Underwater ship intelligent bed distribution method and system based on multi-modal sensing and dynamic planning

Abstract

The invention discloses an underwater ship intelligent bed distribution method and system based on multi-modal sensing and dynamic planning. The method comprises the steps of collecting bed surface pressure distribution data of an intelligent bed in real time; acquiring temperature data of the intelligent bed; obtaining a crew scheduling table, extracting a to-be-distributed crew set of the current shift, and obtaining state data of each crew; constructing an intelligent bed distribution function based on the bed surface pressure distribution data, the temperature data of the intelligent bed and the state data of each crew; obtaining an optimal allocation scheme based on a dynamic programming algorithm; and pushing the distribution result to the crew intelligent terminal. The method has the advantages that the distribution efficiency is improved, sanitation and privacy are guaranteed, the comfort degree is optimized, and energy conservation and consumption reduction are achieved.

Description

Technical Field

[0001] The present invention belongs to the field of computer system engineering, and in particular relates to a method and system for allocating intelligent berths for underwater ships based on multimodal perception and dynamic programming. Background Art

[0002] In underwater operating environments such as ocean-going vessels and submarines, crew members are in a closed, high-pressure space for a long time. The rational allocation of bed resources directly affects the crew's physical and mental health and work efficiency. The traditional bed allocation method has the following technical defects: Inefficient static allocation: The existing system relies on fixed schedules to allocate beds, without considering the crew's actual rest needs (such as fatigue and biological rhythms), resulting in a 20% to 30% bed idle rate.

[0003] Hygiene and privacy issues: Sharing beds with multiple people ("hot bunks") can easily lead to cross-infection and lack privacy protection measures. Crew satisfaction is less than 40%.

[0004] Poor environmental adaptability: The bed microenvironment (temperature, humidity, and pressure distribution) is not linked to the crew's physiological state, resulting in local discomfort (such as concentrated pressure on the waist and uneven temperature).

[0005] In the existing technology, CN1105555A proposes an RFID-based bed management system, but this only implements identity recognition and does not address dynamic optimization. US2023004567 uses pressure sensors to detect occupancy status but does not integrate multimodal data. Therefore, an intelligent dynamic allocation method is urgently needed. Summary of the Invention

[0006] In view of the above-mentioned defects in the prior art, the present invention provides an underwater ship intelligent berth allocation method based on multimodal perception and dynamic programming, comprising the following steps: Step S101: collecting the bed surface pressure distribution data of the smart bed in real time; Step S103: Acquire temperature data of the smart bed; Step S105: Obtain the crew schedule, extract the crew members to be assigned for the current shift, and obtain the status data of each crew member; Step S107: constructing an intelligent bed allocation function based on the bed surface pressure distribution data, the temperature data of the intelligent bed, and the status data of each crew member; Step S109: Obtaining an optimal allocation solution based on a dynamic programming algorithm; Step S1011: Push the allocation result to the crew's smart terminal.

[0007] Wherein, the step 101 also includes generating a pressure distribution matrix P based on the bed surface pressure distribution data.

[0008] Wherein, the temperature data in the step S103 includes a surface temperature field T of the smart bed, and a thermal residual index τ.

[0009] Wherein, the state data in the step S105 includes heart rate variability and a time interval of the bed from last use.

[0010] Wherein, the smart bed allocation function in the step S107 adopts the following formula: , wherein represents the allocation priority of the crew member, α, β, γ, δ, ϵ are adjustable weight coefficients, is a pressure gradient norm, represents the total available time of the bed, represents the remaining rest time, represents the heart rate variability of the crew member, represents the time interval of the bed from last use of the crew member, represents the heart rate variability of the crew member, represents the time interval of the bed from last use of the crew member, represents the crew member, represents the crew member.

[0011] Wherein, the dynamic programming algorithm in the step S109 adopts a hierarchical decision-making framework.

[0012] Wherein, the obtaining of the optimal allocation scheme specifically includes: dividing the crew members into , wherein R represents the total number of duty levels; solving sub-problems for each level ; obtaining a global optimal allocation sequence by backtracking.

[0013] Wherein, the objective function for solving the optimal allocation scheme based on the dynamic programming algorithm in the step S109 is: , wherein N represents the total number of beds, .

[0014] Wherein, the method further includes adjusting the local temperature and humidity according to the surface temperature field T and the heart rate variability .

[0015] The application further provides an underwater ship smart bed allocation system based on multi-modal perception and dynamic programming, comprising: a pressure sensor for collecting bed surface pressure distribution data of the smart bed in real time; a temperature sensor for acquiring temperature data of the smart bed; ​a crew scheduling acquisition module, configured to acquire a crew scheduling table, and extract a set of crew members to be assigned in a current shift; a crew state acquisition module, configured to acquire state data of each crew member; an allocation function construction module, configured to construct an intelligent bunk allocation function based on the bed surface pressure distribution data, temperature data of the intelligent bunk, and the state data of each crew member; a scheme acquisition module, configured to acquire an optimal allocation scheme based on a dynamic programming algorithm; a pushing module, configured to push an allocation result to a crew intelligent terminal.

[0016] Compared with the prior art, the present application has the following advantages: The allocation efficiency is improved, the bunk utilization rate is increased to more than 90%, and the crew waiting time is shortened by 70% (simulation data); Health and privacy protection, the privacy curtain blocking rate controlled by the electromagnetic lock is 99.9%, and the heat residue removal efficiency is improved by 50%; Comfort optimization, the PMV (Predicted Mean Vote) index is optimized from ±2.5 to ±0.8, and the HRV (Heart Rate Variability) is improved by 35%; Energy saving and consumption reduction, the FPGA accelerator reduces the computing power consumption by 40%, and the dynamic temperature control saves 15% of the electric energy. BRIEF DESCRIPTION OF DRAWINGS

[0017] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which several embodiments of the present disclosure are shown by way of example, and wherein like or corresponding elements show like or corresponding parts, in which: Figure 1 is a flow chart showing a method for intelligent bunk allocation of underwater ship based on multi-modal perception and dynamic programming according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0019] The terminology used in the description of the embodiments herein is for the purpose of describing particular embodiments only and is not intended to be limiting thereof. As used in the description of the embodiments and the appended claims herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, objects, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, objects, and / or components.

[0020] It is to be understood that the terms first, second, third, etc. can be used herein to describe various... merely for the sake of convenience and are in no way intended to limit the scope of the present embodiments. For example, a first... could also be termed a second... and, similarly, a second... could also be termed a first... without departing from the scope of the present embodiments.

[0021] It is to be understood that the term "and / or", used in the present description, is merely an open term that refers to a conjunctive inclusion, such that the association of items "associated with the... can occur, for example, only in the case of one of the items, in the case of all of the items, or in the case of some of the items.

[0022] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting." Similarly, the phrase "if determined" or "if detecting (a stated condition or event)" can be interpreted to mean "when determined" or "in response to determining" or "when detecting (a stated condition or event)" or "in response to detecting (a stated condition or event)," depending on the context.

[0023] It is also to be understood that the terms "comprise", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or a process that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such product or process. Without further limitation, an element defined by the phrase "comprising a... " does not exclude the existence of additional identical elements in the product or process that includes the stated element.

[0024] The optional embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0025] Embodiment one, As Figure 1 shown, the present application discloses a kind of underwater ship intelligent bunk allocation method based on multi-modal perception and dynamic programming, comprising the following steps: Step S101, the bed surface pressure distribution data of the intelligent bunk is collected in real time; Step S103, the temperature data of the intelligent bunk is acquired; Step S105: Obtain the crew schedule, extract the crew members to be assigned for the current shift, and obtain the status data of each crew member; Step S107: constructing an intelligent bed allocation function based on the bed surface pressure distribution data, the temperature data of the intelligent bed, and the status data of each crew member; Step S109: Obtaining an optimal allocation solution based on a dynamic programming algorithm; Step S1011: Push the allocation result to the crew's smart terminal.

[0026] Example 2 The present invention proposes an underwater ship intelligent berth allocation method based on multimodal perception and dynamic programming, comprising the following steps: Step S101: collecting the bed surface pressure distribution data of the smart bed in real time; Step S103: Acquire temperature data of the smart bed; Step S105: Obtain the crew schedule, extract the crew members to be assigned for the current shift, and obtain the status data of each crew member; Step S107: constructing an intelligent bed allocation function based on the bed surface pressure distribution data, the temperature data of the intelligent bed, and the status data of each crew member; Step S109: Obtaining an optimal allocation solution based on a dynamic programming algorithm; Step S1011: Push the allocation result to the crew's smart terminal.

[0027] Wherein, the step 101 also includes generating a pressure distribution matrix P based on the bed surface pressure distribution data.

[0028] The temperature data in step S103 includes the surface temperature field W of the smart bed and the heat residual index τ.

[0029] The status data in step S105 includes heart rate variability and the time interval between the bed and the last use.

[0030] The smart bed allocation function in step S107 adopts the following formula: ,in Indicates the The allocation priority of the crew members, α, β, γ, δ, ϵ are adjustable weight coefficients, is the pressure gradient norm, Indicates the total available time of the bed, Indicates the remaining rest time. Indicates the Heart rate variability and The bed of the crew member is indicated. The time interval since the last use of the bed of the crew member, The bed of the crew member is indicated. The crew member.

[0031] wherein HRV (Heart Rate Variability) refers to the small fluctuations in consecutive heart beat intervals (RR intervals), reflecting the activity of the autonomic nervous system, and is a key physiological indicator for assessing the fatigue and stress level of the crew member.

[0032] It collects real-time electrocardiogram signals through the crew member wearing a smart bracelet / chest strap (such as Polar H10, Garmin, etc.) through ECG or PPG sensors, or detects heart beat vibrations by laying piezoelectric film or optical fiber sensors on the bed (suitable for sleep period monitoring).

[0033] Wavelet transform (such as Daubechies 4 wavelet) is used to filter out motion artifacts and power frequency interference. The Pan-Tompkins algorithm is used to locate the QRS complex and extract the RR interval sequence.

[0034] The time domain analysis calculates SDNN (standard deviation) and RMSSD (root mean square difference), while the frequency domain analysis obtains LF (0.04-0.15 Hz) and HF (0.15-0.4 Hz) power spectrum through FFT to assess the balance of sympathetic / parasympathetic nerves.

[0035] wherein the adjustable weight coefficients α, β, γ, δ, ϵ are dynamically adjusted through reinforcement learning.

[0036] wherein T total The data source is the shift table of the ship's scheduling system (such as 8-hour shift system), and the formula is wherein represents the start time of the next shift, represents the current time. For example, if the current time is 14:00 and the next shift starts at 22:00, then T total = 8 hours.

[0037] wherein T rest is calculated as follows, and its core variable is the thermal residual index τ (reflecting the temperature residual duration of the bed).

[0038] wherein the thermal residual index τ is the time integral of the temperature field, calculated using the following formula: wherein is the temperature matrix collected by the infrared thermal imager.

[0039] The normalization process is as follows: , which means mapping τ to [0, 1].

[0040] introducing a decay factor, where μ is the decay coefficient, default 0.5. Its physical meaning is that the higher τ (the bed is hotter), the smaller T rest , the lower the allocation priority.

[0041] For example, the infrared data of a bed shows τ norm = 0.8 (high temperature residual), the current shift remaining T total = 6 hours, calculation: T rest = 6⋅(1−0.50.8)≈2.3 hours.

[0042] The allocation impact, the bed's , if γ = 0.3, contributes 0.114 points in the priority function, significantly lower than the cooling bed (such as τ norm = 0.2 contributes 0.26 points).

[0043] In the experiment, T total is obtained in real time by the scheduling system API, with an accuracy of ±1 minute; T rest in the calculation, μ is dynamically adjusted according to the cabin ventilation efficiency (range 0.3~0.7), and the optimal value μ = 0.5 is calibrated through experiments, and the health complaint rate is reduced by 60%.

[0044] The step S109 adopts a hierarchical decision-making framework.

[0045] The optimal allocation scheme is obtained by the following steps: Divide the crew into R layers according to their ranks, for example, 3 layers of captain, chief officer, and sailor, then R = 3; Solve the sub-problems for each layer ; Obtain the global optimal allocation sequence by backtracking.

[0046] The sub-problems are solved by the following formula: where q represents the sequence number of the current crew rank being processed , is a state function, representing the maximum cumulative priority when the first q layers of crew are allocated to the first j beds, and j represents the bed number, .

[0047] The physical meaning of the above formula is that in layer L q , a crew member i is selected to be allocated to bed j, and its priority score Pr i is added to the optimal solution V q−1 (j−1) of the first q−1 layers to the first j−1 beds.

[0048] Among them, crew members of different positions only compete within their own level to avoid cross-level conflicts; after bunk j is allocated, the remaining j-1 bunks are available for use by higher-priority levels.

[0049] In a ship's environment, high-ranking crew members need to prioritize rest (for example, captains face high decision-making pressure). A hierarchical structure ensures positional privileges while reducing the number of computational combinations. For example, a hierarchical structure might be L1 for the captain / first mate (decision-making positions); L2 for the engineer (technical positions); and L3 for the sailor (operational positions). Experiments show that this structure increases solution speed by five times (when p=3 and N=20).

[0050] The objective function of solving the optimal allocation solution based on the dynamic programming algorithm in step S109 is: , where N represents the total number of beds, .

[0051] For example, in order to reasonably allocate k crew members to N berths (usually N ≥ k), the following conditions must be met: One bed per person, with only one berth allocated to each crew member (constraint); Global optimization, maximizing the combined priority scores of all crew members .

[0052] The mathematical form is .

[0053] The dynamic programming solution process is as follows: (1) Status definition The state V(i,S) represents the maximum total priority when assigning the first i crew members to the bunk set S (|S|=i).

[0054] The initial state is V(0,∅)=0.

[0055] (2) State transition equation For crew member i and bunk j∉S: , select the unassigned bed j that maximizes the cumulative priority.

[0056] (3) Backtracking solution Fill in the table, from i=1 to k, traverse all possible S (number of combinations ); Backtracking path, trace back from the final state V(k,S∗) to the allocation of Aij=1.

[0057] The method further comprises the following steps: Adjust local temperature and humidity.

[0058] hierarchical optimization, which directly solves the complexity , needs to be optimized.

[0059] The solution is to stratify by job level (such as captain, chief officer, sailor): , the effect of which reduces the complexity to .

[0060] Example three, The application further provides an underwater ship intelligent bunk allocation system based on multi-modal perception and dynamic programming, comprising: a pressure sensor configured to collect bed surface pressure distribution data of the intelligent bunk in real time; a temperature sensor configured to acquire temperature data of the intelligent bunk; a crew scheduling acquisition module configured to acquire a crew scheduling table and extract a set of crew members to be allocated in a current shift; a crew state acquisition module configured to acquire state data of each crew member; an allocation function construction module configured to construct an intelligent bunk allocation function based on the bed surface pressure distribution data, the temperature data of the intelligent bunk, and the state data of each crew member; a scheme acquisition module configured to acquire an optimal allocation scheme based on a dynamic programming algorithm; a pushing module configured to push an allocation result to a crew intelligent terminal.

[0061] Example four, The embodiment of the present disclosure provides a non-volatile computer storage medium, which stores computer executable instructions, and the computer executable instructions can execute the method steps of the above embodiment.

[0062] Note that the computer readable medium described above can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus or device. In the disclosure, the computer readable signal medium can include a computer readable program code propagated on or through a computer readable medium, in baseband or as part of a carrier wave. The computer readable signal medium can take a variety of forms, including but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0063] The computer readable medium described above can be included in the electronic device described above; alternatively, the computer readable medium can exist as a separate entity in which the electronic device is incorporated.

[0064] Computer program code for carrying out operations of the disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0065] The computer program product of the present disclosure can be a computer program embodied on a non-transitory computer readable medium. When the program runs on a computer, the flowchart and / or block diagram in the flowchart and / or block diagram can be implemented.

[0066] The units described in the embodiments of the present disclosure can be implemented by software or by hardware. In some cases, the names of the units do not constitute a limitation on the units themselves.

[0067] The above describes the preferred embodiments of the present disclosure, which aims to make the spirit of the present disclosure clearer and easier to understand, and is not intended to limit the present disclosure. Any modifications, replacements, improvements made within the spirit and principle of the present disclosure shall be included in the protection scope of the appended claims of the present disclosure.

Claims

1. A method for allocating intelligent berths for underwater ships based on multimodal perception and dynamic programming, characterized in that: The following steps are involved: Step S101: collecting the bed surface pressure distribution data of the smart bed in real time; Step S103: Acquire temperature data of the smart bed; Step S105: Obtain the crew schedule, extract the crew members to be assigned for the current shift, and obtain the status data of each crew member; Step S107: constructing an intelligent bed allocation function based on the bed surface pressure distribution data, the temperature data of the intelligent bed, and the status data of each crew member; Step S109: Obtaining an optimal allocation solution based on a dynamic programming algorithm; Step S1011: Push the allocation result to the crew's smart terminal.

2. The method according to claim 1, wherein The step 101 also includes generating a pressure distribution matrix P based on the bed surface pressure distribution data.

3. The method according to claim 2, wherein: The temperature data in step S103 includes the surface temperature field T of the smart bed and the heat residual index τ.

4. The method according to claim 3, wherein: The status data in step S105 includes heart rate variability and the time interval between the bed and the last use.

5. The method according to claim 4, wherein: The smart bed allocation function in step S107 adopts the following formula: ,in Indicates the The allocation priority of the crew members, α, β, γ, δ, ϵ are adjustable weight coefficients, is the pressure gradient norm, Indicates the total available time of the bed, Indicates the remaining rest time. Indicates the Heart rate variability and Indicates the The time interval between the last use of the crew member's bunk, Indicates the crew members.

6. The method according to claim 1, wherein: The dynamic programming algorithm in step S109 adopts a hierarchical decision framework.

7. The method according to claim 6, wherein: The obtaining of the optimal allocation plan specifically includes: The crew is divided into , where R represents the total number of job levels; For each level , solve the subproblem; The global optimal allocation sequence is obtained through backtracking method.

8. The method according to claim 1, wherein: The objective function of solving the optimal allocation solution based on the dynamic programming algorithm in step S109 is: , where N represents the total number of beds, .

9. The method according to claim 1, wherein: The method further comprises determining the surface temperature field T and the heart rate variability Adjust local temperature and humidity.

10. An intelligent berth allocation system for underwater ships based on multimodal perception and dynamic programming, comprising: A pressure sensor, which is used to collect bed surface pressure distribution data of the smart bed in real time; A temperature sensor, used to obtain temperature data of the smart bed; Crew schedule acquisition module, which is used to obtain the crew schedule and extract the set of crew members to be assigned for the current shift; Crew status acquisition module, which is used to obtain status data of each crew member; an allocation function construction module, configured to construct an intelligent bed allocation function based on the bed surface pressure distribution data, the temperature data of the intelligent beds, and the status data of each crew member; A solution acquisition module is used to obtain the optimal allocation solution based on a dynamic programming algorithm; The push module is used to push the allocation results to the crew's smart terminal.

Images