Prediction method and device for scaling thickness of machine room water pipe, medium and program product

Abstract

The invention discloses a machine room water pipe scaling thickness prediction method and device, a medium and a program product. The method relates to the field of artificial intelligence, and comprises the steps that a target prediction request is received, the target prediction request is used for requesting to predict the scaling thickness of a target water pipe after a target duration, and the target water pipe comprises a water pipe in a machine room of a financial institution; responding to the target prediction request, and obtaining water quality data of a target water pipe; the water quality data and the target duration are input into a target neural network model, the target scaling thickness is obtained, and the target neural network model is used for predicting the scaling thickness of the target water pipe after the target duration; the target neural network model comprises a neural network model obtained by optimizing parameters of the fuzzy neural network based on a crayfish optimization algorithm. According to the invention, the problem that the scaling thickness of the water pipe of the machine room is difficult to accurately predict in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular, to a method, device, medium and program product for predicting the thickness of scale deposits on water pipes in a computer room. Background Art

[0002] With the widespread application of precision air conditioners in computer rooms in modern information-based enterprises, their efficient and stable operation is crucial to ensuring the safety of data centers. However, due to water quality issues, the scaling of pipes in air conditioning cooling systems is becoming increasingly serious, directly threatening the normal operation and service life of equipment. The factors that affect the thickness of pipe scaling are complex and varied.

[0003] In the related art, the scale thickness in the water pipes in the computer room is generally determined by manual measurement. However, the manual measurement method can only detect the scale thickness at the current moment and cannot accurately predict the scale thickness of the water pipes after a period of time.

[0004] With regard to the problem that it is difficult to accurately predict the scaling thickness of the water pipes in the computer room in the relevant technologies, no effective solution has been proposed so far. Summary of the invention

[0005] The main purpose of this application is to provide a method, device, medium and program product for predicting the scaling thickness of water pipes in a computer room, so as to solve the problem in the related art that it is difficult to accurately predict the scaling thickness of water pipes in a computer room.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for predicting the scaling thickness of a water pipe in a computer room is provided. The method comprises: receiving a target prediction request, wherein the target prediction request is used to request a prediction of the scaling thickness of a target water pipe after a target time period, and the target water pipe comprises: a water pipe in a computer room of a financial institution; in response to the target prediction request, obtaining water quality data of the target water pipe; inputting the water quality data and the target time period into a target neural network model to obtain a target scaling thickness, wherein the target neural network model is used to predict the scaling thickness of the target water pipe after the target time period, and the target neural network model comprises: a neural network model obtained by optimizing the parameters of a fuzzy neural network based on a crayfish optimization algorithm.

[0007] Furthermore, the target neural network model is obtained in the following manner: obtaining training samples, wherein the training samples include: water quality data of the target water pipe in a historical time period and the scaling thickness of the target water pipe after M time periods, where M is a positive integer; performing model training on the fuzzy neural network based on the training samples, and during the model training process, adjusting the model parameters of the fuzzy neural network based on the crayfish optimization algorithm to obtain the adjusted model parameters, and determining the target neural network model based on the adjusted model parameters.

[0008] Furthermore, the model parameters include: parameters of the membership function and weights of the neurons of the fuzzy neural network, and the model parameters of the fuzzy neural network are adjusted based on the crayfish optimization algorithm to obtain the adjusted model parameters including: constructing a crayfish population of the crayfish optimization algorithm based on the parameters of the membership function and the weights of the neurons of the fuzzy neural network, wherein the crayfish population includes: N groups of candidate solutions, and the N groups of candidate solutions are used to represent the model parameters; based on the crayfish optimization algorithm, performing T iterative updates on the N groups of candidate solutions in the crayfish population to obtain updated N groups of candidate solutions, wherein T is a positive integer; based on the updated N groups of candidate solutions, obtaining the adjusted model parameters.

[0009] Furthermore, each time the N candidate solutions in the crayfish population are iteratively updated, it also includes: generating a random number, and based on the random number, generating environmental parameters of the crayfish optimization algorithm; comparing the environmental parameters with a preset parameter threshold to obtain a comparison result; based on the comparison result, updating the N groups of candidate solutions in the crayfish population.

[0010] Furthermore, based on the comparison result, the N groups of candidate solutions in the crayfish population are updated, which also includes: when the comparison result indicates that the environmental parameter is greater than the preset parameter threshold, the N groups of candidate solutions in the crayfish population are updated based on the summer vacation stage of the crayfish optimization algorithm; when the comparison result indicates that the environmental parameter is not greater than the preset parameter threshold, the N groups of candidate solutions in the crayfish population are updated based on the foraging stage of the crayfish optimization algorithm.

[0011] Furthermore, the water quality data and the target duration are input into a target neural network model to obtain a target scaling thickness, including: inputting the water quality data and the target duration into an input layer of the target neural network model to obtain a first output result, wherein the input layer is used to receive the water quality data and the target duration, and transmit the water quality data and the target duration in the target neural network model; inputting the first output result into a fuzzification layer of the target neural network model to obtain a second output result, wherein the fuzzification layer is used to fuzzify the first output result based on fuzzy rules; inputting the second output result into a rule layer of the target neural network model to obtain a third output result, wherein the rule layer is used to determine the applicability of the fuzzy rules; inputting the third output result into a normalization layer of the target neural network model to obtain a fourth output result, wherein the normalization layer is used to normalize the third output result; inputting the fourth output result into the output layer of the target neural network model to obtain the target scaling thickness.

[0012] Furthermore, the water quality data includes at least one of the following: water hardness, total dissolved solids, pH, water flow rate and water temperature.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for predicting the scaling thickness of a water pipe in a computer room is provided. The device comprises: a receiving unit, for receiving a target prediction request, wherein the target prediction request is used to request a prediction of the scaling thickness of a target water pipe after a target time length, and the target water pipe comprises: a water pipe in a computer room of a financial institution; a first acquisition unit, for responding to the target prediction request and acquiring water quality data of the target water pipe; a processing unit, for inputting the water quality data and the target time length into a target neural network model to obtain a target scaling thickness, wherein the target neural network model is used to predict the scaling thickness of the target water pipe after the target time length, and the target neural network model comprises: a neural network model obtained by optimizing the parameters of a fuzzy neural network based on a crayfish optimization algorithm.

[0014] Furthermore, the target neural network model is obtained through the following units: a second acquisition unit, used to acquire training samples, wherein the training samples include: water quality data of the target water pipe in a historical time period and the scaling thickness of the target water pipe after M time periods, M being a positive integer; a training unit, used to perform model training on the fuzzy neural network based on the training samples, and during the model training process, the model parameters of the fuzzy neural network are adjusted based on the crayfish optimization algorithm to obtain adjusted model parameters, and based on the adjusted model parameters, the target neural network model is determined.

[0015] Furthermore, the model parameters include: parameters of the membership function and weights of the neurons of the fuzzy neural network, and the training unit includes: a construction subunit, used to construct a crayfish population of the crayfish optimization algorithm based on the parameters of the membership function and the weights of the neurons of the fuzzy neural network, wherein the crayfish population includes: N groups of candidate solutions, and the N groups of candidate solutions are used to represent the model parameters; an updating subunit, used to perform T iterative updates on the N groups of candidate solutions in the crayfish population based on the crayfish optimization algorithm to obtain updated N groups of candidate solutions, wherein T is a positive integer; a first processing subunit, used to obtain the adjusted model parameters based on the updated N groups of candidate solutions.

[0016] Furthermore, in each iterative update process of the N candidate solutions in the crayfish population, it also includes: a generation module for generating random numbers, and based on the random numbers, generating environmental parameters of the crayfish optimization algorithm; a comparison module for comparing the environmental parameters with preset parameter thresholds to obtain comparison results; and an update module for updating the N groups of candidate solutions in the crayfish population based on the comparison results.

[0017] Furthermore, the update module includes: a first update sub-module, used to update the N groups of candidate solutions in the crayfish population based on the summer vacation stage of the crayfish optimization algorithm when the comparison result indicates that the environmental parameter is greater than the preset parameter threshold; a second update sub-module, used to update the N groups of candidate solutions in the crayfish population based on the foraging stage of the crayfish optimization algorithm when the comparison result indicates that the environmental parameter is not greater than the preset parameter threshold.

[0018] Furthermore, the processing unit includes: a second processing subunit, used to input the water quality data and the target duration into the input layer of the target neural network model to obtain a first output result, wherein the input layer is used to receive the water quality data and the target duration, and transmit the water quality data and the target duration in the target neural network model; a second processing subunit, used to input the first output result into the fuzzification layer of the target neural network model to obtain a second output result, wherein the fuzzification layer is used to fuzzify the first output result based on fuzzy rules; a third processing subunit, used to input the second output result into the rule layer of the target neural network model to obtain a third output result, wherein the rule layer is used to determine the applicability of the fuzzy rules; a fourth processing subunit, used to input the third output result into the normalization layer of the target neural network model to obtain a fourth output result, wherein the normalization layer is used to normalize the third output result; a fifth processing subunit, used to input the fourth output result into the output layer of the target neural network model to obtain the target scaling thickness.

[0019] Furthermore, the water quality data includes at least one of the following: water hardness, total dissolved solids, pH, water flow rate and water temperature.

[0020] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the method for predicting the thickness of scale deposits on water pipes in a computer room.

[0021] According to another aspect of the present application, an electronic device is provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the method for predicting the thickness of scale deposits on water pipes in a computer room is executed when the program is running.

[0022] According to another aspect of the present application, a computer program product is provided, comprising computer instructions, which, when executed by a processor, implement the steps of the method for predicting the thickness of scaling of water pipes in a computer room.

[0023] In an embodiment of the present application, a target prediction request is received, wherein the target prediction request is used to request a prediction of the scaling thickness of a target water pipe after a target duration, and the target water pipe includes: a water pipe in a computer room of a financial institution; in response to the target prediction request, water quality data of the target water pipe is obtained; the water quality data and the target duration are input into a target neural network model to obtain a target scaling thickness, wherein the target neural network model is used to predict the scaling thickness of the target water pipe after the target duration, and the target neural network model includes: a neural network model obtained by optimizing the parameters of a fuzzy neural network based on a crayfish optimization algorithm, thereby solving the technical problem in the related art that it is difficult to accurately predict the scaling thickness of the water pipe in the computer room. In the present invention, the scaling thickness of the water pipe is predicted based on a fuzzy neural network model optimized by a crayfish optimization algorithm, thereby avoiding the related art that can only manually measure the scaling thickness of the water pipe in the computer room at the current moment, thereby achieving the technical effect of accurately predicting the scaling thickness of the water pipe in the computer room. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] Figure 1 A hardware structure block diagram of a computer terminal for implementing a method for predicting the thickness of scaling of water pipes in a machine room is shown;

[0026] Figure 2 It is a flow chart of a method for predicting the thickness of scaling of water pipes in a computer room provided in an embodiment of the present application;

[0027] Figure 3 It is a flow chart of model training and scaling thickness prediction provided according to the embodiment of the present application;

[0028] Figure 4 is a flow chart of a crayfish optimization algorithm provided according to an embodiment of the present application;

[0029] Figure 5 is a schematic diagram of a fuzzy neural network structure provided according to an embodiment of the present application;

[0030] Figure 6 It is a schematic diagram of a device for predicting the thickness of scaling of water pipes in a machine room provided in an embodiment of the present application;

[0031] Figure 7 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0035] Embodiment 1

[0036] According to an embodiment of the present application, a method embodiment of a method for predicting the scale thickness of water pipes in a computer room is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1The hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for predicting the thickness of scaling in water pipes in a machine room is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0038] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0039] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for predicting the thickness of scaling of water pipes in the computer room in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the method for predicting the thickness of scaling of water pipes in the computer room is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0040] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0041] The display may be, for example, a touch screen liquid crystal display (LCD), which may enable a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0042] Under the above operating environment, this application provides Figure 2 The method for predicting the scale thickness of the water pipes in the computer room is shown. Figure 2 It is a flow chart of a method for predicting scaling thickness of water pipes in a computer room according to the first embodiment of the present application.

[0043] Step S201, receiving a target prediction request, wherein the target prediction request is used to request a prediction of a scaling thickness of a target water pipe after a target time period, and the target water pipe includes: a water pipe in a computer room of a financial institution.

[0044] The above target prediction request is used to request prediction of the scaling thickness of the target water pipe after the target time period, and the above target water pipe includes the water pipe in the computer room of the financial institution (referred to as the computer room water pipe).

[0045] Step S202, responding to the target prediction request and acquiring water quality data of the target water pipe.

[0046] After receiving the target prediction request, water quality data in the water pipe can also be collected. The water quality data may include but is not limited to: water hardness, total dissolved solids, pH value, water flow rate and water temperature.

[0047] Step S203, input the water quality data and the target duration into the target neural network model to obtain the target scaling thickness, wherein the target neural network model is used to predict the scaling thickness of the target water pipe after the target duration, and the target neural network model includes: a neural network model obtained by optimizing the parameters of the fuzzy neural network based on the crayfish optimization algorithm.

[0048] The above-mentioned target neural network model may include: a neural network model obtained by optimizing the model parameters of the fuzzy neural network based on the crayfish optimization algorithm during the model training process.

[0049] In order to achieve the purpose of automatically predicting the scaling thickness of the water pipes in the computer room, in this embodiment, the water quality data and the target duration can be input into the target neural network model, and the target neural network model can be used to predict the scaling thickness of the target water pipe after the target duration to obtain the target scaling thickness. In an optional example, the water quality data and the target duration can be converted into vectors, and the converted vectors can be input into the target neural network model to predict the scaling thickness of the target water pipe after the target duration to obtain the target scaling thickness.

[0050] In this embodiment, through the above steps, the scaling thickness of the water pipe is predicted based on the fuzzy neural network model optimized by the crayfish optimization algorithm, avoiding the related technology that can only manually measure the scaling thickness of the water pipe in the computer room at the current moment, thereby achieving the technical effect of accurately predicting the scaling thickness of the water pipe in the computer room, and further solving the technical problem in the related technology that it is difficult to accurately predict the scaling thickness of the water pipe in the computer room.

[0051] Figure 3 is a flow chart of model training and scaling thickness prediction according to the embodiment of the present application, such as Figure 3 As shown, it includes: detecting the water consumption data of the computer room to obtain parameters such as water quality, water temperature, time, etc., importing the fuzzy neural network model for model training, and exporting the parameters of the fuzzy neural network model during the model training process, and using the crayfish optimization algorithm to optimize the parameters. In the process of using the crayfish optimization algorithm to optimize the parameters, the environment in which the crayfish is located can be simulated, and the behavior can be judged according to environmental factors to determine the entry into the foraging stage and the competition stage. After completing the model training, the new water quality parameters can be input into the trained fuzzy neural network (i.e., the target neural network model) to predict the scaling thickness of the water pipe.

[0052] Optionally, the target neural network model is obtained in the following manner: obtaining training samples, wherein the training samples include: water quality data of the target water pipe in the historical time period and the scaling thickness of the target water pipe after M time periods, where M is a positive integer; performing model training on the fuzzy neural network based on the training samples, and during the model training process, adjusting the model parameters of the fuzzy neural network based on the crayfish optimization algorithm to obtain the adjusted model parameters, and determining the target neural network model based on the adjusted model parameters.

[0053] The training samples mentioned above may include: water quality data of the target water pipe in the historical time period and the scaling thickness of the target water pipe after M time periods. The fuzzy neural network model mentioned above may be a fuzzy neural network that has not been trained.

[0054] In this embodiment, the scale thickness of the target water pipe after M time periods can be used as a training label to perform model training on the fuzzy neural network, and during the model training process, the model parameters of the fuzzy neural network are optimized and adjusted based on the crayfish optimization algorithm to obtain the adjusted model parameters. The adjusted model parameters can be used as the model parameters of the fuzzy neural network to obtain the target neural network model.

[0055] Based on the crayfish optimization algorithm, parameter optimization is performed during the model training process of the fuzzy neural network, achieving the technical effect of improving the accuracy of scaling thickness prediction of the trained target neural network model.

[0056] Optionally, the model parameters include: parameters of the membership function and weights of neurons in the fuzzy neural network, and the model parameters of the fuzzy neural network are adjusted based on the crayfish optimization algorithm to obtain the adjusted model parameters including: based on the parameters of the membership function and weights of neurons in the fuzzy neural network, a crayfish population of the crayfish optimization algorithm is constructed, wherein the crayfish population includes: N groups of candidate solutions, and the N groups of candidate solutions are used to represent the model parameters; based on the crayfish optimization algorithm, the N groups of candidate solutions in the crayfish population are iteratively updated T times to obtain updated N groups of candidate solutions, wherein T is a positive integer; based on the updated N groups of candidate solutions, the adjusted model parameters are obtained.

[0057] The above-mentioned model parameters may include but are not limited to: the central value c of the membership function, the width σ of the membership function, and the weight w.

[0058] For example, on the basis of fuzzy neural network, the crayfish optimization algorithm is introduced for parameter collaborative optimization, thereby constructing a new type of fuzzy neural network model. In the model training process, the crayfish algorithm is used to optimize parameters such as membership function and network weight. By setting the input sample set and the network parameter set, a matrix is ​​established, where the input sample set is X = [X1, X2, ..., Xn], and the parameter set is c = (c 11 , c 21 , ..., c i1 , c 12 , c 22 , ..., c ij )σ=(σ 11 , σ 21 , ..., σ i1 , σ 12 , σ 22 , ..., σ ij )w=(w 1 , w 2 , ..., w k ), use the crayfish algorithm to adjust the membership and weight parameters to obtain the optimal parameter configuration that minimizes the model loss function.

[0059] In this embodiment, a crayfish population of the crayfish optimization algorithm can be constructed based on the parameters of the membership function and the weights of the neurons of the fuzzy neural network. For example, multiple sets of fuzzy neural network parameters, namely, the center value c of the membership function, the width σ of the membership function, and the weight w can be set as candidate solutions Y to form a crayfish population. The formula for the crayfish population is shown in formula (1).

[0060] Y=[Y 1 , Y 2 , ..., Y n ] (1)

[0061] Among them, Y n A set of candidate solutions may be represented by, for example, a central value c of the membership function and a set of values ​​of the width σ of the membership function and the weight w.

[0062] Each candidate solution Y i，j The composition of is shown in formula (2).

[0063] Y i，j =lb i +(ub i -lb j )×rand (2)

[0064] Among them, Y i，j It can be used to represent the jth model parameter in the i-th group of candidate solutions. j represents the lower bound of the jth variable, μb j represents the lower bound of the j-th variable, and rand represents a random number.

[0065] In this embodiment, based on the crayfish optimization algorithm, the N groups of candidate solutions in the crayfish population can be iteratively updated T times, and the best group of candidate solutions during the T iterative updates can be used as the updated N groups of candidate solutions. In the process of evaluating the candidate solutions of the optimal solution, the candidate solutions can be input into the fuzzy neural network and determined by calculating the fitness value, and then the updated N groups of candidate solutions can be determined as the adjusted model parameters.

[0066] In this embodiment, the model parameters of the fuzzy neural network are globally optimized by using the crayfish optimization algorithm to further improve the accuracy and stability of the model in predicting scaling thickness.

[0067] Optionally, each time the N candidate solutions in the crayfish population are iteratively updated, it also includes: generating random numbers, and based on the random numbers, generating environmental parameters of the crayfish optimization algorithm; comparing the environmental parameters with preset parameter thresholds to obtain comparison results; based on the comparison results, updating the N groups of candidate solutions in the crayfish population.

[0068] In this embodiment, the temperature (environmental condition, corresponding to the environmental parameter) in the crayfish optimization algorithm can be defined as follows: Specifically, the behavior of the crayfish is affected by the environment, and corresponding actions are taken under different environmental conditions. The environmental conditions determine the behavior of the crayfish in the next stage. The composition of the environmental condition δ (corresponding to the environmental parameter) is shown in formula (3).

[0069] δ=rand×15+20 (3)

[0070] Among them, rand represents a random number.

[0071] In this embodiment, the environmental parameters and the preset parameter thresholds can be compared, and the N groups of candidate solutions in the crayfish population are updated according to the comparison results. Specifically, since the exploration mechanism in the crayfish optimization algorithm is affected by temperature changes, the temperature (i.e., the environmental parameters) is used as a random variable to adjust the algorithm behavior. When the temperature is high (i.e., the environmental parameters are greater than the preset parameters), the crayfish (corresponding to the candidate solutions in the crayfish population) will look for caves to escape the heat; if there are no other crayfish competing for the cave, it will directly enter the cave, which is the summer stage. If there is competition, the crayfish will compete and enter the competition stage of the algorithm. When the temperature is suitable (i.e., the environmental parameters are not greater than the preset parameter threshold), the crayfish optimization algorithm enters the foraging stage. At this stage, the crayfish decides to eat directly or tear it up first and then eat it according to the size of the food, and the amount of food eaten is affected by the foraging amount. Through the balance of the temperature regulation mechanism, a more efficient optimization effect is achieved when searching for the optimal fitness value through the crayfish optimization algorithm, and the accuracy of the model parameter optimization is improved.

[0072] Optionally, based on the comparison results, N groups of candidate solutions in the crayfish population are updated, and the method also includes: when the comparison results indicate that the environmental parameters are greater than a preset parameter threshold, the N groups of candidate solutions in the crayfish population are updated based on the summer vacation stage of the crayfish optimization algorithm; when the comparison results indicate that the environmental parameters are not greater than the preset parameter threshold, the N groups of candidate solutions in the crayfish population are updated based on the foraging stage of the crayfish optimization algorithm.

[0073] In this embodiment, the different stages of the crayfish optimization algorithm (for example, the summer retreat stage, the foraging stage) can be controlled to be entered according to whether the environmental parameters indicated by the comparison results are greater than the preset parameter threshold, and the N candidate solutions in the crayfish population are updated. Figure 4 This is a flowchart of the crayfish optimization algorithm provided in the embodiment of the present application. The following is a combination of the environmental parameter δ and the preset parameter threshold of 30. Figure 4 Let's take an example:

[0074] After initializing the population, evaluate the fitness and obtain X L and X GAfter generating the environmental factor δ (corresponding to the environmental parameter), the following steps may be included:

[0075] When δ>30, the crayfish (i.e., the candidate solution) will seek cool areas to escape the heat, i.e., the summer heat escape stage; and when δ≤30, the crayfish will enter the foraging stage. The amount of food consumed by crayfish is closely related to δ, with 15≤δ≤30 being the optimal range, and δ=25 being the most ideal environment. Therefore, the amount of food consumed by crayfish can be approximated as a normal distribution, showing characteristics affected by δ., as shown in formula (4).

[0076]

[0077] Among them, the random parameters μ and C are used respectively 1 To control the intake of crayfish at different temperatures, p represents the food intake of crayfish.

[0078] The following is an explanation of the processing procedures for the summer retreat phase and the foraging phase:

[0079] 1 Summer vacation stage:

[0080] When δ>30, it means that the environment is not suitable for eating. At this time, crayfish will enter the cave to escape the heat. The definition of the cave is shown in formula (5).

[0081]

[0082] Among them, X G represents the optimal position obtained by the number of iterations, X L It represents the optimal position obtained after the previous generation population is updated. It should be noted that the position here can represent a candidate solution. Since it is not in the passing stage, a different expression is used.

[0083] The competition for the cave by crayfish is a random event. In COA (Crayfish Optimization Algorithm), when rand < 0.5, it means that there are no other crayfish competing for the cave, and the crayfish directly enters the cave to escape the heat. The crayfish enters the cave to escape the heat as shown in formula (6), and the formula for updating the candidate solution is shown in formula (7).

[0084]

[0085] Among them, represents the current iteration number, t+1 represents the next generation iteration number, T is the maximum iteration number, C 2 It is a decreasing curve.

[0086] Competition phase during the summer vacation phase:

[0087] When δ>30, rand≥0.5, it means that other crayfish have also chosen this cave. At this time, they will compete for this cave. The competition for the cave is shown in formula (8), and the update of the candidate solution is shown in formula (9).

[0088] z=round(rand×(N-1))+1 (8)

[0089]

[0090] Among them, z is a random individual of crayfish.

[0091] 2 Foraging stage:

[0092] When δ≤30, it means that the environment is suitable for crayfish to eat. At this time, crayfish can go out to look for food. When eating, crayfish will choose whether to tear the food into pieces according to the size of the food. If the food is of the right size, crayfish will directly ingest the food. If the food is too big, crayfish will use claws to tear the food into pieces and then use the second and third walking legs to alternately pick up the food and ingest it. The definition of food is shown in formula (10).

[0093] Y food =Y G (10)

[0094] Among them, Y G It can also represent a candidate solution, which has the same meaning as X G The same is true, but different letters are used to represent different meanings at different stages.

[0095] The definition of food size is shown in formula (11).

[0096]

[0097] Among them, C 3 is the food factor, representing the maximum food, and its value is a constant 3. i represents the fitness value of the i-th crayfish, fitness food Indicates the fitness value of the location where the food is located.

[0098] when In this case, the crayfish will tear the food into pieces as shown in formula (12):

[0099]

[0100] After tearing the food into pieces, the crayfish will use the second and third walking legs to alternately pick up the food and ingest it. In order to simulate the alternating feeding behavior, a combination of sine and cosine functions is used in the equation to simulate the alternating process. In addition, the food obtained by the crayfish is also related to the food intake. The equation for feeding is shown in formula (13).

[0101]

[0102] when The crayfish will move directly toward the food and eat it, as shown in formula (14).

[0103]

[0104] In the crayfish optimization algorithm, the fitness value fitness and Y can also be updated iteratively. food and Y G . At this time, if t<T, a new cycle begins. If t>T, keep the optimal Y end As a result, a candidate solution that makes the prediction result of the neural network model more accurate is output.

[0105] After T rounds of iterations, the Y obtained based on the crayfish optimization algorithm end The optimization parameters are imported into the fuzzy neural network, and the collected water hardness, total dissolved solids (TDS), pH value, water flow rate, water temperature and time are used as the input variables of the model. The trained fuzzy neural network intelligent prediction model is used to calculate and output the predicted value of the water pipe scaling thickness after the specified time, thereby achieving the technical effect of improving the accuracy of the water pipe scaling thickness prediction results.

[0106] Optionally, water quality data and target duration are input into a target neural network model to obtain a target scaling thickness, including: inputting the water quality data and target duration into an input layer of the target neural network model to obtain a first output result, wherein the input layer is used to receive the water quality data and target duration, and transmit the water quality data and target duration in the target neural network model; inputting the first output result into a fuzzification layer of the target neural network model to obtain a second output result, wherein the fuzzification layer is used to fuzzify the first output result based on fuzzy rules; inputting the second output result into a rule layer of the target neural network model to obtain a third output result, wherein the rule layer is used to determine the applicability of the fuzzy rules; inputting the third output result into a normalization layer of the target neural network model to obtain a fourth output result, wherein the normalization layer is used to normalize the third output result; inputting the fourth output result into the output layer of the target neural network model to obtain a target scaling thickness.

[0107] Figure 5is a schematic diagram of a fuzzy neural network structure provided according to an embodiment of the present application. Figure 5 The following examples illustrate the model structure of each layer of the fuzzy neural network and the corresponding processing methods:

[0108] The first layer is the input layer: the data is input into the fuzzy neural network and the input value is transmitted to the next layer, which can be expressed as shown in formula (15).

[0109] X=(x 1 , x 2 , ..., x 6 ) T (15)

[0110] Where X is the input vector, x 1 is the water hardness, x 2 is the total dissolved solids (TDS), x 3 is pH value, x 4 is the water flow velocity, x 5 is water temperature, x 6 is time (corresponding to the target duration), and the number of nodes in this layer is 6.

[0111] The second layer is the fuzzification layer: fuzzy processing is performed on the data, and the input space is mapped to the Gaussian distribution space. The number of nodes is K i is relative to x i Each node represents a fuzzy verbal variable value, and its function is to calculate the membership function of the input vector component to the fuzzy set of the respective verbal variable. Where (i=1, 2, ..., 6; j=1, 2, ..., K), K is the number of levels of the fuzzy rule. There are K groups of membership functions in total, and each group has P membership functions. The membership function can be expressed as formula (16).

[0112]

[0113] Among them, c ij is the central value of the membership function and σ ij is the width of the membership function, and t is the number of iterations of the crayfish optimization algorithm.

[0114] The third layer is the rule layer: the data is represented by fuzzy rules to calculate the total fuzzy membership of the data. The total number of points in this layer is k, which is used to judge the applicability of each rule. The output is shown in formula (17).

[0115]

[0116] Among them, uk(t) is the output value of the kth neuron.

[0117] The fourth layer is the normalization layer: the applicability of each rule is normalized and calculated. The number of nodes in the normalization layer is consistent with that in the rule layer, and the output is shown in formula (18).

[0118]

[0119] Among them, v k (t) is the output value of the kth neuron.

[0120] The fifth layer is the output layer: fuzzy rules are integrated to achieve clear calculation output as shown in formula (19).

[0121]

[0122] y(t) is the output of the fuzzy neural network, and w k (t) is the weight of the kth normalized neuron in the fuzzy neural network.

[0123] Through the nonlinear fitting ability of fuzzy neural networks, the problem of modeling the nonlinear relationship between the complexity of various water quality parameters and scaling thickness can be effectively solved, and the technical effect of accurately predicting the scaling thickness of water pipes can be achieved.

[0124] Optionally, the water quality data includes at least one of the following: water hardness, total dissolved solids, pH, water flow rate and water temperature.

[0125] The above-mentioned water quality data may include but are not limited to: water hardness, total dissolved solids (TDS), pH value (acidity and alkalinity), water flow rate, water temperature, water pipe material and other parameters, avoiding the situation where a single parameter leads to inaccurate scaling thickness prediction results, thereby achieving the technical effect of improving the accuracy of scaling thickness prediction results.

[0126] By combining the nonlinear fitting ability of fuzzy neural networks and the unique advantages of crayfish optimization algorithm in balancing global and local search, the problem of modeling the nonlinear relationship between the complexity of water quality parameters and the thickness of scale can be effectively solved. It avoids the situation in related technologies that are limited by the long-term variation characteristics of pipe scale thickness and its complex nonlinear chemical change process. Traditional machine learning methods still have many shortcomings in prediction accuracy and generalization ability. Specifically, fuzzy neural networks are used to analyze multiple parameters such as hardness, alkalinity, pH value (whose variation law shows strong nonlinearity) of water used in computer room air conditioners, and the parameters of fuzzy neural networks are globally optimized through crayfish optimization algorithm, further improving the accuracy and stability of the model in predicting the thickness of water pipe scale.

[0127] The method for predicting the thickness of scale in the water pipes in the computer room provided by this embodiment, on the one hand, adopts a fuzzy neural network, which can handle the fuzzy relationship between complex water quality parameters, thereby realizing accurate prediction of the thickness of scale; on the other hand, the crayfish optimization algorithm provides an efficient global optimization mechanism by simulating the foraging and avoidance behavior of crayfish in a complex environment, overcoming the deficiency that traditional machine learning methods are prone to fall into local optimality. By combining the water quality data of the historical real time period with the changing trend of the pipe scale thickness, the optimized fuzzy neural network model can provide an accurate prediction basis for the water quality management of the computer room, and provide important technical support for optimizing the operating efficiency of the air conditioning cooling system and extending the operating stability of the air conditioning in the computer room.

[0128] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0129] Embodiment 2

[0130] The embodiment of the present application also provides a device for predicting the thickness of scaling of water pipes in a computer room. It should be noted that the device for predicting the thickness of scaling of water pipes in a computer room in the embodiment of the present application can be used to execute the method for predicting the thickness of scaling of water pipes in a computer room provided in the embodiment of the present application. The device for predicting the thickness of scaling of water pipes in a computer room provided in the embodiment of the present application is introduced below.

[0131] According to an embodiment of the present application, a device for implementing the above-mentioned method for predicting the scaling thickness of the water pipe in the equipment room is also provided. Figure 6 As shown, the device includes: a receiving unit 61, a first acquiring unit 62 and a processing unit 63.

[0132] The receiving unit 61 is used to receive a target prediction request, wherein the target prediction request is used to request a prediction of the scaling thickness of a target water pipe after a target time period, and the target water pipe includes: a water pipe in a computer room of a financial institution;

[0133] A first acquisition unit 62 is used to respond to the target prediction request and acquire water quality data of the target water pipe;

[0134] The processing unit 63 is used to input the water quality data and the target time into the target neural network model to obtain the target scaling thickness, wherein the target neural network model is used to predict the scaling thickness of the target water pipe after the target time, and the target neural network model includes: a neural network model obtained by optimizing the parameters of the fuzzy neural network based on the crayfish optimization algorithm.

[0135] In the device for predicting the scaling thickness of the water pipe in the computer room provided by the embodiment of the present application, a target prediction request can be received by a receiving unit 61, wherein the target prediction request is used to request the prediction of the scaling thickness of the target water pipe after the target time length, and the target water pipe includes: the water pipe in the computer room of the financial institution; the first acquisition unit 62 is used to respond to the target prediction request, obtain the water quality data of the target water pipe, and input the water quality data and the target time length into the target neural network model through the processing unit 63 to obtain the target scaling thickness, wherein the target neural network model is used to predict the scaling thickness of the target water pipe after the target time length, and the target neural network model includes: a neural network model obtained by optimizing the parameters of the fuzzy neural network based on the crayfish optimization algorithm. Thus, the technical problem that it is difficult to accurately predict the scaling thickness of the water pipe in the computer room in the related art is solved. In this embodiment, the scaling thickness of the water pipe is predicted based on the fuzzy neural network model optimized by the crayfish optimization algorithm, which avoids the related art that can only manually measure the scaling thickness of the water pipe in the computer room at the current moment, thereby achieving the technical effect of accurately predicting the scaling thickness of the water pipe in the computer room.

[0136] Optionally, in the device for predicting the scale thickness of the computer room water pipe provided in the embodiment of the present application, the target neural network model is obtained through the following units: a second acquisition unit, used to obtain training samples, wherein the training samples include: water quality data of the target water pipe in the historical time period and the scale thickness of the target water pipe after M time periods, M is a positive integer; a training unit, used to perform model training on the fuzzy neural network based on the training samples, and during the model training process, the model parameters of the fuzzy neural network are adjusted based on the crayfish optimization algorithm to obtain the adjusted model parameters, and based on the adjusted model parameters, the target neural network model is determined.

[0137] Optionally, in the device for predicting the scale thickness of water pipes in a computer room provided in an embodiment of the present application, the model parameters include: parameters of a membership function and weights of neurons in a fuzzy neural network, and the training unit includes: a construction subunit, used to construct a crayfish population of a crayfish optimization algorithm based on the parameters of the membership function and the weights of neurons in the fuzzy neural network, wherein the crayfish population includes: N groups of candidate solutions, and the N groups of candidate solutions are used to represent the model parameters; an update subunit, used to perform T iterative updates on the N groups of candidate solutions in the crayfish population based on the crayfish optimization algorithm to obtain updated N groups of candidate solutions, wherein T is a positive integer; and a first processing subunit, used to obtain adjusted model parameters based on the updated N groups of candidate solutions.

[0138] Optionally, in the device for predicting the scale thickness of water pipes in a computer room provided in an embodiment of the present application, during each iterative update of N candidate solutions in the crayfish population, it also includes: a generation module for generating random numbers, and based on the random numbers, generating environmental parameters for the crayfish optimization algorithm; a comparison module for comparing the environmental parameters with preset parameter thresholds to obtain comparison results; and an update module for updating the N groups of candidate solutions in the crayfish population based on the comparison results.

[0139] Optionally, in the device for predicting the thickness of scale formation in water pipes in a computer room provided in an embodiment of the present application, the update module includes: a first update sub-module, for updating N groups of candidate solutions in the crayfish population based on the summer vacation stage of the crayfish optimization algorithm when the comparison result indicates that the environmental parameter is greater than the preset parameter threshold; a second update sub-module, for updating N groups of candidate solutions in the crayfish population based on the foraging stage of the crayfish optimization algorithm when the comparison result indicates that the environmental parameter is greater than the preset parameter threshold.

[0140] Optionally, in the prediction device for the scale thickness of the computer room water pipe provided in the embodiment of the present application, the processing unit includes: a second processing subunit, used to input water quality data and target duration into the input layer of the target neural network model to obtain a first output result, wherein the input layer is used to receive the water quality data and target duration, and transmit the water quality data and target duration in the target neural network model; a second processing subunit, used to input the first output result into the fuzzification layer of the target neural network model to obtain a second output result, wherein the fuzzification layer is used to fuzzify the first output result based on fuzzy rules; a third processing subunit, used to input the second output result into the rule layer of the target neural network model to obtain a third output result, wherein the rule layer is used to determine the applicability of the fuzzy rules; a fourth processing subunit, used to input the third output result into the normalization layer of the target neural network model to obtain a fourth output result, wherein the normalization layer is used to normalize the third output result; a fifth processing subunit, used to input the fourth output result into the output layer of the target neural network model to obtain a target scaling thickness.

[0141] Optionally, in the device for predicting the thickness of scale in water pipes in a computer room provided in an embodiment of the present application, water quality data includes at least one of the following: water hardness, total dissolved solids, pH, water flow rate, and water temperature.

[0142] It should be noted that the above-mentioned receiving unit 61, first acquisition unit 62 and processing unit 63 correspond to steps S201 to S203 in the first embodiment, and the examples and application scenarios implemented by the two modules and the corresponding steps are the same, but are not limited to the contents disclosed in the first embodiment. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules can also be part of the device and can be run in the computer terminal 10 provided in the first embodiment.

[0143] Embodiment 3

[0144] An embodiment of the present application may provide an electronic device, Figure 7 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 7 As shown, the electronic device may include: one or more ( Figure 7 (only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0145] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0146] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: receiving a target prediction request, wherein the target prediction request is used to request a prediction of the scaling thickness of the target water pipe after a target time length, and the target water pipe includes: a water pipe in a computer room of a financial institution; responding to the target prediction request, obtaining water quality data of the target water pipe; inputting the water quality data and the target time length into a target neural network model to obtain a target scaling thickness, wherein the target neural network model is used to predict the scaling thickness of the target water pipe after a target time length, and the target neural network model includes: a neural network model obtained by optimizing the parameters of the fuzzy neural network based on a crayfish optimization algorithm.

[0147] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: The target neural network model is obtained in the following manner: obtaining training samples, wherein the training samples include: water quality data of the target water pipe in the historical time period and the scaling thickness of the target water pipe after M time periods, where M is a positive integer; performing model training on the fuzzy neural network based on the training samples, and during the model training process, adjusting the model parameters of the fuzzy neural network based on the crayfish optimization algorithm to obtain the adjusted model parameters, and determining the target neural network model based on the adjusted model parameters.

[0148] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: the model parameters include: the parameters of the membership function and the weights of the neurons of the fuzzy neural network, and the model parameters of the fuzzy neural network are adjusted based on the crayfish optimization algorithm to obtain the adjusted model parameters including: based on the parameters of the membership function and the weights of the neurons of the fuzzy neural network, a crayfish population of the crayfish optimization algorithm is constructed, wherein the crayfish population includes: N groups of candidate solutions, and the N groups of candidate solutions are used to represent the model parameters; based on the crayfish optimization algorithm, the N groups of candidate solutions in the crayfish population are iteratively updated T times to obtain the updated N groups of candidate solutions, wherein T is a positive integer; based on the updated N groups of candidate solutions, the adjusted model parameters are obtained.

[0149] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: in each iterative update process of N candidate solutions in the crayfish population, it also includes: generating random numbers, and based on the random numbers, generating environmental parameters for the crayfish optimization algorithm; comparing the environmental parameters with preset parameter thresholds to obtain comparison results; based on the comparison results, updating the N groups of candidate solutions in the crayfish population.

[0150] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: based on the comparison result, updating the N groups of candidate solutions in the crayfish population, also including: when the comparison result indicates that the environmental parameter is greater than the preset parameter threshold, updating the N groups of candidate solutions in the crayfish population based on the summer vacation stage of the crayfish optimization algorithm; when the comparison result indicates that the environmental parameter is not greater than the preset parameter threshold, updating the N groups of candidate solutions in the crayfish population based on the foraging stage of the crayfish optimization algorithm.

[0151] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: input the water quality data and the target duration into the target neural network model to obtain the target scaling thickness, including: inputting the water quality data and the target duration into the input layer of the target neural network model to obtain a first output result, wherein the input layer is used to receive the water quality data and the target duration, and transmit the water quality data and the target duration in the target neural network model; inputting the first output result into the fuzzification layer of the target neural network model to obtain a second output result, wherein the fuzzification layer is used to fuzzify the first output result based on fuzzy rules; inputting the second output result into the rule layer of the target neural network model to obtain a third output result, wherein the rule layer is used to determine the applicability of the fuzzy rules; inputting the third output result into the normalization layer of the target neural network model to obtain a fourth output result, wherein the normalization layer is used to normalize the third output result; inputting the fourth output result into the output layer of the target neural network model to obtain the target scaling thickness.

[0152] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: the water quality data includes at least one of the following: water hardness, total dissolved solids, pH, water flow rate and water temperature.

[0153] By adopting the embodiment of the present application, the scaling thickness of the water pipe is predicted based on the fuzzy neural network model optimized by the crayfish optimization algorithm, thereby avoiding the problem that the related technology can only manually measure the scaling thickness of the water pipe in the computer room at the current moment, thereby achieving the technical effect of accurately predicting the scaling thickness of the water pipe in the computer room, and further solving the technical problem that it is difficult to accurately predict the scaling thickness of the water pipe in the computer room in the related technology.

[0154] It can be understood by those skilled in the art that Figure 7 The structure shown is for illustration only, and the electronic device may also be a smart phone, a tablet computer, a PDA, a mobile Internet device (MID), a PAD or other terminal device. Figure 7 The structure of the electronic device is not limited. Figure 7 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 7 Different configurations shown.

[0155] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0156] Embodiment 4

[0157] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for predicting the scaling thickness of the water pipe in the computer room provided in the first embodiment.

[0158] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0159] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program steps of the method for predicting the scaling thickness of water pipes in a computer room.

[0160] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0161] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0162] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0163] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0165] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0166] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for predicting the thickness of scaling of water pipes in a machine room, characterized in that: include: Receiving a target prediction request, wherein the target prediction request is used to request a prediction of a scaling thickness of a target water pipe after a target time period, the target water pipe comprising: a water pipe in a computer room of a financial institution; In response to the target prediction request, obtaining water quality data of the target water pipe; The water quality data and the target duration are input into a target neural network model to obtain a target scaling thickness, wherein the target neural network model is used to predict the scaling thickness of a target water pipe after the target duration, and the target neural network model comprises: a neural network model obtained by optimizing parameters of a fuzzy neural network based on a crayfish optimization algorithm.

2. The prediction method according to claim 1, characterized in that: The target neural network model is obtained in the following way: Acquire training samples, wherein the training samples include: water quality data of the target water pipe in a historical time period and scaling thickness of the target water pipe after M time periods, where M is a positive integer; The fuzzy neural network is trained based on the training samples. During the model training, the model parameters of the fuzzy neural network are adjusted based on the crayfish optimization algorithm to obtain the adjusted model parameters. Based on the adjusted model parameters, the target neural network model is determined.

3. The prediction method according to claim 2, characterized in that: The model parameters include: the parameters of the membership function and the weights of the neurons of the fuzzy neural network. The model parameters of the fuzzy neural network are adjusted based on the crayfish optimization algorithm, and the adjusted model parameters include: Based on the parameters of the membership function and the weights of the neurons of the fuzzy neural network, constructing a crayfish population of the crayfish optimization algorithm, wherein the crayfish population includes: N groups of candidate solutions, and the N groups of candidate solutions are used to represent the model parameters; Based on the crayfish optimization algorithm, performing T iteration updates on the N groups of candidate solutions in the crayfish population to obtain updated N groups of candidate solutions, wherein T is a positive integer; Based on the updated N groups of candidate solutions, the adjusted model parameters are obtained.

4. The prediction method according to claim 3, characterized in that: In each iterative update process of the N candidate solutions in the crayfish population, the process further includes: Generate a random number, and based on the random number, generate environmental parameters of the crayfish optimization algorithm; Comparing the environmental parameter with a preset parameter threshold to obtain a comparison result; Based on the comparison result, the N groups of candidate solutions in the crayfish population are updated.

5. The prediction method according to claim 4, characterized in that: Based on the comparison result, updating the N groups of candidate solutions in the crayfish population includes: When the comparison result indicates that the environmental parameter is greater than the preset parameter threshold, updating the N groups of candidate solutions in the crayfish population based on the summer vacation stage of the crayfish optimization algorithm; When the comparison result indicates that the environmental parameter is not greater than the preset parameter threshold, the N groups of candidate solutions in the crayfish population are updated based on the foraging stage of the crayfish optimization algorithm.

6. The prediction method according to claim 1, characterized in that: The water quality data and the target duration are input into a target neural network model to obtain a target scaling thickness, including: Inputting the water quality data and the target duration into an input layer of a target neural network model to obtain a first output result, wherein the input layer is used to receive the water quality data and the target duration, and transmit the water quality data and the target duration in the target neural network model; Inputting the first output result into the fuzzification layer of the target neural network model to obtain a second output result, wherein the fuzzification layer is used to perform fuzzification processing on the first output result based on fuzzy rules; Inputting the second output result into the rule layer of the target neural network model to obtain a third output result, wherein the rule layer is used to determine the applicability of the fuzzy rule; Inputting the third output result into a normalization layer of the target neural network model to obtain a fourth output result, wherein the normalization layer is used to perform normalization processing on the third output result; The fourth output result is input into the output layer of the target neural network model to obtain the target scaling thickness.

7. The prediction method according to claim 1, characterized in that: The water quality data includes at least one of the following: water hardness, total dissolved solids, pH, water flow rate and water temperature.

8. A device for predicting the thickness of scale deposits on water pipes in a machine room, characterized in that: include: A receiving unit, configured to receive a target prediction request, wherein the target prediction request is used to request a prediction of a scaling thickness of a target water pipe after a target time period, wherein the target water pipe includes: a water pipe in a computer room of a financial institution; A first acquisition unit, configured to respond to the target prediction request and acquire water quality data of a target water pipe; A processing unit is used to input the water quality data and the target time into a target neural network model to obtain a target scaling thickness, wherein the target neural network model is used to predict the scaling thickness of the target water pipe after the target time, and the target neural network model includes: a neural network model obtained by optimizing the parameters of the fuzzy neural network based on a crayfish optimization algorithm.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the method for predicting the scaling thickness of the water pipe in the computer room according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by the processor, the steps of the method for predicting the thickness of scale deposits on water pipes in a computer room as described in any one of claims 1 to 7 are implemented.

Images