Intelligent control method and system for automatic snail breeding facility

Abstract

The invention relates to the technical field of aquaculture facility control, in particular to an intelligent control method and system for an automatic snail aquaculture facility, and the method comprises the steps: obtaining the real-time working data of each subunit block in the automatic snail aquaculture facility within a preset time period based on the Internet of Things; importing the real-time working data of each sub-unit block in a preset time period into a Bayesian network fault prediction model to perform fault prediction on each sub-unit block to obtain a fault probability of each sub-unit block in a future time period; a regulation and control scheme is generated according to the fault probability and the fault type of each sub-unit block in the future time period, regulation and control are performed based on the actual working data of the corresponding sub-unit block corresponding to the regulation and control scheme, the fault probability of the automatic snail breeding facility can be effectively reduced, the shutdown maintenance time of the automatic snail breeding facility is shortened, and the working efficiency of the automatic snail breeding facility is improved. Various breeding parameters in the snail breeding pond can be always kept in the optimal range, and intelligent breeding is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of aquaculture facility control, and in particular to an intelligent control method and system for automatic snail breeding facilities. Background Art

[0002] Snails are an important aquaculture resource and are highly favored due to their high protein, low fat, and low cholesterol characteristics. Automated snail breeding facilities refer to a breeding method that uses modern technology and equipment to intelligently monitor and control the snail breeding environment. The long-term and effective operation of automated snail breeding facilities can ensure that the breeding environment in the breeding pond is maintained within an appropriate range, thereby increasing the growth rate and yield of snails. Affected by factors such as the installation location of the automated snail breeding facilities, when the automated snail breeding facilities fail, they often need to be shut down for a long time for fault diagnosis and repair. During the shutdown and maintenance of the automated snail breeding facilities, the breeding environment is difficult to maintain within an appropriate range, which has a great impact on the growth of snails. Adding spare breeding facilities will increase the breeding cost. Therefore, how to ensure the long-term and effective operation of the automated snail breeding facilities through intelligent control is a technical problem that needs to be overcome. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent control method and system for an automated snail breeding facility.

[0004] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention discloses an intelligent control method for an automated snail breeding facility, comprising the following steps:

[0006] S102: Acquire historical service data of the snail automated breeding facility in a data repository, and classify and process the historical service data to obtain sub-historical service data of each sub-unit block in the snail automated breeding facility;

[0007] S104: Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, and filter the sub-historical service data of each sub-unit block according to the fault time periods when various historical faults occurred, to obtain fault feature data when various historical faults occurred;

[0008] S106: obtaining the real-time working data of each sub-unit block in the snail automated breeding facility within a preset time period based on the Internet of Things, importing the real-time working data of each sub-unit block within the preset time period into the Bayesian network fault prediction model to perform fault prediction on each sub-unit block, and obtaining the fault probability of each sub-unit block in the future time period;

[0009] S108: Generate a control scheme according to the failure probability and failure type of each sub-unit block in the future time period, and perform control corresponding to the actual working data of the corresponding sub-unit block based on the control scheme.

[0010] Furthermore, in a preferred embodiment of the present invention, the historical service data of the snail automated breeding facility is obtained in the data storage library, and the historical service data is classified and processed to obtain the sub-historical service data of each sub-unit block in the snail automated breeding facility, specifically:

[0011] S202: Acquire historical service data of the automatic snail breeding facility in the data repository, and construct a plurality of service data storage spaces corresponding to each sub-unit block in the automatic snail breeding facility according to each sub-unit block in the automatic snail breeding facility, and prefabricate feature data corresponding to each sub-unit block in the automatic snail breeding facility;

[0012] S204: introducing a cosine similarity algorithm, randomly accessing a historical service data, and calculating the similarity between the accessed historical service data and the feature data corresponding to each sub-unit block based on the cosine similarity algorithm to obtain multiple similarities;

[0013] S206: constructing a sorting table, importing multiple similarities into the sorting table for sorting, obtaining a sorting result, extracting the maximum similarity according to the sorting result, obtaining a sub-unit block corresponding to the maximum similarity, and dividing the accessed historical service data into the service data storage space of the sub-unit block corresponding to the maximum similarity as the sub-historical service data of the sub-unit block;

[0014] S208: Randomly access the next unaccessed historical service data, and repeat steps S204 to S206; until all historical service data are accessed and classified, and the sub-historical service data of each sub-unit block in the snail automated breeding facility are obtained.

[0015] Furthermore, in a preferred embodiment of the present invention, the fault time period when various historical faults occurred in the snail automated breeding facility is obtained, and the sub-historical service data of each sub-unit block is screened according to the fault time period when various historical faults occurred, and the fault characteristic data when various historical faults occurred are obtained, specifically:

[0016] Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, and obtain the timestamps of the sub-historical service data of each sub-unit block;

[0017] Extracting the sub-historical service data of each sub-unit block in the corresponding fault time period when various historical faults occur based on the fault time period and the timestamp of the sub-historical service data of each sub-unit block;

[0018] Obtain the fault type information of various historical faults and the functional information of each sub-unit block, introduce the grey correlation analysis method, and calculate the correlation between the fault type information of various historical faults and the functional information of each sub-unit block through the grey correlation analysis method;

[0019] Obtain sub-unit blocks with a correlation degree greater than a preset correlation degree, and define them as fault-related sub-unit blocks; and aggregate the sub-historical service data of all fault-related sub-unit blocks in the corresponding fault time period to obtain fault characteristic data when the relevant historical fault occurs;

[0020] Repeat the above steps to obtain fault characteristic data when various historical faults occur.

[0021] Furthermore, in a preferred embodiment of the present invention, the real-time working data of each sub-unit block in a preset time period is imported into the Bayesian network fault prediction model to perform fault prediction on each sub-unit block, and the fault probability and fault type of each sub-unit block in the future time period are obtained, specifically:

[0022] Generate multiple network nodes according to the fault type information of various historical faults, and construct a Bayesian network fault prediction model according to the network nodes;

[0023] Import the fault feature data of various historical faults into the corresponding network nodes of the Bayesian network fault prediction model;

[0024] Iteratively learn each network node in the Bayesian network fault prediction model based on the expectation maximization algorithm until the log-likelihood function of each network node in the Bayesian network fault prediction model reaches the maximum value, save the node parameters of each network node, and output the trained Bayesian network fault prediction model;

[0025] The real-time working data of each sub-unit block within a preset time period is imported into the trained Bayesian network fault prediction model to predict the faults of each sub-unit block, and the fault probability and fault type of each sub-unit block in the future time period are obtained.

[0026] Furthermore, in a preferred embodiment of the present invention, a control scheme is generated according to the failure probability and failure type of each sub-unit block in the future time period, and control is performed based on the actual working data of the corresponding sub-unit block according to the control scheme, specifically:

[0027] Compare the failure probability of each subunit block in the future time period with a preset threshold;

[0028] If the failure probability of all sub-unit blocks in the future time period is not greater than the preset threshold, it means that the snail automated breeding facility will not have abnormal operation in the future time period, and the snail automated breeding facility will not be regulated;

[0029] If the failure probability of one or more sub-unit blocks in the future time period is greater than the preset threshold, it means that the snail automated breeding facility will have abnormal operation in the future time period, and the snail automated breeding facility will be regulated.

[0030] Furthermore, in a preferred embodiment of the present invention, if the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, it means that the snail automated breeding facility will have an abnormal operation condition in the future time period, and the snail automated breeding facility is regulated and processed, specifically:

[0031] If there is a situation where the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, then the failure type of the sub-unit block with the failure probability greater than the preset threshold is obtained;

[0032] Prefabricate the corresponding preventive control schemes for each subunit block before various preset fault types occur, construct a knowledge graph, and import the preventive control schemes into the knowledge graph;

[0033] Generate a search tag according to the fault type of the subunit block whose fault probability is greater than a preset threshold, and retrieve the corresponding preventive control scheme in the knowledge graph based on the search tag;

[0034] Obtaining the preset working data of each sub-unit block in the corresponding preventive control scheme, and obtaining the actual working data of each sub-unit block at the current time node;

[0035] Calculate the difference between the actual working data of each sub-unit block and the preset working data to obtain the working data difference of each sub-unit block, and determine whether the working data difference of each sub-unit block is greater than the preset difference;

[0036] If it is not greater than, the actual working data of the sub-unit block is not adjusted; if it is greater than, the actual working data of the corresponding sub-unit block is adjusted based on the working data difference.

[0037] The second aspect of the present invention discloses an intelligent control system for an automated snail breeding facility, the intelligent control system comprising a memory and a processor, the memory storing an intelligent control method program, and when the intelligent control method program is executed by the processor, the following steps are implemented:

[0038] S102: Acquire historical service data of the snail automated breeding facility in a data repository, and classify and process the historical service data to obtain sub-historical service data of each sub-unit block in the snail automated breeding facility;

[0039] S104: Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, and filter the sub-historical service data of each sub-unit block according to the fault time periods when various historical faults occurred, to obtain fault feature data when various historical faults occurred;

[0040] S106: obtaining the real-time working data of each sub-unit block in the snail automated breeding facility within a preset time period based on the Internet of Things, importing the real-time working data of each sub-unit block within the preset time period into the Bayesian network fault prediction model to perform fault prediction on each sub-unit block, and obtaining the fault probability of each sub-unit block in the future time period;

[0041] S108: Generate a control scheme according to the failure probability and failure type of each sub-unit block in the future time period, and perform control corresponding to the actual working data of the corresponding sub-unit block based on the control scheme.

[0042] Furthermore, in a preferred embodiment of the present invention, the historical service data of the snail automated breeding facility is obtained in the data storage library, and the historical service data is classified and processed to obtain the sub-historical service data of each sub-unit block in the snail automated breeding facility, specifically:

[0043] S202: Acquire historical service data of the automatic snail breeding facility in the data repository, and construct a plurality of service data storage spaces corresponding to each sub-unit block in the automatic snail breeding facility according to each sub-unit block in the automatic snail breeding facility, and prefabricate feature data corresponding to each sub-unit block in the automatic snail breeding facility;

[0044] S204: introducing a cosine similarity algorithm, randomly accessing a historical service data, and calculating the similarity between the accessed historical service data and the feature data corresponding to each sub-unit block based on the cosine similarity algorithm to obtain multiple similarities;

[0045] S206: constructing a sorting table, importing multiple similarities into the sorting table for sorting, obtaining a sorting result, extracting the maximum similarity according to the sorting result, obtaining a sub-unit block corresponding to the maximum similarity, and dividing the accessed historical service data into the service data storage space of the sub-unit block corresponding to the maximum similarity as the sub-historical service data of the sub-unit block;

[0046] S208: Randomly access the next unaccessed historical service data, and repeat steps S204 to S206; until all historical service data are accessed and classified, and the sub-historical service data of each sub-unit block in the snail automated breeding facility are obtained.

[0047] Furthermore, in a preferred embodiment of the present invention, a control scheme is generated according to the failure probability and failure type of each sub-unit block in the future time period, and control is performed based on the actual working data of the corresponding sub-unit block according to the control scheme, specifically:

[0048] Compare the failure probability of each subunit block in the future time period with a preset threshold;

[0049] If the failure probability of all sub-unit blocks in the future time period is not greater than the preset threshold, it means that the snail automated breeding facility will not have abnormal operation in the future time period, and the snail automated breeding facility will not be regulated;

[0050] If the failure probability of one or more sub-unit blocks in the future time period is greater than the preset threshold, it means that the snail automated breeding facility will have abnormal operation in the future time period, and the snail automated breeding facility will be regulated.

[0051] Furthermore, in a preferred embodiment of the present invention, if the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, it means that the snail automated breeding facility will have an abnormal operation condition in the future time period, and the snail automated breeding facility is regulated and processed, specifically:

[0052] If there is a situation where the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, then the failure type of the sub-unit block with the failure probability greater than the preset threshold is obtained;

[0053] Prefabricate the corresponding preventive control schemes for each subunit block before various preset fault types occur, construct a knowledge graph, and import the preventive control schemes into the knowledge graph;

[0054] Generate a search tag according to the fault type of the subunit block whose fault probability is greater than a preset threshold, and retrieve the corresponding preventive control scheme in the knowledge graph based on the search tag;

[0055] Obtaining the preset working data of each sub-unit block in the corresponding preventive control scheme, and obtaining the actual working data of each sub-unit block at the current time node;

[0056] Calculate the difference between the actual working data of each sub-unit block and the preset working data to obtain the working data difference of each sub-unit block, and determine whether the working data difference of each sub-unit block is greater than the preset difference;

[0057] If it is not greater than, the actual working data of the sub-unit block is not adjusted; if it is greater than, the actual working data of the corresponding sub-unit block is adjusted based on the working data difference.

[0058] The present invention solves the technical defects existing in the background technology, and has the following beneficial effects: obtaining the fault time period when various historical faults occur in the automatic breeding facility for snails, screening the sub-historical service data of each sub-unit block according to the fault time period when various historical faults occur, and obtaining the fault characteristic data when various historical faults occur; obtaining the real-time working data of each sub-unit block in the automatic breeding facility for snails in a preset time period based on the Internet of Things, importing the real-time working data of each sub-unit block in the preset time period into a Bayesian network fault prediction model to perform fault prediction on each sub-unit block, and obtaining the failure probability of each sub-unit block in the future time period; generating a control scheme according to the failure probability and fault type of each sub-unit block in the future time period, and controlling the actual working data of the corresponding sub-unit block based on the control scheme, and through the intelligent control of the automatic breeding facility for snails, the probability of failure of the automatic breeding facility for snails can be effectively reduced, ensuring that the automatic breeding facility for snails can operate effectively for a long time, reducing the downtime and maintenance time of the automatic breeding facility for snails, so that various breeding parameters in the snail breeding pool can always be kept within the optimal range, and intelligent breeding is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0060] Figure 1 The present invention is a flow chart of an overall method of an intelligent control method for an automated snail breeding facility;

[0061] Figure 2 A partial method flow chart of an intelligent control method for an automated snail breeding facility;

[0062] Figure 3 The system block diagram of an intelligent control system for an automated snail breeding facility. DETAILED DESCRIPTION

[0063] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0065] like Figure 1 As shown, the first aspect of the present invention discloses an intelligent control method for an automated snail breeding facility, comprising the following steps:

[0066] S102: Acquire historical service data of the snail automated breeding facility in a data repository, and classify and process the historical service data to obtain sub-historical service data of each sub-unit block in the snail automated breeding facility;

[0067] S104: Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, and filter the sub-historical service data of each sub-unit block according to the fault time periods when various historical faults occurred, to obtain fault feature data when various historical faults occurred;

[0068] S106: obtaining the real-time working data of each sub-unit block in the snail automated breeding facility within a preset time period based on the Internet of Things, importing the real-time working data of each sub-unit block within the preset time period into the Bayesian network fault prediction model to perform fault prediction on each sub-unit block, and obtaining the fault probability of each sub-unit block in the future time period;

[0069] S108: Generate a control scheme according to the failure probability and failure type of each sub-unit block in the future time period, and perform control corresponding to the actual working data of the corresponding sub-unit block based on the control scheme.

[0070] like Figure 2 As shown, further, in a preferred embodiment of the present invention, the historical service data of the snail automated breeding facility is obtained in the data storage library, and the historical service data is classified and processed to obtain the sub-historical service data of each sub-unit block in the snail automated breeding facility, specifically:

[0071] S202: Acquire historical service data of the automatic snail breeding facility in the data repository, and construct a plurality of service data storage spaces corresponding to each sub-unit block in the automatic snail breeding facility according to each sub-unit block in the automatic snail breeding facility, and prefabricate feature data corresponding to each sub-unit block in the automatic snail breeding facility;

[0072] S204: introducing a cosine similarity algorithm, randomly accessing a historical service data, and calculating the similarity between the accessed historical service data and the feature data corresponding to each sub-unit block based on the cosine similarity algorithm to obtain multiple similarities;

[0073] S206: constructing a sorting table, importing multiple similarities into the sorting table for sorting, obtaining a sorting result, extracting the maximum similarity according to the sorting result, obtaining a sub-unit block corresponding to the maximum similarity, and dividing the accessed historical service data into the service data storage space of the sub-unit block corresponding to the maximum similarity as the sub-historical service data of the sub-unit block;

[0074] S208: Randomly access the next unaccessed historical service data, and repeat steps S204 to S206; until all historical service data are accessed and classified, and the sub-historical service data of each sub-unit block in the snail automated breeding facility are obtained.

[0075] The feature data corresponding to each sub-unit block can represent the data features of each sub-unit block, and the feature data includes information such as numerical features, category features, binary features, text features, and spectrum features.

[0076] It should be noted that the sub-unit blocks of the snail automated breeding facility include water quality control unit blocks, water temperature control unit blocks, feed delivery unit blocks, monitoring unit blocks, oxygen concentration control unit blocks, and energy management unit blocks. The historical service data includes the voltage data, current data, internal temperature data, internal humidity data, etc. of each sub-unit block at a certain time point in the past.

[0077] It should be noted that for the convenience of transmission and storage, the historical service data of the snail automated breeding facility will be summarized and stored in the data repository. Therefore, when the historical service data of the snail automated breeding facility is extracted to construct the Bayesian network fault prediction model, it is not known at this time which historical service data belongs to which sub-unit block of sub-historical service data. Therefore, it is necessary to classify the extracted historical service data through the above method steps to obtain the sub-historical service data of each sub-unit block in the snail automated breeding facility, so that the Bayesian network fault prediction model can be constructed based on the sub-historical service data of each sub-unit block in the subsequent process.

[0078] Furthermore, in a preferred embodiment of the present invention, the fault time period when various historical faults occurred in the snail automated breeding facility is obtained, and the sub-historical service data of each sub-unit block is screened according to the fault time period when various historical faults occurred, and the fault characteristic data when various historical faults occurred are obtained, specifically:

[0079] Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, and obtain the timestamps of the sub-historical service data of each sub-unit block;

[0080] Extracting the sub-historical service data of each sub-unit block in the corresponding fault time period when various historical faults occur based on the fault time period and the timestamp of the sub-historical service data of each sub-unit block;

[0081] Obtain the fault type information of various historical faults and the functional information of each sub-unit block, introduce the grey correlation analysis method, and calculate the correlation between the fault type information of various historical faults and the functional information of each sub-unit block through the grey correlation analysis method;

[0082] Obtain sub-unit blocks with a correlation degree greater than a preset correlation degree, and define them as fault-related sub-unit blocks; and aggregate the sub-historical service data of all fault-related sub-unit blocks in the corresponding fault time period to obtain fault characteristic data when the relevant historical fault occurs;

[0083] Repeat the above steps to obtain fault characteristic data when various historical faults occur.

[0084] The functional information of each sub-unit block is the functional role of each sub-unit block, such as the water temperature control unit block is used to control the aquaculture water temperature.

[0085] It should be noted that in this step, by obtaining the fault time period when various historical faults occurred in the snail automated breeding facilities, the sub-historical service data of each sub-unit block is screened to obtain the fault characteristic data when various historical faults occurred. For example, when the temperature control unit block fails and causes an abnormal increase in energy consumption, it may cause abnormal operation of the energy management unit block, thereby causing the energy management unit block to fail. Therefore, the temperature control unit block and the energy management unit block are fault-related sub-unit blocks. Through this step, it is possible to extract and obtain complete fault characteristic data when various historical faults occur, thereby improving the modeling accuracy of the subsequent Bayesian network fault prediction model and improving the accuracy of the prediction results.

[0086] Furthermore, in a preferred embodiment of the present invention, the real-time working data of each sub-unit block in a preset time period is imported into the Bayesian network fault prediction model to perform fault prediction on each sub-unit block, and the fault probability and fault type of each sub-unit block in the future time period are obtained, specifically:

[0087] Generate multiple network nodes according to the fault type information of various historical faults, and construct a Bayesian network fault prediction model according to the network nodes;

[0088] Import the fault feature data of various historical faults into the corresponding network nodes of the Bayesian network fault prediction model;

[0089] Iteratively learn each network node in the Bayesian network fault prediction model based on the expectation maximization algorithm until the log-likelihood function of each network node in the Bayesian network fault prediction model reaches the maximum value, save the node parameters of each network node, and output the trained Bayesian network fault prediction model;

[0090] The real-time working data of each sub-unit block within a preset time period is imported into the trained Bayesian network fault prediction model to predict the faults of each sub-unit block, and the fault probability and fault type of each sub-unit block in the future time period are obtained.

[0091] It should be noted that the Bayesian network fault prediction model describes the probability relationship between various variables in the system based on the probability graph model, thereby realizing the function of fault prediction. The advantage of the Bayesian network is that it can handle uncertainty and complex probability relationships. By combining historical data and real-time observation data, the Bayesian network can provide a probability prediction of future faults. This method can be combined with the Bayesian network fault prediction model to predict the fault probability and fault type of each sub-unit block in the future time period based on the real-time working data of each sub-unit block in the preset time period.

[0092] Furthermore, in a preferred embodiment of the present invention, a control scheme is generated according to the failure probability and failure type of each sub-unit block in the future time period, and control is performed based on the actual working data of the corresponding sub-unit block according to the control scheme, specifically:

[0093] Compare the failure probability of each subunit block in the future time period with a preset threshold;

[0094] If the failure probability of all sub-unit blocks in the future time period is not greater than the preset threshold, it means that the snail automated breeding facility will not have abnormal operation in the future time period, and the snail automated breeding facility will not be regulated;

[0095] If the failure probability of one or more sub-unit blocks in the future time period is greater than the preset threshold, it means that the snail automated breeding facility will have abnormal operation in the future time period, and the snail automated breeding facility will be regulated.

[0096] Furthermore, in a preferred embodiment of the present invention, if the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, it means that the snail automated breeding facility will have an abnormal operation condition in the future time period, and the snail automated breeding facility is regulated and processed, specifically:

[0097] If there is a situation where the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, then the failure type of the sub-unit block with the failure probability greater than the preset threshold is obtained;

[0098] Prefabricate the corresponding preventive control schemes for each subunit block before various preset fault types occur, construct a knowledge graph, and import the preventive control schemes into the knowledge graph;

[0099] Generate a search tag according to the fault type of the subunit block whose fault probability is greater than a preset threshold, and retrieve the corresponding preventive control scheme in the knowledge graph based on the search tag;

[0100] Obtaining the preset working data of each sub-unit block in the corresponding preventive control scheme, and obtaining the actual working data of each sub-unit block at the current time node;

[0101] Calculate the difference between the actual working data of each sub-unit block and the preset working data to obtain the working data difference of each sub-unit block, and determine whether the working data difference of each sub-unit block is greater than the preset difference;

[0102] If it is not greater than, the actual working data of the sub-unit block is not adjusted; if it is greater than, the actual working data of the corresponding sub-unit block is adjusted based on the working data difference.

[0103] It should be noted that, if it is predicted that a certain sub-unit block will have a high probability of high-temperature failure in the future time period, the high-temperature failure can be avoided by increasing the cooling power of the cooler in advance to reduce the temperature of the sub-unit block. The preventive control scheme corresponding to various preset fault types before the occurrence can be obtained through a large number of experiments or through a big data network, that is, the optimal control scheme, which includes the optimal working data of each sub-unit block, such as voltage data, circuit data, power data, etc. Through this step, the failure probability and failure type of each sub-unit block in the future time period can generate a corresponding control scheme, so as to intelligently control the automatic breeding facilities of snails, effectively reduce the probability of failure of the automatic breeding facilities of snails, ensure that the automatic breeding facilities of snails can operate effectively for a long time, reduce the downtime and maintenance time of the automatic breeding facilities of snails, so that the various breeding parameters in the snail breeding pool can always be kept within the optimal range, and realize intelligent breeding.

[0104] In addition, the method further comprises the following steps:

[0105] Obtain various standard breeding environment parameters of snails at different growth stages through a big data network, build a database, and import various standard breeding environment parameters of snails at different growth stages into the database to obtain a characteristic database;

[0106] At a preset time point, real-time growth image information of snails in the breeding pond is obtained through an underwater camera, the real-time growth stage of the snails is identified based on the real-time growth image information, the real-time growth stage is imported into the characteristic database for pairing, and various standard breeding environment parameters of the snails in the current real-time growth stage are obtained;

[0107] Obtain various actual breeding environment parameters in the breeding pond, compare the various actual breeding environment parameters with various standard breeding environment parameters, and obtain various breeding environment parameter deviations; compare the various breeding environment parameter deviations with preset deviation values;

[0108] If a certain aquaculture environment parameter deviation is greater than a preset deviation value, then the actual aquaculture environment parameter whose aquaculture environment parameter deviation is greater than the preset deviation value is obtained, and is defined as the aquaculture environment parameter that needs to be adjusted;

[0109] The type information of the aquaculture environment parameter to be regulated is obtained, and based on the type information of the aquaculture environment parameter to be regulated, an associated subunit block for regulating the aquaculture environment parameter to be regulated is obtained, and the associated subunit block is regulated based on the aquaculture environment parameter deviation.

[0110] It should be noted that the associated sub-unit block is a unit block that adjusts a certain breeding environment through a certain sub-unit block, such as adjusting the breeding water temperature through the water temperature adjustment unit block. Through this method, standard breeding environment parameters can be automatically matched according to the current real-time growth stage of the snail, so that the breeding environment can be regulated according to the standard breeding environment parameters, realizing intelligent breeding.

[0111] The real-time growth stage of the snail is identified based on the real-time growth image information, specifically:

[0112] Graying, noise reduction and smoothing the real-time growth image information to obtain processed real-time growth image information;

[0113] Select one or more appropriate seed points as the starting point of growth, and define the criteria for regional growth based on the difference in pixel values ​​and gradient information;

[0114] Using the region growing algorithm, the region is gradually grown from the seed point, and the pixels matching the growth criteria are added to the same region; according to the result of region growing, the image is segmented into two regions: the snail image and the background;

[0115] Acquire characteristic images corresponding to snails at different growth stages through a big data network, build a pairing database, and import the characteristic images corresponding to snails at different growth stages into the pairing database;

[0116] Calculating the degree of overlap between the snail image and each feature image in the pairing database based on the Euclidean distance algorithm to obtain multiple degrees of overlap;

[0117] The maximum overlap is extracted from multiple overlaps, a feature image corresponding to the maximum overlap is obtained, and the real-time growth stage of the snails in the breeding pond is obtained according to the feature image corresponding to the maximum overlap.

[0118] It should be noted that the snail and the background image are segmented by a region growing algorithm to obtain a separate snail image. Then, the overlap between the snail image and each feature image in the pairing database is calculated by a Euclidean distance algorithm, so as to quickly pair and obtain the real-time growth stage of the snail.

[0119] like Figure 3 As shown, the second aspect of the present invention discloses an intelligent control system for an automated snail breeding facility, the intelligent control system comprising a memory 60 and a processor 90, the memory 60 stores an intelligent control method program, and when the intelligent control method program is executed by the processor 90, the following steps are implemented:

[0120] S102: Acquire historical service data of the snail automated breeding facility in a data repository, and classify and process the historical service data to obtain sub-historical service data of each sub-unit block in the snail automated breeding facility;

[0121] S104: Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, and filter the sub-historical service data of each sub-unit block according to the fault time periods when various historical faults occurred, to obtain fault feature data when various historical faults occurred;

[0122] S106: obtaining the real-time working data of each sub-unit block in the snail automated breeding facility within a preset time period based on the Internet of Things, importing the real-time working data of each sub-unit block within the preset time period into the Bayesian network fault prediction model to perform fault prediction on each sub-unit block, and obtaining the fault probability of each sub-unit block in the future time period;

[0123] S108: Generate a control scheme according to the failure probability and failure type of each sub-unit block in the future time period, and perform control corresponding to the actual working data of the corresponding sub-unit block based on the control scheme.

[0124] Furthermore, in a preferred embodiment of the present invention, the historical service data of the snail automated breeding facility is obtained in the data storage library, and the historical service data is classified and processed to obtain the sub-historical service data of each sub-unit block in the snail automated breeding facility, specifically:

[0125] S202: Acquire historical service data of the automatic snail breeding facility in the data repository, and construct a plurality of service data storage spaces corresponding to each sub-unit block in the automatic snail breeding facility according to each sub-unit block in the automatic snail breeding facility, and prefabricate feature data corresponding to each sub-unit block in the automatic snail breeding facility;

[0126] S204: introducing a cosine similarity algorithm, randomly accessing a historical service data, and calculating the similarity between the accessed historical service data and the feature data corresponding to each sub-unit block based on the cosine similarity algorithm to obtain multiple similarities;

[0127] S206: constructing a sorting table, importing multiple similarities into the sorting table for sorting, obtaining a sorting result, extracting the maximum similarity according to the sorting result, obtaining a sub-unit block corresponding to the maximum similarity, and dividing the accessed historical service data into the service data storage space of the sub-unit block corresponding to the maximum similarity as the sub-historical service data of the sub-unit block;

[0128] S208: Randomly access the next unaccessed historical service data, and repeat steps S204 to S206; until all historical service data are accessed and classified, and the sub-historical service data of each sub-unit block in the snail automated breeding facility are obtained.

[0129] Furthermore, in a preferred embodiment of the present invention, a control scheme is generated according to the failure probability and failure type of each sub-unit block in the future time period, and control is performed based on the actual working data of the corresponding sub-unit block according to the control scheme, specifically:

[0130] Compare the failure probability of each subunit block in the future time period with a preset threshold;

[0131] If the failure probability of all sub-unit blocks in the future time period is not greater than the preset threshold, it means that the snail automated breeding facility will not have abnormal operation in the future time period, and the snail automated breeding facility will not be regulated;

[0132] If the failure probability of one or more sub-unit blocks in the future time period is greater than the preset threshold, it means that the snail automated breeding facility will have abnormal operation in the future time period, and the snail automated breeding facility will be regulated.

[0133] Furthermore, in a preferred embodiment of the present invention, if the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, it means that the snail automated breeding facility will have an abnormal operation condition in the future time period, and the snail automated breeding facility is regulated and processed, specifically:

[0134] If there is a situation where the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, then the failure type of the sub-unit block with the failure probability greater than the preset threshold is obtained;

[0135] Prefabricate the corresponding preventive control schemes for each subunit block before various preset fault types occur, construct a knowledge graph, and import the preventive control schemes into the knowledge graph;

[0136] Generate a search tag according to the fault type of the subunit block whose fault probability is greater than a preset threshold, and retrieve the corresponding preventive control scheme in the knowledge graph based on the search tag;

[0137] Obtaining the preset working data of each sub-unit block in the corresponding preventive control scheme, and obtaining the actual working data of each sub-unit block at the current time node;

[0138] Calculate the difference between the actual working data of each sub-unit block and the preset working data to obtain the working data difference of each sub-unit block, and determine whether the working data difference of each sub-unit block is greater than the preset difference;

[0139] If it is not greater than, the actual working data of the sub-unit block is not adjusted; if it is greater than, the actual working data of the corresponding sub-unit block is adjusted based on the working data difference.

[0140] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. 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, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0141] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; 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 present embodiment.

[0142] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0143] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0144] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0145] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent control method for automatic snail breeding facilities, characterized in that: The following steps are involved: S102: Acquire historical service data of the snail automated breeding facility in a data repository, and classify and process the historical service data to obtain sub-historical service data of each sub-unit block in the snail automated breeding facility; S104: Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, and filter the sub-historical service data of each sub-unit block according to the fault time periods when various historical faults occurred, to obtain fault feature data when various historical faults occurred; S106: obtaining the real-time working data of each sub-unit block in the snail automated breeding facility within a preset time period based on the Internet of Things, importing the real-time working data of each sub-unit block within the preset time period into the Bayesian network fault prediction model to perform fault prediction on each sub-unit block, and obtaining the fault probability of each sub-unit block in the future time period; S108: Generate a control scheme according to the failure probability and failure type of each sub-unit block in the future time period, and perform control corresponding to the actual working data of the corresponding sub-unit block based on the control scheme.

2. The intelligent control method for an automated snail breeding facility according to claim 1, characterized in that: The historical service data of the snail automated breeding facility is obtained in the data repository, and the historical service data is classified and processed to obtain the sub-historical service data of each sub-unit block in the snail automated breeding facility, specifically: S202: Acquire historical service data of the automatic snail breeding facility in the data repository, and construct a plurality of service data storage spaces corresponding to each sub-unit block in the automatic snail breeding facility according to each sub-unit block in the automatic snail breeding facility, and prefabricate feature data corresponding to each sub-unit block in the automatic snail breeding facility; S204: introducing a cosine similarity algorithm, randomly accessing a historical service data, and calculating the similarity between the accessed historical service data and the feature data corresponding to each sub-unit block based on the cosine similarity algorithm to obtain multiple similarities; S206: constructing a sorting table, importing multiple similarities into the sorting table for sorting, obtaining a sorting result, extracting the maximum similarity according to the sorting result, obtaining a sub-unit block corresponding to the maximum similarity, and dividing the accessed historical service data into the service data storage space of the sub-unit block corresponding to the maximum similarity as the sub-historical service data of the sub-unit block; S208: Randomly access the next unaccessed historical service data, and repeat steps S204 to S206; until all historical service data are accessed and classified, and the sub-historical service data of each sub-unit block in the snail automated breeding facility are obtained.

3. The intelligent control method for the automatic breeding facility of snails according to claim 1, characterized in that: Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, filter the sub-historical service data of each sub-unit block according to the fault time periods when various historical faults occurred, and obtain the fault feature data when various historical faults occurred, specifically: Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, and obtain the timestamps of the sub-historical service data of each sub-unit block; Extracting the sub-historical service data of each sub-unit block in the corresponding fault time period when various historical faults occur based on the fault time period and the timestamp of the sub-historical service data of each sub-unit block; Obtain the fault type information of various historical faults and the functional information of each sub-unit block, introduce the grey correlation analysis method, and calculate the correlation between the fault type information of various historical faults and the functional information of each sub-unit block through the grey correlation analysis method; Obtain sub-unit blocks with a correlation degree greater than a preset correlation degree, and define them as fault-related sub-unit blocks; and aggregate the sub-historical service data of all fault-related sub-unit blocks in the corresponding fault time period to obtain fault characteristic data when the relevant historical fault occurs; Repeat the above steps to obtain fault characteristic data when various historical faults occur.

4. The intelligent control method for an automated snail breeding facility according to claim 1, characterized in that: The real-time working data of each sub-unit block in the preset time period is imported into the Bayesian network fault prediction model to predict the fault of each sub-unit block, and the fault probability and fault type of each sub-unit block in the future time period are obtained, specifically: Generate multiple network nodes according to the fault type information of various historical faults, and construct a Bayesian network fault prediction model according to the network nodes; Import the fault feature data of various historical faults into the corresponding network nodes of the Bayesian network fault prediction model; Iteratively learn each network node in the Bayesian network fault prediction model based on the expectation maximization algorithm until the log-likelihood function of each network node in the Bayesian network fault prediction model reaches the maximum value, save the node parameters of each network node, and output the trained Bayesian network fault prediction model; The real-time working data of each sub-unit block within a preset time period is imported into the trained Bayesian network fault prediction model to predict the faults of each sub-unit block, and the fault probability and fault type of each sub-unit block in the future time period are obtained.

5. The intelligent control method for the automatic breeding facility of snails according to claim 1, characterized in that: Generate a control scheme based on the failure probability and failure type of each sub-unit block in the future time period, and perform control based on the actual working data of the corresponding sub-unit block according to the control scheme, specifically: Compare the failure probability of each subunit block in the future time period with a preset threshold; If the failure probability of all sub-unit blocks in the future time period is not greater than the preset threshold, it means that the snail automated breeding facility will not have abnormal operation in the future time period, and the snail automated breeding facility will not be regulated; If the failure probability of one or more sub-unit blocks in the future time period is greater than the preset threshold, it means that the snail automated breeding facility will have abnormal operation in the future time period, and the snail automated breeding facility will be regulated.

6. The intelligent control method for the automatic breeding facility of snails according to claim 5, characterized in that: If the failure probability of one or more sub-unit blocks in the future time period is greater than the preset threshold, it means that the snail automated breeding facility will have an abnormal operation in the future time period, and the snail automated breeding facility will be regulated and processed, specifically: If there is a situation where the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, then the failure type of the sub-unit block with the failure probability greater than the preset threshold is obtained; Prefabricate the corresponding preventive control schemes for each subunit block before various preset fault types occur, construct a knowledge graph, and import the preventive control schemes into the knowledge graph; Generate a search tag according to the fault type of the subunit block whose fault probability is greater than a preset threshold, and retrieve the corresponding preventive control scheme in the knowledge graph based on the search tag; Obtaining the preset working data of each sub-unit block in the corresponding preventive control scheme, and obtaining the actual working data of each sub-unit block at the current time node; Calculate the difference between the actual working data of each sub-unit block and the preset working data to obtain the working data difference of each sub-unit block, and determine whether the working data difference of each sub-unit block is greater than the preset difference; If it is not greater than, the actual working data of the sub-unit block will not be regulated; If it is greater than, the actual working data of the corresponding sub-unit block is adjusted based on the working data difference.

7. An intelligent control system for automated snail breeding facilities, characterized in that: The intelligent control system includes a memory and a processor. The memory stores an intelligent control method program. When the intelligent control method program is executed by the processor, the following steps are implemented: S102: Acquire historical service data of the snail automated breeding facility in a data repository, and classify and process the historical service data to obtain sub-historical service data of each sub-unit block in the snail automated breeding facility; S104: Obtain the fault time periods when various historical faults occurred in the snail automated breeding facility, and filter the sub-historical service data of each sub-unit block according to the fault time periods when various historical faults occurred, to obtain fault feature data when various historical faults occurred; S106: obtaining the real-time working data of each sub-unit block in the snail automated breeding facility within a preset time period based on the Internet of Things, importing the real-time working data of each sub-unit block within the preset time period into the Bayesian network fault prediction model to perform fault prediction on each sub-unit block, and obtaining the fault probability of each sub-unit block in the future time period; S108: Generate a control scheme according to the failure probability and failure type of each sub-unit block in the future time period, and perform control corresponding to the actual working data of the corresponding sub-unit block based on the control scheme.

8. The intelligent control system for the automatic breeding facility of snails according to claim 7, characterized in that: The historical service data of the snail automated breeding facility is obtained in the data repository, and the historical service data is classified and processed to obtain the sub-historical service data of each sub-unit block in the snail automated breeding facility, specifically: S202: Acquire historical service data of the automatic snail breeding facility in the data repository, and construct a plurality of service data storage spaces corresponding to each sub-unit block in the automatic snail breeding facility according to each sub-unit block in the automatic snail breeding facility, and prefabricate feature data corresponding to each sub-unit block in the automatic snail breeding facility; S204: introducing a cosine similarity algorithm, randomly accessing a historical service data, and calculating the similarity between the accessed historical service data and the feature data corresponding to each sub-unit block based on the cosine similarity algorithm to obtain multiple similarities; S206: constructing a sorting table, importing multiple similarities into the sorting table for sorting, obtaining a sorting result, extracting the maximum similarity according to the sorting result, obtaining a sub-unit block corresponding to the maximum similarity, and dividing the accessed historical service data into the service data storage space of the sub-unit block corresponding to the maximum similarity as the sub-historical service data of the sub-unit block; S208: Randomly access the next unaccessed historical service data, and repeat steps S204 to S206; until all historical service data are accessed and classified, and the sub-historical service data of each sub-unit block in the snail automated breeding facility are obtained.

9. The intelligent control system for the automatic breeding facility of snails according to claim 7, characterized in that: Generate a control scheme based on the failure probability and failure type of each sub-unit block in the future time period, and perform control based on the actual working data of the corresponding sub-unit block according to the control scheme, specifically: Compare the failure probability of each subunit block in the future time period with a preset threshold; If the failure probability of all sub-unit blocks in the future time period is not greater than the preset threshold, it means that the snail automated breeding facility will not have abnormal operation in the future time period, and the snail automated breeding facility will not be regulated; If the failure probability of one or more sub-unit blocks in the future time period is greater than the preset threshold, it means that the snail automated breeding facility will have abnormal operation in the future time period, and the snail automated breeding facility will be regulated.

10. The intelligent control system for the automatic breeding facility of snails according to claim 9, characterized in that: If the failure probability of one or more sub-unit blocks in the future time period is greater than the preset threshold, it means that the snail automated breeding facility will have an abnormal operation in the future time period, and the snail automated breeding facility will be regulated and processed, specifically: If there is a situation where the failure probability of one or more sub-unit blocks in the future time period is greater than a preset threshold, then the failure type of the sub-unit block with the failure probability greater than the preset threshold is obtained; Prefabricate the corresponding preventive control schemes for each subunit block before various preset fault types occur, construct a knowledge graph, and import the preventive control schemes into the knowledge graph; Generate a search tag according to the fault type of the subunit block whose fault probability is greater than a preset threshold, and retrieve the corresponding preventive control scheme in the knowledge graph based on the search tag; Obtaining the preset working data of each sub-unit block in the corresponding preventive control scheme, and obtaining the actual working data of each sub-unit block at the current time node; Calculate the difference between the actual working data of each sub-unit block and the preset working data to obtain the working data difference of each sub-unit block, and determine whether the working data difference of each sub-unit block is greater than the preset difference; If it is not greater than, the actual working data of the sub-unit block will not be regulated; If it is greater than, the actual working data of the corresponding sub-unit block is adjusted based on the working data difference.

Images