CN117211973A - Ship liquid ammonia fuel supply control system and method - Google Patents
Ship liquid ammonia fuel supply control system and method Download PDFInfo
- Publication number
- CN117211973A CN117211973A CN202311297657.4A CN202311297657A CN117211973A CN 117211973 A CN117211973 A CN 117211973A CN 202311297657 A CN202311297657 A CN 202311297657A CN 117211973 A CN117211973 A CN 117211973A
- Authority
- CN
- China
- Prior art keywords
- time sequence
- flow
- vector
- liquid ammonia
- timing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000446 fuel Substances 0.000 title claims abstract description 147
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 title claims abstract description 136
- 238000000034 method Methods 0.000 title claims abstract description 53
- 239000013598 vector Substances 0.000 claims abstract description 208
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 230000003247 decreasing effect Effects 0.000 claims abstract description 15
- 238000012546 transfer Methods 0.000 claims description 64
- 239000011159 matrix material Substances 0.000 claims description 41
- 238000005070 sampling Methods 0.000 claims description 37
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims 1
- 230000001105 regulatory effect Effects 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 36
- 238000002485 combustion reaction Methods 0.000 abstract description 7
- 230000002829 reductive effect Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 3
- 229910052799 carbon Inorganic materials 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000001257 hydrogen Substances 0.000 description 2
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 229910052757 nitrogen Inorganic materials 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 229910021529 ammonia Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 239000003034 coal gas Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 150000002431 hydrogen Chemical class 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
Abstract
The application discloses a ship liquid ammonia fuel supply control system and a method thereof, wherein a sensor group is used for collecting pressure values, flow values and temperature values of a plurality of preset time points in a preset time period of liquid ammonia fuel supply; the pressure time sequence input vector, the flow time sequence input vector and the temperature time sequence input vector are arranged according to the time dimension; performing timing collaborative analysis on the pressure timing input vector, the flow timing input vector and the temperature timing input vector to obtain parameter timing collaborative correlation characteristics; and further determines whether the liquid ammonia fuel flow rate value at the current time point should be increased or decreased. Therefore, the parameter automation self-adaptive control of the liquid ammonia fuel supply process can be realized, so that the low efficiency and the untimely caused by the traditional manual control are avoided, the liquid ammonia fuel supply process of the ship is optimized, the combustion efficiency and the energy utilization rate of the liquid ammonia fuel of the ship are improved, and the safe and efficient operation of the ship is ensured.
Description
Technical Field
The application relates to the technical field of intelligent control, in particular to a system and a method for controlling supply of liquid ammonia fuel to a ship.
Background
With the growing awareness of environmental protection and the demand for renewable energy, the shipping industry is increasingly demanding for clean energy. Liquid ammonia is a clean energy source for ship fuel, has the advantages of high energy density, low carbon emission and low cost, can reduce environmental pollution and improve energy utilization rate, and is widely focused and applied in ship fuel systems.
In the process of supplying the liquid ammonia fuel to the ship, the waste and carbon emission of the fuel can be reduced and the pollution to the atmosphere and the water area can be reduced by controlling the supplying process of the liquid ammonia fuel to the ship, thereby realizing more environment-friendly shipping. Meanwhile, the combustion efficiency and the energy utilization rate can be improved, and the fuel consumption is reduced, so that the operation cost is reduced.
However, conventional control schemes for supplying liquid ammonia fuel to ships are generally based on empirical rules or simple feedback control, and cannot fully utilize the dynamic characteristics and complexity of a liquid ammonia fuel system, so that the requirements for accurate control under different working conditions cannot be met. Moreover, conventional marine liquid ammonia fuel supply control typically requires manual parameter adjustment by a crew, which can be very difficult and time consuming for large vessels with a low degree of automation. In addition, in the traditional scheme, monitoring and feedback of the liquid ammonia fuel supply process are often limited, so that ship operators cannot obtain information of key parameters in time, and timely adjustment and optimization are difficult to perform.
Accordingly, an optimized marine liquid ammonia fuel supply control system is desired.
Disclosure of Invention
The embodiment of the application provides a ship liquid ammonia fuel supply control system and a ship liquid ammonia fuel supply control method, wherein a sensor group is used for collecting pressure values, flow values and temperature values of a plurality of preset time points in a preset time period of liquid ammonia fuel supply; the pressure time sequence input vector, the flow time sequence input vector and the temperature time sequence input vector are arranged according to the time dimension; performing timing collaborative analysis on the pressure timing input vector, the flow timing input vector and the temperature timing input vector to obtain parameter timing collaborative correlation characteristics; and further determines whether the liquid ammonia fuel flow rate value at the current time point should be increased or decreased. Therefore, the parameter automation self-adaptive control of the liquid ammonia fuel supply process can be realized, so that the low efficiency and the untimely caused by the traditional manual control are avoided, the liquid ammonia fuel supply process of the ship is optimized, the combustion efficiency and the energy utilization rate of the liquid ammonia fuel of the ship are improved, and the safe and efficient operation of the ship is ensured.
The embodiment of the application also provides a ship liquid ammonia fuel supply control system, which comprises:
the liquid ammonia fuel supply data acquisition module is used for acquiring pressure values, flow values and temperature values of a plurality of preset time points in a preset liquid ammonia fuel supply time period through the sensor group;
the data parameter time sequence arrangement module is used for respectively arranging the pressure values, the flow values and the temperature values of the plurality of preset time points into a pressure time sequence input vector, a flow time sequence input vector and a temperature time sequence input vector according to the time dimension;
the data parameter time sequence collaborative analysis module is used for performing time sequence collaborative analysis on the pressure time sequence input vector, the flow time sequence input vector and the temperature time sequence input vector to obtain parameter time sequence collaborative correlation characteristics;
and the fuel flow rate real-time control module is used for determining that the liquid ammonia fuel flow rate value at the current time point should be increased or decreased based on the parameter time sequence cooperative correlation characteristic.
The embodiment of the application also provides a control method for supplying liquid ammonia fuel to the ship, which comprises the following steps:
collecting pressure values, flow values and temperature values of a plurality of preset time points in a preset time period of liquid ammonia fuel supply through a sensor group;
arranging the pressure values, the flow values and the temperature values of the plurality of preset time points into a pressure time sequence input vector, a flow time sequence input vector and a temperature time sequence input vector according to time dimensions respectively;
performing timing collaborative analysis on the pressure timing input vector, the flow timing input vector and the temperature timing input vector to obtain parameter timing collaborative correlation characteristics;
and determining that the liquid ammonia fuel flow rate value at the current time point is increased or decreased based on the parameter time sequence cooperative correlation characteristic.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a block diagram of a liquid ammonia fuel supply control system for a ship according to an embodiment of the present application.
Fig. 2 is a flowchart of a method for controlling supply of liquid ammonia fuel to a ship according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a system architecture of a method for controlling supply of liquid ammonia fuel to a ship according to an embodiment of the present application.
Fig. 4 is an application scenario diagram of a ship liquid ammonia fuel supply control system provided in an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present application and their descriptions herein are for the purpose of explaining the present application, but are not to be construed as limiting the application.
Unless defined otherwise, all technical and scientific terms used in the embodiments of the application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In describing embodiments of the present application, unless otherwise indicated and limited thereto, the term "connected" should be construed broadly, for example, it may be an electrical connection, or may be a communication between two elements, or may be a direct connection, or may be an indirect connection via an intermediate medium, and it will be understood by those skilled in the art that the specific meaning of the term may be interpreted according to circumstances.
It should be noted that, the term "first\second\third" related to the embodiment of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the application described herein may be practiced in sequences other than those illustrated or described herein.
Liquid Ammonia (Ammonia) is a compound composed of nitrogen (N) and hydrogen (H) elements, and has the chemical formula of NH 3 Is a colorless gas which can be converted into a liquid state by pressurization and temperature reduction at normal temperature. Liquid ammonia has special smell, is alkaline and is soluble in water. Liquid ammonia has higher energy density, is a potential high-efficiency energy source, contains more hydrogen elements than fuel oil and natural gas in unit mass, and is considered as a potential clean fuel substitute in the transportation fields of ships, vehicles and the like. The main emissions generated during the combustion of liquid ammonia are water vapor and nitrogen, without carbon dioxide (CO 2 ) Compared with the traditional fossil fuels such as coal, petroleum and natural gas, the emission of greenhouse gases can be remarkably reduced by using the liquid ammonia, and the environment is more friendly.
In the process of supplying the liquid ammonia fuel to the ship, the waste and carbon emission of the fuel can be reduced and the pollution to the atmosphere and the water area can be reduced by controlling the supplying process of the liquid ammonia fuel to the ship, thereby realizing more environment-friendly shipping. Meanwhile, the combustion efficiency and the energy utilization rate can be improved, and the fuel consumption is reduced, so that the operation cost is reduced. Conventional marine liquid ammonia fueling control schemes are typically based on empirical rules or simple feedback control, which rely primarily on crew experience and manual operation for fueling control.
Specifically, the crew controls parameters of the liquid ammonia fuel supply system, such as valve opening, pump speed, etc., by manual operation, and the crew judges the fuel supply requirement according to experience and observation and adjusts accordingly. Conventional marine liquid ammonia fueling control schemes are typically based on crew experience rules. The crew establishes a set of supply control rules according to the running state of the ship, the load demand, the fuel property and other factors, and the rules may include setting specific parameters such as valve opening, pump speed or fuel flow. In the conventional scheme, a simple feedback control method is also used, and the ship liquid ammonia fuel supply system may be provided with sensors for monitoring parameters in the fuel supply process, such as pressure, temperature, flow rate and the like, and the changes of the parameters can be used as feedback signals for adjusting the control system.
However, conventional solutions require manual manipulation and parameter adjustment by a crew, which can be very difficult and time consuming for large vessels. Moreover, manual operations are susceptible to human factors, which may lead to inaccurate or untimely control. Control schemes based on empirical rules, which are generally static and cannot accommodate the precise control requirements under different conditions, may not fully utilize the dynamic characteristics and complexity of the liquid ammonia fuel system. Monitoring and feedback to the liquid ammonia fuel supply process in the traditional scheme are often limited, and ship operators may not be able to obtain information of key parameters in time, and timely adjustment and optimization are difficult.
The traditional control scheme for supplying liquid ammonia fuel to the ship mainly depends on the experience and manual operation of a crew, and has the problems of manual operation limitation, limitation of experience rules, limitation of monitoring and feedback and the like. Accordingly, there is a need for an optimized automated liquid ammonia fueling control system to improve the efficiency and accuracy of ship fueling.
In one embodiment of the present application, fig. 1 is a block diagram of a liquid ammonia fuel supply control system for a ship provided in the embodiment of the present application. As shown in fig. 1, a ship liquid ammonia fuel supply control system 100 according to an embodiment of the present application includes: a liquid ammonia fuel supply data acquisition module 110 for acquiring pressure values, flow rate values, and temperature values at a plurality of predetermined time points within a predetermined period of liquid ammonia fuel supply by a sensor group; a data parameter time sequence arrangement module 120, configured to arrange the pressure values, the flow values, and the temperature values of the plurality of predetermined time points into a pressure time sequence input vector, a flow time sequence input vector, and a temperature time sequence input vector according to a time dimension, respectively; a data parameter timing collaborative analysis module 130, configured to perform timing collaborative analysis on the pressure timing input vector, the flow timing input vector, and the temperature timing input vector to obtain parameter timing collaborative correlation characteristics; the fuel flow rate real-time control module 140 is used for determining that the liquid ammonia fuel flow rate value at the current time point should be increased or decreased based on the parameter time sequence cooperative correlation characteristic.
In the liquid ammonia fuel supply data acquisition module 110, pressure values, flow rate values, and temperature values at a plurality of predetermined time points within a predetermined period of liquid ammonia fuel supply are acquired by a sensor group. When the module is designed, proper sensors are selected to acquire accurate data, and the factors such as the installation positions of the sensors and the parameter acquisition frequency are ensured to meet the requirements.
The data acquisition module can acquire key parameter data such as pressure, flow and temperature in the liquid ammonia fuel supply process in real time, and the data can be used for subsequent analysis and control to help optimize the performance and efficiency of a fuel supply system.
In the data parameter timing arrangement module 120, the pressure values, the flow values and the temperature values at a plurality of predetermined time points are arranged into a pressure timing input vector, a flow timing input vector and a temperature timing input vector according to a time dimension, and when the module is implemented, it is required to ensure that the timing relationship of data is correct, and that the data is aligned and synchronized. The acquired data can be arranged according to the time sequence through the time sequence arrangement module to form a time sequence input vector, so that the change trend and the relevance of the data can be better analyzed, and a basis is provided for subsequent collaborative analysis and control.
In the data parameter timing collaborative analysis module 130, timing collaborative analysis is performed on the pressure timing input vector, the flow timing input vector, and the temperature timing input vector to obtain parameter timing collaborative correlation characteristics. In implementing the module, a suitable timing analysis method and algorithm, and a suitable feature extraction method need to be selected. By means of the time sequence collaborative analysis module, time sequence association characteristics among different parameters can be mined, and the characteristics can help to understand the interaction relation among the parameters in the fuel supply system, so that basis is provided for subsequent control decisions.
In the fuel flow rate real-time control module 140, it is determined that the liquid ammonia fuel flow rate value at the current time point should be increased or decreased based on the parameter timing cooperative correlation characteristic. When the module is realized, the dynamic response and stability of the system need to be considered by combining an actual control strategy and an algorithm. Through the real-time control module, the fuel flow rate can be adjusted in real time according to the parameter time sequence cooperative correlation characteristics, so that the accurate control of liquid ammonia fuel supply can be realized, and the stability and the efficiency of the system are improved.
Aiming at the technical problems, the technical concept of the application is to monitor and collect the pressure value, the flow value and the temperature value in the liquid ammonia fuel supply process in real time through the sensor group, introduce a data processing and analyzing algorithm at the rear end to carry out the time sequence collaborative analysis of the liquid ammonia fuel supply process parameters, so as to automatically adjust the liquid ammonia supply process parameters in real time based on actual conditions.
Specifically, in the technical scheme of the application, first, pressure values, flow rate values and temperature values at a plurality of preset time points in a preset time period of liquid ammonia fuel supply are collected through a sensor group. The state of the fuel supply system can be monitored in real time by the parameter data such as pressure, flow and temperature collected by the sensor, abnormal conditions or change trends can be found in time by analyzing and processing the data, and feedback information is provided. Based on the collected data, prediction and analysis of fuel demand can be performed, and whether the fuel demand at the current time point is increased or decreased can be inferred by analyzing the change trend of parameters such as pressure, flow, temperature, and the like. The collected pressure, flow, temperature and other parameter data can be used for time sequence collaborative analysis, and the mutual influence relation among different parameters can be revealed by analyzing the time sequence correlation characteristics among the different parameters, so that the dynamic characteristics of the fuel supply system can be better understood, and a basis is provided for the adjustment of the fuel flow rate. Based on the parameter time sequence collaborative correlation characteristic and the fuel demand prediction, the flow velocity value of the liquid ammonia fuel at the current time point can be determined to be increased or decreased, and the control parameters of the liquid ammonia fuel supply system can be adjusted according to the acquired data and the analysis result through the real-time control decision module so as to realize accurate control of the flow velocity.
The sensor is used for collecting the parameter data of the liquid ammonia fuel supply system, so that real-time monitoring and feedback can be provided, the fuel demand is predicted, the parameter time sequence collaborative analysis is performed, and finally, a basis is provided for real-time control decision. These effects can help optimize the performance and efficiency of the liquid ammonia fuel supply system, enabling more accurate and reliable fuel flow rate control.
Then, considering that the pressure value, the flow value and the temperature value in the liquid ammonia fuel supply process have a time sequence dynamic change rule in the time dimension, and have a time sequence cooperative association relationship with each other, the control of the liquid ammonia fuel supply process and the optimization of the energy utilization rate are influenced together. Therefore, in order to capture and describe the time sequence collaborative correlation characteristics among the pressure value, the flow value and the temperature value in the liquid ammonia fuel supply process, so as to perform parameter optimization control, in the technical scheme of the application, the pressure value, the flow value and the temperature value at a plurality of preset time points are further arranged into a pressure time sequence input vector, a flow time sequence input vector and a temperature time sequence input vector according to the time dimension, so that the distribution information of the pressure value, the flow value and the temperature value in time sequence is respectively integrated.
In one embodiment of the present application, the data parameter timing collaborative analysis module includes: the up-sampling unit is used for up-sampling the pressure time sequence input vector, the flow time sequence input vector and the temperature time sequence input vector based on linear interpolation to obtain an up-sampling pressure time sequence input vector, an up-sampling flow time sequence input vector and an up-sampling temperature time sequence input vector; the vector-image conversion unit is used for respectively passing the up-sampling pressure time sequence input vector, the up-sampling flow time sequence input vector and the up-sampling temperature time sequence input vector through the vector-image conversion module to obtain a pressure time sequence input image, a flow time sequence input image and a temperature time sequence input image; the data parameter time sequence feature extraction unit is used for respectively carrying out feature extraction on the pressure time sequence input image, the flow time sequence input image and the temperature time sequence input image through a time sequence feature extractor based on a deep neural network model so as to obtain a pressure time sequence feature vector, a flow time sequence feature vector and a temperature time sequence feature vector; and the data parameter time sequence feature collaborative correlation coding unit is used for fusing the pressure time sequence feature vector, the flow time sequence feature vector and the temperature time sequence feature vector to obtain parameter time sequence collaborative correlation features.
Wherein the deep neural network model is the convolutional neural network model.
Then, in order to improve the capturing capability of fine time sequence variation of each parameter in the liquid ammonia fuel supply process, in the technical scheme of the application, up-sampling based on linear interpolation is further carried out on the pressure time sequence input vector, the flow time sequence input vector and the temperature time sequence input vector respectively to obtain an up-sampling pressure time sequence input vector, an up-sampling flow time sequence input vector and an up-sampling temperature time sequence input vector, so that the density and smoothness of each liquid ammonia fuel supply parameter data are increased, and the subsequent better representation of the parameter time sequence characteristics of the liquid ammonia fuel supply process is facilitated.
Further, in order to better extract time sequence change characteristics of each parameter in the liquid ammonia fuel supply process, in the technical scheme of the application, the up-sampling pressure time sequence input vector, the up-sampling flow time sequence input vector and the up-sampling temperature time sequence input vector are respectively passed through a vector-image conversion module to obtain a pressure time sequence input image, a flow time sequence input image and a temperature time sequence input image. It should be appreciated that, since the images have rich visual information, the time sequence distribution and the variation trend of the data can be more easily understood and analyzed, and thus, by converting the parameter time sequence input vector in the liquid ammonia fuel supply process into the images, the variation trend and the mode of the data can be more intuitively displayed, which is beneficial to the subsequent data processing and analysis and the real-time self-adaptive control of the liquid ammonia fuel supply process parameters.
And then, further extracting the characteristics of the pressure time sequence input image, the flow time sequence input image and the temperature time sequence input image respectively by a time sequence characteristic extractor based on a convolutional neural network model so as to extract time sequence distribution information of the pressure value, the flow value and the temperature value in the liquid ammonia fuel supply process in the time dimension respectively in the pressure time sequence input image, the flow time sequence input image and the temperature time sequence input image, thereby obtaining a pressure time sequence characteristic vector, a flow time sequence characteristic vector and a temperature time sequence characteristic vector.
In one embodiment of the present application, the data parameter timing characteristic cooperative association coding unit is configured to: and fusing the pressure time sequence feature vector, the flow time sequence feature vector and the temperature time sequence feature vector by using a Bayesian model to obtain a parameter posterior feature vector as the parameter time sequence cooperative correlation feature.
And then, carrying out feature fusion on the pressure time sequence feature vector, the flow time sequence feature vector and the temperature time sequence feature vector, so as to improve the accuracy of real-time control of the flow rate of the liquid ammonia fuel. It should be appreciated that bayesian models can effectively cope with uncertainties, and that in a ship liquid ammonia fuel supply control system, there is often some noise and error in the measurement of parameters such as pressure, flow rate and temperature, while ship liquid ammonia fuel supply control involves a plurality of parameters, the time-series changes of which can affect each other. Therefore, in the technical scheme of the application, a Bayesian model is further used for fusing the pressure time sequence feature vector, the flow time sequence feature vector and the temperature time sequence feature vector to obtain a parameter posterior feature vector. That is, by using the bayesian model, the time sequence feature vectors of a plurality of parameters such as pressure, flow rate and temperature can be comprehensively considered, and the time sequence feature information of the time sequence feature vectors can be fused to obtain a more comprehensive and comprehensive parameter posterior feature vector.
In one embodiment of the present application, the fuel flow rate real-time control module includes: the transfer association coding unit is used for calculating a transfer matrix of the flow time sequence feature vector relative to the parameter posterior feature vector so as to obtain a flow time sequence transfer feature matrix; the characteristic distribution optimizing unit is used for performing Hilbert orthogonal space domain representation decoupling on the flow time sequence transfer characteristic vector obtained after the flow time sequence transfer characteristic matrix is unfolded so as to obtain an optimized flow time sequence transfer characteristic matrix; and the flow rate regulation and control unit is used for enabling the optimized flow time sequence transfer characteristic matrix to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating that the flow rate value of the liquid ammonia fuel at the current time point is required to be increased or decreased.
In order to perform real-time adaptive control on parameters in the liquid ammonia fuel supply process more accurately, in the technical scheme of the application, a transfer matrix of the flow time sequence feature vector relative to the parameter posterior feature vector is further calculated, so that the flow time sequence distribution feature is mapped into a high-dimensional space of each parameter time sequence collaborative association distribution feature in the liquid ammonia fuel supply process, and a flow time sequence transfer feature matrix is obtained.
Further, the transfer association encoding unit is configured to: calculating a transfer matrix of the flow time sequence feature vector relative to the parameter posterior feature vector according to the following transfer formula to obtain a flow time sequence transfer feature matrix; wherein, the transfer formula is:
M1=VaT⊗Vc
where Va represents the flow timing eigenvector, vaT represents a transpose of the flow timing eigenvector, vc represents the parametric posterior eigenvector, M1 represents the flow timing transfer eigenvector, and ⊗ represents matrix multiplication.
In particular, in the technical solution of the present application, the pressure timing feature vector, the flow timing feature vector, and the temperature timing feature vector express the local time domain-local time domain timing correlation feature in the global time domain of the vector-image conversion, respectively, so that the parameter posterior feature vector obtained by using a bayesian model to fuse the pressure timing feature vector, the flow timing feature vector, and the temperature timing feature vector also has a local time domain-local time domain timing correlation parameter posterior feature representation in the global time domain, so that the flow timing transfer feature matrix obtained by calculating the transfer matrix of the flow timing feature vector relative to the parameter posterior feature vector has a diversified feature representation corresponding to a multi-time domain spatial scale in the local time domain-global time domain in addition to the a priori-posterior domain transfer feature. Therefore, when the flow time sequence transfer feature matrix passes through the classifier, the time domain space diversity time sequence association feature representation of the flow time sequence transfer feature matrix influences the generalization effect from the time domain feature space domain to the classification regression domain as a whole, namely, influences the accuracy of the classification result of the flow time sequence transfer feature matrix.
Based on this, when classifying the flow timing transfer feature matrix, the applicant of the present application preferably performs hilbert orthogonal spatial domain representation decoupling on the flow timing transfer feature vector obtained after the flow timing transfer feature matrix is expanded, for example, denoted as V, and the method is expressed as: performing Hilbert orthogonal space domain representation decoupling on the flow time sequence transfer characteristic vector obtained after the flow time sequence transfer characteristic matrix is unfolded by using the following optimization formula to obtain the optimized flow time sequence transfer characteristic matrix;
wherein, the optimization formula is:
V'=V1⊝V2
V1=Cov1D[v, V2L, V]
V2=I⊝V1
wherein V is a flow timing transfer feature vector obtained after the flow timing transfer feature matrix is expanded, V is a global feature mean value of the flow timing transfer feature vector, V2 is a two-norm value of the flow timing transfer feature vector, L is a length of the flow timing transfer feature vector, I is a unit vector, ⊝ is a vector subtraction, cov1D (∙) is a covariance matrix, and V' is an optimized flow timing transfer feature vector obtained after the optimized flow timing transfer feature matrix is expanded.
Here, the hilbert orthogonal spatial domain representation decoupling is used to enhance the domain-adaptive generalization performance of the traffic timing transfer feature vector V from the time domain feature spatial domain to the classification regression domain by emphasizing the domain-specific (domain-specific) information within the diversified feature representation of the traffic timing transfer feature vector V, i.e., by performing the orthogonal spatial domain decoupling of domain-invariant (domain-invariant) representation within the overall domain representation of the traffic timing transfer feature vector V based on the vector-self-spatial metric and the hilbert spatial metric under the vector-self-inner product representation, thereby enhancing the accuracy of the classification values of the traffic timing transfer feature matrix obtained by the classifier. Therefore, the process parameters of liquid ammonia supply can be automatically adjusted in real time based on actual conditions, so that parameter automatic self-adaptive control of a liquid ammonia fuel supply process is realized, the liquid ammonia fuel supply process of a ship is optimized, the combustion efficiency and the energy utilization rate of the liquid ammonia fuel of the ship are improved, and the safe and efficient operation of the ship is ensured.
In one embodiment of the present application, the flow rate regulation unit includes: a matrix expansion subunit, configured to expand the optimized traffic timing transfer feature matrix into a classification feature vector according to a row vector or a column vector; a full-connection coding subunit, configured to perform full-connection coding on the classification feature vector by using multiple full-connection layers of the classifier to obtain a coded classification feature vector; and the classification subunit is used for passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
And further, the optimized flow time sequence transfer characteristic matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the liquid ammonia fuel flow rate value at the current time point is required to be increased or decreased. That is, classification processing is performed based on timing distribution characteristic information on the flow rate in the background of timing cooperative correlation characteristics of each parameter in the liquid ammonia fuel supply process, so that the liquid ammonia fuel flow rate value at the current time point is adaptively controlled. Therefore, the process parameters of liquid ammonia supply can be automatically adjusted in real time based on actual conditions, and parameter automatic self-adaptive control of the liquid ammonia fuel supply process is realized, so that low efficiency and untimely caused by traditional manual control are avoided, the liquid ammonia fuel supply process of the ship is optimized, the combustion efficiency and the energy utilization rate of the liquid ammonia fuel of the ship are improved, and meanwhile, the safe and efficient operation of the ship is ensured.
In summary, the ship liquid ammonia fuel supply control system 100 according to the embodiment of the application is illustrated, the pressure value, the flow value and the temperature value in the liquid ammonia fuel supply process are monitored and collected in real time through the sensor group, and the data processing and analysis algorithm is introduced into the rear end to perform the time sequence collaborative analysis of the liquid ammonia fuel supply process parameters, so as to automatically adjust the liquid ammonia supply process parameters in real time based on actual conditions.
As described above, the ship liquid ammonia fuel supply control system 100 according to the embodiment of the present application can be implemented in various terminal devices, such as a server or the like for ship liquid ammonia fuel supply control. In one example, the ship liquid ammonia fueling control system 100 according to an embodiment of the present application may be integrated into the terminal device as a software module and/or hardware module. For example, the ship liquid ammonia fuel supply control system 100 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the ship liquid ammonia fuel supply control system 100 can equally be one of the numerous hardware modules of the terminal device.
Alternatively, in another example, the ship liquid ammonia fuel supply control system 100 and the terminal device may be separate devices, and the ship liquid ammonia fuel supply control system 100 may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information in a contracted data format.
Fig. 2 is a flowchart of a method for controlling supply of liquid ammonia fuel to a ship according to an embodiment of the present application. Fig. 3 is a schematic diagram of a system architecture of a method for controlling supply of liquid ammonia fuel to a ship according to an embodiment of the present application. As shown in fig. 2 and 3, a method for controlling liquid ammonia fuel supply to a ship comprises: 210, collecting pressure values, flow values and temperature values of a plurality of preset time points in a preset time period of liquid ammonia fuel supply through a sensor group; 220, arranging the pressure values, the flow values and the temperature values of the plurality of preset time points into a pressure time sequence input vector, a flow time sequence input vector and a temperature time sequence input vector according to a time dimension respectively; 230, performing timing collaborative analysis on the pressure timing input vector, the flow timing input vector and the temperature timing input vector to obtain parameter timing collaborative correlation characteristics; 240, determining that the liquid ammonia fuel flow rate value at the current time point should be increased or decreased based on the parameter time sequence cooperative correlation characteristic.
In the ship liquid ammonia fuel supply control method, performing timing collaborative analysis on the pressure timing input vector, the flow timing input vector and the temperature timing input vector to obtain parameter timing collaborative correlation characteristics, including: up-sampling based on linear interpolation is respectively carried out on the pressure time sequence input vector, the flow time sequence input vector and the temperature time sequence input vector so as to obtain an up-sampling pressure time sequence input vector, an up-sampling flow time sequence input vector and an up-sampling temperature time sequence input vector; the up-sampling pressure time sequence input vector, the up-sampling flow time sequence input vector and the up-sampling temperature time sequence input vector are respectively passed through a vector-image conversion module to obtain a pressure time sequence input image, a flow time sequence input image and a temperature time sequence input image; respectively carrying out feature extraction on the pressure time sequence input image, the flow time sequence input image and the temperature time sequence input image through a time sequence feature extractor based on a deep neural network model so as to obtain a pressure time sequence feature vector, a flow time sequence feature vector and a temperature time sequence feature vector; and fusing the pressure time sequence feature vector, the flow time sequence feature vector and the temperature time sequence feature vector to obtain parameter time sequence cooperative association features.
It will be appreciated by those skilled in the art that the specific operation of each step in the above-described ship liquid ammonia fuel supply control method has been described in detail in the above description with reference to the ship liquid ammonia fuel supply control system of fig. 1, and thus, repetitive description thereof will be omitted.
Fig. 4 is an application scenario diagram of a ship liquid ammonia fuel supply control system provided in an embodiment of the present application. As shown in fig. 4, in this application scenario, first, pressure values (e.g., C1 as illustrated in fig. 4), flow rate values (e.g., C2 as illustrated in fig. 4), and temperature values (e.g., C3 as illustrated in fig. 4) at a plurality of predetermined time points within a predetermined period of liquid ammonia fuel supply are acquired by a sensor group; the acquired pressure value, flow value and temperature value are then input into a server (e.g. S as illustrated in fig. 4) deployed with a ship liquid ammonia fueling control algorithm, wherein the server is capable of processing the pressure value, the flow value and the temperature value based on the ship liquid ammonia fueling control algorithm to determine whether the liquid ammonia fuel flow rate value at the current point in time should be increased or decreased.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (10)
1. A liquid ammonia fuel supply control system for a ship, comprising:
the liquid ammonia fuel supply data acquisition module is used for acquiring pressure values, flow values and temperature values of a plurality of preset time points in a preset liquid ammonia fuel supply time period through the sensor group;
the data parameter time sequence arrangement module is used for respectively arranging the pressure values, the flow values and the temperature values of the plurality of preset time points into a pressure time sequence input vector, a flow time sequence input vector and a temperature time sequence input vector according to the time dimension;
the data parameter time sequence collaborative analysis module is used for performing time sequence collaborative analysis on the pressure time sequence input vector, the flow time sequence input vector and the temperature time sequence input vector to obtain parameter time sequence collaborative correlation characteristics;
and the fuel flow rate real-time control module is used for determining that the liquid ammonia fuel flow rate value at the current time point should be increased or decreased based on the parameter time sequence cooperative correlation characteristic.
2. The ship liquid ammonia fuel supply control system of claim 1, wherein the data parameter timing collaborative analysis module comprises:
the up-sampling unit is used for up-sampling the pressure time sequence input vector, the flow time sequence input vector and the temperature time sequence input vector based on linear interpolation to obtain an up-sampling pressure time sequence input vector, an up-sampling flow time sequence input vector and an up-sampling temperature time sequence input vector;
the vector-image conversion unit is used for respectively passing the up-sampling pressure time sequence input vector, the up-sampling flow time sequence input vector and the up-sampling temperature time sequence input vector through the vector-image conversion module to obtain a pressure time sequence input image, a flow time sequence input image and a temperature time sequence input image;
the data parameter time sequence feature extraction unit is used for respectively carrying out feature extraction on the pressure time sequence input image, the flow time sequence input image and the temperature time sequence input image through a time sequence feature extractor based on a deep neural network model so as to obtain a pressure time sequence feature vector, a flow time sequence feature vector and a temperature time sequence feature vector;
and the data parameter time sequence feature collaborative correlation coding unit is used for fusing the pressure time sequence feature vector, the flow time sequence feature vector and the temperature time sequence feature vector to obtain parameter time sequence collaborative correlation features.
3. The marine liquid ammonia fuel supply control system of claim 2, wherein the deep neural network model is the convolutional neural network model.
4. A ship liquid ammonia fuel supply control system according to claim 3, wherein the data parameter timing characteristics cooperatively associated with the encoding unit is configured to: and fusing the pressure time sequence feature vector, the flow time sequence feature vector and the temperature time sequence feature vector by using a Bayesian model to obtain a parameter posterior feature vector as the parameter time sequence cooperative correlation feature.
5. The ship liquid ammonia fuel supply control system of claim 4, wherein the fuel flow rate real-time control module comprises:
the transfer association coding unit is used for calculating a transfer matrix of the flow time sequence feature vector relative to the parameter posterior feature vector so as to obtain a flow time sequence transfer feature matrix;
the characteristic distribution optimizing unit is used for performing Hilbert orthogonal space domain representation decoupling on the flow time sequence transfer characteristic vector obtained after the flow time sequence transfer characteristic matrix is unfolded so as to obtain an optimized flow time sequence transfer characteristic matrix;
and the flow rate regulation and control unit is used for enabling the optimized flow time sequence transfer characteristic matrix to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating that the flow rate value of the liquid ammonia fuel at the current time point is required to be increased or decreased.
6. The ship liquid ammonia fuel supply control system according to claim 5, wherein the transfer association encoding unit is configured to: calculating a transfer matrix of the flow time sequence feature vector relative to the parameter posterior feature vector according to the following transfer formula to obtain a flow time sequence transfer feature matrix;
wherein, the transfer formula is:
M1=VaT⊗Vc
where Va represents the flow timing eigenvector, vaT represents a transpose of the flow timing eigenvector, vc represents the parametric posterior eigenvector, M1 represents the flow timing transfer eigenvector, and ⊗ represents matrix multiplication.
7. The ship liquid ammonia fuel supply control system according to claim 6, wherein the characteristic distribution optimizing unit is configured to: performing Hilbert orthogonal space domain representation decoupling on the flow time sequence transfer characteristic vector obtained after the flow time sequence transfer characteristic matrix is unfolded by using the following optimization formula to obtain the optimized flow time sequence transfer characteristic matrix;
wherein, the optimization formula is:
V'=V1⊝V2
V1=Cov1D[v, V2L, V]
V2=I⊝V1
wherein V is a flow timing transfer feature vector obtained after the flow timing transfer feature matrix is expanded, V is a global feature mean value of the flow timing transfer feature vector, V2 is a two-norm value of the flow timing transfer feature vector, L is a length of the flow timing transfer feature vector, I is a unit vector, ⊝ is a vector subtraction, cov1D (∙) is a covariance matrix, and V' is an optimized flow timing transfer feature vector obtained after the optimized flow timing transfer feature matrix is expanded.
8. The ship liquid ammonia fuel supply control system according to claim 7, wherein the flow rate regulating unit comprises:
a matrix expansion subunit, configured to expand the optimized traffic timing transfer feature matrix into a classification feature vector according to a row vector or a column vector;
a full-connection coding subunit, configured to perform full-connection coding on the classification feature vector by using multiple full-connection layers of the classifier to obtain a coded classification feature vector; and
and the classification subunit is used for passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
9. A method for controlling supply of liquid ammonia fuel to a ship, comprising:
collecting pressure values, flow values and temperature values of a plurality of preset time points in a preset time period of liquid ammonia fuel supply through a sensor group;
arranging the pressure values, the flow values and the temperature values of the plurality of preset time points into a pressure time sequence input vector, a flow time sequence input vector and a temperature time sequence input vector according to time dimensions respectively;
performing timing collaborative analysis on the pressure timing input vector, the flow timing input vector and the temperature timing input vector to obtain parameter timing collaborative correlation characteristics;
and determining that the liquid ammonia fuel flow rate value at the current time point is increased or decreased based on the parameter time sequence cooperative correlation characteristic.
10. The ship liquid ammonia fuel supply control method according to claim 9, wherein performing timing collaborative analysis on the pressure timing input vector, the flow timing input vector, and the temperature timing input vector to obtain parameter timing collaborative correlation characteristics, comprises:
up-sampling based on linear interpolation is respectively carried out on the pressure time sequence input vector, the flow time sequence input vector and the temperature time sequence input vector so as to obtain an up-sampling pressure time sequence input vector, an up-sampling flow time sequence input vector and an up-sampling temperature time sequence input vector;
the up-sampling pressure time sequence input vector, the up-sampling flow time sequence input vector and the up-sampling temperature time sequence input vector are respectively passed through a vector-image conversion module to obtain a pressure time sequence input image, a flow time sequence input image and a temperature time sequence input image;
respectively carrying out feature extraction on the pressure time sequence input image, the flow time sequence input image and the temperature time sequence input image through a time sequence feature extractor based on a deep neural network model so as to obtain a pressure time sequence feature vector, a flow time sequence feature vector and a temperature time sequence feature vector;
and fusing the pressure time sequence feature vector, the flow time sequence feature vector and the temperature time sequence feature vector to obtain parameter time sequence cooperative association features.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311297657.4A CN117211973A (en) | 2023-10-09 | 2023-10-09 | Ship liquid ammonia fuel supply control system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311297657.4A CN117211973A (en) | 2023-10-09 | 2023-10-09 | Ship liquid ammonia fuel supply control system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117211973A true CN117211973A (en) | 2023-12-12 |
Family
ID=89037089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311297657.4A Pending CN117211973A (en) | 2023-10-09 | 2023-10-09 | Ship liquid ammonia fuel supply control system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117211973A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117520993A (en) * | 2023-12-29 | 2024-02-06 | 杭州杭叉桥箱有限公司 | Electric drive axle test system and method thereof |
| CN117803946A (en) * | 2024-02-29 | 2024-04-02 | 山西漳电科学技术研究院(有限公司) | Safety control system and method for low-calorific-value coal burning boiler |
-
2023
- 2023-10-09 CN CN202311297657.4A patent/CN117211973A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117520993A (en) * | 2023-12-29 | 2024-02-06 | 杭州杭叉桥箱有限公司 | Electric drive axle test system and method thereof |
| CN117520993B (en) * | 2023-12-29 | 2024-03-08 | 杭州杭叉桥箱有限公司 | Electric drive axle test system and method thereof |
| CN117803946A (en) * | 2024-02-29 | 2024-04-02 | 山西漳电科学技术研究院(有限公司) | Safety control system and method for low-calorific-value coal burning boiler |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117211973A (en) | Ship liquid ammonia fuel supply control system and method | |
| Zhao et al. | A data-enhanced distributionally robust optimization method for economic dispatch of integrated electricity and natural gas systems with wind uncertainty | |
| CN109614981B (en) | Power system intelligent fault detection method and system based on spearman level-dependent convolutional neural network | |
| Zhan et al. | Deepthermal: Combustion optimization for thermal power generating units using offline reinforcement learning | |
| CN101266462B (en) | Process control and optimization technique using immunological concepts | |
| CN109034260B (en) | Desulfurization tower oxidation fan fault diagnosis system and method based on statistical principle and intelligent optimization | |
| WO2009025561A1 (en) | System and method for empirical ensemble-based virtual sensing | |
| Hu et al. | Hierarchical pressure data recovery for pipeline network via generative adversarial networks | |
| CN110349067A (en) | A kind of intelligent operational system and method for ocean nuclear power platform | |
| CN116688754A (en) | Ship flue gas desulfurization automatic control system and method thereof | |
| CN112232373A (en) | Method and system for predicting carbon content of boiler fly ash | |
| Chang et al. | Consistent-contrastive network with temporality-awareness for robust-to-anomaly industrial soft sensor | |
| US11761623B2 (en) | Apparatus for combustion optimization and method therefor | |
| CN114444811A (en) | Aluminum electrolysis mixing data superheat degree prediction method based on attention mechanism | |
| Shuvo et al. | Prediction of hourly total energy in combined cycle power plant using machine learning techniques | |
| CN116534237B (en) | Marine methanol supply method and system | |
| CN114170138A (en) | Unsupervised industrial image anomaly detection model establishing method, detection method and system | |
| Zdravković et al. | Towards explainable AI-assisted operations in District Heating Systems | |
| US20200166205A1 (en) | Apparatus for managing combustion optimization and method therefor | |
| Liao et al. | Wind power prediction based on periodic characteristic decomposition and multi-layer attention network | |
| CN109657943A (en) | Dynamic assessment method, device and the electronic equipment of wind power plant operating states of the units | |
| Fei et al. | Evaluation of complex industrial process operating state based on static and dynamic cooperative perception | |
| Zhang et al. | Prediction Method of NO x from Power Station Boilers Based on Neural Network | |
| CN115456451B (en) | AIS-based ship oil consumption estimation method and system | |
| Guanglei et al. | Design of Ship Monitoring System Based on Unsupervised Learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |