Full-life-cycle management method and system for offshore wind power

Abstract

The invention relates to the technical field of offshore wind power plants, in particular to a full-life-cycle management method and system for offshore wind power. Comprising the following steps: setting a plurality of operation sub-cycles according to the life cycle of an offshore wind plant; constructing a first-level decision tree according to all the operation sub-cycles and the expected construction plan, and generating a plurality of management sub-strategies according to the first-level decision tree; setting a first-level management strategy according to all the management sub-strategies and the simulation operation and maintenance model, and judging whether the first-level management strategy is corrected or not according to a preset feedback time node; according to the method, the whole life cycle of offshore wind power is dynamically divided to construct a plurality of operation sub-cycles and construct a decision tree, so that a plurality of management sub-strategies are generated, all management sub-strategies are optimized, fine management of all life cycles of the offshore wind power plant is achieved, and the management efficiency of the offshore wind power plant is improved.

Description

Technical Field

[0001] The present application relates to the technical field of offshore wind farms, and in particular to a full life cycle management method and system for offshore wind power. Background Art

[0002] As the global energy structure transforms towards cleaner and lower-carbon energy, offshore wind power, as an important component of renewable energy, has developed rapidly in recent years due to its advantages such as stable resources, proximity to load centers and no occupation of land resources.

[0003] Offshore wind power projects are characterized by large investment scale, long construction period, harsh operation and maintenance environment, and high equipment reliability requirements. Traditional management methods are difficult to meet the refined and intelligent needs of the entire life cycle. Summary of the Invention

[0004] The purpose of this application is: to solve the above technical problems, this application provides a full life cycle management method and system for offshore wind power, aiming to improve the full life cycle management efficiency of offshore wind farms, and realize dynamic optimization, coordinated management and control, and low-carbon operation from design to decommissioning.

[0005] In some embodiments of the present application, a full life cycle management method for offshore wind power is provided, including: Set multiple operation sub-cycles according to the life cycle of the offshore wind farm; Construct a first-level decision tree based on all operational sub-cycles and expected construction plans, and generate multiple management sub-strategies based on the first-level decision tree; Set the first-level management strategy based on all management sub-strategies and the simulation operation and maintenance model, and determine whether to modify the first-level management strategy based on the preset feedback time node; When multiple operating sub-cycles are set, it includes: Establish a running sub-cycle sequence A, A=(a1,a2…a i …a n ), where a i is the i-th operating sub-cycle; n is the number of operating sub-cycles.

[0006] In some embodiments of the present application, generating multiple management sub-strategies includes: Set up multiple equipment points according to the expected construction plan; Establish a device point sequence B, B=(b1, b2…b i …b m ), where b i is the i-th device point; m is the number of device points; Set b in sequence according to the device point column B i is the target device point; Generate multiple management sub-strategies for target equipment points based on the first-level decision tree; Establish the management sub-strategy sequence P of the target device point, P=(p1, p2…p i …p r ), where p i is the i-th management sub-strategy of the target device point; r is the number of management sub-strategies of the target device point; Generate a series of management sub-strategies for each device point in sequence.

[0007] In some embodiments of the present application, setting a primary management policy includes: According to the equipment point number list B, set bi as the equipment point to be decided; Get the management sub-strategy sequence P1 of the device point to be decided, P1=(p 11 , p 12 …p 1i …p 1r1 ), where p 1i is the i-th management sub-strategy of the device point to be decided; r1 is the number of management sub-strategies of the device point to be decided; Obtain the feature data packet of the device point to be decided; Generate the benefit evaluation value of each management sub-strategy in the management sub-strategy sequence P1 based on the feature data package and the simulation operation and maintenance model; Establish a benefit evaluation series V, V=(v1, v2…v i …v r1 ), where v i is the benefit evaluation value of the i-th management sub-strategy of the equipment point to be decided; Set the maximum value v in the income evaluation value sequence V max The corresponding management sub-strategy is the first-level sub-strategy of the device point to be decided; Generate first-level sub-strategies for each device point in sequence; Generate a first-level management policy based on all first-level sub-policies.

[0008] In some embodiments of the present application, establishing the revenue evaluation value sequence V includes: According to the management sub-strategy sequence P1, set p 1i is the target sub-strategy; Obtain the simulation results of the target sub-strategy and generate the benefit evaluation value v of the target sub-strategy; v=e1*Q1*[ j i ]+e2*Q2*[ β i *k i ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; j i is the expected return value of the target sub-strategy in the i-th operating sub-cycle; n is the number of operating sub-cycles; θ1 is the number of auxiliary evaluation indicators; β i is the influencing factor of the i-th auxiliary evaluation index; k i Generate a reference value of the i-th auxiliary evaluation index for the simulation results of the target sub-strategy; Generate the profit evaluation value of each management sub-strategy in the management sub-strategy sequence P1 in sequence.

[0009] In some embodiments of the present application, determining whether to modify the primary management policy according to a preset feedback time node includes: Set the end time node of each running sub-cycle as the feedback time node; Get the monitoring data packet of the current feedback time node; Generate the profit deviation value of each device point based on the monitoring data packet; Establish the return deviation value series C, C=(c1, c2…c i …c m ), where c i is the ith profit deviation value; m is the number of equipment points; Generate the corrected evaluation value d at the current feedback time node based on the return deviation value sequence C; d=e3*Q3*[ c i ]+e4*Q4*[ (c i -c') 2 ]; Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; c' is the average value of all data in the return deviation value series C; Preset correction evaluation value threshold D1; If d>D1, the current feedback time node generates a first-level correction instruction.

[0010] In some embodiments of the present application, the first-level correction instruction includes: Establish a correlation model for the current feedback time node; Preset return deviation value threshold C1; If c i >C1, set the i-th device point as an abnormal device point; Create abnormal equipment point column B1, B1=(b 11 , b 12 …b 1i …b1m1 ), where b 1i is the i-th abnormal device point at the current feedback time node; m1 is the number of abnormal device points at the current feedback time node; Generate correction sub-strategies for each abnormal device point based on the association model.

[0011] In some embodiments of the present application, establishing the association model of the current feedback time node includes: Set b in sequence according to the device point column B i The equipment point to be evaluated; Generate the associated evaluation value of the device point to be evaluated and each device point; f i =[ η s *(h s -h is ) 2 ]; Among them, f i is the associated evaluation value between the equipment point to be evaluated and the i-th equipment point; θ2 is the number of equipment evaluation indicators; η s is the influencing factor of the sth equipment evaluation index; h s h is the reference value of the sth device evaluation index in the device to be evaluated at the current feedback time node; is is the reference value of the sth device evaluation index in the i-th device point at the current feedback time node; Preset associated evaluation value threshold F1; If f i >F1, set the i-th device point at the current feedback time node as the associated device point of the device point to be evaluated; Establish a mapping sub-table based on all associated equipment points of the equipment point to be evaluated at the current feedback time node; Generate the associated sub-table of each equipment point in turn; Establish the association model of the current feedback time node based on all associated sub-tables.

[0012] In some embodiments of the present application, when generating a correction sub-strategy for each abnormal device point based on the association model, the following steps are included: Set b in sequence according to the abnormal equipment point B1 1i is the target outlier point; Obtain all associated device points of the target abnormal point according to the association model; Generate the management evaluation value G of each associated equipment point, G=(g1, g2…g i …g m2 ), where g i$g_i$ is the management evaluation value of the $i$-th associated device point of the target abnormal point at the current feedback time node; $m_2$ is the number of associated device points of the target abnormal point at the current feedback time node; The preset associated evaluation value threshold $G_1$; If $g$ max $> G_1$, generate a first-level correction sub-strategy for the target abnormal point; If $g$ max $< G_1$, generate a second-level correction sub-strategy for the target abnormal point; Among them, $g$ max is the maximum value in the management evaluation value $G$.

[0013] In some embodiments of the present application, a full life cycle management system for offshore wind power is provided, including: A central control unit for setting multiple operation sub-cycles according to the life cycle of an offshore wind farm; A monitoring unit for collecting monitoring data of an offshore wind farm and generating monitoring data packets according to preset feedback time nodes: The central control unit includes: A first processing module for constructing a first-level decision tree according to all operation sub-cycles and an expected construction plan; Setting multiple device points according to the expected construction plan; Establishing a device point sequence $B$, $B = (b_1, b_2 \ldots b$ i $\ldots b$ m $)$, where $b$ i is the $i$-th device point; $m$ is the number of device points; Successively setting $b$ i as the target device point according to the device point sequence $B$; Generating multiple management sub-strategies for the target device point according to the first-level decision tree; Establishing a management sub-strategy sequence $P$ for the target device point, $P = (p_1, p_2 \ldots p$ i $\ldots p$ r $)$, where $p$ i is the $i$-th management sub-strategy of the target device point; $r$ is the number of management sub-strategies of the target device point; Successively generating management sub-strategy sequences for each device point; A second processing module for setting a first-level management strategy according to all management sub-strategies and a simulation operation and maintenance model; A correction module for judging whether to correct the first-level management strategy according to a preset feedback time node; A third processing module for establishing an operation sub-cycle sequence $A$, $A = (a_1, a_2 \ldots a$ i $\ldots a$ n $)$, where $a$ i is the $i$-th operation sub-cycle; $n$ is the number of operation sub-cycles.

[0014] In some embodiments of the present application, the second processing module is further configured to: According to the equipment point number list B, set bi as the equipment point to be decided; Get the management sub-strategy sequence P1 of the device point to be decided, P1=(p 11 , p 12 …p 1i …p 1r1 ), where p 1i is the i-th management sub-strategy of the device point to be decided; r1 is the number of management sub-strategies of the device point to be decided; Obtain the feature data packet of the device point to be decided; Generate the benefit evaluation value of each management sub-strategy in the management sub-strategy sequence P1 based on the feature data package and the simulation operation and maintenance model; Establish a benefit evaluation series V, V=(v1, v2…v i …v r1 ), where v i is the benefit evaluation value of the i-th management sub-strategy of the equipment point to be decided; Set the maximum value v in the income evaluation value sequence V max The corresponding management sub-strategy is the first-level sub-strategy of the device point to be decided; Generate first-level sub-strategies for each device point in sequence; Generate a first-level management policy based on all first-level sub-policies.

[0015] Compared with the prior art, the full life cycle management method and system for offshore wind power in the embodiment of the present application has the following beneficial effects: By dynamically dividing the entire life cycle of offshore wind power to construct multiple operating sub-cycles and a decision tree, multiple management sub-strategies are generated. By optimizing all management sub-strategies, refined management of the entire life cycle of offshore wind farms is achieved, thereby improving the management efficiency of offshore wind farms.

[0016] By setting multiple feedback time nodes, the actual operating status of the offshore wind farm is analyzed, and abnormal conditions are dynamically optimized in a timely manner. At the same time, through the analysis of all internal wind turbines, collaborative linkage is achieved to ensure the efficient operation of the offshore wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a full life cycle management method for offshore wind power in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0018] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0019] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0020] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0021] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections, electrical connections; direct connections, indirect connections through an intermediate medium, and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0022] like Figure 1 As shown, a full life cycle management method for offshore wind power according to a preferred embodiment of the present application includes: S101: setting a plurality of operation sub-cycles according to the life cycle of the offshore wind farm; S102: Constructing a first-level decision tree based on all operation sub-cycles and the expected construction plan, and generating multiple management sub-strategies based on the first-level decision tree; S103: Setting a primary management strategy based on all management sub-strategies and the simulation operation and maintenance model, and determining whether to modify the primary management strategy based on a preset feedback time node; When multiple operating sub-cycles are set, it includes: Establish a running sub-cycle sequence A, A=(a1,a2…a i …a n ), where a i is the i-th operating sub-cycle; n is the number of operating sub-cycles.

[0023] Specifically, the entire life cycle of a wind farm includes the construction phase, the operation and maintenance phase, and the decommissioning and recovery phase. By further refining each phase, multiple operation sub-cycles can be constructed. For example, in the construction phase, multiple operation sub-cycles can be set based on the design site selection and different stages of construction. In the operation and maintenance phase, an operation sub-cycle is set based on the equipment aging curve of the wind turbine and the fault parameters.

[0024] Specifically, the first-level decision tree uses each operating sub-cycle as a node. By analyzing historical parameters, it sets management plans that can be executed within each operating sub-cycle, and each management plan is used as a branch. For example, during design and construction, different branches are generated based on whether the wind turbine uses fixed piles or floating piles, and the equipment casing material. During the operation and maintenance phase, different branches are generated based on whether parts are replaced or the entire unit is replaced. During the decommissioning phase, complete decommissioning is adopted, and multiple branches are generated based on whether all components and foundations are disassembled or whether the waste is partially decommissioned, that is, used for municipal construction.

[0025] Specifically, when generating multiple management sub-strategies, including: Set up multiple equipment points according to the expected construction plan; Establish a device point sequence B, B=(b1, b2…b i …b m ), where b i is the i-th device point; m is the number of device points; Set b in sequence according to the device point column B i is the target device point; Generate multiple management sub-strategies for target equipment points based on the first-level decision tree; Establish the management sub-strategy sequence P of the target device point, P=(p1, p2…p i …p r ), where p i is the i-th management sub-strategy of the target device point; r is the number of management sub-strategies of the target device point; Generate a series of management sub-strategies for each device point in sequence.

[0026] Specifically, the site selection points of the wind turbines are obtained through the expected construction plan, and each site selection point is set as an equipment point.

[0027] Specifically, according to the branch structure of the first-level decision tree, a management plan is randomly selected in each operating sub-area to construct a management sub-strategy, and all management sub-strategies of the target equipment point are generated through the exhaustive method, and the management plans within any two management sub-strategies are not exactly the same.

[0028] In a preferred embodiment of the present application, when setting the first-level management policy, the following steps are included: According to the equipment point number list B, set bi as the equipment point to be decided; Get the management sub-strategy sequence P1 of the device point to be decided, P1=(p 11 , p 12 …p 1i …p 1r1 ), where p 1i is the i-th management sub-strategy of the device point to be decided; r1 is the number of management sub-strategies of the device point to be decided; Obtain the feature data packet of the device point to be decided; Generate the benefit evaluation value of each management sub-strategy in the management sub-strategy sequence P1 based on the feature data package and the simulation operation and maintenance model; Establish a benefit evaluation series V, V=(v1, v2…v i …v r1 ), where v i is the benefit evaluation value of the i-th management sub-strategy of the equipment point to be decided; Set the maximum value v in the income evaluation value sequence V max The corresponding management sub-strategy is the first-level sub-strategy of the device point to be decided; Generate first-level sub-strategies for each device point in sequence; Generate a first-level management policy based on all first-level sub-policies.

[0029] Specifically, the feature data package includes the periodic environmental parameters of the device point (wind speed, humidity, temperature, etc. with an annual cycle).

[0030] Specifically, each management sub-strategy is simulated using a simulation operation and maintenance model, comprehensively analyzing parameters such as construction cost, operation and maintenance cost, decommissioning and recovery cost, and expected benefits. This generates a benefit evaluation value for each management sub-strategy. The greater the benefit evaluation, the more suitable the current management sub-strategy is for the full lifecycle management of the equipment point under decision.

[0031] Specifically, when establishing the income evaluation value series V, it includes: According to the management sub-strategy sequence P1, set p 1i is the target sub-strategy; Obtain the simulation results of the target sub-strategy and generate the benefit evaluation value v of the target sub-strategy; v=e1*Q1*[ j i ]+e2*Q2*[ β i *k i ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; ji is the expected return value of the target sub-strategy in the i-th operating sub-cycle; n is the number of operating sub-cycles; θ1 is the number of auxiliary evaluation indicators; β i is the influencing factor of the i-th auxiliary evaluation index; k i Generate a reference value of the i-th auxiliary evaluation index for the simulation results of the target sub-strategy; Generate the profit evaluation value of each management sub-strategy in the management sub-strategy sequence P1 in sequence.

[0032] Specifically, the expected benefit values are comprehensively analyzed based on the operation and maintenance content within different operation sub-cycles. The larger the expected benefit value, the better the adoption of the above management sub-strategies within that operation sub-cycle. For example, during the operation sub-cycle corresponding to the construction phase, parameters such as material costs, installation and commissioning costs, and cable laying costs are analyzed. During the operation sub-cycle corresponding to the decommissioning phase, parameters such as wind turbine disassembly, waste equipment transportation, site cleanup, and recycling costs are analyzed.

[0033] Specifically, auxiliary evaluation indicators include but are not limited to the correlation effects between various management sub-strategies (for example, reducing later maintenance costs through high-cost construction in the early stage), the probability of environmental fluctuations at equipment points, the confidence level of the operation and maintenance simulation model, and other parameters.

[0034] It can be understood that in the above embodiments, Specifically, all parameters in the model are normalized by presetting a first fixed coefficient and a second fixed coefficient, so that each parameter in the model is in the same value range.

[0035] It can be understood that in the above embodiment, the entire life cycle of offshore wind power is dynamically divided to construct multiple operating sub-cycles, and a decision tree is constructed to generate multiple management sub-strategies. By optimizing all management sub-strategies, refined management of the entire life cycle of the offshore wind farm is achieved, thereby improving the management efficiency of the offshore wind farm.

[0036] In a preferred embodiment of the present application, when determining whether to modify the primary management policy according to the preset feedback time node, the method includes: Set the end time node of each running sub-cycle as the feedback time node; Get the monitoring data packet of the current feedback time node; Generate the profit deviation value of each device point based on the monitoring data packet; Establish the return deviation value series C, C=(c1, c2…c i …c m ), where c i is the ith profit deviation value; m is the number of equipment points; Generate the corrected evaluation value d at the current feedback time node based on the return deviation value sequence C; d=e3*Q3*[ c i ]+e4*Q4*[ (c i -c') 2 ]; Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; c' is the average value of all data in the return deviation value series C; Preset correction evaluation value threshold D1; If d>D1, the current feedback time node generates a first-level correction instruction.

[0037] Specifically, the revised evaluation value threshold can be set according to historical parameters.

[0038] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient and the fourth fixed coefficient, so that each parameter in the model is within the same value range.

[0039] Specifically, the first-level correction instructions include: Establish a correlation model for the current feedback time node; Preset return deviation value threshold C1; If c i >C1, set the i-th device point as an abnormal device point; Create abnormal equipment point column B1, B1=(b 11 , b 12 …b 1i …b 1m1 ), where b 1i is the i-th abnormal device point at the current feedback time node; m1 is the number of abnormal device points at the current feedback time node; Generate correction sub-strategies for each abnormal device point based on the association model.

[0040] Specifically, when establishing the correlation model of the current feedback time node, it includes: Set b in sequence according to the device point column B i The equipment point to be evaluated; Generate the associated evaluation value of the device point to be evaluated and each device point; f i =[ η s *(h s -h is ) 2 ]; Among them, f iis the associated evaluation value between the device point to be evaluated and the i-th device point; θ2 is the number of device evaluation indicators; η s is the influence factor of the s-th device evaluation indicator; h s is the reference value of the s-th device evaluation indicator in the device point to be evaluated at the current feedback time node; h is is the reference value of the s-th device evaluation indicator in the i-th device point at the current feedback time node; The preset associated evaluation value threshold F1; If f i > F1, set the i-th device point as the associated device point of the device point to be evaluated at the current feedback time node; Establish a mapping sub-table based on all the associated device points of the device point to be evaluated at the current feedback time node; Generate the associated sub-tables of each device point in sequence; Establish an association model at the current feedback time node based on all the associated sub-tables.

[0041] Specifically, the device evaluation indicators include, but are not limited to, multiple parameters such as device construction materials, device construction methods, the number of device failures and maintenance methods, average operating power of the device, life loss, etc. The larger the associated evaluation value, the more similar the overall operating states between the device point to be evaluated and the corresponding device point.

[0042] Specifically, when generating the correction sub-strategies for each abnormal device point according to the association model, it includes: Set b in sequence according to the abnormal device point B1 1i as the target abnormal point;<* Obtain all the associated device points of the target abnormal point according to the association model; Generate the management evaluation value G for each associated device point, G = (g1, g2…g i …g m2 ), where, g i is the management evaluation value of the i-th associated device point of the target abnormal point at the current feedback time node; m2 is the number of associated device points of the target abnormal point at the current feedback time node; The preset associated evaluation value threshold G1; If g max > G1, generate the first-level correction sub-strategy for the target abnormal point; If g max < G1, generate the second-level correction sub-strategy for the target abnormal point; Among them, g max is the maximum value in the management evaluation value G.

[0043] Specifically, the first-level correction strategy means selecting g maxThe historical management strategy of the corresponding equipment point amends the remaining management parameters of the target abnormal point. The secondary correction sub-strategy refers to amending the abnormal management parameters of the target abnormal point based on the historical management strategy of the equipment point with the best operation in the wind farm.

[0044] It can be understood that in the above embodiment, by setting multiple feedback time nodes, the actual operating status of the offshore wind farm is analyzed, and abnormal conditions are dynamically optimized in a timely manner. At the same time, by analyzing all internal wind turbines, collaborative correlation is achieved to ensure the efficient operation of the offshore wind farm.

[0045] Based on another preferred embodiment of a full life cycle management method for offshore wind power in any of the above preferred embodiments, this preferred embodiment provides a full life cycle management system for offshore wind power, including: A central control unit, used to set multiple operating sub-cycles according to the life cycle of the offshore wind farm; The monitoring unit is used to collect monitoring data of the offshore wind farm and generate monitoring data packets according to the preset feedback time nodes: The central control unit includes: The first processing module is used to construct a first-level decision tree based on all operating sub-cycles and the expected construction plan; Set up multiple equipment points according to the expected construction plan; Establish a device point sequence B, B=(b1, b2…b i …b m ), where b i is the i-th device point; m is the number of device points; Set b in sequence according to the device point column B i is the target device point; Generate multiple management sub-strategies for target equipment points based on the first-level decision tree; Establish the management sub-strategy sequence P of the target device point, P=(p1, p2…p i …p r ), where p i is the i-th management sub-strategy of the target device point; r is the number of management sub-strategies of the target device point; Generate a series of management sub-strategies for each device point in sequence; The second processing module is used to set the first-level management strategy based on all management sub-strategies and the simulation operation and maintenance model; The correction module is used to determine whether to correct the primary management strategy according to the preset feedback time node; The third processing module is used to establish the running sub-cycle sequence A, A=(a1, a2…a i …a n ), where a iis the i-th operating sub-cycle; n is the number of operating sub-cycles.

[0046] In a preferred embodiment of the present application, the second processing module is further configured to: According to the equipment point number list B, set bi as the equipment point to be decided; Get the management sub-strategy sequence P1 of the device point to be decided, P1=(p 11 , p 12 …p 1i …p 1r1 ), where p 1i is the i-th management sub-strategy of the device point to be decided; r1 is the number of management sub-strategies of the device point to be decided; Obtain the feature data packet of the device point to be decided; Generate the benefit evaluation value of each management sub-strategy in the management sub-strategy sequence P1 based on the feature data package and the simulation operation and maintenance model; Establish a benefit evaluation series V, V=(v1, v2…v i …v r1 ), where v i is the benefit evaluation value of the i-th management sub-strategy of the equipment point to be decided; Set the maximum value v in the income evaluation value sequence V max The corresponding management sub-strategy is the first-level sub-strategy of the device point to be decided; Generate first-level sub-strategies for each device point in sequence; Generate a first-level management policy based on all first-level sub-policies.

[0047] According to the first concept of the present application, by dynamically dividing the entire life cycle of offshore wind power to construct multiple operating sub-cycles, a decision tree is constructed to generate multiple management sub-strategies. By optimizing all management sub-strategies, refined management of the entire life cycle of offshore wind farms is achieved, thereby improving the management efficiency of offshore wind farms.

[0048] According to the second concept of this application, by setting multiple feedback time nodes, the actual operating status of the offshore wind farm is analyzed, and abnormal conditions are dynamically optimized in a timely manner. At the same time, by analyzing all internal wind turbines, collaborative linkage is achieved to ensure the efficient operation of the offshore wind farm.

[0049] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. A full life cycle management method for offshore wind power, characterized in that: include: Set multiple operation sub-cycles according to the life cycle of the offshore wind farm; Construct a first-level decision tree based on all operational sub-cycles and expected construction plans, and generate multiple management sub-strategies based on the first-level decision tree; Set the first-level management strategy based on all management sub-strategies and the simulation operation and maintenance model, and determine whether to modify the first-level management strategy based on the preset feedback time node; When multiple operating sub-cycles are set, it includes: Establish a running sub-cycle sequence A, A=(a1,a2…a i …a n ), where a i is the i-th operating sub-cycle; n is the number of operating sub-cycles.

2. The full life cycle management method for offshore wind power according to claim 1, characterized in that: When generating multiple management sub-policies, include: Set up multiple equipment points according to the expected construction plan; Establish a device point sequence B, B=(b1, b2…b i …b m ), where b i is the i-th device point; m is the number of device points; Set b in sequence according to the device point column B i is the target device point; Generate multiple management sub-strategies for target equipment points based on the first-level decision tree; Establish the management sub-strategy sequence P of the target device point, P=(p1, p2…p i …p r ), where p i is the i-th management sub-strategy of the target device point; r is the number of management sub-strategies of the target device point; Generate a series of management sub-strategies for each device point in sequence.

3. The full life cycle management method for offshore wind power according to claim 2, characterized in that: When setting the first-level management strategy, include: According to the equipment point number list B, set bi as the equipment point to be decided; Get the management sub-strategy sequence P1 of the device point to be decided, P1=(p 11 , p 12 …p 1i …p 1r1 ), where p 1i is the i-th management sub-strategy of the device point to be decided; r1 is the number of management sub-strategies of the device point to be decided; Obtain the feature data packet of the device point to be decided; Generate the benefit evaluation value of each management sub-strategy in the management sub-strategy sequence P1 based on the feature data package and the simulation operation and maintenance model; Establish a benefit evaluation series V, V=(v1, v2…v i …v r1 ), where v i is the benefit evaluation value of the i-th management sub-strategy of the equipment point to be decided; Set the maximum value v in the income evaluation value sequence V max The corresponding management sub-strategy is the first-level sub-strategy of the device point to be decided; Generate first-level sub-strategies for each device point in sequence; Generate a first-level management policy based on all first-level sub-policies.

4. The full life cycle management method for offshore wind power according to claim 3, characterized in that: When establishing the income evaluation value series V, it includes: According to the management sub-strategy sequence P1, set p 1i is the target sub-strategy; Obtain the simulation results of the target sub-strategy and generate the benefit evaluation value v of the target sub-strategy; v=e1*Q1*[ j i ]+e2*Q2*[ β i *k i ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; j i is the expected return value of the target sub-strategy in the i-th operating sub-cycle; n is the number of operating sub-cycles; θ1 is the number of auxiliary evaluation indicators; β i is the influencing factor of the i-th auxiliary evaluation index; k i Generate a reference value of the i-th auxiliary evaluation index for the simulation results of the target sub-strategy; Generate the profit evaluation value of each management sub-strategy in the management sub-strategy sequence P1 in sequence.

5. The full life cycle management method for offshore wind power according to claim 4, characterized in that: When determining whether to revise the primary management strategy based on the preset feedback time node, it includes: Set the end time node of each running sub-cycle as the feedback time node; Get the monitoring data packet of the current feedback time node; Generate the profit deviation value of each device point based on the monitoring data packet; Establish the return deviation value series C, C=(c1, c2…c i …c m ), where c i is the ith profit deviation value; m is the number of equipment points; Generate the corrected evaluation value d at the current feedback time node based on the return deviation value sequence C; d=e3*Q3*[ c i ]+e4*Q4*[ (c i -c') 2 ]; Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; c' is the average value of all data in the return deviation value series C; Preset correction evaluation value threshold D1; If d>D1, the current feedback time node generates a first-level correction instruction.

6. The full life cycle management method for offshore wind power according to claim 5, characterized in that: The first-level correction instructions include: Establish a correlation model for the current feedback time node; Preset return deviation value threshold C1; If c i >C1, set the i-th device point as an abnormal device point; Create abnormal equipment point column B1, B1=(b 11 , b 12 …b 1i …b 1m1 ), where b 1i is the i-th abnormal device point at the current feedback time node; m1 is the number of abnormal device points at the current feedback time node; Generate correction sub-strategies for each abnormal device point based on the association model.

7. The full life cycle management method for offshore wind power according to claim 6, characterized in that: When establishing the association model of the current feedback time node, it includes: Set b in sequence according to the device point column B i The equipment point to be evaluated; Generate the associated evaluation value of the device point to be evaluated and each device point; f i =[ η s *(h s -h is ) 2 ]; Among them, f i is the associated evaluation value between the equipment point to be evaluated and the i-th equipment point; θ2 is the number of equipment evaluation indicators; η s is the influencing factor of the sth equipment evaluation index; h s h is the reference value of the sth device evaluation index in the device to be evaluated at the current feedback time node; is is the reference value of the sth device evaluation index in the i-th device point at the current feedback time node; Preset associated evaluation value threshold F1; If f i >F1, set the i-th device point at the current feedback time node as the associated device point of the device point to be evaluated; Establish a mapping sub-table based on all associated equipment points of the equipment point to be evaluated at the current feedback time node; Generate the associated sub-table of each equipment point in turn; Establish the association model of the current feedback time node based on all associated sub-tables.

8. The full life cycle management method for offshore wind power according to claim 7, characterized in that: When generating correction sub-strategies for each abnormal device point based on the association model, the following are included: Set b in sequence according to the abnormal equipment point B1 1i is the target outlier point; Obtain all associated device points of the target abnormal point according to the association model; Generate the management evaluation value G of each associated equipment point, G=(g1, g2…g i …g m2 ), where g i is the management evaluation value of the i-th associated device point of the target abnormal point at the current feedback time node; m2 is the number of associated device points of the target abnormal point at the current feedback time node; Preset associated evaluation value threshold G1; If g max >G1, a first-level correction sub-strategy for generating target outliers; If g max <G1, generate a secondary correction sub-strategy for the target anomaly point; Among them, g max It is the maximum value among the management evaluation values G.

9. A full life cycle management system for offshore wind power, adopting the full life cycle management method for offshore wind power according to any one of claims 1 to 8, characterized in that: include: A central control unit, used to set multiple operating sub-cycles according to the life cycle of the offshore wind farm; The monitoring unit is used to collect monitoring data of the offshore wind farm and generate monitoring data packets according to the preset feedback time nodes: The central control unit includes: The first processing module is used to construct a first-level decision tree based on all operating sub-cycles and the expected construction plan; Set up multiple equipment points according to the expected construction plan; Establish a device point sequence B, B=(b1, b2…b i …b m ), where b i is the i-th device point; m is the number of device points; Set b in sequence according to the device point column B i is the target device point; Generate multiple management sub-strategies for target equipment points based on the first-level decision tree; Establish the management sub-strategy sequence P of the target device point, P=(p1, p2…p i …p r ), where p i is the i-th management sub-strategy of the target device point; r is the number of management sub-strategies of the target device point; Generate a series of management sub-strategies for each device point in sequence; The second processing module is used to set the first-level management strategy based on all management sub-strategies and the simulation operation and maintenance model; The correction module is used to determine whether to correct the primary management strategy according to the preset feedback time node; The third processing module is used to establish the running sub-cycle sequence A, A=(a1, a2…a i …a n ), where a i is the i-th operating sub-cycle; n is the number of operating sub-cycles.

10. The full life cycle management system for offshore wind power according to claim 9, characterized in that: The second processing module is further configured to: According to the equipment point number list B, set bi as the equipment point to be decided; Get the management sub-strategy sequence P1 of the device point to be decided, P1=(p 11 , p 12 …p 1i …p 1r1 ), where p 1i is the i-th management sub-strategy of the device point to be decided; r1 is the number of management sub-strategies of the device point to be decided; Obtain the feature data packet of the device point to be decided; Generate the benefit evaluation value of each management sub-strategy in the management sub-strategy sequence P1 based on the feature data package and the simulation operation and maintenance model; Establish a benefit evaluation series V, V=(v1, v2…v i …v r1 ), where v i is the benefit evaluation value of the i-th management sub-strategy of the equipment point to be decided; Set the maximum value v in the income evaluation value sequence V max The corresponding management sub-strategy is the first-level sub-strategy of the device point to be decided; Generate first-level sub-strategies for each device point in sequence; Generate a first-level management policy based on all first-level sub-policies.

Images