Control method, device and computer equipment for power generation equipment

Abstract

This specification relates to the field of new energy power generation technology, and in particular to a control method, device and computer equipment for power generation equipment. The control method for power generation equipment includes: constructing an equipment fault development model based on the historical operation data of the power generation equipment; constructing an objective function based on the equipment fault development model, wherein the objective function represents the efficiency loss of the wind turbine; obtaining the maintenance constraints of the power generation equipment; determining the maintenance strategy of the power generation equipment based on the maintenance constraints and the objective function; and controlling the power generation equipment to enter the maintenance state based on the determined maintenance strategy. The embodiments of this specification can be combined with the fault development law of the power generation equipment to perform precise maintenance control on the power generation equipment and reduce the efficiency loss caused by the maintenance.

Description

Technical Field

[0001] The present invention relates to the field of renewable energy power generation technology, and in particular to a control method, device and computer equipment for power generation equipment. Background Art

[0002] New energy power generation can convert renewable energy in nature into electrical energy. These renewable energy sources can include solar energy, wind energy, geothermal energy, biomass energy, ocean energy, etc. New energy power generation equipment can provide electrical energy for power supply systems, distribution systems, electric energy storage systems, etc. Due to factors such as production environment, operation mode, equipment loss, etc., new energy power generation equipment may have defects that affect the normal operation of the equipment, and under the continuous action of external stress and internal heat, functional disorders may occur and eventually develop into actual failures. In recent years, with the gradual aging of new energy power generation equipment, the probability of its failure has continued to increase, resulting in an increase in efficiency loss year by year. Therefore, it is necessary to study the control method of new energy power generation equipment to overhaul new energy power generation equipment and reduce the impact on power supply systems, distribution systems, electric energy storage systems, etc.

[0003] In the related art, the operation of the new energy power generation equipment can be controlled according to the maintenance plan of the upper power grid or weather data to achieve the maintenance of the new energy power generation equipment. For example, the maintenance plan of the upper power grid can be obtained, and the new energy power generation equipment can be controlled according to the maintenance plan of the upper power grid to achieve the maintenance of the new energy power generation equipment. For another example, the new energy power generation equipment can be controlled to enter the maintenance state on the date with less wind power to achieve the maintenance of the new energy power generation equipment.

[0004] The above-mentioned related technologies are relatively simple in terms of the maintenance and control of the new energy power generation equipment, and are unable to perform accurate maintenance and control of the new energy power generation equipment. Summary of the invention

[0005] The embodiments of this specification provide a control method, device and computer equipment for power generation equipment, which are used to perform precise maintenance control on the power generation equipment in combination with the fault development law of the power generation equipment.

[0006] The embodiment of this specification provides a control method for power generation equipment, including:

[0007] Build equipment failure development model based on historical operation data of power generation equipment;

[0008] According to the equipment failure development model, an objective function is constructed, wherein the objective function represents the efficiency loss of the wind turbine generator set;

[0009] Obtain maintenance constraints of power generation equipment;

[0010] Determine the maintenance strategy of power generation equipment according to maintenance constraints and objective functions;

[0011] According to the determined maintenance strategy, the power generation equipment is controlled to enter the maintenance state.

[0012] The embodiment of this specification also provides a control device for power generation equipment, including:

[0013] A first construction unit is used to construct a device failure development model based on historical operation data of the power generation equipment;

[0014] A second construction unit is used to construct an objective function according to the equipment failure development model, wherein the objective function represents the efficiency loss of the wind turbine generator set;

[0015] An acquisition unit, used for acquiring maintenance constraint conditions of power generation equipment;

[0016] A determination unit, used for determining a maintenance strategy of the power generation equipment according to maintenance constraints and an objective function;

[0017] The control unit is used to control the power generation equipment to enter a maintenance state according to a determined maintenance strategy.

[0018] The embodiments of the present specification also provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above control method when executing the computer program.

[0019] The embodiments of the present specification also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned power generation equipment control method is implemented.

[0020] The embodiments of the present specification also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above-mentioned power generation equipment control method is implemented.

[0021] The power generation equipment control method of the embodiment of this specification can construct an equipment fault development model based on the historical operation data of the power generation equipment; can construct an objective function based on the equipment fault development model, and the objective function represents the efficiency loss of the wind turbine; can obtain the maintenance constraints of the power generation equipment; can determine the maintenance strategy of the power generation equipment based on the maintenance constraints and the objective function; can control the power generation equipment to enter the maintenance state according to the determined maintenance strategy. The equipment fault development model can accurately describe the fault evolution state of the power generation equipment, thereby more accurately describing the accumulation process of the probability of failure of the power generation equipment over time. By constructing the objective function according to the equipment fault development model, determining the maintenance strategy of the power generation equipment according to the maintenance constraints and the objective function, and controlling the power generation equipment to enter the maintenance state according to the determined maintenance strategy. In this way, the power generation equipment can be accurately maintained and controlled in combination with the fault development law of the power generation equipment, thereby reducing the efficiency loss caused by maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 It is a flowchart of a control method of a power generation device in an embodiment of this specification;

[0024] Figure 2 It is a flowchart of the control process of the power generation equipment in the embodiment of this specification;

[0025] Figure 3 This is a schematic diagram of the development process of equipment failure in the embodiments of this specification;

[0026] Figure 4 A schematic diagram of historical maintenance data and historical operation data in the embodiments of this specification;

[0027] Figure 5 A schematic diagram showing the comparison of cumulative probabilities in the embodiments of this specification;

[0028] Figure 6 This is a schematic diagram of the relationship between the failure probability and time in the embodiments of this specification;

[0029] Figure 7 A schematic diagram of the total maintenance loss at each time point in the embodiments of this specification;

[0030] Figure 8 This is a schematic diagram of expected failure loss sensitivity analysis in the embodiments of this specification;

[0031] Fig. 9 It is a schematic diagram of the structure of the control device of the power generation equipment in the embodiment of this specification. DETAILED DESCRIPTION

[0032] The technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, rather than all of the embodiments. The specific embodiments described herein are only used to explain the present disclosure, rather than to limit the present disclosure. Based on the described embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art are within the scope of protection of the present disclosure. In addition, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0033] See also Figure 1 and Figure 2 The embodiment of this specification provides a control method for power generation equipment.

[0034] The power generation equipment may include new energy power generation equipment. The new energy power generation equipment can convert renewable energy in nature into electrical energy. These renewable energy sources may include solar energy, wind energy, geothermal energy, biomass energy, ocean energy, etc. The new energy power generation equipment can provide electrical energy for power supply systems, distribution systems, electrical energy storage systems, etc. The new energy power generation equipment may include generators and related equipment. For example, the new energy power generation equipment may include wind power equipment. The power generation equipment refers to equipment that uses wind energy to generate electricity. The power generation equipment may include wind turbine generators and related equipment. The wind turbine generator set may include an impeller, a generator, a transmission system, a brake system, an electronic control system, etc. The related equipment may include an anemometer, a reactive power compensation device, etc. The control method may be applied to computer equipment, and may specifically include the following steps.

[0035] Step 11: Construct an equipment failure development model based on the historical operation data of the power generation equipment.

[0036] In some embodiments, the equipment failure development model is used to represent the failure evolution state of the power generation equipment. The equipment failure development model can represent the relationship between the failure probability of the power generation equipment and the time change. For example, the equipment failure development model can represent the relationship between the failure probability and the time change in the time interval from the generation of the equipment defect to the generation of the failure.

[0037] The equipment failure development model may include a first development model and a second development model. The first development model is used to represent the relationship between the probability of a defect occurring in a first time interval and the time of the change. The first time interval may include the time interval from the generation of equipment defects to the generation of functional disorders in the power generation equipment. The second development model is used to represent the relationship between the probability of a failure occurring in a second time interval and the time of the change. The second time interval may include the time interval from the generation of functional disorders to the generation of failures in the power generation equipment. Thus, the time interval formed by the first time interval and the second time interval may be used as a third time interval. The third time interval may be the union of the first time interval and the second time interval. The equipment failure development model can represent the relationship between the probability of a failure occurring in the third time interval and the time of the change.

[0038] See also Figure 3 . According to the time delay theory, the fault development process of power generation equipment can be divided into three stages: defect generation, functional disorder generation, and failure generation. Power generation equipment can enter the equipment defect state from the normal state, then enter the functional disorder state from the equipment defect state, and finally enter the fault state. In this way, the probability of power generation equipment failure accumulation over time can be accurately characterized. Among them, equipment defects are defects that do not affect the normal operation of power generation equipment. After the equipment defects occur, the normal operation of the power generation equipment is not affected temporarily, but it poses a certain threat to the safe operation of the power generation equipment, and it is necessary to strengthen monitoring or change the operation mode. Functional disorders are obstacles that affect the normal operation of power generation equipment. After the equipment obstacles occur, it poses a serious threat to the equipment, power grid, personal safety, etc., and may cause equipment damage, casualties, large-scale power outages and other failures at any time, requiring power-limited operation. Failure generation means that the power generation equipment actually fails and cannot be operated at limited power. Wind power accidents can cause large economic losses and even casualties, and the social impact generated is more serious than the economic losses. It is necessary to try to avoid direct equipment damage and other failures. Therefore, it is necessary to complete equipment elimination before the failure occurs, that is, to perform maintenance between the generation of equipment defects and the generation of failures.

[0039] The time interval from the generation of equipment defects to the generation of functional impairment of the power generation equipment can be h, the probability of the defect is F(h), and the probability density function can be f(h). The time interval from the generation of functional impairment to the generation of failure of the power generation equipment is k, the probability of the functional impairment is G(k), and the probability density function is g(k). The above two stages are independent of each other. By analyzing the historical operation data of the power generation equipment and comprehensively considering the fitting effect and availability, the first development model can be represented by Weibull Distribution, and the second development model can be represented by Exponential Distribution. The probability density function of the first development model can be The distribution function of the first development model can be . Wherein, h is the time interval from the generation of equipment defects to the generation of functional disorders, that is, the length of the first time interval. α and β are parameters of the first development model. For example, α is a scale parameter and β is a shape parameter. The probability density function of the second development model can be The distribution function of the first development model can be Wherein, k is the time interval from the occurrence of functional disorder to the occurrence of failure, that is, the length of the second time interval. λ is a parameter of the second development model. For example, λ can be a rate parameter.

[0040] The probability P(t) of a power generation device failing at time t can be expressed as the probability of a device defect and a functional disorder and the opposite probability of no failure. Therefore, the device failure development model can be expressed as:

[0041] .

[0042] t represents a time in a third time interval formed by the first time interval and the second time interval, α and β represent parameters of the first development model, and λ represents parameters of the second development model. P(t) represents the probability of a failure occurring at time t.

[0043] In some embodiments, historical operating data of one or more power generation equipment may be collected; the values ​​of the parameters in the above equipment failure development model may be determined based on the collected historical operating data, thereby constructing the equipment failure development model.

[0044] The historical operation data may include a time interval h from the generation of equipment defects to the generation of functional failures and a time interval k from the generation of functional failures to the generation of failures. The parameters of the above equipment failure development model may include α, β and λ. α, β and λ may be calculated based on h and k of one or more power generation equipment using a maximum likelihood estimation method or the like.

[0045] The two stages from the generation of equipment defects to the generation of functional failures and from the generation of functional failures to the generation of failures can be independent of each other. Therefore, the parameters α and β of the first development model and the parameter λ of the second development model can be determined respectively. For example, the parameters α and β of the first development model can be estimated using the maximum likelihood estimation (MLE) method based on h of one or more power generation equipment.

[0046] The likelihood function can be constructed for f(h;α,β) . Taking the logarithm of the likelihood function yields . Performing partial derivative operations on α and β respectively gives . n is the number of power generation equipment. h i is the time interval from the occurrence of equipment defects to the occurrence of functional failure of the i-th power generation equipment. The solutions of α and β can be obtained by combining the above partial derivative calculation results.

[0047] The parameter λ of the second development model can also be estimated using the maximum likelihood estimation method according to k of one or more power generation equipments. The specific process is similar to the parameter estimation of α and β, and will not be described in detail here.

[0048] This allows us to construct a model for the development of equipment failures. .

[0049] Step 12: Construct the objective function based on the equipment failure development model.

[0050] In some embodiments, an equipment maintenance optimization model may be determined based on an equipment failure development model. The equipment maintenance optimization model may include an objective function. The objective function is used to represent the efficiency loss of a wind turbine. The efficiency loss may be a negative loss caused by the failure of a power generation device to reach its ideal operating state. The efficiency loss may include, for example, a loss of power generation (e.g., a reduction in power generation), or a resource loss (e.g., resource input during maintenance), etc.

[0051] In some embodiments, the objective function includes a first term. The efficiency loss may include a first sub-efficiency loss. The first term is used to represent the first sub-efficiency loss. The first sub-efficiency loss is the efficiency loss caused by the expected failure of the power generation equipment. For example, in the time interval between the occurrence of a defect and the actual failure, the power generation equipment is in a state of operating with a defect. In this state, the performance of the power generation equipment will gradually decline, the probability of failure will gradually increase, and the efficiency loss caused will also become greater and greater.

[0052] The first item can be constructed based on the equipment failure development model. For example, the first item can include Among them, t1 represents the actual maintenance time, P(t1) represents the probability of failure at the maintenance time t1, and C s Indicates the safety factor.

[0053] In some embodiments, the objective function may include a second term. The efficiency loss may include a second sub-efficiency loss. The second term is used to represent the second sub-efficiency loss. The second sub-efficiency loss may be an efficiency loss caused by power limitation of the power generation equipment. For example, during the time interval from the generation of a functional disorder to the actual occurrence of a failure, the power generation equipment needs to operate with limited functions to ensure safe operation. In this case, the power generation of the power generation equipment will be lower than the rated capacity, resulting in efficiency loss.

[0054] The second item may include . Where t1 represents the actual maintenance time, and h represents the time when the functional disorder occurs. g(t) represents the exchange rate between power generation and resources at time t. For example, g(t) can represent the on-grid electricity price of the power market at time t. p(t) represents the expected power generation of the power generation equipment at time t. When the power generation equipment is operating at limited power, it can be estimated by the adjacent power generation equipment operating at full power. η represents the output limit rate of the wind turbine.

[0055] In some embodiments, the objective function may include a third term. The efficiency loss may include a third sub-efficiency loss. The third term is used to represent the third sub-efficiency loss. The third sub-efficiency loss may be an efficiency loss caused by the shutdown of the power generation equipment. For example, the power generation equipment needs to be shut down during the maintenance process, thereby causing efficiency loss, such as causing power generation efficiency loss. The efficiency loss caused by the shutdown of the power generation equipment can be determined based on the power loss, for example, it can be determined based on the power loss and the grid-connected electricity price.

[0056] The third item may include Among them, t1 represents the actual maintenance time, △t represents the maintenance time, g(t) represents the exchange rate between power generation and resources at time t. P(t) represents the expected power generation of the power generation equipment at time t.

[0057] In some embodiments, the objective function may include a fourth term. The efficiency loss may include a fourth sub-efficiency loss. The fourth term is used to represent the fourth sub-efficiency loss. The fourth sub-efficiency loss may be the efficiency loss caused by the operation and maintenance of the power generation equipment. For example, the maintenance of the power generation equipment requires consumption of various resources, such as labor resources, material resources, safety resources, etc. The resource consumption during maintenance is related to the state of the power generation equipment. The longer the operation time of the power generation equipment, the more resources are consumed during maintenance.

[0058] The fourth item may include . Among them, ω0 represents the initial resource consumption coefficient. C l Indicates the consumption of human resources, , N represents the resource consumption per unit person, and Q represents the number of people. C m Indicates the consumption of material resources. , μ m It represents the resource consumption per kilowatt, and M represents the number of wind turbines. C s Indicates the security resource consumption, , μ s Indicates the resource consumption per kilowatt for safety assurance.

[0059] In some embodiments, the objective function may include any one of the first item, the second item, the third item, and the fourth item. Alternatively, the objective function may also include any multiple of the first item, the second item, the third item, and the fourth item. Thus, the efficiency loss of the wind turbine generator set can be comprehensively determined from multiple perspectives such as expected failure, power limitation, shutdown, operation and maintenance, etc.

[0060] For example, the objective function can be expressed as C = C r +C d +C o +C e .

[0061] In some embodiments, historical maintenance data of one or more power generation equipment may be collected; the values ​​of the parameters in the above objective function may be determined based on the collected historical maintenance data, thereby constructing the objective function.

[0062] The historical maintenance data may include safety factor, power generation, exchange rate between power generation and resources, resource consumption, etc. The historical maintenance data may be statistically analyzed to determine the values ​​of the parameters in the above objective function. For example, C s ,g(t),△t,T,N, μ m , μ s The values ​​of parameters such as .

[0063] Step 13: Obtain maintenance constraints of power generation equipment.

[0064] In some embodiments, the maintenance constraint condition can be determined according to the equipment fault development model. For example, a fault probability threshold can be obtained as the upper limit of the tolerable fault probability; according to the fault probability threshold, the maintenance time threshold can be calculated using the equipment fault development model as the maintenance deadline. The maintenance deadline is the maintenance time corresponding to the fault probability threshold in the equipment fault development model. The maintenance constraint condition is used to constrain the actual maintenance time to be earlier than the maintenance deadline.

[0065] The upper limit of the failure probability may be a maximum failure probability, and the maintenance deadline may be a latest maintenance time.

[0066] Of course, the maintenance constraint condition can also be determined based on other data. For example, weather data can also be obtained; the maintenance constraint condition can be determined based on the weather data. The maintenance constraint condition is used to restrict maintenance from being performed in windy weather.

[0067] In some embodiments, the maintenance constraint condition is a safety constraint condition. The maintenance constraint condition may include any one or more of a first constraint condition, a second constraint condition, a third constraint condition, and a fourth constraint condition.

[0068] The first constraint condition is used to constrain maintenance before a fault occurs. The first constraint condition may include t1<T. t1 represents the actual maintenance time, T represents the maintenance deadline, and T can be calculated according to the equipment fault development model.

[0069] The second constraint condition is used to restrict maintenance in windy weather. The second constraint condition may include v t < V max . v t is the wind speed at the actual time of maintenance, V max is the maximum safe wind speed, V max It can be determined based on weather data.

[0070] The third constraint condition is used to restrict maintenance at night. The third constraint condition may include: . floor() is the floor rounding function.

[0071] The fourth constraint condition is used to constrain continuous maintenance. The fourth constraint condition may include: . θ t Indicates the status of the power generation equipment, 1 means it is in maintenance status, and 0 means it is in operation status.

[0072] Step 14: Determine the maintenance strategy of the power generation equipment based on the maintenance constraints and the objective function.

[0073] In some embodiments, the objective function can be optimized according to the maintenance constraint conditions to obtain the maintenance strategy of the power generation equipment. The maintenance strategy may include the maintenance time. The maintenance time may be the time when the maintenance starts. The optimization goal may be to minimize the value of the objective function, that is, to minimize the efficiency loss of the wind turbine. Considering that the optimization of the objective function belongs to a nonlinear optimization problem, a genetic algorithm or the like can be used to optimize the objective function to obtain a better maintenance strategy.

[0074] The parameters of the genetic algorithm can be set, such as the population size, the number of iterations, the crossover probability, the mutation probability, etc. The genetic algorithm can be used to solve the objective function according to the maintenance constraints to obtain one or more maintenance strategies. The optimal maintenance strategy can be selected by comparing and analyzing the one or more maintenance strategies.

[0075] In some embodiments, the equipment fault development model may be a fault development model of one or more components (eg, a gearbox) in the power generation equipment, and thus the maintenance strategy may be a maintenance strategy of one or more components in the power generation equipment.

[0076] Of course, the above equipment fault development model may also be a fault development model of the power generation equipment as a whole, and thus the above maintenance strategy may also be a maintenance strategy of the power generation equipment as a whole.

[0077] Step 15: According to the determined maintenance strategy, control the power generation equipment to enter the maintenance state.

[0078] In some embodiments, the maintenance strategy includes an actual maintenance time. After reaching the actual maintenance time, the power generation equipment can be controlled to enter a maintenance state from an operating state. For example, the power generation equipment can be controlled to shut down to perform maintenance on the power generation equipment.

[0079] In some embodiments, after the maintenance of the power generation equipment is completed, the operation and maintenance personnel can input an operation instruction. After receiving the operation instruction, the computer device can control the power generation equipment to enter the operation state, so that the power generation equipment resumes operation.

[0080] The power generation equipment control method of the embodiment of this specification can construct an equipment fault development model based on the historical operation data of the power generation equipment; can construct an objective function based on the equipment fault development model, and the objective function represents the efficiency loss of the wind turbine; can obtain the maintenance constraints of the power generation equipment; can determine the maintenance strategy of the power generation equipment based on the maintenance constraints and the objective function; can control the power generation equipment to enter the maintenance state according to the determined maintenance strategy. The equipment fault development model can accurately describe the fault evolution state of the power generation equipment, thereby more accurately describing the accumulation process of the probability of failure of the power generation equipment over time. By constructing the objective function according to the equipment fault development model, determining the maintenance strategy of the power generation equipment according to the maintenance constraints and the objective function, and controlling the power generation equipment to enter the maintenance state according to the determined maintenance strategy. In this way, the power generation equipment can be accurately maintained and controlled in combination with the fault development law of the power generation equipment, thereby reducing the efficiency loss caused by maintenance.

[0081] The power generation equipment control method of the embodiment of this specification establishes an equipment failure development model based on the time delay theory, provides a basis for determining the maintenance strategy, and establishes an equipment maintenance optimization model in combination with historical maintenance data to reduce the efficiency loss caused by maintenance. First, based on the time delay theory, the power generation equipment failure development process is divided into three stages: defect generation, functional impairment, and failure. Weibull distribution and exponential distribution are used to describe them respectively to establish an equipment failure development model. Secondly, the maintenance deadline is determined based on the fault development model, and multiple angles such as expected failures, power limits, shutdowns, and operation and maintenance are comprehensively considered. With the goal of minimizing the total efficiency loss, various maintenance safety constraints are considered to establish an equipment maintenance optimization model.

[0082] A specific application scenario of the embodiments of this specification is introduced below.

[0083] Get the basic data.

[0084] Taking a wind farm in a certain region as the research object, it carried out a gearbox maintenance in September 2023. The relevant data of one of the wind power equipment can be referred to to optimize the maintenance strategy. Select the 15-minute power generation data of the unit from August 28, 2023 to October 11, 2023 and the corresponding market clearing electricity price, such as Figure 4 The historical gearbox failure information of 134 wind turbines in the wind farm was collected and sorted out. The relevant obstacles and failure intervals are shown in Figure 1. Figure 4 The relevant parameters can be shown in Table 1 below.

[0085] Table 1

[0086]

[0087] Get parameter estimation results.

[0088] Based on the first development model and the second development model, the time interval data from equipment defects to functional failure and from equipment functional failure to actual failure are used to calculate the parameters using the maximum likelihood estimation method. The specific results are shown in Table 2.

[0089] Table 2

[0090]

[0091] According to the above parameter values, the cumulative probability curves of Weibull distribution and exponential distribution are fitted, and compared with the cumulative probability of actual sample data. Figure 5 As shown. Figure 5 From (a) and (b) in the figure, we can see that the fitting results of the two distributions are consistent with the actual samples. Chi-square test is performed on the two distributions respectively. Weibull distribution , exponential distribution It can be seen that there is no significant difference between the fitting results and the actual results, and the parameter estimates are valid.

[0092] Substituting the above parameter estimates into the equipment failure development model, the probability of the gearbox failing over time after the defect is detected can be calculated. The specific results can be shown as follows: Figure 6 As shown. Figure 6 It can be seen that the failure probability is low in the first 20 days, and the failure probability increases rapidly to close to 0.8 from 20 to 50 days. For safety reasons, this scenario example takes the probability of wind power equipment failure not exceeding 0.7 as the benchmark, and obtains the maintenance deadline T=45, that is, maintenance can be carried out within 45 days.

[0093] Optimize maintenance strategies.

[0094] The previous calculations obtained the development curve of the equipment failure probability over time and the maintenance deadline of the equipment. The following example analysis is based on the objective function of the embodiment of this specification. In the following, the expected failure loss is the efficiency loss caused by the expected failure of the wind power equipment (the first sub-loss), the power restriction loss is the efficiency loss caused by the power limitation of the wind power equipment (the second sub-loss), the shutdown loss is the efficiency loss caused by the shutdown of the wind power equipment (the third sub-loss), and the operation and maintenance loss is the efficiency loss caused by the operation and maintenance of the wind power equipment (the fourth sub-loss). The total maintenance loss is the efficiency loss represented by the objective function.

[0095] To verify the effectiveness of the objective function, the following four scenarios are set:

[0096] Plan 1: The actual maintenance plan is expected to start on August 28, 2023, but due to the slow equipment procurement process, it will be postponed to September 2, 2023, with a construction period of 15 days;

[0097] Option 2: Minimizing power-cutting losses;

[0098] Option 3: Minimize downtime losses;

[0099] Option 4: Aim to minimize total maintenance losses.

[0100] According to the objective function of the embodiment of this specification, a genetic algorithm is used to solve the problem, and the optimization results of each solution are shown in Table 3.

[0101] Table 3

[0102]

[0103] Among them, Scheme 1 starts maintenance on the 6th day. At this time, the probability of equipment failure is extremely low, so the expected failure loss and operation and maintenance loss are low, but the power generation power during this period is high, resulting in a large amount of power restriction losses, resulting in the highest total maintenance loss. Scheme 2 starts maintenance on the 26th day. This scheme has the least power restriction loss, but due to the high market electricity price during this period, the downtime loss is not the lowest, but its total maintenance loss is relatively low. Scheme 3 starts maintenance on the 44th day. This scheme has the lowest downtime loss, but it causes a large amount of power restriction losses, and due to the high probability of equipment failure, the expected failure loss and operation and maintenance loss of the equipment are high, resulting in a high total maintenance loss. Scheme 4 starts maintenance on the 16th day. At this time, although the sub-losses are not the lowest, they are all within a lower range, making the total maintenance loss the lowest. This proves that the objective function of the embodiment of this specification can comprehensively consider the sub-losses and obtain the optimal maintenance strategy.

[0104] Based on the above analysis, the total maintenance loss of all optional time points is calculated as follows: Figure 7 As shown. Figure 7 It can be seen that the total maintenance loss remained at a high level in the first 1000 hours, mainly due to the high amount of abandoned electricity and high downtime losses during the period; the total maintenance loss dropped rapidly from 1000 to 1500 hours, mainly due to the decrease in abandoned electricity and electricity prices; the total maintenance loss fluctuated up and down due to factors such as abandoned electricity, electricity prices, and operation and maintenance losses from 1500 to 2500 hours; the total maintenance loss increased rapidly from 2500 to 4000 hours, mainly due to fluctuations in electricity and electricity prices, as well as increased operation and maintenance losses and expected failure losses, and power restriction losses began to appear later. It can be seen that the main influencing factors of the total maintenance loss are abandoned electricity and electricity prices, followed by expected failure losses, operation and maintenance losses, and power restriction losses.

[0105] Conduct sensitivity analysis.

[0106] The expected failure loss has a great influence on the selection of maintenance strategy, but the expected failure loss of different equipment is different and its value is subjective, with strong uncertainty in different environments. Therefore, it is necessary to conduct sensitivity analysis to verify the stability of the objective function. The fluctuation range of the expected failure loss in the example is set to -50%-50%, and the unit change interval is 10%. The impact on the total maintenance loss is calculated. The results are as follows: Figure 8 shown.

[0107] according to Figure 8It can be seen that a 50% reduction in the expected failure loss can reduce the total maintenance loss by about 6.94%, and the maintenance time point is still 1570 within this variation range. A 50% increase in the expected failure loss can increase the total maintenance loss by about 4.17%, and the maintenance time point is optimized to 1378 within this variation range. In order to reduce the impact of the expected failure loss, maintenance can be carried out two days in advance. This proves that the objective function of the embodiment of this specification can effectively cope with the fluctuation of the loss term and optimize the optimal maintenance strategy.

[0108] See also Fig. 9 The embodiment of this specification also provides a control device for power generation equipment, including:

[0109] A first construction unit 91 is used to construct a device failure development model according to historical operation data of the power generation equipment;

[0110] A second construction unit 92 is used to construct an objective function according to the equipment failure development model, wherein the objective function represents the efficiency loss of the wind turbine generator set;

[0111] An acquisition unit 93, used to acquire maintenance constraint conditions of power generation equipment;

[0112] A determination unit 94, used to determine the maintenance strategy of the power generation equipment according to the maintenance constraint conditions and the objective function;

[0113] The control unit 95 is used to control the power generation equipment to enter a maintenance state according to the determined maintenance strategy.

[0114] The embodiments of the present specification also provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned power generation equipment control method when executing the computer program.

[0115] The embodiments of the present specification also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned power generation equipment control method is implemented.

[0116] The embodiments of the present specification also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above-mentioned power generation equipment control method is implemented.

[0117] Those skilled in the art will appreciate that this specification may be provided as a method, system, or computer program product. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0118] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. The computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0119] The various functional units in the embodiments of this specification may be integrated into one processing unit, or each functional unit may exist physically separately, or two or more functional units may be integrated into one processing unit.

[0120] Those skilled in the art will understand that the description of each embodiment in this specification has its own emphasis. For parts not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments. In addition, it is understood that after reading this specification, those skilled in the art can think of any combination of some or all of the embodiments listed in this specification without creative work, and these combinations are also within the scope of disclosure and protection of this specification.

[0121] Although the present specification is described by way of examples, it is known to those skilled in the art that the above examples are only used to help understand the core idea of ​​the present specification. It is understood by those skilled in the art that there are many variations and changes in the present specification. It is hoped that the appended claims include these variations and changes without departing from the spirit of the present specification.

Claims

1. A control method for a power generation device, characterized in that: include: Build equipment failure development model based on historical operation data of power generation equipment; The equipment failure development model is used to represent the failure evolution process of the power generation equipment; The equipment failure development model includes a first development model and a second development model, wherein the first development model represents the relationship between the probability of a defect occurring in a first time interval and the time change, and the second development model represents the relationship between the probability of a failure occurring in a second time interval and the time change; the first time interval includes the time interval from when the power generation equipment has an equipment defect to when a functional disorder occurs; the second time interval includes the time interval from when the power generation equipment has a functional disorder to when a failure occurs; the equipment failure development model includes , t represents the time in the third time interval formed by the first time interval and the second time interval, α and β represent the parameters of the first development model, λ represents the parameters of the second development model, h is the length of the first time interval, and P(t) is the probability of failure of the power generation equipment at time t; According to the equipment failure development model, an objective function is constructed, wherein the objective function represents the efficiency loss of the wind turbine generator set; the objective function includes a first item, wherein the first item represents a first sub-efficiency loss, and the first sub-efficiency loss is the efficiency loss caused by the expected failure of the power generation equipment; the first item includes , t1 represents the maintenance time, P(t1) represents the probability of failure at the maintenance time t1, C s represents the safety factor; The constructing the objective function comprises: constructing the first item; Obtaining maintenance constraints of power generation equipment; the obtaining of maintenance constraints of power generation equipment comprises: calculating the maintenance deadline using the equipment failure development model according to the tolerable upper limit of failure probability; the maintenance constraints are used to constrain the actual maintenance time to be earlier than the maintenance deadline; Determine the maintenance strategy of power generation equipment according to maintenance constraints and objective functions; According to the determined maintenance strategy, the power generation equipment is controlled to enter the maintenance state.

2. The method according to claim 1, characterized in that The objective function includes a second item, a third item and a fourth item, the second item represents a second sub-efficiency loss, which is the efficiency loss caused by power limitation of the power generation equipment, the third item represents a third sub-efficiency loss, which is the efficiency loss caused by shutdown of the power generation equipment, and the fourth item represents a fourth sub-efficiency loss, which is the efficiency loss caused by operation and maintenance of the power generation equipment.

3. The method according to claim 1, characterized in that The step of determining a maintenance strategy for power generation equipment comprises: According to the maintenance constraints, the genetic algorithm is used to optimize the objective function and obtain the maintenance time of the power generation equipment.

4. A control device for a power generation device, characterized in that: include: A first construction unit is used to construct a device failure development model based on historical operation data of the power generation equipment; The equipment failure development model is used to represent the failure evolution process of the power generation equipment; The equipment failure development model includes a first development model and a second development model, wherein the first development model represents the relationship between the probability of a defect occurring in a first time interval and the time change, and the second development model represents the relationship between the probability of a failure occurring in a second time interval and the time change; the first time interval includes the time interval from when the power generation equipment has an equipment defect to when a functional disorder occurs; the second time interval includes the time interval from when the power generation equipment has a functional disorder to when a failure occurs; the equipment failure development model includes , t represents the time in the third time interval formed by the first time interval and the second time interval, α and β represent the parameters of the first development model, λ represents the parameters of the second development model, h is the length of the first time interval, and P(t) is the probability of failure of the power generation equipment at time t; The second construction unit is used to construct an objective function according to the equipment failure development model, wherein the objective function represents the efficiency loss of the wind turbine generator set; the objective function includes a first item, wherein the first item represents a first sub-efficiency loss, and the first sub-efficiency loss is the efficiency loss caused by the expected failure of the power generation equipment; the first item includes , t1 represents the maintenance time, P(t1) represents the probability of failure at the maintenance time t1, C s represents the safety factor; The constructing the objective function comprises: constructing the first item; An acquisition unit is used to acquire maintenance constraint conditions of power generation equipment; the acquisition of maintenance constraint conditions of power generation equipment comprises: calculating the maintenance deadline time by using the equipment failure development model according to the tolerable upper limit of failure probability; the maintenance constraint condition is used to constrain the actual maintenance time to be earlier than the maintenance deadline time; A determination unit, used for determining a maintenance strategy of the power generation equipment according to maintenance constraints and an objective function; The control unit is used to control the power generation equipment to enter a maintenance state according to a determined maintenance strategy.

5. A computer device, characterized in that: include: at least one processor; A memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, and the program instructions include instructions for executing the method according to any one of claims 1-3.

Images