A method for producing insect oil at low temperature

By monitoring and optimizing the stirring temperature and rate in real time during insect oil extraction, and using deep neural network and factor decomposition algorithms, the problem of low efficiency of insect oil extraction is solved, and a low energy consumption and efficient production process is achieved.

CN118185698BActive Publication Date: 2024-11-19QINGDAO SINO CROWN BIOLOGICAL ENG CO
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410468988.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-18
Publication Date
2024-11-19
Estimated Expiration
2044-04-18

AI Technical Summary

Technical Problem

The existing insect oil extraction methods consume a lot of time and energy, have low production efficiency, resulting in high production costs and are difficult to widely use.

Method used

The method of producing insect oil at low temperature is adopted. By extracting insect slurry from energy insects and mixing and stirring, the stirring temperature and rate are monitored in real time with sensors, and coordinated control is carried out through algorithms based on deep neural networks and factor decomposition machines. Optimize stirring conditions to improve extraction efficiency.

Benefits of technology

Real-time monitoring and optimization of the stirring process is realized, energy consumption is reduced, insect oil extraction efficiency is improved, and the production process is promoted.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118185698B_ABST
    Figure CN118185698B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a method for producing insect oil at low temperature. The method comprises: extracting insect pulp from energy insects, and mixing and stirring the insect pulp with a fat extractant to obtain a mixture, wherein the fat extractant is a reaction solution of a cationic surfactant and sulfuric acid, and the cationic surfactant is one or more of an amine salt, a quaternary ammonium salt, a heterocycle, and a pyrochloric acid salt; separating the mixture into a liquid to obtain an extractant-fat mixed liquid; washing and separating the extractant-fat mixed liquid to obtain insect oil. In this way, the stirring conditions can be monitored and controlled in real time, the mixing and stirring process is optimized, and it is helpful to promote the intelligentization of the insect oil production process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of insect oil, and in particular, to a method for producing insect oil at low temperature. Background Art

[0002] Insect oil is a biological resource with potential commercial value and can be widely used in medicine, cosmetics, bioenergy and other fields. At present, the methods for extracting insect oil mainly include Soxhlet extraction, microwave-assisted solvent extraction, ultrasound-assisted solvent extraction, mechanical extrusion, and solvent extraction hot immersion. These methods require a lot of time and energy to extract insect oil, resulting in low production efficiency. At the same time, a lot of manpower is required, which makes the production cost high and difficult to be widely used. Although Soxhlet extraction is widely used, it has a long working time and is more suitable for the extraction of small amounts of oil in the laboratory.

[0003] Therefore, an optimized low-temperature production scheme for insect oil is desired. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a method for producing insect oil at low temperature, the method comprising:

[0006] Extracting insect pulp from energy insects, and mixing the insect pulp with a fat extractant to obtain a mixture, wherein the fat extractant is a reaction solution of a cationic surfactant and sulfuric acid, and the cationic surfactant is one or more of an amine salt, a quaternary ammonium salt, a heterocyclic ring, and a pyrochloric acid salt;

[0007] Separating the mixture into a liquid and a material to obtain an extractant-oil mixture;

[0008] The extractant-oil mixture is washed and separated to obtain insect oil.

[0009] Optionally, extracting insect pulp from energy insects, and mixing the insect pulp with an oil extractant to obtain a mixture, comprising: obtaining a time series of stirring temperature and a time series of stirring rate collected by a sensor group; arranging the time series of stirring temperature and the time series of stirring rate into a stirring temperature timing input vector and a stirring rate timing input vector according to a time dimension; performing nonlinear response correction on the stirring temperature timing input vector and the stirring rate timing input vector to obtain an optimized stirring temperature timing input vector and an optimized stirring rate timing input vector; and extracting the mixture by a time series pattern feature extractor based on a deep neural network. Feature extraction is performed on the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector respectively to obtain a stirring temperature timing associated feature vector and a stirring rate timing associated feature vector; a feature collaborative analysis module based on a factor decomposition machine is used to perform feature collaborative association analysis on the stirring temperature timing associated feature vector and the stirring rate timing associated feature vector to obtain a stirring temperature-stirring speed collaborative timing characterization feature vector as a stirring temperature-stirring speed collaborative timing characterization feature; based on the stirring temperature-stirring speed collaborative timing characterization feature, it is determined whether the stirring rate at the current time point should be increased, decreased or kept unchanged.

[0010] Optionally, the stirring temperature timing input vector and the stirring rate timing input vector are subjected to nonlinear response correction to obtain an optimized stirring temperature timing input vector and an optimized stirring rate timing input vector, comprising: processing the stirring temperature timing input vector and the stirring rate timing input vector respectively through a nonlinear response correction module using the following nonlinear response correction formula to obtain the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector; wherein the nonlinear response correction formula is:

[0011] ;

[0012] in, is the characteristic value of the th position of one of the time series input vectors of the stirring temperature time series input vector and the stirring rate time series input vector, A , B , C and D To tune the hyperparameters, is the first of the corresponding corrected timing input vectors in the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector. The feature value at each position.

[0013] Optionally, the deep neural network-based temporal pattern feature extractor is a one-dimensional convolutional layer-based temporal pattern feature extractor.

[0014] Optionally, using a feature collaborative analysis module based on a factor decomposition machine to perform feature collaborative association analysis on the stirring temperature timing association feature vector and the stirring rate timing association feature vector to obtain a stirring temperature-stirring speed collaborative timing characterization feature vector as a stirring temperature-stirring speed collaborative timing characterization feature, including: using the feature collaborative analysis module based on a factor decomposition machine to perform feature collaborative association analysis on the stirring temperature timing association feature vector and the stirring rate timing association feature vector using the following feature collaborative analysis formula to obtain the stirring temperature-stirring speed collaborative timing characterization feature vector; wherein the feature collaborative analysis formula is:

[0015] ;

[0016] in, and are the characteristic values ​​of each position in the stirring temperature time series associated characteristic vector and the stirring rate time series associated characteristic vector, represents a constant bias, is the bias vector, is the bias matrix, is the number of eigenvalues ​​in the stirring temperature time series associated eigenvector, is the number of eigenvalues ​​in the stirring rate time series associated eigenvector, It is the characteristic value of each position in the characteristic vector that characterizes the coordinated timing of stirring temperature and stirring speed.

[0017] Optionally, based on the stirring temperature-stirring speed coordinated timing characterization feature, determining whether the stirring rate at the current time point should increase, decrease or remain unchanged includes: passing the stirring temperature-stirring speed coordinated timing characterization feature vector through a classifier-based stirring rate controller to obtain a control instruction, wherein the control instruction is used to indicate that the stirring rate at the current time point should increase, decrease or remain unchanged.

[0018] Optionally, it also includes a training step: for training the nonlinear response correction module, the temporal pattern feature extractor based on the one-dimensional convolutional layer, the feature collaborative analysis module based on the factor decomposition machine and the stirring rate controller based on the classifier.

[0019] Optionally, the training step includes: acquiring a time series of a training stirring temperature and a time series of a training stirring rate collected by the sensor group; arranging the time series of the training stirring temperature and the time series of the training stirring rate into a training stirring temperature timing input vector and a training stirring rate timing input vector according to the time dimension; performing nonlinear response correction on the training stirring temperature timing input vector and the training stirring rate timing input vector to obtain a training optimized stirring temperature timing input vector and a training optimized stirring rate timing input vector; performing feature extraction on the training optimized stirring temperature timing input vector and the training optimized stirring rate timing input vector respectively through the timing pattern feature extractor based on the deep neural network to obtain a training stirring temperature timing association feature vector and a training stirring rate timing input vector. rate-time-related feature vector; use the feature synergy analysis module based on the factor decomposition machine to perform feature synergy association analysis on the training stirring temperature timing-related feature vector and the training stirring rate timing-related feature vector to obtain a training stirring temperature-stirring speed synergy timing characterization feature vector; pass the training stirring temperature-stirring speed synergy timing characterization feature vector through the stirring rate controller based on the classifier to obtain a classification loss function value; based on the classification loss function value, train the nonlinear response correction module, the timing pattern feature extractor based on the one-dimensional convolutional layer, the feature synergy analysis module based on the factor decomposition machine and the stirring rate controller based on the classifier, and optimize the training stirring temperature-stirring speed synergy timing characterization feature vector in each iteration.

[0020] The above technical scheme is adopted to extract insect pulp from energy insects, and mix the insect pulp with a fat extractant to obtain a mixture, wherein the fat extractant is a reaction solution of a cationic surfactant and sulfuric acid, and the cationic surfactant is one or more of an amine salt, a quaternary ammonium salt, a heterocycle and a pyrochloric acid salt; the mixture is subjected to material-liquid separation to obtain an extractant-fat mixed liquid; the extractant-fat mixed liquid is washed and separated to obtain insect oil. In this way, the stirring conditions can be monitored and controlled in real time, the mixing and stirring process is optimized, and it is helpful to promote the intelligentization of the insect oil production process.

[0021] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0023] Figure 1 The present invention is a flow chart showing a method for producing insect oil at low temperature according to an exemplary embodiment.

[0024] Figure 2 is based on Figure 1 The illustrated embodiment shows a flow chart of step 101 of a method for producing insect oil at low temperature.

[0025] Figure 3 The invention is a block diagram of a system for producing insect oil at low temperature according to an exemplary embodiment.

[0026] Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment.

[0027] Figure 5 It is an application scenario diagram of a method for producing insect oil at low temperature according to an exemplary embodiment. DETAILED DESCRIPTION

[0028] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0029] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0030] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0031] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0033] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0034] Insect oil, as an emerging biological resource, is attracting more and more attention due to its unique composition and wide application potential. This resource mainly comes from the oil stored in insects, such as the wax gland secretions of lepidoptera insects, and the fat in termites and beetles. Insect oil not only contains rich bioactive ingredients such as fatty acids, glycerides, sterols, vitamins and minerals, but also has the characteristics of biodegradability and environmental friendliness, which makes it show great commercial value and application prospects in many industries.

[0035] In the medical field, the various bioactive ingredients in insect oils have a variety of pharmacological effects such as anti-inflammatory, antioxidant, antibacterial and antiviral. For example, specific fatty acids in some insect oils have been found to have positive effects on treating skin diseases and promoting wound healing. In addition, sterols in insect oils are also used to lower cholesterol and maintain cardiovascular health.

[0036] In the cosmetics industry, the unique composition of insect oil makes it a highly effective natural additive. Its good antioxidant properties help maintain product stability, while its rich fatty acids and vitamins can moisturize the skin and improve skin texture. In addition, the natural origin of insect oil also meets the current consumer demand for environmental protection and sustainable development.

[0037] In the field of bioenergy, insect oil, as a renewable resource, can be converted into biodiesel or other forms of biofuels. After proper conversion, the fatty acid components in insect oil can be used as a clean energy to replace petroleum diesel, reduce dependence on fossil fuels, and reduce environmental pollution.

[0038] The extraction technology of insect oil is an important part of the insect industry. It can effectively extract oils with high nutritional value from insects. These oils not only contain rich unsaturated fatty acids, but also contain a variety of biologically active substances that are beneficial to the human body. At present, there are various methods for extracting insect oil, mainly including the following:

[0039] 1. Soxhlet extraction: This is a traditional organic solvent extraction method, which uses solvents to soak and heat insect raw materials to dissolve oil in the solvent, and then evaporates the solvent to obtain insect oil. The advantages of this method are simple equipment and easy operation, but the extraction efficiency is low, the solvent consumption is large, and it has a certain impact on the environment.

[0040] 2. Microwave-assisted solvent extraction: This method uses the characteristics of microwave heating to quickly and evenly transfer heat to the interior of the insect raw material, thereby accelerating the contact and mixing of the solvent and oil and improving the extraction efficiency. The advantages of microwave-assisted extraction are fast extraction speed and low energy consumption, but the equipment cost is relatively high.

[0041] 3. Ultrasonic-assisted solvent extraction: The cavitation effect of ultrasound can destroy the cell structure of the insect raw material, making the oil easier to be extracted by the solvent. This method has the advantages of high extraction efficiency, low energy consumption, and environmental friendliness, but the intensity and action time of ultrasound need to be precisely controlled to avoid damage to the oil components.

[0042] 4. Mechanical extrusion method: This is a physical extraction method that squeezes the oil out of the insect body through mechanical pressure. This method does not require the use of chemical solvents and is environmentally friendly, but the extraction efficiency and oil purity may not be as good as the chemical extraction method.

[0043] 5. Solvent extraction hot soaking method: This is an extraction method that combines solvent extraction and heating. By controlling the appropriate temperature and pressure, the solvent's ability to dissolve oil can be increased, thereby improving the extraction efficiency. The advantage of this method is that it can extract oils with higher purity, but it has higher requirements for equipment.

[0044] However, these methods require a lot of time and energy to extract insect oil, resulting in low production efficiency. At the same time, they also require a lot of manpower, which makes the production cost high and difficult to be widely used. Although Soxhlet extraction is widely used, it takes a long time to work and is more suitable for extracting small amounts of oil in the laboratory.

[0045] In order to solve the above problems, the present disclosure provides a method for producing insect oil at low temperature, by extracting insect pulp from energy insects, and mixing the insect pulp with a fat extractant to obtain a mixture, wherein the fat extractant is a reaction solution of a cationic surfactant and sulfuric acid, and the cationic surfactant is one or more of an amine salt, a quaternary ammonium salt, a heterocycle and a pyrochloric acid salt; the mixture is subjected to material-liquid separation to obtain an extractant-fat mixed solution; the extractant-fat mixed solution is washed and separated to obtain insect oil. In this way, the stirring conditions can be monitored and controlled in real time, the mixing and stirring process is optimized, and it is helpful to promote the intelligentization of the insect oil production process.

[0046] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0047] In view of the above technical problems, in the technical solution of this application, a method for producing insect oil at low temperature is proposed. Figure 1 is a flow chart of a method for producing insect oil at low temperature according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0048] Step 101, extracting insect pulp from energy insects, and mixing the insect pulp with a fat extractant to obtain a mixture, wherein the fat extractant is a reaction solution of a cationic surfactant and sulfuric acid, and the cationic surfactant is one or more of an amine salt, a quaternary ammonium salt, a heterocyclic ring, and a pyrochloric acid salt;

[0049] Step 102, separating the mixture into a material and a liquid to obtain an extractant-oil mixture;

[0050] Step 103: washing and separating the extractant-oil mixture to obtain insect oil.

[0051] Accordingly, in the above-mentioned method for producing insect oil at low temperature, in the process of extracting insect pulp from energy insects and mixing and stirring the insect pulp with a fat extractant to obtain a mixture, it is very important to coordinate the control between the stirring temperature and the stirring rate. Appropriate stirring temperature and rate can promote the full mixing and reaction of the insect pulp and the fat extractant, which is beneficial to the release and extraction of fats and obtains a uniform mixture. In addition, reasonable control of the stirring temperature can reduce energy consumption while ensuring the reaction rate, thereby achieving energy conservation and optimization of benefits.

[0052] Based on this, the technical concept of the present application is to monitor and collect the stirring temperature and stirring rate in real time through the sensor group during the mixing and stirring process, and introduce artificial intelligence-based data processing and analysis algorithms at the back end to perform time-series coordinated correlation analysis of the stirring temperature and stirring rate, so as to perform coordinated control between the stirring temperature and stirring rate. In this way, the stirring conditions can be monitored and controlled in real time, the mixing and stirring process is optimized, and it is helpful to promote the intelligent production process of insect oil.

[0053] In one embodiment of the present disclosure, Figure 2 is based on Figure 1 The embodiment shown is a flow chart of step 101 of a method for producing insect oil at low temperature. Figure 2 As shown, step 101, extracting insect pulp from energy insects, and mixing the insect pulp with a fat extractant to obtain a mixture, comprises:

[0054] Step 1011, obtaining the time series of the stirring temperature and the time series of the stirring rate collected by the sensor group;

[0055] Step 1012, arranging the time series of the stirring temperature and the time series of the stirring rate into a stirring temperature time series input vector and a stirring rate time series input vector respectively according to the time dimension;

[0056] Step 1013, performing nonlinear response correction on the stirring temperature timing input vector and the stirring rate timing input vector to obtain an optimized stirring temperature timing input vector and an optimized stirring rate timing input vector;

[0057] Step 1014: extracting features of the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector respectively by using a timing pattern feature extractor based on a deep neural network to obtain a stirring temperature timing associated feature vector and a stirring rate timing associated feature vector;

[0058] Step 1015: Use a feature collaborative analysis module based on a factor decomposition machine to perform feature collaborative association analysis on the stirring temperature time series association feature vector and the stirring rate time series association feature vector to obtain a stirring temperature-stirring rate collaborative time series characterization feature vector as a stirring temperature-stirring rate collaborative time series characterization feature;

[0059] Step 1016: Based on the stirring temperature-stirring speed coordinated timing characterization feature, determine whether the stirring rate at the current time point should be increased, decreased, or kept unchanged.

[0060] Specifically, in the technical solution of the present application, first, the time series of the stirring temperature and the time series of the stirring rate collected by the sensor group are obtained. Next, considering that the stirring temperature and the stirring rate both have a dynamic change law of the time series in the time dimension, that is, the time series of the stirring temperature and the time series of the stirring rate both have a correlation relationship of the time series. Based on this, in the technical solution of the present application, it is necessary to arrange the time series of the stirring temperature and the time series of the stirring rate into a stirring temperature time series input vector and a stirring rate time series input vector according to the time dimension, respectively, so as to retain the time information in the time series of the stirring temperature and the stirring rate, so that the time correlation and change trend in the data of the stirring temperature and the rate can be better understood later.

[0061] Then, considering that the responses of stirring temperature and stirring rate in the time dimension are often nonlinear, in order to better simulate and adjust the impact of the timing changes of stirring conditions on the production process, and provide a data basis for the subsequent stirring condition timing characteristic analysis and stirring condition optimization, in the technical solution of the present application, the stirring temperature timing input vector and the stirring rate timing input vector are further corrected by a nonlinear response correction module to obtain an optimized stirring temperature timing input vector and an optimized stirring rate timing input vector.

[0062] In one embodiment of the present disclosure, the stirring temperature timing input vector and the stirring rate timing input vector are subjected to nonlinear response correction to obtain an optimized stirring temperature timing input vector and an optimized stirring rate timing input vector, comprising: respectively processing the stirring temperature timing input vector and the stirring rate timing input vector through a nonlinear response correction module using the following nonlinear response correction formula to obtain the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector; wherein the nonlinear response correction formula is:

[0063] ;

[0064] in, is the characteristic value of the th position of one of the time series input vectors of the stirring temperature time series input vector and the stirring rate time series input vector, A , B , C and D To tune the hyperparameters, is the first of the corresponding corrected timing input vectors in the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector. The feature value at each position.

[0065] Furthermore, in order to extract key timing features from the timing data of stirring temperature and stirring rate, so as to better understand and utilize the timing patterns and changing laws of data parameters in the stirring process to optimize the mixing and stirring process, in the technical solution of the present application, it is necessary to perform feature mining on the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector in a timing pattern feature extractor based on a one-dimensional convolutional layer, so as to respectively extract the timing-related feature information of the stirring temperature and the stirring rate in the time dimension, thereby obtaining the stirring temperature timing-related feature vector and the stirring rate timing-related feature vector.

[0066] In one embodiment of the present disclosure, the temporal pattern feature extractor based on a deep neural network is a temporal pattern feature extractor based on a one-dimensional convolutional layer.

[0067] It should be understood that since the stirring temperature time series associated feature vector and the stirring rate time series associated feature vector respectively contain the time series feature information about different stirring parameters in the mixing process in the time dimension, and since there is an implicit correlation relationship between the stirring temperature and the stirring rate, this relationship is crucial for the process optimization control of mixing. Specifically, the coordinated optimization control of the stirring temperature and rate can promote the full mixing and reaction of the insect paste and the oil extractant, which is beneficial to the release and extraction of oil and obtain a uniform mixture. In addition, reasonable control of the stirring temperature can reduce energy consumption while ensuring the reaction rate, thereby achieving energy conservation and optimization of benefits. Based on this, in order to explore the complex correlation between the stirring temperature and the stirring rate, so as to better understand the interaction and influence between the two, in the technical solution of the present application, a feature collaborative analysis module based on a factor decomposition machine is further used to perform feature collaborative association analysis on the stirring temperature time series associated feature vector and the stirring rate time series associated feature vector to obtain a stirring temperature-stirring speed collaborative time series characterization feature vector. In particular, the feature collaborative analysis module based on the factor decomposition machine can effectively capture the nonlinear correlation between the stirring temperature time series characteristics and the stirring rate time series characteristics, and find out the potential interaction patterns and characteristics between the two, thereby improving the model's understanding of the complex relationship between the two and the modeling accuracy, and achieving better optimization and control of the stirring process.

[0068] In one embodiment of the present disclosure, a feature collaborative analysis module based on a factor decomposition machine is used to perform feature collaborative association analysis on the stirring temperature time series association feature vector and the stirring rate time series association feature vector to obtain a stirring temperature-stirring speed collaborative time series characterization feature vector as a stirring temperature-stirring speed collaborative time series characterization feature, including: using the feature collaborative analysis module based on a factor decomposition machine to perform feature collaborative association analysis on the stirring temperature time series association feature vector and the stirring rate time series association feature vector using the following feature collaborative analysis formula to obtain the stirring temperature-stirring speed collaborative time series characterization feature vector; wherein the feature collaborative analysis formula is:

[0069] ;

[0070] in, and are the characteristic values ​​of each position in the stirring temperature time series associated characteristic vector and the stirring rate time series associated characteristic vector, represents a constant bias, is the bias vector, is the bias matrix, is the number of eigenvalues ​​in the stirring temperature time series associated eigenvector, is the number of eigenvalues ​​in the stirring rate time series associated eigenvector, It is the characteristic value of each position in the characteristic vector that characterizes the coordinated timing of stirring temperature and stirring speed.

[0071] Furthermore, the stirring temperature-stirring speed coordinated time series characterization feature vector is passed through a stirring rate controller based on a classifier to obtain a control instruction, and the control instruction is used to indicate whether the stirring rate at the current time point should increase, decrease, or remain unchanged. In other words, the time series coordinated correlation characterization features of the stirring temperature and the stirring speed are used for classification processing, so as to perform coordinated control between the stirring temperature and the stirring rate, thereby obtaining a control instruction for indicating that the stirring rate at the current time point should increase, decrease, or remain unchanged. In this way, the stirring conditions can be monitored and controlled in real time, the mixing and stirring process is optimized, and it is helpful to promote the intelligentization of the insect oil production process.

[0072] In one embodiment of the present disclosure, based on the stirring temperature-stirring speed coordinated timing characterization feature, it is determined whether the stirring rate at the current time point should increase, decrease or remain unchanged, including: passing the stirring temperature-stirring speed coordinated timing characterization feature vector through a classifier-based stirring rate controller to obtain a control instruction, wherein the control instruction is used to indicate that the stirring rate at the current time point should increase, decrease or remain unchanged.

[0073] Furthermore, in one embodiment of the present disclosure, the method for producing insect oil at low temperature also includes a training step: for training the nonlinear response correction module, the one-dimensional convolutional layer-based temporal pattern feature extractor, the factor decomposition machine-based feature collaborative analysis module, and the classifier-based stirring rate controller. The training step includes: acquiring the time series of the training stirring temperature and the time series of the training stirring rate collected by the sensor group; arranging the time series of the training stirring temperature and the time series of the training stirring rate into a training stirring temperature temporal input vector and a training stirring rate temporal input vector according to the time dimension respectively; performing nonlinear response correction on the training stirring temperature temporal input vector and the training stirring rate temporal input vector to obtain a training optimized stirring temperature temporal input vector and a training optimized stirring rate temporal input vector; performing feature extraction on the training optimized stirring temperature temporal input vector and the training optimized stirring rate temporal input vector respectively through the temporal pattern feature extractor based on a deep neural network to obtain a training stirring temperature temporal correlation feature vector and a training stirring rate temporal correlation feature vector. The invention discloses a method for preparing a time series correlation feature vector; performing a feature synergistic analysis on the training stirring temperature time series correlation feature vector and the training stirring rate time series correlation feature vector using the feature synergistic analysis module based on the factor decomposition machine to obtain a training stirring temperature-stirring speed synergistic time series characterization feature vector; passing the training stirring temperature-stirring speed synergistic time series characterization feature vector through the stirring rate controller based on the classifier to obtain a classification loss function value; training the nonlinear response correction module, the time series pattern feature extractor based on the one-dimensional convolutional layer, the feature synergistic analysis module based on the factor decomposition machine and the stirring rate controller based on the classifier based on the classification loss function value, and optimizing the training stirring temperature-stirring speed synergistic time series characterization feature vector in each iteration.

[0074] In the technical solution described above, the training stirring temperature time series association feature vector and the training stirring rate time series association feature vector respectively express the time series association features of the training stirring temperature and the training stirring rate. In this way, considering the source time series distribution misalignment of the training stirring temperature and the training stirring rate and the nonlinear response correction to strengthen the main trend of the time series distribution by correcting the local nonlinear response, the training stirring temperature-stirring speed collaborative time series characterization feature vector calculated by the feature collaborative analysis based on the factor decomposition machine will also have the local distribution non-uniformity based on the eigenvalue granularity due to the difference in the alignment of the eigenvalue distribution corresponding to the training stirring temperature time series association feature vector and the training stirring rate time series association feature vector. That is, the training stirring temperature-stirring speed collaborative time series characterization feature vector has the illusion of local distribution non-uniformity class mapping, thereby affecting the convergence effect of the training stirring temperature-stirring speed collaborative time series characterization feature vector to the class probability density space when classified by the classifier.

[0075] Therefore, the applicant of the present application optimizes the training stirring temperature-stirring speed collaborative timing characterization feature vector each time the training stirring temperature-stirring speed collaborative timing characterization feature vector is classified and iterated by the classifier, which is expressed as follows: the training stirring temperature-stirring speed collaborative timing characterization feature vector is optimized by the following optimization formula to obtain the optimized training stirring temperature-stirring speed collaborative timing characterization feature vector; wherein the optimization formula is:

[0076] ;

[0077] in, and They are the training stirring temperature-stirring speed coordinated time series characterization feature vectors No. and The eigenvalues ​​of the positions, is the training stirring temperature-stirring speed coordinated time series characterization feature vector, is the optimized training stirring temperature-stirring speed coordinated time series characterization feature vector, represents positional addition, Represents matrix multiplication.

[0078] That is, by introducing the training stirring temperature-stirring speed coordinated time series characterization feature vector The local statistical information distribution is used as an external information source to enhance the retrieval of the feature vector, so as to avoid the local overflow information distribution based on the local statistical dense information structure, resulting in the training stirring temperature-stirring speed collaborative time series characterization feature vector The non-uniform feature distribution class mapping illusion is obtained to obtain the training stirring temperature-stirring speed coordinated time series characterization feature vector Information credible response reasoning based on local distribution group dimension preservation, that is, obtaining the training stirring temperature-stirring speed coordinated time series characterization feature vector Based on the credible distribution response in the probability density space of the non-uniform local feature distribution, the convergence effect of the class probability density space is improved to improve the training speed and the accuracy of the training results. In this way, the stirring conditions can be monitored and controlled in real time based on the temporal synergistic correlation between the stirring temperature and the stirring speed, which realizes the optimization of the mixing and stirring process and helps to promote the intelligent production process of insect oil.

[0079] In summary, the above scheme is adopted to monitor and collect the stirring temperature and stirring rate in real time through the sensor group during the mixing and stirring process, and introduce artificial intelligence-based data processing and analysis algorithms at the back end to perform time-series coordinated correlation analysis of the stirring temperature and stirring rate, so as to perform coordinated control between the stirring temperature and stirring rate. In this way, the stirring conditions can be monitored and controlled in real time, the mixing and stirring process is optimized, and it is helpful to promote the intelligent production process of insect oil.

[0080] Figure 3 FIG. 1 is a block diagram of a system for producing insect oil at low temperature according to an exemplary embodiment. Figure 3 As shown, the system 200 includes:

[0081] A mixing and stirring module 201 is used to extract insect pulp from energy insects, and mix and stir the insect pulp with a fat extractant to obtain a mixture, wherein the fat extractant is a reaction solution of a cationic surfactant and sulfuric acid, and the cationic surfactant is one or more of an amine salt, a quaternary ammonium salt, a heterocyclic ring, and a pyrochloric acid salt;

[0082] A feed-liquid separation module 202 is used to separate the mixture into a feed-liquid mixture to obtain an extractant-oil mixture;

[0083] The washing and separation processing module 203 is used to wash and separate the extractant-oil mixture to obtain insect oil.

[0084] Reference below Figure 4, which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0085] like Figure 4 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0086] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0087] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0088] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0089] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0090] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0091] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0092] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0093] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a test parameter acquisition module may also be described as a "module for acquiring device test parameters corresponding to a target device".

[0094] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0095] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0096] Figure 5 FIG. 1 is an application scenario diagram of a method for producing insect oil at low temperature according to an exemplary embodiment. Figure 5 As shown, in this application scenario, first, the time series of the stirring temperature collected by the sensor group is obtained (for example, Figure 5 C1) and the time series of stirring rate (e.g., Figure 5 Then, the obtained time series of stirring temperature and stirring rate are input to a server (for example, Figure 5 In S) shown in , the server is capable of processing the time series of the stirring temperature and the time series of the stirring rate based on the low-temperature production of insect oil algorithm to determine whether the stirring rate at the current time point should be increased, decreased or kept unchanged.

[0097] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0098] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0099] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A method for producing insect oil at low temperature, characterized in that: include: Extracting insect pulp from energy insects, and mixing the insect pulp with a fat extractant to obtain a mixture, wherein the fat extractant is a reaction solution of a cationic surfactant and sulfuric acid, and the cationic surfactant is one or more of an amine salt, a quaternary ammonium salt, a heterocyclic ring, and a pyrochloric acid salt; Separating the mixture into a liquid and a material to obtain an extractant-oil mixture; The extractant-oil mixture is washed and separated to obtain insect oil; Extracting insect pulp from energy insects, and mixing the insect pulp with a fat extractant to obtain a mixture, comprising: Acquire a time series of stirring temperature and a time series of stirring rate collected by the sensor group; Arrange the time series of the stirring temperature and the time series of the stirring rate into a stirring temperature timing input vector and a stirring rate timing input vector respectively according to the time dimension; Performing nonlinear response correction on the stirring temperature timing input vector and the stirring rate timing input vector to obtain an optimized stirring temperature timing input vector and an optimized stirring rate timing input vector; The optimized stirring temperature timing input vector and the optimized stirring rate timing input vector are respectively subjected to feature extraction by a timing pattern feature extractor based on a deep neural network to obtain a stirring temperature timing associated feature vector and a stirring rate timing associated feature vector; the timing pattern feature extractor based on a deep neural network is a timing pattern feature extractor based on a one-dimensional convolutional layer; Using a feature collaborative analysis module based on a factor decomposition machine to perform feature collaborative association analysis on the stirring temperature time series association feature vector and the stirring rate time series association feature vector to obtain a stirring temperature-stirring rate collaborative time series characterization feature vector as a stirring temperature-stirring rate collaborative time series characterization feature; Based on the stirring temperature-stirring speed coordinated time series characterization feature, determining whether the stirring rate at the current time point should be increased, decreased, or kept unchanged, comprising: passing the stirring temperature-stirring speed coordinated time series characterization feature vector through a stirring rate controller based on a classifier to obtain a control instruction, wherein the control instruction is used to indicate that the stirring rate at the current time point should be increased, decreased, or kept unchanged; The stirring temperature timing input vector and the stirring rate timing input vector are processed by a nonlinear response correction module using a nonlinear response correction formula to obtain the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector; The method further comprises a training step for training a nonlinear response correction module, a temporal pattern feature extractor based on a one-dimensional convolutional layer, a feature synergy analysis module based on a factorization machine, and a stirring rate controller based on a classifier; The training step comprises: Acquire a time series of a training stirring temperature and a time series of a training stirring rate collected by a sensor group; Arranging the time series of the training stirring temperature and the time series of the training stirring rate into a training stirring temperature timing input vector and a training stirring rate timing input vector respectively according to the time dimension; Performing nonlinear response correction on the training stirring temperature timing input vector and the training stirring rate timing input vector to obtain a training optimized stirring temperature timing input vector and a training optimized stirring rate timing input vector; The training optimized stirring temperature timing input vector and the training optimized stirring rate timing input vector are respectively subjected to feature extraction by the timing pattern feature extractor based on the deep neural network to obtain a training stirring temperature timing associated feature vector and a training stirring rate timing associated feature vector; Using the feature synergy analysis module based on the factor decomposition machine to perform feature synergy association analysis on the training stirring temperature time series association feature vector and the training stirring rate time series association feature vector to obtain a training stirring temperature-stirring rate synergy time series characterization feature vector; Passing the training stirring temperature-stirring speed coordinated time series characterization feature vector through the classifier-based stirring rate controller to obtain a classification loss function value; The nonlinear response correction module, the one-dimensional convolutional layer-based temporal pattern feature extractor, the factor decomposition machine-based feature synergy analysis module, and the classifier-based stirring rate controller are trained based on the classification loss function value, and in each iteration, the training stirring temperature-stirring speed synergy timing characterization feature vector is optimized; Each time the training stirring temperature-stirring speed coordinated timing characterization feature vector is classified and iterated by the classifier, the training stirring temperature-stirring speed coordinated timing characterization feature vector is optimized, which is expressed as follows: the training stirring temperature-stirring speed coordinated timing characterization feature vector is optimized by the following optimization formula to obtain the optimized training stirring temperature-stirring speed coordinated timing characterization feature vector; wherein the optimization formula is: ; in, and They are the training stirring temperature-stirring speed coordinated time series characterization feature vectors No. and The eigenvalues ​​of the positions, is the training stirring temperature-stirring speed coordinated time series characterization feature vector, is the optimized training stirring temperature-stirring speed coordinated time series characterization feature vector, represents positional addition, Represents matrix multiplication.

2. The method for producing insect oil at low temperature according to claim 1, characterized in that: The stirring temperature timing input vector and the stirring rate timing input vector are subjected to nonlinear response correction to obtain an optimized stirring temperature timing input vector and an optimized stirring rate timing input vector, comprising: respectively processing the stirring temperature timing input vector and the stirring rate timing input vector through a nonlinear response correction module using the following nonlinear response correction formula to obtain the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector; Wherein, the nonlinear response correction formula is: ; in, is the characteristic value of the th position of one of the time series input vectors of the stirring temperature time series input vector and the stirring rate time series input vector, A , B , C and D To tune the hyperparameters, is the first of the corresponding corrected timing input vectors in the optimized stirring temperature timing input vector and the optimized stirring rate timing input vector. The feature value at each position.

3. The method for producing insect oil at low temperature according to claim 2, characterized in that: Using a feature collaborative analysis module based on a factor decomposition machine to perform feature collaborative association analysis on the stirring temperature time series association feature vector and the stirring rate time series association feature vector to obtain a stirring temperature-stirring speed collaborative time series characterization feature vector as a stirring temperature-stirring speed collaborative time series characterization feature, including: using the feature collaborative analysis module based on a factor decomposition machine to perform feature collaborative association analysis on the stirring temperature time series association feature vector and the stirring rate time series association feature vector using the following feature collaborative analysis formula to obtain the stirring temperature-stirring speed collaborative time series characterization feature vector; The feature collaborative analysis formula is: ; in, and are the characteristic values ​​of each position in the stirring temperature time series associated characteristic vector and the stirring rate time series associated characteristic vector, represents a constant bias, is the bias vector, is the bias matrix, is the number of eigenvalues ​​in the stirring temperature time series associated eigenvector, is the number of eigenvalues ​​in the stirring rate time series associated eigenvector, It is the characteristic value of each position in the characteristic vector that characterizes the coordinated timing of stirring temperature and stirring speed.