefficient are calculated to obtain the corrected operating index.

5. The method for optimizing the energy efficiency and controlling emissions of a diesel generator according to claim 4, characterized in that, Three stress acquisition points are set on the key load-bearing components. A spatial topology is constructed using these three stress acquisition points as endpoints. The spatial topology is then subdivided and calculated to obtain shape factors, including: Three stress acquisition points are set on the key load-bearing components. The three stress acquisition points are located at the center of the main load-bearing area of ​​the key load-bearing components, the connection and transition area between the main load-bearing area and the auxiliary support structure, and the end constraint area farthest from the main load-bearing area. Dynamic stress data are collected according to the three stress acquisition points to obtain the first stress time series data, the second stress time series data and the third stress time series data. A spatial topology is constructed using three stress acquisition sites as endpoints, and the three stress time series data are mapped to the corresponding endpoints of the spatial topology to obtain a stress-correlated spatial topology. The stress-related spatial topology is divided into multiple spatial elements. The stress gradient is calculated based on the stress values ​​at each endpoint within each spatial element to obtain the set of element stress gradients. Based on the set of element stress gradients, the uniformity of stress gradient distribution of all spatial elements in the stress-correlated spatial topology is calculated to obtain the stress field uniformity coefficient. Based on the set of element stress gradients, the dispersion of stress gradient distribution of all spatial elements in the stress-correlated spatial topology is calculated to obtain the stress concentration characteristic value. The stress field uniformity coefficient and the stress concentration characteristic value are then used to calculate the shape coefficient.

6. The method for optimizing the energy efficiency and controlling emissions of a diesel generator according to claim 5, characterized in that, The modified operating indicators are corrected based on the morphological coefficient to obtain the final operating indicators; fuel consumption, nitrogen oxide emissions and particulate matter emissions are calculated based on the process parameters to obtain energy consumption indicators and environmental protection indicators respectively. The final operating indicators, energy consumption indicators, and environmental indicators are calculated to obtain the energy efficiency value, including: Based on the morphological coefficient, the compensation coefficient of the operating index is calculated to obtain the morphological compensation coefficient; the corrected operating index is calculated with the morphological compensation coefficient to obtain the final operating index. Based on process parameters, fuel consumption rate data and runtime data are extracted to calculate fuel consumption and obtain energy consumption indicators; based on process parameters, exhaust temperature data, air-fuel ratio data, and combustion pressure data are extracted to calculate nitrogen oxide generation and obtain nitrogen oxide emissions; based on process parameters, exhaust smoke opacity data and particulate matter concentration data are extracted to calculate particulate matter emissions; nitrogen oxide emissions and particulate matter emissions are weighted and fused to obtain environmental protection indicators. The final operating indicators, energy consumption indicators, and environmental protection indicators are normalized to obtain normalized operating indicators, normalized energy consumption indicators, and normalized environmental protection indicators. Based on preset weighting coefficients, the normalized operating indicators, normalized energy consumption indicators, and normalized environmental protection indicators are weighted and summed to obtain the energy efficiency value.

7. The method for optimizing the energy efficiency and controlling emissions of a diesel generator according to claim 6, characterized in that, Based on the energy efficiency value, multi-objective optimization is performed to obtain the target solution; Based on the target scheme, power and voltage frequency adjustments are performed, including: Based on the energy efficiency value, the objective function and constraints are determined in combination with the final operation indicators, energy consumption indicators and environmental protection indicators, and a multi-objective solution model is obtained. The multi-objective solution model is calculated to generate a set of candidate solutions. One solution is selected from the set of candidate solutions to obtain the target solution. Based on the target scheme, the expected power output value, expected voltage output value, and expected frequency output value are extracted to obtain the expected operating state vector. The position and attitude of the current speed regulating component and excitation component of the diesel generator set are collected to obtain the current operating state vector. Based on the expected operating state vector and the current operating state vector, a mapping relationship from control quantity to operating state is established to obtain the kinematic model. The kinematic model is solved in reverse to obtain the initial value of the analytical control quantity; the initial value of the analytical control quantity is used as the starting point for iteration to obtain the iterative control quantity; the iterative control quantity is input into the kinematic model for calculation to obtain the forward calculation result; the deviation between the forward calculation result and the desired running state vector is used to determine whether the convergence condition is met. If not, the iterative control quantity is further modified until the convergence condition is met, and the set of control quantities is obtained. Based on the set of control quantities, the control quantity corresponding to power regulation is extracted, the power regulation command is obtained and transmitted to the speed control component of the diesel generator set for power regulation; based on the set of control quantities, the control quantity corresponding to voltage regulation and the control quantity corresponding to frequency regulation are extracted, the voltage regulation command and the frequency regulation command are obtained and transmitted to the excitation component of the diesel generator set for voltage and frequency regulation.

8. A diesel generator energy efficiency optimization and emission control system, wherein the system implements the method as described in any one of claims 1 to 7, characterized in that, include: The parameter acquisition module is used to collect analog parameters, switch status values ​​and pulse values ​​of the diesel generator set as process parameters during operation. The calculation module is used to extract dynamic stress data of key load-bearing components based on process parameters, and obtain the cumulative fatigue damage through cycle counting and cumulative damage calculation. Based on the process parameters, the speed, power output and fuel consumption rate values ​​are extracted to obtain the operating indicators. The operating indicators are then corrected based on the cumulative fatigue damage to obtain the corrected operating indicators. Three stress acquisition points are set on the key load-bearing components. A spatial topology is constructed with the three stress acquisition points as endpoints. The spatial topology is then subdivided and calculated to obtain the shape coefficients. The correction module is used to correct the modified operating indicators based on the morphological coefficient to obtain the final operating indicators; based on the process parameters, fuel consumption, nitrogen oxide emissions and particulate matter emissions are calculated to obtain energy consumption indicators and environmental protection indicators respectively. The final operating indicators, energy consumption indicators, and environmental protection indicators are calculated to obtain the energy efficiency value; The adjustment module is used to perform multi-objective optimization based on the energy efficiency value to obtain the target solution; According to the target scheme, power and voltage frequency are adjusted.

9. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images