Phosphor shrimp ship waste heat temperature control method, model, device and storage medium

Abstract

The application discloses a phosphorus shrimp ship waste heat temperature control method, a model, equipment and a storage medium, and the method comprises the following steps: collecting waste heat power and waste heat pressure of a phosphorus shrimp ship waste gas pipeline, and generating a time-related waste heat sequence according to the waste heat power and the waste heat pressure; decomposing the time-related waste heat sequence into a preset number of waste heat subsequences through a VMD algorithm model; optimizing model parameters of an Elman neural network according to the preset number of waste heat subsequences through a GWO algorithm model; and performing temperature prediction through the optimized Elman neural network, so that a preset temperature control model realizes target phosphorus shrimp ship waste heat temperature control through a PID controller based on predicted waste heat temperature and actual waste heat temperature. Through the combination of the VMD-GWO-Elman-PID model, better temperature control and shorter training time are realized, so that the phosphorus shrimp ship waste heat temperature control precision is significantly improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of temperature control, and particularly relates to a phosphorus shrimp ship waste heat temperature control method, model, device and storage medium. BACKGROUND

[0002] At present, the magnetic suspension cold water unit is widely used in phosphorus shrimp ships, and the conventional PID control algorithm is commonly used. The difference between the actual outlet water temperature of the phosphorus shrimp ship waste gas pipeline and the set temperature is taken as the control object, and the proportional coefficient (P), integral coefficient (I) and differential coefficient (D) are adjusted. The conventional PID algorithm has stable control effect on simple control system, but for the magnetic suspension variable frequency type cold water unit control system, because there are too many uncertain variables, the running mode of each component of the unit is difficult to describe through accurate mathematical model, and the whole control feedback system has strong nonlinearity, high time lag and non-minimum phase difficulty. The existence of non-minimum phase makes the system have certain phase lag, which leads to higher delay of the control feedback of the phosphorus shrimp ship waste gas pipeline outlet water temperature, and further leads to poor control effect, especially the rapid response of the phosphorus shrimp ship waste gas pipeline outlet water temperature feedback change becomes poor, and the tracking calibration of the system also has high difficulty, which leads to a certain degree of calibration error of the conventional PID algorithm, so that the ideal control effect cannot be achieved.

[0003] The above content is only used to assist in understanding the technical solutions of the present application, and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a phosphorus shrimp ship waste heat temperature control method, model, device and storage medium, which aims to solve the technical problem of how to improve the control precision of phosphorus shrimp ship waste heat temperature.

[0005] To achieve the above purpose, the present application provides a phosphorus shrimp ship waste heat temperature control method, which comprises:

[0006] Collecting the waste heat power and waste heat pressure of the phosphorus shrimp ship waste gas pipeline, and generating a time-related waste heat sequence according to the waste heat power and the waste heat pressure;

[0007] The time-related waste heat sequence is input into a preset temperature control model, and the preset temperature prediction model is composed of a VMD algorithm model, a GWO algorithm model, an Elman neural network and a PID controller.

[0008] The time-dependent waste heat sequence is decomposed into a preset number of waste heat subsequences by the VMD algorithm model, the model parameters of the Elman neural network are optimized according to the preset number of waste heat subsequences by the GWO algorithm model, and temperature prediction is performed by the optimized Elman neural network, so that the preset temperature control model realizes target waste heat temperature control based on the predicted waste heat temperature and the actual waste heat temperature by the PID controller.

[0009] Optionally, the step of generating a time-dependent waste heat sequence according to the waste heat power and the waste heat pressure comprises:

[0010] According to the waste heat power and the waste heat pressure, a waste heat point set is constructed according to time coding, and a waste heat distribution map is generated according to the waste heat point set;

[0011] Based on the waste heat distribution map, a plurality of waste heat pressure intervals and a plurality of waste heat power intervals are divided;

[0012] The quartile points of the waste heat pressure in each waste heat pressure interval and the quartile points of the waste heat power in each waste heat power interval are determined by the quintile algorithm;

[0013] According to the quartile points of the waste heat pressure in each waste heat pressure interval, a pressure quartile point interval corresponding to each waste heat pressure interval is constructed, and according to the quartile points of the waste heat power in each waste heat power interval, a power quartile point interval corresponding to each waste heat power interval is constructed;

[0014] Based on the pressure quartile point interval corresponding to each waste heat pressure interval and the power quartile point interval corresponding to each waste heat power interval, a time-dependent waste heat sequence is determined.

[0015] Optionally, the step of determining a time-dependent waste heat sequence based on the pressure quartile point interval corresponding to each waste heat pressure interval and the power quartile point interval corresponding to each waste heat power interval comprises:

[0016] Abnormal pressure data outside the pressure quartile point interval corresponding to each waste heat pressure interval is determined, and the average waste heat pressure in the waste heat pressure interval corresponding to the abnormal pressure data is calculated, so that the average waste heat pressure replaces the abnormal pressure data;

[0017] Abnormal power data outside the power quartile point interval corresponding to each waste heat power interval is determined, and the average waste heat power in the waste heat power interval corresponding to the abnormal power data is calculated, so that the average waste heat power replaces the abnormal power data;

[0018] The waste heat pressure data and the waste heat power data corresponding to the waste heat distribution map are output in time coding order;

[0019] generating a waste heat pressure power sequence according to the waste heat pressure data and the waste heat power data;

[0020] normalizing the waste heat pressure power sequence to obtain a time-dependent waste heat sequence.

[0021] Optionally, the step of decomposing the time-dependent waste heat sequence into a preset number of waste heat subsequences through a VMD algorithm model comprises:

[0022] constructing a modal broadband constrained variational problem through a VMD algorithm model according to the time-dependent waste heat sequence;

[0023] converting the modal broadband constrained variational problem into a modal broadband unconstrained variational problem through a quadratic penalty factor and a Lagrange multiplier operator;

[0024] solving the modal broadband unconstrained variational problem through an alternating direction method of multipliers and a Fourier transform to obtain the preset number of waste heat subsequences.

[0025] Optionally, the step of optimizing model parameters of an Elman neural network according to the preset number of waste heat subsequences through a GWO algorithm model comprises:

[0026] optimizing the GWO algorithm model based on a convergence factor varying according to a sine law to obtain a GWO modified expression;

[0027] constructing a temperature search formula according to the GWO modified expression;

[0028] obtaining an optimal temperature measurement value through the temperature search formula according to the preset number of waste heat subsequences;

[0029] constructing a waste heat temperature dataset according to the temperature measurement value of a preset time, the preset number of waste heat subsequences and the optimal temperature measurement value;

[0030] optimizing model parameters of an Elman neural network based on the waste heat temperature dataset.

[0031] Optionally, the step of achieving target waste heat temperature control through a PID control algorithm based on the predicted waste heat temperature and the actual waste heat temperature comprises:

[0032] determining a temperature difference signal according to a target waste heat temperature and the actual waste heat temperature;

[0033] achieving target waste heat temperature control through a PID control algorithm according to the temperature difference signal and the predicted waste heat temperature.

[0034] In addition, to achieve the above object, the application further provides a preset temperature control model based on the waste heat temperature control method of the euphausiid ship.

[0035] The VMD algorithm model is used to decompose the time-related waste heat sequence into a preset number of waste heat subsequences.

[0036] The GWO algorithm model is used to optimize the model parameters of the Elman neural network according to the preset number of waste heat subsequences, so that the optimized Elman neural network performs temperature prediction.

[0037] The PID controller is used to realize target waste heat temperature control through the PID control algorithm based on the predicted waste heat temperature and the actual waste heat temperature.

[0038] In addition, to achieve the above object, the application further provides a waste heat temperature control device for a euphausiid ship, which comprises a memory, a processor and a waste heat temperature control program for a euphausiid ship stored on the memory and executable on the processor, wherein the waste heat temperature control program for a euphausiid ship is configured to realize the steps of the waste heat temperature control method for a euphausiid ship as described above.

[0039] In addition, to achieve the above object, the application further provides a storage medium having a waste heat temperature control program for a euphausiid ship stored thereon, wherein the waste heat temperature control program for a euphausiid ship is executed by a processor to realize the steps of the waste heat temperature control method for a euphausiid ship as described above.

[0040] The application first collects the waste heat power and waste heat pressure of the exhaust pipe of the euphausiid ship, generates a time-related waste heat sequence according to the waste heat power and waste heat pressure, then decomposes the time-related waste heat sequence into a preset number of waste heat subsequences through the VMD algorithm model, optimizes the model parameters of the Elman neural network according to the preset number of waste heat subsequences through the GWO algorithm model, performs temperature prediction through the optimized Elman neural network, outputs the predicted waste heat temperature, and finally realizes target waste heat temperature control through the PID control algorithm based on the predicted waste heat temperature and the actual waste heat temperature. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 is a structural schematic view of the phosphorus shrimp ship waste heat temperature control device of the hardware running environment related to the embodiment scheme of the present application.

[0042] Figure 2 is a flow schematic view of the first embodiment of the phosphorus shrimp ship waste heat temperature control method of the present application.

[0043] Figure 3 is a structural block diagram of the first embodiment of the preset temperature control model of the present application.

[0044] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.

[0046] Referring to Figure 1 , Figure 1 is a structural schematic view of the phosphorus shrimp ship waste heat temperature control device of the hardware running environment related to the embodiment scheme of the present application.

[0047] As Figure 1 shown, the phosphorus shrimp ship waste heat temperature control device can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between the components. The user interface 1003 can include a display, an input unit such as a keyboard, and can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 can be a high-speed random access memory (RAM), and can also be a stable non-volatile memory (NVM), such as a disk memory. The memory 1005 can also be an independent storage system from the aforementioned processor 1001.

[0048] Those skilled in the art can understand that Figure 1 the structure shown in the foregoing embodiments does not constitute a limitation on the phosphorus shrimp ship waste heat temperature control device, and can include more or fewer components than the illustrated components, or combine certain components, or different component arrangements.

[0049] As Figure 1As shown, the memory 1005 as a storage medium can include an operating system, a network communication module, a user interface module, and a krill ship waste heat temperature control program.

[0050] In Figure 1 In the krill ship waste heat temperature control device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the krill ship waste heat temperature control device can be arranged in the krill ship waste heat temperature control device, and the krill ship waste heat temperature control device calls the krill ship waste heat temperature control program stored in the memory 1005 through the processor 1001, and executes the krill ship waste heat temperature control method provided by the embodiment of the present application.

[0051] The embodiment of the present application provides a krill ship waste heat temperature control method, which refers to Figure 2 , Figure 2 The flowchart of the first embodiment of the krill ship waste heat temperature control method of the present application is shown.

[0052] In this embodiment, the krill ship waste heat temperature control method includes the following steps:

[0053] Step S10: Collecting the waste heat power and the waste heat pressure of the krill ship exhaust pipeline, and generating a time-related waste heat sequence according to the waste heat power and the waste heat pressure.

[0054] It is easy to understand that the execution subject of the embodiment can be a processor with functions of data processing, network communication and program running, or other computer devices with similar functions, and the embodiment is not limited thereto.

[0055] It should be noted that the target waste heat temperature to be controlled is input, the water temperature is detected by a sensor, and the waste heat power p1 and the waste heat pressure p2 of the krill ship exhaust pipeline are collected.

[0056] Further, the processing method for generating a time-related waste heat sequence according to the waste heat power and the waste heat pressure is to construct a waste heat point set according to the waste heat power and the waste heat pressure according to time coding, and to generate a waste heat distribution map according to the waste heat point set; to divide a plurality of waste heat pressure intervals and a plurality of waste heat power intervals based on the waste heat distribution map; to determine the quartile points of the waste heat pressure on each waste heat pressure interval and the quartile points of the waste heat power on each waste heat power interval by a five-quantile algorithm; to construct the pressure quartile point intervals corresponding to each waste heat pressure interval according to the quartile points of the waste heat pressure on each waste heat pressure interval, and to construct the power quartile point intervals corresponding to each waste heat power interval according to the quartile points of the waste heat power on each waste heat power interval; and to determine the time-related waste heat sequence based on the pressure quartile point intervals corresponding to each waste heat pressure interval and the power quartile point intervals corresponding to each waste heat power interval.

[0057] In a specific implementation, the waste heat power p1 and the waste heat pressure p2 are coded according to the sampling time t to form a point set (p1, p2) (i.e., a waste heat point set), and a raw data (p1, p2) distribution diagram (i.e., a waste heat distribution diagram) is drawn. Based on the waste heat distribution diagram, an interval Δp2 is divided on the waste heat pressure p2, and four quantile points M1, M2, M3, and M4 of the waste heat pressure p2 are sequentially found on each Δp2 interval by using a five-quantile algorithm, N = M4-M1 is calculated, and a pressure quantile point interval [M1-1.5N, M4+1.5N] is constructed. Based on the waste heat distribution diagram, an interval Δp1 is divided on the waste heat power p1, and four quantile points M1, M2, M3, and M4 of the waste heat power p1 are sequentially found on each Δp1 interval by using a five-quantile algorithm, N = M4-M1 is calculated, and a power quantile point interval [M1-1.5N, M4+1.5N] is constructed.

[0058] Further, the processing mode of the time-dependent waste heat sequence is determined based on the pressure quantile point interval corresponding to each waste heat pressure interval and the power quantile point interval corresponding to each waste heat power interval. The abnormal pressure data outside the pressure quantile point interval corresponding to each waste heat pressure interval is determined, and the average waste heat pressure in the waste heat pressure interval corresponding to the abnormal pressure data is calculated to replace the abnormal pressure data with the average waste heat pressure. The abnormal power data outside the power quantile point interval corresponding to each waste heat power interval is determined, and the average waste heat power in the waste heat power interval corresponding to the abnormal power data is calculated to replace the abnormal power data with the average waste heat power. The waste heat pressure data and the waste heat power data corresponding to the waste heat distribution diagram are output in the order of time coding. The waste heat pressure power sequence is generated according to the waste heat pressure data and the waste heat power data. The waste heat pressure power sequence is normalized to obtain the time-dependent waste heat sequence.

[0059] In a specific implementation, the abnormal pressure data outside the pressure quantile point interval corresponding to the interval Δp2 is deleted, and the average waste heat pressure in each interval Δp2 is taken to replace the abnormal pressure data outside the pressure quantile point interval. The abnormal power data outside the power quantile point interval corresponding to the interval Δp1 is deleted, and the average waste heat power in each interval Δp1 is taken to replace the abnormal pressure data outside the power quantile point interval.

[0060] Further, the correct waste heat pressure data and the waste heat power data are output in the order of time coding, and the waste heat pressure power sequence pa is generated according to the waste heat pressure data and the waste heat power data. The sequence pa is normalized to obtain the sequence Pi (i.e., the time-dependent waste heat sequence).

[0061] Step S20: inputting the time-related waste heat sequence into a preset temperature control model, the preset temperature prediction model being constructed by a VMD algorithm model, a GWO algorithm model, an Elman neural network and a PID controller combination;

[0062] Step S30: decomposing the time-related waste heat sequence into a preset number of waste heat subsequences by the VMD algorithm model, optimizing the model parameters of the Elman neural network according to the preset number of waste heat subsequences by the GWO algorithm model, and performing temperature prediction by the optimized Elman neural network, so that the preset temperature control model realizes target waste heat temperature control by the PID controller based on the predicted waste heat temperature and the actual waste heat temperature.

[0063] In a specific implementation, compared with a traditional control algorithm, the combination model of the variational mode decomposition (VMD)-grey wolf optimization algorithm (GWO)-Elman neural network-PID controller (i.e., the preset temperature control model) has stronger self-learning ability, and can control and adjust the unit operation by continuously adjusting the changes of various parameters in the control model running, with stronger nonlinear mapping ability and adaptive control adjustment ability.

[0064] Compared with the control effect of a traditional PID algorithm, the VMD-GWO-ELMAN-PID combination model can further shorten the time for the water temperature at the outlet of the waste gas pipeline of the shrimp boat to reach the target temperature.

[0065] After the VMD-GWO-ELMAN-PID combination model is used, the overshoot of the water temperature at the outlet of the waste gas pipeline of the shrimp boat is reduced, and the temperature fluctuation is reduced. When the traditional PID algorithm is used, the water temperature will immediately fluctuate when the disturbance occurs, and will recover after a period of adjustment, but the deviation still exists. The VMD-GWO-ELMAN-PID combination model can make the water temperature at the outlet stable at the set value.

[0066] In this embodiment, the time-related waste heat sequence is decomposed into a preset number of waste heat subsequences by the VMD algorithm model.

[0067] Further, the processing manner of decomposing the time-dependent waste heat sequence into a preset number of waste heat subsequences through the VMD algorithm model is that a modal broadband constrained variational problem is constructed according to the time-dependent waste heat sequence through the VMD algorithm model; the modal broadband constrained variational problem is converted into a modal broadband unconstrained variational problem through a quadratic penalty factor and a Lagrange multiplier operator; the modal broadband unconstrained variational problem is solved through an alternating direction method of multipliers and a Fourier transform to obtain the preset number of waste heat subsequences.

[0068] In a specific implementation, the modal broadband constrained variational problem is constructed according to the time-dependent waste heat sequence through the VMD algorithm model to ensure that the decomposed waste heat subsequences are modal components with a limited bandwidth of a center frequency, and the sum of the estimated bandwidths of the modes is minimum, thereby establishing a constraint condition.

[0069] In this embodiment, the time-dependent waste heat sequence is written as a time sequence y(t), that is, y(t) is the sum of the modal components, and first, the analytic spectrum of each modal component mk(t) is obtained through Hilbert transform, where the one-sided spectrum Amk(t) is:

[0070]

[0071] where δ represents a Dirac distribution, and j represents a virtual unit.

[0072] The center frequency is mixed into the decomposed time sequence, and the spectrum will be adjusted to the baseband, that is, Amk(t).

[0073] where ω k represents the kth center frequency; the bandwidth of each modal signal is estimated by using a Gaussian smoothing method of a demodulation signal, and the variational problem with a bandwidth constraint is solved;

[0074] The objective function is represented as:

[0075]

[0076] where {m k}={m1m2...m k}, {ω k}={ω1ω2...ω k}, K represents the number of modes (that is, the preset number of waste heat subsequences) that need to be decomposed, m k represents the kth modal component, ω k represents the kth center frequency, δ(t) represents a Dirac function, and * represents a convolution operation.

[0077] A quadratic penalty factor α and a Lagrange multiplier operator λ(t) are introduced to convert the constrained variational problem into an unconstrained variational problem:

[0078] The reconstruction accuracy of the alpha guarantee signal is ensured, and the lambda(t) is strictly constrained:

[0079] The alternating direction method of multipliers and the Fourier transform are used to solve the above variational problem, and the optimal solution of the augmented Lagrangian function expression is obtained by alternating update optimization The expression after alternating optimization iteration is as follows:

[0080]

[0081] Wherein, respectively represent The Fourier equidistant transform of m1(t), m2(t), m3(t),..., τ represents the noise tolerance.

[0082] It should be noted that before starting running, the initial value of and the maximum iteration number N need to be set, and then the value of is updated. The Fourier transform is performed on

[0083] According to the preset number of waste heat subsequences, the model parameters of the Elman neural network are optimized by the GWO algorithm model, and the temperature is predicted by the optimized Elman neural network to output the predicted waste heat temperature.

[0084] Further, the GWO algorithm model is optimized based on the convergence factor changing according to the sine law, and the GWO modified expression is obtained; the temperature search formula is constructed according to the GWO modified expression; the optimal temperature measurement value (i.e., X α , X β and X χ ) is obtained according to the preset number of waste heat subsequences through the temperature search formula; the waste heat temperature data set is constructed according to the temperature measurement value X(t) of the preset time, the preset number of waste heat subsequences and the optimal temperature measurement value; and the model parameters of the Elman neural network are optimized based on the waste heat temperature data set.

[0085] The GWO modified expression is:

[0086]

[0087] Initialize the wolf population parameters. Set the gray wolf population size, search space and maximum iteration number and other parameters;

[0088] Calculate the fitness value of each gray wolf individual in the population;

[0089] According to the fitness value, the first three L subsequences in the preset number of waste heat subsequences are recorded as the best three gray wolves, which are recorded as alpha, beta and chi.

[0090] Temperature search formula:

[0091] D = rand{0, 2} X P (t) - X(t)

[0092] X(t+1) = X P (t) - rand(-2, 2) * rand(0, 2)

[0093]

[0094] D i = rand{0, 2} X i - X

[0095] In the formula, X P (t) is the optimal value of the current solution, X(t) is the temperature measurement value of the current solution, i.e. time t. X α , X β and X χ are the values obtained by GWO optimization of the first three wolves.

[0096] In this embodiment, it is also necessary to establish an Elman neural network:

[0097] x(k) = f(w 1 x c (k) + w 2 (x(k-1)) + b s ), y k = g(w 3 x(k) + b t )

[0098] x c (k) = [X(t), u(t), X α , X β , X χ ]

[0099] Where x c (k) is the waste heat temperature data set, x(k) is the state vector of the hidden layer, f(·) is the activation function ReLU, w 1 is the weight matrix from the input to the hidden layer, w 2 is the feedback connection weight matrix from the hidden layer state at the previous moment to the hidden layer state at the current moment. b s is the bias vector of the hidden layer. y k is the output (i.e. predicted waste heat temperature), g(·) is the activation function of the output layer, w 3 is the weight matrix from the hidden layer to the output layer, and b t is the bias vector of the output layer.

[0100] It should be noted that the model parameters of the Elman neural network are optimized based on the waste heat temperature data set, so that the optimized Elman neural network outputs the predicted waste heat temperature.

[0101] Based on the predicted waste heat temperature and the actual waste heat temperature, the target waste heat temperature control is realized through the PID control algorithm.

[0102] Further, the temperature difference signal is determined according to the target waste heat temperature and the actual waste heat temperature; and the target waste heat temperature control is realized through the PID control algorithm according to the temperature difference signal and the predicted waste heat temperature.

[0103] In a specific implementation, the PID controller output x adopts the following incremental PID algorithm:

[0104] y k =y(k-1)+k p [e(k)-e(k-1)]+k i e(k)+k d [e(k)-2e(k-1)+e(k-2)]

[0105] e(k)=T r (k)-T o (k)

[0106] In the formula, k p ,k i ,k d are the proportional, integral, and differential control parameters of the VMD-GWO-ELMAN-PID controller, respectively, k is the time, T r (k) is the target temperature, T o (k) is the actual temperature, and e(k) is the temperature difference signal.

[0107] It should be further noted that the PID controller transmits the signal to the frequency converter to adjust the compressor speed, and finally the waste heat pipeline transmits the water temperature. The water temperature parameter is output, and if it is equal to the target temperature, the current working environment is maintained. If it is not equal, the temperature is transmitted back to the PID controller. The above cycle is restarted until the temperature is equal.

[0108] In the embodiment, first, waste heat power and waste heat pressure of the exhaust pipeline of the euphausiid ship are collected, and a time-dependent waste heat sequence is generated according to the waste heat power and the waste heat pressure, then the time-dependent waste heat sequence is decomposed into a preset number of waste heat subsequences through a VMD algorithm model, then model parameters of an Elman neural network are optimized through a GWO algorithm model according to the preset number of waste heat subsequences, and temperature prediction is performed through the optimized Elman neural network to output a predicted waste heat temperature, and finally, target waste heat temperature control is realized through a PID control algorithm based on the predicted waste heat temperature and the actual waste heat temperature. In the embodiment, a series of finite stationary subsequence components are obtained through the VMD algorithm model based on the time-dependent waste heat sequence, and the GWO algorithm model is used for clustering the subsequence components, and each class is superimposed to reduce the training time, the neural network is trained respectively using the clustered sequence for prediction, the prediction results of each subsequence are superimposed and de-normalized to obtain the final prediction result, and the final prediction result is output to the PID for temperature control until the actual temperature is consistent with the target temperature, so that the temperature control precision is improved.

[0109] Referring to Figure 3 , Figure 3 is a structure block diagram of a preset temperature control model according to the embodiment of the present application.

[0110] As Figure 3 shown, the preset temperature control model based on the waste heat temperature control method of the euphausiid ship according to the embodiment of the present application includes a VMD algorithm model, a GWO algorithm model, an Elman neural network and a PID controller.

[0111] The VMD algorithm model 3001 is used for decomposing the time-dependent waste heat sequence into a preset number of waste heat subsequences.

[0112] The GWO algorithm model 3002 is used for optimizing model parameters of the Elman neural network 3003 according to the preset number of waste heat subsequences, so that the optimized Elman neural network performs temperature prediction.

[0113] The PID controller 3004 is used for realizing target waste heat temperature control through a PID control algorithm based on a predicted waste heat temperature and an actual waste heat temperature.

[0114] Other embodiments or specific implementation manners of the preset temperature control model can refer to the above-mentioned method embodiments, and will not be described here.

[0115] It should be noted that, in this document, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0116] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0117] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and the necessary general hardware platform, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk) and includes a number of instructions for making a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the methods described in the various embodiments of the present application.

[0118] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for controlling the waste heat temperature of a krill boat, characterized in that, The method for controlling the waste heat temperature of the krill ship includes the following steps: Waste heat power and waste heat pressure from the exhaust gas pipeline of the krill boat are collected, and a time-related waste heat sequence is generated based on the waste heat power and waste heat pressure. The time-related waste heat sequence is input into a preset temperature control model, which is constructed by combining a VMD algorithm model, a GWO algorithm model, an Elman neural network, and a PID controller. The time-related waste heat sequence is decomposed into a preset number of waste heat subsequences using the VMD algorithm model. Based on the preset number of waste heat subsequences, the model parameters of the Elman neural network are optimized using the GWO algorithm model. Temperature prediction is then performed using the optimized Elman neural network, so that the preset temperature control model can achieve target waste heat temperature control based on the predicted waste heat temperature and the actual waste heat temperature through the PID controller. The step of generating a waste heat sequence based on the waste heat power and the waste heat pressure time includes: A waste heat hotspot set is constructed according to the waste heat power and waste heat pressure using time encoding, and a waste heat distribution map is generated based on the waste heat hotspot set; Based on the waste heat distribution map, multiple waste heat pressure ranges and multiple waste heat power ranges are divided; The quartile algorithm is used to determine the quartiles of waste heat pressure in each waste heat pressure range and the quartiles of waste heat power in each waste heat power range. Based on the quartiles of the waste heat pressure in each waste heat pressure range, construct the pressure quartile range corresponding to each waste heat pressure range; and based on the quartiles of the waste heat power in each waste heat power range, construct the power quartile range corresponding to each waste heat power range. The time-dependent waste heat sequence is determined based on the pressure quantile intervals corresponding to each waste heat pressure interval and the power quantile intervals corresponding to each waste heat power interval.

2. The method as described in claim 1, characterized in that, The step of determining the time-related waste heat sequence based on the pressure quantile intervals corresponding to each waste heat pressure interval and the power quantile intervals corresponding to each waste heat power interval includes: Determine the abnormal pressure data outside the pressure quantile interval corresponding to each waste heat pressure interval, and calculate the average waste heat pressure within the waste heat pressure interval corresponding to the abnormal pressure data, so that the average waste heat pressure replaces the abnormal pressure data. Identify the abnormal power data outside the power quantile interval corresponding to each waste heat power interval, and calculate the average waste heat power within the waste heat power interval corresponding to the abnormal power data, so that the average waste heat power replaces the abnormal power data. Output the waste heat pressure data and waste heat power data corresponding to the waste heat distribution map in time-coded order; A waste heat pressure-power sequence is generated based on the waste heat pressure data and the waste heat power data. The waste heat pressure-power sequence is normalized to obtain a time-dependent waste heat sequence.

3. The method according to any one of claims 1-2, characterized in that, The step of decomposing the time-related waste heat sequence into a predetermined number of waste heat subsequences using the VMD algorithm model includes: Based on the time-related waste heat sequence, a modal broadband constrained variational problem is constructed using the VMD algorithm model. The modal broadband constrained variational problem is transformed into a modal broadband unconstrained variational problem by using a quadratic penalty factor and the Lagrange multiplication operator. The modal broadband unconstrained variational problem is solved by using the alternating direction method of multipliers and Fourier transform to obtain a predetermined number of waste heat subsequences.

4. The method as described in claim 3, characterized in that, The step of optimizing the model parameters of the Elman neural network using the GWO algorithm model based on the preset number of waste heat subsequences includes: The GWO algorithm model is optimized based on the sinusoidal convergence factor to obtain the GWO modified expression; Construct a temperature search formula based on the GWO modified expression; The optimal temperature measurement value is obtained by using the temperature search formula based on the preset number of waste heat subsequences. A waste heat temperature dataset is constructed based on the temperature measurement values ​​at a preset time, the preset number of waste heat subsequences, and the optimal temperature measurement values. The model parameters of the Elman neural network are optimized based on the waste heat temperature dataset.

5. The method as described in claim 4, characterized in that, The step of controlling the target waste heat temperature using the PID controller based on the predicted waste heat temperature and the actual waste heat temperature includes: The temperature difference signal is determined based on the target waste heat temperature and the actual waste heat temperature. The target waste heat temperature is controlled by the PID controller based on the temperature difference signal and the predicted waste heat temperature.

6. A preset temperature control model based on a krill ship waste heat temperature control method, characterized in that, The preset temperature control model implements the method described in claim 1, and the preset temperature control model is constructed by combining a VMD algorithm model, a GWO algorithm model, an Elman neural network, and a PID controller. The VMD algorithm model is used to decompose time-related waste heat sequences into a preset number of waste heat subsequences; The GWO algorithm model is used to optimize the model parameters of the Elman neural network based on the preset number of waste heat subsequences, so that the optimized Elman neural network can make temperature predictions. The PID controller is used to achieve target waste heat temperature control based on the predicted waste heat temperature and the actual waste heat temperature using a PID control algorithm.

7. A waste heat temperature control device for krill boats, characterized in that, The device includes: a memory, a processor, and a krill boat waste heat temperature control program stored in the memory and executable on the processor, the krill boat waste heat temperature control program being configured to implement the steps of the krill boat waste heat temperature control method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores a krill boat waste heat temperature control program, which, when executed by a processor, implements the steps of the krill boat waste heat temperature control method as described in any one of claims 1 to 5.

Images