Fuzzy control method for igv attendance based on job demand prediction, medium

Abstract

The application provides a fuzzy control method for IGV attendance based on job demand prediction, comprising the following steps: S1, obtaining a first IGV allocation D1 based on experience optimization and a second IGV allocation D2 suitable for dynamic jobs of a port; S2, obtaining an IGV gap amount; S3, synthesizing an IGV control amount according to a formulated fuzzy rule; S4, then, defuzzifying the IGV control amount into an accurate IGV amount; S5, numerically adjusting the IGV attendance according to the accurate IGV amount obtained in S4; S6, judging whether the IGV attendance adjusted in S5 meets the job requirements of the automated container terminal, and if the answer is yes, the fuzzy control of the IGV attendance is completed, and if the answer is no, the step S1 is executed circularly; the application further provides a computer readable storage medium applying the fuzzy control method for IGV attendance based on job demand prediction; and the application can accurately control the job dispatch amount of the IGV of the automated container terminal and improve the utilization rate of port job resources.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of port operation equipment scheduling management, and particularly relates to a fuzzy control method for IGV attendance based on operation demand prediction and a medium. BACKGROUND

[0002] An intelligent guided vehicle (IGV) is one of the important devices responsible for horizontal transportation in an automated container terminal, undertakes multiple key tasks, and is widely used in cargo loading and handling; as a key link connecting the quay crane, the yard and the rail-mounted gantry, the IGV needs to perform multiple tasks in a complex terminal operating environment, including cargo handover with the quay crane, yard operation with the rail-mounted gantry, dynamic avoidance of other IGVs, etc.; at the same time, the IGV also needs to interact with the scheduling system in real time to complete the specified tasks according to the task priority, operation demand and path planning; the operation efficiency and task completion accuracy of the IGV directly affect the overall throughput capacity of the terminal; in the operating scenario of the automated container terminal, the IGV involves the interaction of multiple devices and systems, including automatic interaction with the quay crane, automatic interaction with the rail-mounted gantry, interaction with the charging system, position confirmation between other IGVs, and human-machine interaction during disassembly and assembly of the lock, etc.; therefore, optimizing the attendance rate of the IGV and reasonably allocating the number of IGVs according to the operation demand have important significance for improving the work efficiency of the terminal.

[0003] Currently, the IGV scheduling strategy in the automated container terminal is usually based on preset rules or empirical formulas, and mainly relies on daily shift plans to allocate the number of vehicles; however, this traditional scheduling method has obvious limitations: on the one hand, it cannot flexibly respond to dynamic changes in operation demand, for example, resource allocation may be insufficient during demand peaks, while vehicles may be idle and resources may be wasted during demand troughs; on the other hand, other influencing factors such as the urgency of IGV operation tasks, device health status and path congestion are not fully considered in the scheduling process, resulting in low resource utilization efficiency; in addition, real-time requirements are high in IGV scheduling, and traditional linear programming cannot meet the needs of dynamic adjustment;

[0004] The existing IGV regulation scheme is usually relatively simple, mainly using fixed allocation rules, and lacks detailed consideration of complex working conditions; in the case of large demand fluctuations or complex operation environment, the scheduling strategy may exhibit significant hysteresis and inefficiency, affecting the efficiency of terminal operations; especially during task peaks, insufficient vehicle allocation may cause operation delays, while excessive vehicle allocation during demand troughs may increase energy consumption and equipment wear and tear;

[0005] The existing IGV regulation scheme also has the following disadvantages:

[0006] 1. The number of IGVs currently used by the terminal is a predefined dispatching rule, which lacks flexibility when demand changes and is difficult to respond to unexpected situations;

[0007] 2. Poor adaptability to uncertainties such as demand fluctuations and AGV failures, and low robustness of the scheduling results;

[0008] 3. The control is not accurate enough, and there are problems of insufficient and inappropriate resource utilization. SUMMARY

[0009] Therefore, it is necessary to propose a fuzzy control method for IGV attendance based on job demand prediction to overcome the shortcomings in the background art and solve the following technical problems:

[0010] How to accurately control the number of IGVs in automated container terminals and improve the utilization rate of port operation resources.

[0011] To achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows:

[0012] The present application proposes a fuzzy control method for IGV attendance based on job demand prediction, which is applied to an automated container terminal comprising multiple IGVs, a TOS system and an automated equipment management system in communication with the TOS system, the TOS system being used to manage the operation of the automated container terminal, and the automated equipment management system being used to obtain the actual attendance of IGVs, the fuzzy control method comprising:

[0013] Step S1, obtaining a first IGV allocation D1 based on experience optimization according to the historical operation of the terminal, and obtaining a second IGV allocation D2 adapted to the dynamic operation of the terminal according to the fluctuation of the terminal operation, and then executing step S2;

[0014] Step S2, obtaining the IGV gap: determining whether the second IGV allocation D2 is greater than the first IGV allocation D1, if the determination is yes, the IGV gap is equal to the first IGV allocation D1 minus the actual attendance of IGVs, if the determination is no, the IGV gap is equal to the second IGV allocation D2 minus the actual attendance of IGVs, and the IGV gap is taken as the fuzzy control input; then executing step S3;

[0015] Step S3, synthesizing the IGV control quantity according to the formulated fuzzy rule; then executing step S4;

[0016] Step S4, then defuzzifying the IGV control quantity into an accurate value of the number of IGVs; then executing step S5;

[0017] Step S5, numerical adjustment of the IGV attendance quantity according to the IGV quantity accurate value obtained in step S4; then step S6 is executed;

[0018] Step S6, judging whether the IGV attendance quantity adjusted in step S5 meets the operation requirement of the automated container terminal, when judging as yes, completing the fuzzy control of the IGV attendance quantity, if judging as no, then step S1 is executed cyclically.

[0019] Further, in step S1, obtaining the first IGV allocation quantity D1 based on experience optimization includes the following steps executed in sequence:

[0020] Step S111, calculating the IGV quantity K corresponding to the single front-end equipment configuration t is:

[0021]

[0022] In formula (1), N is the model coefficient, T m is the change amount of the transportation capacity with time, the operation time of the single transportation includes loading and unloading and driving time, F a is the time delay proportion caused by traffic influence, T c is the operation time of the single transportation, V l is the transportation capacity of the vehicle, η e is the loading and unloading efficiency of the vehicle, T m (t) 2 is the change of the transportation capacity caused by the increase of the operation time, is the proportional relationship between the operation time and the cycle time; γ is the time lag benefit coefficient, γ·D t-1 Considering the time lag effect, D t-1 is the transportation capacity of the previous time, used to reflect the influence of the previous cycle on the current transportation capacity;

[0023] Step S112, calculating the first IGV allocation quantity D1 according to formula (1):

[0024]

[0025] In formula (2), α ij represents the influence coefficient of the front-end equipment and the container allocation quantity; exp(β ij ·K ij ) models the nonlinear relationship between K ij and α ij , so that the influence of K ij is more sensitive; γ t is the time coefficient of the IGV demand quantity; γ t ·D t-1is the IGV demand at the past time point introduced to consider the time lag effect; δ t · sin(ω t · t) is the time to capture periodic changes; ∈ t is the error term, which is used to represent random fluctuations or uncertainties in the model.

[0026] Further, in step S1, obtaining the second IGV allocation amount D2 adapted to the dynamic operation of the terminal includes the following steps executed in sequence:

[0027] Step S121, establishing a basic model formula, which is a formula based on time, ship size, operation box quantity, and equipment capacity, for quantifying the influence of the approaching berthing or departing ship on the IGV demand; the basic model formula is:

[0028] IGV = f(C, T, S, P, ΔQ) (3)

[0029] In formula (3), C is the quantity of containers already handled by the current ship, T is the berthing time of the ship, S is the size of the ship, P is the capacity of the port equipment, and ΔQ is the operation box quantity of the approaching berthing or departing ship;

[0030] Step S122, establishing a linear model:

[0031] D 21 = k1·ΔQ + k2·T + k3·S - k4·P (4)

[0032] In formula (4), k1 is a coefficient to be optimized, representing the influence degree of the increase or decrease of operation box quantity of the approaching berthing or departing ship on the IGV; k2 is a berthing or departing time coefficient, representing the influence of the berthing or departing time on the IGV; k3 is a ship size coefficient, representing the influence of the ship size on the demand; k4 is a front equipment coefficient, representing the influence of the capacity of the front equipment; T is the berthing time of the ship, S is the size of the ship, and P is the capacity of the port equipment;

[0033] Step S123, calculating the yard rail-mounted gantry horizontal transportation change demand operation quantity D 22 :

[0034] D 22 = k 11 · Q ARMG + k 12 · A - k 13 · N (5)

[0035] In formula (5), Q ARMG is the horizontal transportation operation quantity of the yard rail-mounted gantry, A is the attendance quantity of the yard rail-mounted gantry, N is the task quantity of the rail-mounted gantry, k 11 , k 12 , and k13 is an influence coefficient of the IGV demand for the operation amount, the number of attendances and the number of tasks, respectively;

[0036] In step S124, the operation amount D of the change demand of the number of external trailers entering and leaving the gate is calculated 23 :

[0037] D 23 = k 21 ·E-k 22 ·L+k 23 ·C (6)

[0038] In formula (6), E is the number of external trailers entering the gate, L is the number of external trailers leaving the gate, c is the yard capacity, k 21 , k 22 , k 23 are influence coefficients of the IGV demand for the number of entering external trailers, the number of leaving external trailers and the yard capacity, respectively;

[0039] In step S125, the second IGV allocation amount D2 of the dynamic allocation is obtained by dynamically predicting the IGV demand according to the berthing and unberthing of the terminal front, the horizontal transportation of the yard track crane and the number of external trailers entering and leaving the gate.

[0040] D2 = λ 21 ·D 21 + λ 22 ·D 22 + λ 23 ·D 23 (7)

[0041] In formula (7), λ 21 is the adjustment coefficient of the operation amount D 21 of the change demand of the berthing and unberthing of the terminal front, λ 22 is the adjustment coefficient of the operation amount D 22 of the change demand of the horizontal transportation of the yard track crane, and λ 23 is the adjustment coefficient of the operation amount D 23 of the change demand of the number of external trailers entering and leaving the gate.

[0042] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the fuzzy control method for the IGV attendance amount based on the operation demand prediction.

[0043] The application further provides an electronic device, which comprises a storage, a processor and a computer program stored in the storage and executable by the processor, and the processor executes the computer program to implement the steps of the fuzzy control method for the IGV attendance amount based on the operation demand prediction.

[0044] The application further provides an IGV attendance quantity fuzzy control system based on job demand prediction, which is applied to an automated container terminal provided with multiple IGVs, and comprises an automated container terminal job management software module and an automated equipment management software module for obtaining IGV actual attendance quantity, wherein the automated container terminal job management software module and the automated equipment management software module perform information interaction, and the automated container terminal job management software module performs the following steps:

[0045] In step S1, a first IGV allocation quantity D1 based on experience optimization is obtained according to terminal job history, and a second IGV allocation quantity D2 suitable for dynamic terminal job is obtained according to terminal job fluctuation, and then step S2 is performed;

[0046] In step S2, an IGV gap quantity is obtained: whether the second IGV allocation quantity D2 is greater than the first IGV allocation quantity D1 is judged, if yes, the IGV gap quantity is equal to the first IGV allocation quantity D1 minus the IGV actual attendance quantity, if no, the IGV gap quantity is equal to the second IGV allocation quantity D2 minus the IGV actual attendance quantity, and the IGV gap quantity is taken as a fuzzy control input quantity; and then step S3 is performed;

[0047] In step S3, an IGV control quantity is synthesized according to a formulated fuzzy rule; and then step S4 is performed;

[0048] In step S4, the IGV control quantity is defuzzified into an IGV quantity accurate value; and then step S5 is performed;

[0049] In step S5, the IGV attendance quantity is numerically adjusted according to the IGV quantity accurate value obtained in step S4; and then step S6 is performed;

[0050] In step S6, whether the IGV attendance quantity adjusted in step S5 meets the job requirement of the automated container terminal is judged, if yes, the fuzzy control of the IGV attendance quantity is completed, if no, step S1 is circularly performed.

[0051] The application has the following beneficial effects:

[0052] The application can accurately control the dispatching quantity of IGV of an automated container terminal, and significantly improves the utilization rate of port operation resources; the application can flexibly respond to fluctuations in operation demand by introducing a fuzzy control strategy, realize dynamic allocation of vehicles, optimize resource utilization, reduce energy waste, ensure efficient operation of the terminal under high load conditions, provide strong support for the intelligent development of automated terminals, and improve the overall operation efficiency and competitiveness of the terminal; the application can predict the IGV allocation demand according to the actual terminal operation, dynamically determine the number of IGVs to be put into or reduced according to the real-time operation demand, reasonably allocate task resources, and optimize operation efficiency; the application can dynamically adjust the number of IGVs according to actual demand, reduce energy waste, improve the overall system efficiency of the port, quickly respond to operation demand forecasts, reduce calculation time cost, obtain the vehicle demand quantity by combining multiple factors, meet operation demand, and can be deployed on a large scale and simply, so that the fuzzy control vehicle dispatching quantity is more accurate, and the calculation result is more in line with reality. BRIEF DESCRIPTION OF DRAWINGS

[0053] The accompanying drawings are included to provide a further understanding of the application, and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the application and, together with the specification, serve to explain the principles of the application. These drawings are merely schematic and are not drawn to scale, but are for explanation only, and therefore are not limiting of the present application.

[0054] Figure 1 The working flow chart of the fuzzy control method of IGV attendance quantity based on operation demand prediction of the application. DETAILED DESCRIPTION

[0055] In order to make the objects, technical solutions and advantages of the application clearer, the technical solutions of the application will be further clearly and completely described below in combination with the embodiments of the application. It should be noted that the described embodiments are only some of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0056] The terms "first", "second", "third", "fourth" and the like are used only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the definition of "first", "second", "third", "fourth" features can explicitly or implicitly include one or more features.

[0057] The following is a detailed description of embodiments of the application depicted in the accompanying drawings. The embodiments are described in sufficient detail to provide a thorough understanding of the embodiments of the application. The number of details provided is not intended to limit the intended scope of embodiments; on the contrary, it is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the application as defined by the appended claims.

[0058] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the application. It will be apparent, however, to one skilled in the art that the embodiments of the application can be practiced without some or all of these specific details.

[0059] Embodiments of the application include various steps, which will be described below. The steps can be performed by hardware components or can be embodied in machine-executable instructions, which can be used to program a general-purpose or special-purpose processor to perform the steps. Alternatively, the steps can be performed by a combination of hardware, software, and firmware and / or human operators.

[0060] The various methods described herein can be practiced by combining one or more machine-readable storage media containing code in accordance with the present application with appropriate standard computer hardware to execute the code contained in the machine-readable storage media. An apparatus for practicing various embodiments of the present application can include one or more computers (or one or more processors within a single computer) and a storage system containing or having access to computer programs coded in accordance with the various methods described herein, and the method steps of the present application can be accomplished through modules, routines, subroutines, or subparts of the computer program product.

[0061] If the specification states a component, feature, structure, or characteristic "may," "might," "can," "could," "should," "would" or "will" include, have, or have essentially, include or have, or "including," or "have" such, that particular component, feature, structure, or characteristic, the description is not necessarily limited to such component, feature, structure, or characteristic.

[0062] As used in the description of the application and the following claims, the meanings of "a", "an", and "the" include plural references unless the context clearly dictates otherwise. Furthermore, as used in the description of the application, the meaning of "in" includes "in" and "on" unless the context clearly dictates otherwise.

[0063] Exemplary embodiments will now be described below in greater detail in connection with the drawings. These embodiments are provided only to illustrate the exemplary embodiments and should not be construed to limit the scope of the disclosure. The disclosed application can be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Various modifications will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments and applications without departing from the spirit and scope of the present disclosure. Furthermore, all the statements herein should be interpreted as intending to encompass both structural and functional equivalents that are within the scope of the disclosure. Additionally, it is intended that each and every element recited in the claims covers all the equivalent structures and materials that would have been covered by the same element had it been drafted without the use of the term "means for". Furthermore, it is intended that the scope of the present disclosure encompass all alternatives, modifications and equivalents falling within the true spirit and scope of the present disclosure. Accordingly, the application should not be limited by the above description but should be defined by the appended claims in their broadest form. For the purposes of clarity, technical material that is known in the technical field related to the application has not been set forth in detail so as not to unnecessarily obscure the disclosure.

[0064] Thus, for example, it will be appreciated by those skilled in the art that the schematic, block diagram, flow chart, and the like represent conceptual views or processes embodying the application. The functions of the various elements shown in the figures can be provided through the use of dedicated hardware as well as hardware capable of executing software in association with appropriate software. Similarly, any switches shown in the figures are conceptual only. Their function can be carried out through the operation of program logic, through dedicated logic, through the interaction of program control and dedicated logic, or even manually, the particular technique being selectable by the implementer as more specifically set forth in the DETAILED DESCRIPTION section. It should be further understood that the exemplary hardware, software, processes, methods, and / or operating systems described herein are for illustrative purposes and are not meant to limit the scope of the present application.

[0065] Embodiments of the application can be provided as a computer program product, which can include a machine-readable storage medium having stored thereon instructions that can be used to program a computer (or other electronic device) to perform a process. The term "machine-readable storage medium" or "computer-readable storage medium" refers to any medium that participates in providing instructions to a processor for execution. Such a medium can take many forms, including but not limited to, a fixed (hard- wired) drive, a tape, a floppy disc, a compact disc (CD), a compact disc read-only memory (CD-ROM), and a magneto-optical disc, semiconductor memory such as read-only memory (ROM), programmable read-only memory (PROMs), erasable programmable read-only memory (EPROMs), electronically erasable programmable read-only memory (EEPROMs), flash memory, a magnetic or optical card, or other types of media / machine-readable medium suitable for storing electronic instructions (e.g., computer programming code such as software or firmware). For example, a computer program product can include a computer readable medium having stored thereon instructions that, if executed, enable a processor of a computer (or other electronic device) to perform a process. A computer readable medium can include one or more memory devices or storage devices providing program code to a processor of a computer (or other electronic device) in some embodiments. The machine-readable medium can be non-transitory, in that it does not include a carrier wave or other transitory propagating signals. Examples of a machine-readable medium can include, but are not limited to, a magnetic disk or tape, optical storage medium such as compact disc (CD) or digital versatile disc (DVD), flash memory, a memory or memory device, and the like. The computer program product can include code and / or machine-executable instructions that can represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment can be coupled to another code segment or a hardware circuit by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. can be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, etc.

[0066] Furthermore, embodiments can be implemented by hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to perform the necessary tasks (e.g., a computer program product) can be stored in a machine readable medium. A processor(s) can perform the necessary tasks.

[0067] The systems depicted in some of the figures can be provided in various configurations. In some embodiments, the systems can be configured as a distributed system, where one or more components of the system are distributed across one or more networks in a cloud-computing system.

[0068] Each of the claims defines an individual invention, which is considered to include equivalents of the various elements or limitations specified in the claims. Depending on the context, all references below to "the invention" can refer to some specific particular embodiment thereof. Other embodiments can exist that are not explicitly described or claimed, however, and the present disclosure includes all such potential embodiments. In addition, the phrase as used herein does not prohibit having a mix of elements from one or more embodiments as claimed in another. All patents and patent applications are herein incorporated by reference in their entirety. In the event of a conflict in a definition in the incorporated reference, the definition will control solely in this detailed description.

[0069] Unless otherwise indicated herein, or in the context of a contradiction with the application disclosed herein, all of the processes described herein can be performed in any suitable order. The use of any and all examples, or exemplary language (e.g., "such as") provided herein, is intended merely to better illuminate the application and does not pose a limitation on the scope of the application claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the application.

[0070] Various terms used herein are shown below. In the absence of a definition of a term used in the claims below in the following, the broadest definition should be given to the term as it has been reflected in printed publications and granted patents at the time of filing the application by persons skilled in the relevant art.

[0071] Example 1

[0072] As Figure 1 shown:

[0073] The embodiment proposes a fuzzy control method of IGV attendance based on job demand prediction, applied to an automated container terminal including multiple IGVs, a TOS system and an automated equipment management system in communication with the TOS system, the TOS system being used to manage the automated container terminal job, and the automated equipment management system (which can be a port RCMS system or a port ECS system) being used to obtain the actual IGV attendance, the fuzzy control method comprising:

[0074] Step S1, obtaining a first IGV allocation D1 based on experience optimization according to the historical situation of terminal operation, and obtaining a second IGV allocation D2 suitable for dynamic terminal operation according to the fluctuation of terminal operation, and then executing step S2;

[0075] Step S2, obtaining the IGV gap: judging whether the second IGV allocation D2 is greater than the first IGV allocation D1, if the judgment is yes, the IGV gap is equal to the first IGV allocation D1 minus the actual IGV attendance, if the judgment is no, the IGV gap is equal to the second IGV allocation D2 minus the actual IGV attendance, and the IGV gap is taken as the fuzzy control input; then executing step S3;

[0076] Step S3, synthesizing the IGV control according to the formulated fuzzy rule; then executing step S4;

[0077] Step S4, then defuzzifying the IGV control into an accurate value of the IGV number; then executing step S5;

[0078] Step S5, numerically adjusting the IGV attendance according to the accurate value of the IGV number obtained in step S4; then executing step S6;

[0079] Step S6, determine whether the IGV attendance quantity adjusted in step S5 meets the operation requirements of the automated container terminal, if yes, complete the fuzzy control of the IGV attendance quantity, if no, execute step S1 in a loop (i.e. if not met, then recalculate the real-time demand of IGV and get a new IGV control quantity to determine whether the number of IGV attendance should be increased or decreased).

[0080] Optimally, in step S1, obtaining the first IGV allocation quantity D1 based on experience optimization includes the following steps executed in sequence:

[0081] Step S111, calculate the IGV quantity K corresponding to the configuration of a single front-end equipment t For:

[0082]

[0083] In formula (1), N is the model coefficient, T m is the change of transport capacity over time, the operation time of single transport includes loading and unloading and driving time, F a is the time delay ratio caused by traffic, T c is the operation time of single transport, V l is the transport capacity of the vehicle (unit: box / time), η e is the loading and unloading efficiency of the vehicle, T m (t) 2 is the change of transport capacity (acceleration or deceleration) caused by the increase of operation time, is the proportional relationship between operation time and cycle time; γ is the time lag benefit coefficient, γ·D t-1 Considering the time lag effect, D t-1 is the transport capacity at the previous time, which is used to reflect the influence of the previous cycle on the current transport capacity; specifically, the IGV quantity K corresponding to a single front-end equipment configuration t According to the operation scene, the terminal front end allocates a fixed number K i of IGVs for each quay crane, light bridge, and gantry crane, which is obtained by considering vehicle transport capacity, operation time, loading and unloading efficiency, different transport distances, traffic impact, and other factors; specifically, T m (t) 2 Considering the nonlinear impact of transport operation time on transport capacity, the square term of T m (t) is added; specifically, a fixed number K i of IGVs is allocated for a single front-end equipment, and the value range K t, quay crane K1∈[6,8]; light bridge K2∈[5,7]; gantry crane K3∈[4,7]; specifically, the single frontier equipment is a quay crane, light bridge or gantry crane;

[0084] Step S112: Calculate the first IGV supply quantity D1 according to formula (1):

[0085]

[0086] In formula (2), α ij Represents the impact coefficient of frontier equipment and container distribution volume; exp(β ij ·K ij ) Modeling K through exponential function ij With α ij The nonlinear relationship between K ij More sensitive to the influence of γ t is the time coefficient of IGV demand; γ t ·D t-1 is the IGV demand introduced at a past time point to consider the time lag effect; δ t ·sin(ω t t) is the addition of time (such as seasonal fluctuations) to capture periodic changes; ∈ t is the error term, which accounts for random fluctuations or uncertainty in the model.

[0087] Optimally, in step S1, obtaining the second IGV allocation D2 adapted to the dynamic operation of the terminal includes the following steps performed in sequence:

[0088] Step S121: Establish a basic model formula. The basic model formula is based on time, ship size, operation box quantity and equipment capacity, and is used to quantify the impact of upcoming berthing and unberthing ships on the demand for IGVs. The basic model formula is:

[0089] IGV=f(C,T,S,P,ΔQ) (3)

[0090] In formula (3), C is the number of containers handled by the current ship, T is the berthing time of the ship, S is the size of the ship, P is the capacity of the port equipment (for example, the number of quay cranes, light bridges, and gantry cranes), and ΔQ is the number of containers handled by the ship that is about to berth or leave. Specifically, the second IGV allocation D2 takes into account the dynamic changes in operations, such as berthing and leaving at the terminal front, horizontal transportation by rail cranes in the yard, and the number of towing vehicles entering and leaving the gate to dynamically predict the demand for IGVs.

[0091] Step S122: Establish a linear model:

[0092] D 21 =k1·ΔQ+k2·T+k3·S-k4·P (4)

[0093] In formula (4), k1 is a coefficient to be optimized, representing the influence degree of the increase or decrease of the operation box quantity of the approaching or departing ship on the IGV; k2 is a time coefficient of approaching or departing, representing the influence of the approaching or departing time on the IGV; k3 is a ship size coefficient, representing the influence of the ship size on the demand quantity; k4 is a front-end equipment coefficient, representing the influence of the front-end equipment capacity; T is the approaching time of the ship, S is the size of the ship, and P is the capacity of the port equipment.

[0094] Step S123, calculating the change demand operation quantity D of the horizontal transportation of the yard rail-mounted crane 22 :

[0095] D 22 =k 11 ·Q ARMG +k 12 ·A-k 13 ·N (5)

[0096] In formula (5), Q ARMG is the horizontal transportation operation quantity of the yard rail-mounted crane (unit: container quantity), A is the attendance quantity of the yard rail-mounted crane (unit: number), N is the task quantity of the rail-mounted crane (unit: task number), k 11 ,k 12 ,k 13 are respectively the influence coefficients of the operation quantity, the attendance quantity and the task quantity on the IGV demand; specifically, formula (5) is a linear model; specifically, D 22 The influence of the operation quantity, the attendance quantity and the task quantity of the yard rail-mounted crane is considered, so that the formula (5) needs to be calculated;

[0097] Step S124, calculating the change demand operation quantity D of the in-out external tug quantity of the lock 23 :

[0098] D 23 =k 21 ·E-k 22 ·L+k 23 ·C (6)

[0099] In formula (6), E is the in external tug quantity (unit: number) of the lock, L is the out external tug quantity (unit: number) of the lock, C is the yard capacity (unit: container quantity), k 21 ,k 22 ,k 23 are respectively the influence coefficients of the in external tug quantity, the out external tug quantity and the yard capacity on the IGV demand;

[0100] Step S125, the dynamic demand prediction of IGV is obtained by comprehensively considering the berthing and unberthing of the wharf front, the horizontal transportation of the rail-mounted crane in the yard, and the number of external tugs entering and leaving the lock, and the second dynamic allocation of IGV D2 is obtained:

[0101] D2 = λ 21 · D 21 + λ 22 · D 22 + λ 23 · D 23 (7)

[0102] In formula (7), λ 21 is the adjustment coefficient of the berthing and unberthing change demand operation amount D 21 of the wharf front, λ 22 is the adjustment coefficient of the rail-mounted crane horizontal transportation change demand operation amount D 22 of the yard, and λ 23 is the adjustment coefficient of the external tug number change demand operation amount D 23 of the lock.

[0103] Further optimization, step S3 includes the following sequentially executed sub-steps:

[0104] Step S31, according to the predicted allocation amount, define fuzzy sets and membership functions, convert input and output variables, and divide the demand gap into seven fuzzy sets: negative big (NB), negative medium (NM), negative small (NS), zero (ZO), positive small (PS), positive medium (PM), and positive big (PB);

[0105] Step S32, describe the fuzzy rule; design the fuzzy rule according to the experience of the operator, the rule form is in the form of "IF A THEN B", and the specific meaning of the rule is that when the demand gap is negative, the control amount is also negative, indicating that the IGV vehicle is reduced; when the demand gap is positive, the control amount is positive, indicating that the IGV vehicle is increased; if the demand gap is NB, the control amount is NB; if the demand gap is NM, the control amount is NM; if the demand gap is NS, the control amount is NS; if the demand gap is ZO, the control amount is 0; if the demand gap is PS, the control amount is PS; if the demand gap is PM, the control amount is PM; if the demand gap is PB, the control amount is PB;

[0106] Step S32, find the fuzzy relationship; according to the fuzzy rule, express the fuzzy control rule as the relationship between the input and output fuzzy sets, and use the fuzzy matrix to describe these rules; each fuzzy matrix represents the fuzzy relationship between the input variable and the output variable under a certain condition; finally, the maximum membership degree function matrix is obtained by finding the union of the fuzzy matrix, which is the result of the fuzzy relationship;

[0107] Step S33, fuzzy decision; the output of the fuzzy controller is the composition of the error vector and the fuzzy relationship; according to the current error value, the corresponding fuzzy matrix is selected, and the fuzzy output vector is calculated through the composition operation; for example, when the error is NB, the output vector is calculated and the composition result of the fuzzy relationship is obtained;

[0108] Step S34, defuzzification of the control quantity, according to the result of the fuzzy decision, defuzzification is performed through the "maximum membership principle" to determine the final control quantity; for example: if NB is selected after defuzzification, the number of IGV is reduced; if PB is selected, the number of IGV is increased. This process ensures that the control output can meet the actual demand, for example: according to the fuzzy decision, when the error is negative, the number of IGV is sufficient, e = NB, the output of the controller is a fuzzy vector, which can be represented as:

[0109]

[0110] According to the "maximum membership principle" for defuzzification, the control quantity u = -6 is selected, which can accurately reduce the number of IGV, which meets the actual situation that the maintenance demand of IGV is met when the operation is not busy; according to the final control quantity, the number of IGV on duty is increased or decreased.

[0111] The fuzzy control method applied in this embodiment has better stability and higher robustness than conventional control systems based on control rules containing fuzzy information; when improving system characteristics, the fuzzy control system does not have to adjust parameters like conventional control systems, but can also modify system characteristics by changing control rules, membership functions, reasoning methods and decision-making methods; the real-time demand quantity involved in this embodiment is calculated, and the approximate demand equivalent is accurate; the demand gap is also calculated, while the real-time attendance quantity is actual; the fuzzy control method of this embodiment estimates the demand gap, uses fuzzy algorithm to accurately adjust the number of dispatched IGV in time, and realizes precise control of IGV attendance, and finds a balance in the game between the needs of terminal operation and maintenance.

[0112] The fuzzy control method of this embodiment also has the following advantages:

[0113] 1. Set reasonable membership functions for different demand changes, and dynamically adjust the IGV operation strategy combined with other factors (such as the urgency of the current task, the state of equipment use), to avoid situations of insufficient resources under high demand or waste of resources under low demand;

[0114] 2. Through fuzzy algorithm, the real-time demand quantity and the IGV attendance state are comprehensively analyzed, the increase and decrease strategy of IGV is dynamically adjusted, to ensure that resources are quickly increased under high demand and reduced under low demand, and the system runs smoothly and efficiently.

[0115] 3, Reasonable allocation of job resources, avoid because IGV excessive investment or insufficient cause the delay of port operation or energy consumption increase, at the same time ensure that the equipment is in a reasonable use state, prolong the service life of equipment.

[0116] 4, Using fuzzy algorithm technology, low investment, easy deployment, simple maintenance;

[0117] 5, The calculation process of fuzzy control is simple, which can quickly respond to dynamic demand changes through fuzzy rules directly reasoning;

[0118] 6, When the demand fluctuates or other unpredictable factors, the fuzzy control system can maintain stable performance;

[0119] 7, According to the working condition of automated wharf operation, the demand of intelligent guided vehicle based on experience optimization or operation dynamic allocation is established, and the overall scheme of fuzzy control intelligent guided vehicle dispatching quantity is established.

[0120] 8, Fuzzy control is used to balance the relationship between intelligent guided vehicle operation and maintenance.

[0121] 9, Combined with the intelligent guided vehicle quantity demand of each shore crane, light bridge and portal crane in the front of the wharf, considering the vehicle transportation capacity, operation time, loading and unloading efficiency, different transportation distance, traffic influence and other factors, a new intelligent guided vehicle demand evaluation method is proposed.

[0122] Embodiment 2

[0123] The embodiment provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the steps of the fuzzy control method of IGV attendance quantity based on operation demand prediction.

[0124] Embodiment 3

[0125] The embodiment provides an electronic device, which comprises a storage, a processor and a computer program stored in the storage and executable by the processor, and the processor executes the computer program to realize the steps of the fuzzy control method of IGV attendance quantity based on operation demand prediction.

[0126] Embodiment 4

[0127] Embodiment 4 is further optimized and designed on the basis of embodiment 1.

[0128] The application further provides a fuzzy control system of IGV attendance quantity based on job demand prediction, which is applied to an automated container terminal provided with multiple IGVs, and comprises an automated container terminal job management software module and an automated equipment management software module for obtaining IGV actual attendance quantity, wherein the automated container terminal job management software module and the automated equipment management software module perform information interaction, and the automated container terminal job management software module performs the following steps:

[0129] In step S1, a first IGV allocation quantity D1 based on experience optimization is obtained according to terminal job history, and a second IGV allocation quantity D2 suitable for dynamic terminal job is obtained according to terminal job fluctuation, and then step S2 is performed;

[0130] In step S2, an IGV gap quantity is obtained: whether the second IGV allocation quantity D2 is greater than the first IGV allocation quantity D1 is judged, if the judgment is yes, the IGV gap quantity is equal to the first IGV allocation quantity D1 minus the IGV actual attendance quantity, if the judgment is no, the IGV gap quantity is equal to the second IGV allocation quantity D2 minus the IGV actual attendance quantity, and the IGV gap quantity is taken as a fuzzy control input quantity; and then step S3 is performed;

[0131] In step S3, an IGV control quantity is synthesized according to a formulated fuzzy rule; and then step S4 is performed;

[0132] In step S4, the IGV control quantity is defuzzified into an IGV quantity accurate value; and then step S5 is performed;

[0133] In step S5, the IGV attendance quantity is numerically adjusted according to the IGV quantity accurate value obtained in step S4; and then step S6 is performed;

[0134] In step S6, whether the IGV attendance quantity adjusted in step S5 meets the job requirement of the automated container terminal is judged, when the judgment is yes, the fuzzy control of the IGV attendance quantity is completed, if the judgment is no, step S1 is circularly performed.

[0135] The above-mentioned embodiments only express several implementation manners of the application, and the description is more specific and detailed, but it cannot be understood as the limitation of the patent scope of the application. It should be noted that, for those skilled in the art, without departing from the concept of the application, several modifications and improvements can be made, which all belong to the protection scope of the application. Therefore, the protection scope of the patent of the application should be subject to the appended claims.

Claims

1. A fuzzy control method for predicting IGV attendance based on job requirements, applied to an automated container terminal comprising a plurality of IGVs, a TOS system for managing the automated container terminal job, and an automated equipment management system in communication with the TOS system, the automated equipment management system being configured to obtain actual IGV attendance, the method comprising: The fuzzy control method comprises: ​ Step S1, obtaining the first IGV allocation based on experience optimization according to the wharf operation history , obtaining the second IGV allocation suitable for the dynamic operation of the wharf according to the wharf operation fluctuation Then step S2 is performed; Step S2, obtaining IGV gap amount: judging whether the second IGV allocation amount is greater than the first IGV allocation amount Step S3, obtaining IGV gap amount: if the judgment is yes, then the IGV gap amount is equal to the first IGV allocation amount Step S3, obtaining IGV gap amount: if the judgment is no, then the IGV gap amount is equal to the second IGV allocation amount Step S3, obtaining IGV gap amount: if the judgment is no, then the IGV gap amount is equal to the second IGV allocation amount Step S3, obtaining IGV gap amount: if the judgment is no, then the IGV gap amount is equal to the second IGV allocation amount Step S3, synthesizing IGV control quantity according to the established fuzzy rule; then executing step S4; Step S4, then defuzzifying the IGV control quantity into IGV quantity accurate value; then executing step S5; Step S5, numerically adjusting IGV attendance quantity according to the IGV quantity accurate value obtained in step S4; then executing step S6; Step S6, judging whether the IGV attendance quantity adjusted in step S5 meets the operation requirement of the automated container terminal, and if yes, completing the fuzzy control of the IGV attendance quantity, and if no, executing step S1 cyclically; In step S1, a first IGV setting based on experience optimization is obtained comprising the following steps executed in sequence: Step S111, according to the model coefficient , the amount of change in transport capacity over time , the proportion of time delay caused by traffic impact , the operation time of a single transport , the operation time of the single transport includes loading and unloading time, the transport capacity of the vehicle , the loading and unloading efficiency of the vehicle , the change in transport capacity caused by the increase in operation time , the proportional relationship between operation time and cycle time , the time lag benefit coefficient , considering the time lag effect and the transport capacity at the previous time reflecting the influence of the previous cycle on the current transport capacity , calculate the number of IGV corresponding to the single front-end equipment configuration ; Step S112, calculating the first IGV distribution amount according to the number of IGVs corresponding to the single-front-edge device configuration .​ 2. The fuzzy control method of IGV attendance quantity based on operation demand prediction according to claim 1, characterized in that, In step S111, the number of IGVs corresponding to the configuration of the single front-end device is calculated is: （1） In formula (1), is a model coefficient, is a change in transport capacity over time, is a time delay ratio caused by traffic influence, is a single transport operation time, including loading and unloading and travel time, is a transport capacity of a vehicle, is a loading and unloading efficiency of a vehicle, is a change in transport capacity caused by an increase in operation time, is a proportional relationship between operation time and cycle time; is a time lag benefit coefficient, considering time lag effect, is a transport capacity at a previous time, used to reflect the influence of a previous cycle on the current transport capacity; In step S112, the first IGV setting amount is calculated according to formula (1) : （2） In formula (2), represents the impact coefficient of the front-end equipment and the container allocation amount; The nonlinear relationship between and is modeled by an exponential function, making the impact of more sensitive; is the time coefficient of IGV demand; is the IGV demand at the past time point, which is introduced to consider the time lag effect; is the time to capture periodic changes; is the error term, which is used to represent random fluctuations or uncertainties in the model.

3. The fuzzy control method of IGV attendance based on job demand prediction according to claim 1, characterized in that, In step S1, a second IGV allocation amount adapted to a dynamic operation of a terminal is acquired comprising the following steps executed in sequence: Step S121, establishing a basic model formula, which is a formula based on time, ship size, operation box quantity and equipment capacity, for quantifying the influence of the ship about to berth or leave on IGV demand quantity; the basic model formula is: （3） In equation (3), is the amount of containers already handled by the current vessel, is the berthing time of the vessel, is the size of the vessel, is the capacity of the port facilities, is the amount of containers to be handled for the incoming or outgoing vessel; Step S122, establishing a linear model: （4） In formula (4), is the coefficient to be optimized, indicating the influence degree of the increase or decrease of the operation box volume of the ship about to berth or unberth on the IGV; is the berthing or unberthing time coefficient, indicating the influence of the berthing or unberthing time on the IGV; is the ship size coefficient, indicating the influence of the ship size on the demand volume; is the front-end equipment coefficient, indicating the influence of the front-end equipment capacity; T is the berthing time of the ship, S is the size of the ship, and P is the capacity of the port equipment; Step S123, calculate the yard rail-mounted crane horizontal transportation change demand operation quantity : （5） In equation (5), is the number of horizontal transportation tasks of the rail-mounted gantry crane, is the number of service times of the rail-mounted gantry crane, is the number of tasks of the rail-mounted gantry crane, is the influence coefficient of the IGV demand for the number of horizontal transportation tasks, the number of service times and the number of tasks, respectively; Step S124, calculate the number of changes in the demand for the amount of work outside the gate : （6） In equation (6), is the number of external trailers entering the gate, is the number of external trailers leaving the gate, is the yard capacity, , , are the influence coefficients of the number of external trailers entering, the number of external trailers leaving and the yard capacity on the IGV demand, respectively. Step S125, the dynamic demand prediction of IGV by synthesizing the berthing and unberthing of the terminal front, the horizontal transportation of the rail-mounted crane in the yard, and the number of the external tug entering and leaving the lock can obtain the second IGV allocation quantity of dynamic allocation : （7） In formula (7), For the change of the number of berths Adjusting coefficient, For the change of the number of rail-mounted gantry cranes Adjusting coefficient, For the change of the number of tugs Adjusting coefficient.

4. A computer readable storage medium storing a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the fuzzy control method of IGV attendance quantity based on operation demand prediction according to any one of claims 1 to 3.

5. An electronic device, comprising: The computer program is executed by the processor to realize the steps of the fuzzy control method of IGV attendance quantity based on operation demand prediction according to any one of claims 1 to 3.

6. A fuzzy control system for predicting IGV attendance based on job requirements, applied to an automated container terminal provided with a plurality of IGVs, characterized by, The fuzzy control system comprises an automated container terminal operation management software module and an automated equipment management software module for obtaining IGV actual attendance quantity, the automated container terminal operation management software module and the automated equipment management software module perform information interaction, and the automated container terminal operation management software module executes the following steps: Step S1, obtaining the first IGV allocation based on experience optimization according to the wharf operation history , obtaining the second IGV allocation suitable for the dynamic operation of the wharf according to the wharf operation fluctuation Then step S2 is performed; Step S2, obtaining IGV gap amount: judging whether the second IGV allocation amount is greater than the first IGV allocation amount Step S3, obtaining IGV gap amount: judging whether the first IGV allocation amount is greater than the IGV actual attendance amount If the judgment is yes, the IGV gap amount is equal to the first IGV allocation amount If the judgment is no, the IGV gap amount is equal to the second IGV allocation amount Subtracting the IGV actual attendance amount, and taking the IGV gap amount as a fuzzy control input amount; then executing step S3; Step S3, synthesizing IGV control quantity according to the established fuzzy rule; then executing step S4; Step S4, then defuzzifying the IGV control quantity into IGV quantity accurate value; then executing step S5; Step S5, numerically adjusting IGV attendance quantity according to the IGV quantity accurate value obtained in step S4; then executing step S6; Step S6, judging whether the IGV attendance quantity adjusted in step S5 meets the operation requirement of the automated container terminal, and if yes, completing the fuzzy control of the IGV attendance quantity, and if no, executing step S1 cyclically; In step S1, a first IGV setting based on experience optimization is obtained comprising the following steps executed in sequence: Step S111, according to the model coefficient , the amount of change in transport capacity over time , the proportion of time delay caused by traffic impact , the operation time of a single transport , the operation time of the single transport includes loading and unloading time, the transport capacity of the vehicle , the loading and unloading efficiency of the vehicle , the change in transport capacity caused by the increase in operation time , the proportional relationship between operation time and cycle time , the time lag benefit coefficient , considering the time lag effect and the transport capacity at the previous time for reflecting the influence of the previous cycle on the current transport capacity , calculate the number of IGV corresponding to the single front-end equipment configuration ; Step S112, calculating the first IGV distribution amount according to the number of IGVs corresponding to the single-front-edge device configuration .​

Images