A method and device for mixing a feed for aquaculture

Abstract

The present application relates to the technical field of feed mixing and stirring, and particularly relates to a breeding feed mixing method and device. The device comprises a mixing control system. The mixing control system uses a historical feed mixing data analysis module to analyze mixing data generated by known historical mixing batches, and then constructs a mixing difficulty matrix of each historical batch cluster on the basis of the historical data. The initial stirring parameters can be obtained by determining the matching historical batch cluster. Then, the mixing difficulty sequence corresponding to the initial stirring parameters is determined by using the mixing difficulty matrix, and the stirring speed is controlled by using the mixing difficulty in the mixing difficulty sequence. The breeding feed is mixed by adjusting the stirring speed on the basis of the final stirring time. The present application reduces manual intervention and realizes the automatic and efficient mixing of the breeding feed within a fixed time by controlling the speed of the stirring roller.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of feed mixing and stirring, in particular to a breeding feed mixing method and device. BACKGROUND

[0002] In order to scientifically feed the breeding animals in the farm, various feed raw materials will be mixed and fed, for example, forage, expanded feed, nutritional supplements, etc. In order to realize the mixing of breeding feed, the feed mixing device will be used for mixing in the farm. The common feed mixing device contains intermeshing stirring rollers. Through the rotation of the stirring rollers, the feed mixing and crushing can be realized.

[0003] In the prior art, when the feed mixing device is used for mixing feed, the mixing and stirring are carried out by using the stirring speed and stirring time set by human beings. However, some stirring parameters are only suitable for the mixing batch of specific raw material ratio. If the stirring parameters are not suitable for the mixing batch of new raw material ratio, the stirring effect will be poor, the feed will not be fully mixed, the feed quality will be reduced, and the mixing efficiency will be affected. If the optimal stirring parameters are determined through more experiments for the mixing batch of new raw material ratio, the cost will be increased, and the optimal stirring parameters cannot be quickly and effectively determined. SUMMARY

[0004] In order to solve the technical problem that the prior art cannot quickly and effectively determine the optimal stirring parameters and control the stirring for the batch to be mixed when mixing the feed, thereby causing poor feed mixing effect, the purpose of the present application is to provide a breeding feed mixing method and device. The technical scheme adopted is as follows:

[0005] The present application provides a breeding feed mixing device, which comprises a mixing bin, a stirring roller, a discharge port, and a mixing control system. The mixing control system comprises:

[0006] A historical feed mixing data analysis module is used for dividing a plurality of historical batch clusters according to the distribution of raw materials in each historical mixing batch. In the historical batch cluster, the mixing quality scores of all historical mixing batches are arranged according to the stirring speed and stirring time of each historical mixing batch, and the mixing data feature matrix of the historical batch cluster is obtained. The growth trend of each element in the mixing data feature matrix in the stirring time dimension is obtained. According to the change of the growth trend of each element in the stirring speed dimension, the mixing difficulty corresponding to each element is obtained, and the mixing difficulty matrix is constituted.

[0007] An initial mixing parameter setting module is used for obtaining a matching historical batch cluster of the batch to be mixed. The stirring speed and stirring time of the matching historical batch cluster are counted, and the initial stirring speed and final stirring time of the batch to be mixed are obtained.

[0008] The rotation speed control module is configured to intercept a mixing difficulty sequence from a mixing difficulty matrix of matching historical batch clusters according to an initial stirring speed and a final stirring time; a time sequence range of the mixing difficulty sequence corresponds to the final stirring time; and during stirring, the initial stirring speed is updated according to a mixing difficulty corresponding to a stirring time in the mixing difficulty sequence.

[0009] The discharge control module is configured to stop stirring and control opening of a discharge port to output mixed feed in a mixing bin after the final stirring time is reached.

[0010] Further, the historical feed mixing data analysis module further comprises a historical data classification unit; the historical data classification unit is configured to obtain a feature similarity of material distribution characteristics between historical mixing batches, and perform clustering on the historical mixing batches based on the feature similarity by using a Kmeans clustering algorithm to obtain a plurality of historical batch clusters.

[0011] Further, the historical feed mixing data analysis module further comprises a material distribution characteristic extraction module, and the material distribution characteristic extraction module is configured to:

[0012] For each mixing batch, the particle volume of each material in the mixing batch and the content proportion in the mixing batch are obtained; the cutting probability of the material in the mixing batch is obtained according to the particle volume and the content proportion; the material combination characteristic curve of the mixing batch is constructed with the type number of the material as the horizontal axis and the cutting probability of the material as the vertical axis, and the material combination characteristic curve is taken as the material distribution characteristic.

[0013] Further, the mixing data characteristic matrix has a horizontal dimension of stirring time and a vertical dimension of stirring speed; and the specific acquisition method of the mixing data characteristic matrix comprises:

[0014] At the same stirring speed, the mixing quality scores are sorted from small to large according to the stirring time to obtain a first sequence of each stirring speed; and the first sequence is arranged vertically according to the stirring speed from large to small to obtain the mixing data characteristic matrix.

[0015] Further, the growth change trend acquisition method comprises:

[0016] An arbitrary element in the mixed data feature matrix is recorded as a target element, all elements corresponding to the target element in the stirring time dimension direction form a time series trend analysis sequence of the target element; an extreme difference of the time series trend analysis sequence is obtained; a mixing quality score difference between the target element and a subsequent element in the time series trend analysis sequence is obtained; and a product of the mixing quality score difference and the extreme difference is taken as the growth change trend of the target element.

[0017] Further, the mixed difficulty obtaining method comprises:

[0018] An arbitrary element in the mixed data feature matrix is recorded as a target element, and a neighborhood range of the target element is obtained according to a preset size from the target element as a starting point in the direction of increasing stirring speed; growth change trends of elements in the neighborhood range are sorted according to stirring speed from small to large to obtain a growth change trend sequence.

[0019] A difference sequence of the growth change trend sequence is obtained, and a cumulative sum of elements in the difference sequence is negatively correlated and normalized to obtain the mixed difficulty of the target element.

[0020] Further, the matching historical batch class cluster obtaining method comprises:

[0021] A raw material distribution feature similarity between a to-be-mixed batch and a class cluster center of each historical batch class cluster is taken as a matching degree, and the historical batch class cluster with the largest matching degree is taken as the matching historical batch class cluster.

[0022] Further, the initial stirring speed and the final stirring time of the to-be-mixed batch obtaining method comprises:

[0023] An average particle volume and an average density of all raw materials in the to-be-mixed batch are obtained, and a product of the average particle volume and the average density is taken as a raw material form feature of the to-be-mixed batch.

[0024] An average stirring speed of a historical mixed batch with a mixing quality score greater than a preset score threshold in the matching historical batch class cluster is taken as the initial stirring speed.

[0025] A ratio between a volume of a mixing bin and the raw material form feature is taken as a cutting effectiveness.

[0026] The final stirring time is obtained according to the initial stirring speed and the cutting effectiveness.

[0027] Further, the rotating speed control module comprises a stirring speed updating module, which is configured to obtain a speed adjustment coefficient according to the corresponding mixing difficulty and the matching degree of the matching historical batch cluster when the stirring process reaches the stirring time corresponding to each element in the mixing difficulty sequence, and update the initial stirring speed according to the speed adjustment coefficient.

[0028] The application provides a breeding feed mixing method, which mixes breeding feed of a batch to be mixed by using a breeding feed mixing device.

[0029] The application has the following beneficial effects:

[0030] The breeding feed mixing device comprises a mixing control system, which analyzes mixing data generated by historical mixing batches by using a historical feed mixing data analysis module, and further constructs a mixing difficulty matrix of each historical batch cluster on the basis of the historical data. The mixing difficulty can be effectively quantified by counting the change of the mixing quality score in the historical data in two dimensions of stirring speed and stirring time. For a batch to be mixed with a new raw material ratio, only the matching historical batch cluster needs to be determined to obtain the initial stirring parameters, and then the mixing difficulty sequence corresponding to the initial stirring parameters is determined by using the mixing difficulty matrix, and the stirring speed is controlled by using the mixing difficulty in the mixing difficulty sequence, so that effective mixing of the breeding feed is realized on the basis of the final stirring time by adjusting the stirring speed. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0032] Figure 1 A breeding feed mixing device provided by an embodiment of the present application is shown in the figure.

[0033] Figure 2 A structure block diagram of a mixing control system provided by an embodiment of the present application is shown in the figure.

[0034] The figure comprises: 1, a discharge port blocking door; 2, a stirring roller; 3, a mixing control system; 4, a discharge port; 5, a conveying belt; 101, a historical feed mixing data analysis module; 102, an initial mixing parameter setting module; 103, a rotating speed control module; 104, a discharge control module. DETAILED DESCRIPTION

[0035] In order to further clarify the technical means and effects taken by the present application to achieve the predetermined inventive objectives, the following describes in detail the specific implementation, structure, features and effects of a feed mixing method and device according to the present application, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0036] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0037] The present application provides a feed mixing device, which comprises a feed mixing device body, such as a mixing bin, a stirring roller, and a discharge port. On the basis of the feed mixing device body, a mixing control system is further included, which is used to control the stirring speed of the stirring roller and the discharge of the discharge port.

[0038] The specific scheme of the feed mixing method and device provided by the present application is described in detail below in combination with the accompanying drawings.

[0039] Please refer to Figure 1 which shows a schematic diagram of a feed mixing device according to one embodiment of the present application, Figure 1 The feed mixing device in comprises a discharge port blocking door 1, a stirring roller 2, a mixing control system 3, a discharge port 4, and a conveyor belt 5. Figure 1 When the feed mixing device in is used, after the information of the raw materials to be mixed is counted, the information is input to the mixing control system 2, and then the raw materials are put into the mixing bin. After the stirring program is started, the stirring roller 2 begins to rotate. Figure 1 The stirring roller 2 in is two stirring rollers that mesh with each other. Through the rotation of the stirring roller, the feed is mixed, and the large-particle feed such as forage is also crushed. During the stirring process, the conveyor belt 5 also begins to rotate, and the conveyor belt 5 rotates towards the direction of the discharge port 4. Meanwhile, the conveyor belt 5 is also equipped with air bags, which can increase the contact resistance with the feed during rotation. Under the blocking action of the air bags, the feed at the bottom of the mixing bin is driven to accumulate from the through hole to the side of the discharge port 4, so that the feed on the side of the discharge port is upwelled, and then continues to contact the stirring roller 2, forming a continuous stirring cycle. During the stirring process, the stirring speed is controlled by the mixing control system 3, and after the mixing time is reached, the stirring is stopped. The discharge port blocking door 1 at the position of the discharge port 4 is opened, and the mixed feed can be driven from the discharge port 4 by the inflated air bags under the conveying of the conveyor belt 5.

[0040] In one embodiment of the present application, a transparent rectangular observation window is further installed on the mixing bin for observing the mixing state of the feed inside the device.

[0041] It should be noted that in one embodiment of the present application, the data operation process in the mixing control system is mainly processed by the cloud server. The corresponding information is collected and transmitted to the cloud by using the material network technology. After the cloud performs data processing, the corresponding data is fed back to the mixing control system, and the mixing control system feeds back the corresponding control signal to each device.

[0042] Please refer to Figure 2 which shows a mixing control system structure block diagram provided in one embodiment of the present application. The system includes a mixing control system including a historical feed mixing data analysis module 101, an initial mixing parameter setting module 102, a rotating speed control module 103, and a discharge control module 104.

[0043] The historical feed mixing data analysis module 101 first divides a plurality of historical batch clusters according to the distribution of raw materials in each historical mixing batch. Because the historical mixing batch as historical data contains a plurality of mixing conditions, for a raw material ratio, a plurality of historical mixing batches can be included by different stirring speeds and different stirring times. For the batch to be mixed, only the historical mixing batch corresponding to the similar raw material ratio condition of itself can be used as reference information. Therefore, the historical mixing batch is first classified, and then analyzed for each historical batch cluster.

[0044] Because the historical mixing batch is a mixed process, it contains known stirring speed, stirring time, and mixing quality score. It should be noted that the mixing quality score is used to evaluate and quantify the mixing effect. Because the historical mixing batch is a process of stirring by using existing fixed stirring parameters, for each batch, there is a fixed stirring time and a constant stirring speed within the time.

[0045] It should be noted that the mixing quality score can be evaluated by artificial means. Because the mixing bin of the mixing device in the embodiment of the present application includes an observation window, the staff can observe the internal mixing state through the observation window. The score can be obtained by color, shape, fineness, and other dimensions. Finally, the mixing quality score is obtained by statistics. The specific scoring method is a technical means familiar to those skilled in the art, which is not described here.

[0046] In one embodiment of the present application, in order to more conveniently obtain the mixing information of the historical mixing batch, during the execution of the historical mixing batch, because it is a fixed stirring time under a fixed stirring speed, an observation interval can be set within the stirring time, that is, the scoring results corresponding to different stirring times under a stirring speed can be obtained in one mixing process.

[0047] In another embodiment of the present application, in order to obtain the mixing quality score of the historical mixing batch more conveniently, first, a decision tree is constructed based on the stirring mixing information of part of the historical mixing batch, and for other historical mixing batches, the mixing quality score corresponding to the historical mixing batch can be quickly determined by inputting the corresponding information into the decision tree model.

[0048] The historical feed mixing data analysis module 101 further calculates the stirring speed, stirring time and mixing quality score of each historical mixing batch in each historical batch cluster, takes the stirring speed and stirring time as the dimension information in the two-dimensional matrix, and takes the mixing quality score as the element in the matrix, and then obtains the mixing data feature matrix, i.e., the mixing data feature matrix is obtained by arranging the mixing quality scores of all historical mixing batches according to the stirring speed and stirring time of each historical mixing batch. Through the construction of the mixing data feature matrix, targeted analysis can be performed in the stirring speed and stirring time dimensions through the matrix, for example, fixing a stirring speed, i.e., finding any row or column in the matrix, and these elements constitute the change of the mixing quality score with the stirring time at the stirring speed. For an element in the matrix, it corresponds to a stirring speed and stirring time, and by analyzing the growth trend of the element in the stirring time dimension, the cutting efficiency of the element on the feed raw materials at the current speed and time can be obtained, i.e., the higher the cutting efficiency, the more significant the growth of the mixing quality score with the increase of time, and the greater the growth trend.

[0049] It should be noted that for the mixing and stirring process of the feed, because the increase of the stirring speed and the stirring time will further cut and mix the feed, therefore, with the increase of the stirring speed or the stirring time, the mixing quality score will only gradually increase or remain unchanged, and will not gradually decrease.

[0050] With the stirring, the particles of the raw materials themselves gradually become smaller after cutting, and the further cutting of the raw materials by the stirring roller will be more difficult, and the cutting efficiency will gradually decrease; if there is no obvious mixing quality score change trend in the stirring speed mode under this state, it means that the mixing difficulty of the raw materials under this state is high. Therefore, the historical feed mixing data analysis module 101 further obtains the mixing difficulty corresponding to each element according to the change of the growth trend of each element in the stirring speed dimension. Because each element can correspond to a mixing difficulty, the mixing difficulty matrix can be obtained by replacing the elements in the mixing data feature matrix with the mixing difficulty. That is, each element in the mixing difficulty matrix represents the mixing difficulty under the corresponding stirring speed and stirring time of the element.

[0051] Preferably, in one embodiment of the present application, the historical feed mixing data analysis module further comprises a historical data classification unit; the historical data classification unit is configured to obtain a feature similarity of the distribution characteristics of raw materials between historical mixing batches, and perform clustering on the historical mixing batches based on the feature similarity using a Kmeans clustering algorithm to obtain a plurality of historical batch clusters.

[0052] It should be noted that the Kmeans clustering algorithm is a known technical means to those skilled in the art, and the elbow method is used to obtain the optimal K value before clustering, and the specific algorithm is not described or limited herein.

[0053] Preferably, in one embodiment of the present application, the historical feed mixing data analysis module further comprises a raw material distribution characteristic extraction module, which is configured to:

[0054] For each mixing batch, the particle volume of each raw material in the mixing batch and the content ratio in the mixing batch are obtained. It should be noted that the particle volume can be directly obtained according to the type of raw material itself, or can be determined by multiple sampling detection; the content ratio can be directly obtained according to the raw material ratio in the batch to be mixed, and the specific method for obtaining the particle volume and the content ratio is a known technical means to those skilled in the art, which is not described or limited herein.

[0055] According to the particle volume and the content ratio, the cutting probability of the raw material in the mixing batch is obtained, that is, the larger the particle volume and the more the content ratio, the greater the probability that the raw material is cut in the cutting mixing process. The type number of the raw material is taken as the horizontal axis, and the cutting probability of the raw material is taken as the vertical axis to construct a raw material combination characteristic curve of the mixing batch, and the raw material combination characteristic curve is taken as the raw material distribution characteristic. That is, the cutting probability is used as the feature of the raw material in the mixing process in the mixing batch, and then the quantification of the raw material distribution is realized. It should be noted that the type of the raw material needs to be quantified during the construction of the raw material combination characteristic curve, and each raw material can be numbered by using the form of a label, and natural numbers are sequentially used as the labels of each raw material starting from 0, and then the quantification of the raw material type is realized.

[0056] In one embodiment of the present application, the product of the particle volume and the content ratio is taken as the cutting probability.

[0057] It should be noted that, because the raw material distribution characteristic in one embodiment of the present application is a curve, the dynamic time warping similarity between the raw material combination characteristic curves can be obtained by using the DTW algorithm during the clustering process, and then the clustering is obtained.

[0058] Preferably, in one embodiment of the present application, the horizontal dimension of the mixing data feature matrix is the stirring time, and the vertical dimension is the stirring speed; the specific method for obtaining the mixing data feature matrix comprises:

[0059] At the same stirring speed, the mixing quality scores are sorted from small to large according to the stirring time to obtain a first sequence of each stirring speed; the first sequences are arranged vertically according to the stirring speed from large to small to obtain a mixing data feature matrix. It should be noted that in some embodiments of the present application, the time sequence information corresponding to the same position in the first sequences may not be the same, for example, the information of 5 minutes, 8 minutes and 10 minutes is included at speed A, while the information of 4 minutes, 5 minutes, 7 minutes and 10 minutes is included at speed B, because the lengths of the first sequences at the two speeds are different, and the time sequence information between the elements of the same sequence number is also different, therefore, the first sequences need to be standardized, and the data in the first sequences without corresponding time sequence information is interpolated by an interpolation data processing method, so that the lengths of the first sequences are the same and the stirring time dimensions correspond.

[0060] Preferably, in an embodiment of the present application, the growth change trend acquisition method comprises:

[0061] Any element in the mixing data feature matrix is denoted as a target element, and all elements corresponding to the target element in the stirring time dimension direction form a time sequence trend analysis sequence of the target element.

[0062] It should be noted that in an embodiment of the present application, the horizontal dimension of the mixing data feature matrix is stirring time, and the vertical dimension is stirring speed. Therefore, the time sequence trend analysis sequence of the target element is a whole row in which the target element is located in the matrix. Similarly, if in other embodiments of the present application, the vertical dimension of the mixing data feature matrix is stirring time, and the horizontal dimension is stirring speed, then the time sequence trend analysis sequence is a whole column in which the target element is located in the matrix.

[0063] The range of the time sequence trend analysis sequence is obtained, which represents the change range of the mixing quality score in the whole stirring time dimension. The greater the corresponding range at the stirring speed where the target element is located, the more significant the change of the score with the change of the stirring time, and the more obvious the growth change trend.

[0064] The mixing quality score difference between the target element and the next element in the time sequence trend analysis sequence is obtained. The greater the mixing quality score difference, the greater the growth change trend at the position of the target element.

[0065] Therefore, the product of the mixing quality score difference and the range is taken as the growth change trend of the target element.

[0066] Preferably, in an embodiment of the present application, the mixing difficulty acquisition method comprises:

[0067] An arbitrary element in the mixed data feature matrix is denoted as a target element, and a neighborhood range of the target element is obtained according to a preset size from the target element in the direction of increasing stirring speed. In an embodiment of the present application, the preset size is 5, that is, 5 elements are found in the direction of increasing stirring speed from the target element to form the neighborhood range.

[0068] It should be noted that, in an embodiment of the present application, the longitudinal axis of the mixed data feature matrix is the stirring speed, that is, the direction of increasing stirring speed is the vertical upward direction of the matrix.

[0069] The growth change trend of the elements in the neighborhood range is sorted according to the stirring speed from small to large to obtain a growth change trend sequence. A difference sequence of the growth change trend sequence is obtained, and the elements in the difference sequence represent the growth change of the growth change trend sequence. The larger the element is, the more obvious the change of the growth change trend is, and the smaller the mixing difficulty of the current state of the target element is. Therefore, the elements in the difference sequence are negatively correlated and mapped and normalized to obtain the mixing difficulty of the target element.

[0070] In an embodiment of the present application, the elements in the difference sequence are negatively correlated and mapped by the form of reciprocal, and in order to avoid the denominator being 0, the reciprocal of the result obtained by adding a positive integer 1 to the elements in the difference sequence is taken as the mixing difficulty.

[0071] The initial mixing parameter setting module 102 is used to obtain a matching historical batch class cluster of the batch to be mixed. That is, the matching historical batch class cluster is the reference information of the batch to be mixed. Further, the stirring speed and the stirring time of the matching historical batch class cluster are counted, so that the initial stirring speed and the final stirring time of the batch to be mixed are obtained. It should be noted that, in order to realize the rapid stirring of the breeding feed, the final stirring time obtained in the embodiment of the present application is not changed in the subsequent modules, and only the initial stirring speed is adjusted to obtain an effective mixing result after the final stirring time ends.

[0072] Preferably, in an embodiment of the present application, the method for obtaining the matching historical batch class cluster comprises:

[0073] The similarity of the raw material distribution characteristics between the batch to be mixed and the class cluster center of each historical batch class cluster is taken as the matching degree, and the historical batch class cluster with the largest matching degree is taken as the matching historical batch class cluster.

[0074] It should be noted that, in an embodiment of the present application, the raw material distribution characteristics are a curve, so the matching degree can also be obtained by the DTW algorithm, and details are not described herein.

[0075] Preferably, in an embodiment of the present application, the initial stirring speed and the final stirring time of the batch to be mixed are obtained by:

[0076] An average particle volume and an average density of all raw materials in the batch to be mixed are obtained. A product of the average particle volume and the average density is taken as a raw material feature of the batch to be mixed. It should be noted that the average particle volume and the average density can be obtained according to the types and the proportion of the raw materials in the batch to be mixed, and details are not described herein.

[0077] Because the mixing effects of the historical batches are uneven, in order to make the initial stirring speed have certain reference, an average stirring speed of the historical batches in the matching historical batch cluster and having a mixing quality score greater than a preset score threshold is taken as the initial stirring speed. In an embodiment of the present application, the score threshold is set to the top 20% of the mixing quality scores in the matching historical batch cluster.

[0078] A ratio between the volume of the mixing bin and the raw material form feature is taken as a cutting effectiveness. The final stirring time is obtained according to the initial stirring speed and the cutting effectiveness. The greater the initial stirring speed is, the faster the mixing can be completed by adjusting the speed, and the smaller the final stirring time is. The greater the cutting effectiveness is, the smaller the raw material form feature is, and the more difficult the mixing is in the mixing bin, and the greater the final stirring time is. As an example, in an embodiment of the present application, the final stirring time is expressed by a formula as follows:

[0079] ; wherein is the final stirring time, is a preset empirical coefficient, is the volume of the mixing bin, is the initial stirring speed, is the evaluation particle volume, is the average density, is a ceiling function. In an embodiment of the present application, the empirical coefficient is set to 1.2.

[0080] The speed control module 103 is configured to intercept a mixing difficulty sequence from the mixing difficulty matrix of the matching historical batch cluster according to the initial stirring speed and the final stirring time. The time sequence range of the mixing difficulty sequence corresponds to the final stirring time. For example, a row of data or a column of data corresponding to the initial stirring speed is selected from the mixing difficulty matrix as an initial mixing difficulty sequence. The time sequence range of the initial mixing difficulty sequence is the stirring time dimension range of the whole mixing difficulty matrix, for example, can include the time sequences of 4 minutes, 5 minutes, 6 minutes, 7 minutes, 8 minutes, 9 minutes and 10 minutes. When the final stirring time is determined to be 8 minutes, the initial mixing difficulty sequence needs to be intercepted so as to only include the mixing difficulty information of 4 minutes, 5 minutes, 6 minutes, 7 minutes and 8 minutes, thereby constituting the mixing difficulty sequence.

[0081] Further in the stirring process, because the stirring time corresponds to a time sequence information in the mixing difficulty sequence, when the stirring time reaches the time sequence information in the mixing difficulty sequence, the initial stirring speed can be updated according to the corresponding mixing difficulty, that is, the greater the mixing difficulty, the faster the stirring speed needs to be increased, so that the feed in the mixing bin can be more in contact with the stirring roller to achieve effective stirring and cutting. The speed control module 103 updates the initial stirring speed and controls the stirring roller.

[0082] Preferably, in an embodiment of the present application, the speed control module includes a stirring speed updating module, which is used to obtain a speed adjustment coefficient according to the corresponding mixing difficulty and the matching degree of the matching historical batch cluster when the stirring process reaches the stirring time corresponding to each element in the mixing difficulty sequence, and update the initial stirring speed according to the speed adjustment coefficient. That is, the embodiment of the present application considers the matching degree with the matching historical batch cluster when obtaining the speed adjustment coefficient, that is, the matching degree can be used as a reference confidence, and the greater the matching degree, the more the information of the matching historical batch cluster is used as a reference, and the greater the confidence.

[0083] As an example, the speed adjustment coefficient in the embodiment of the present application is obtained by multiplying the matching degree and the mixing difficulty, and normalizing the multiplication result. Because the normalization result is a coefficient between 0 and 1, the normalization result is added to 0.7 to obtain the speed adjustment coefficient. That is, when the normalization result is greater than 0.3, it is proved that the mixing difficulty is large at this time, and the stirring speed needs to be increased, so the speed adjustment coefficient is a result greater than 1. Multiplying the speed adjustment coefficient and the initial stirring speed can update the initial stirring speed.

[0084] It should be noted that the initial stirring speed is a continuous updating process, and the stirring time continues to reach the time corresponding to the element in the mixing difficulty sequence after updating once, and then it needs to be updated until the final stirring time is reached.

[0085] The discharge control module 104 is used to stop stirring after the final stirring time is reached, control the opening of the discharge port, and output the mixed feed in the mixing bin.

[0086] The present application also proposes a breeding feed mixing method, which uses any one of the above breeding feed mixing device embodiments to mix the breeding feed of the batch to be mixed. When mixing, the staff places the raw materials of the batch to be mixed in the mixing bin, and then inputs the raw material information of the batch to be mixed, such as raw material ratio, raw material type, etc. through the control panel, and then starts mixing. The mixing control system will automatically determine the initial mixing parameters and continuously adjust the stirring speed according to the input information through the processing of the cloud server. The whole process is without human intervention, which improves the mixing quality of the final feed mixture and the mixing efficiency of the whole mixing process.

[0087] To sum up, the breeding feed mixing device proposed in the embodiment of the application comprises a mixing control system, the mixing control system analyzes the mixing data generated by known historical mixing batches by using a historical feed mixing data analysis module, and then constructs a mixing difficulty matrix of each historical batch cluster on the basis of the historical data. The initial stirring parameters can be obtained by determining the matching historical batch cluster, and then the mixing difficulty sequence corresponding to the initial stirring parameters is determined by using the mixing difficulty matrix, and then the mixing difficulty in the mixing difficulty sequence is used to control the stirring speed, and the breeding feed is mixed by adjusting the stirring speed on the basis of the final stirring time. The embodiment of the application reduces manual intervention and realizes the automatic and efficient mixing of the breeding feed in a fixed time by controlling the speed of the stirring roller.

[0088] It should be noted that the above-mentioned embodiment sequence of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0089] Each embodiment in the specification is described in a progressive manner, and the same and similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

Claims

1. A breeding feed mixing device comprising a mixing bin, a stirring roller, a discharge port, characterized in that, The mixing control system comprises: The historical feed mixing data analysis module is configured to divide a plurality of historical batch clusters according to the distribution of raw materials in each historical mixing batch; arrange the mixing quality scores of all historical mixing batches according to the stirring speed and stirring time of each historical mixing batch in the historical batch cluster to obtain a mixing data feature matrix of the historical batch cluster; obtain the growth trend of each element in the mixing data feature matrix in the stirring time dimension; obtain the mixing difficulty corresponding to each element according to the change of the growth trend of each element in the stirring speed dimension to form a mixing difficulty matrix; The initial mixing parameter setting module is configured to obtain a matching historical batch cluster of the batch to be mixed; and count the stirring speed and stirring time of the matching historical batch cluster to obtain an initial stirring speed and a final stirring time of the batch to be mixed; The speed control module is configured to intercept a mixing difficulty sequence from the mixing difficulty matrix of the matching historical batch cluster according to the initial stirring speed and the final stirring time; the time sequence range of the mixing difficulty sequence corresponds to the final stirring time; and the initial stirring speed is updated according to the mixing difficulty corresponding to the stirring time in the mixing difficulty sequence during the stirring process; The discharge control module is configured to stop stirring and control the opening of the discharge port after the final stirring time is reached to output the mixed feed in the mixing bin; The growth trend obtaining method comprises: Any element in the mixing data feature matrix is recorded as a target element, and all elements in the stirring time dimension direction corresponding to the position of the target element form a time sequence trend analysis sequence of the target element; the range of the time sequence trend analysis sequence is obtained; the difference in the mixing quality score between the target element and the next element in the time sequence trend analysis sequence is obtained; and the product of the mixing quality score difference and the range is taken as the growth trend of the target element; The mixing difficulty obtaining method comprises: Any element in the mixing data feature matrix is recorded as a target element, and the neighborhood range of the target element is obtained in the direction of increasing stirring speed from the target element as a starting point according to a preset size; the growth trends of the elements in the neighborhood range are sorted according to the stirring speed from small to large to obtain a growth trend sequence; The difference sequence of the growth trend sequence is obtained, the elements in the difference sequence are negatively correlated and mapped, and then normalized to obtain the mixing difficulty of the target element; The matching historical batch cluster obtaining method comprises: The similarity of the distribution of raw materials between the batch to be mixed and the cluster center of each historical batch cluster is taken as the matching degree; and the historical batch cluster with the largest matching degree is taken as the matching historical batch cluster; The horizontal dimension of the mixing data feature matrix is the stirring time, and the vertical dimension is the stirring speed; and the specific obtaining method of the mixing data feature matrix comprises: At the same stirring speed, the mixing quality scores are sorted according to the stirring time from small to large to obtain a first sequence of each stirring speed; and the first sequence is arranged vertically according to the stirring speed from large to small to obtain the mixing data feature matrix; The initial stirring speed and the final stirring time of the batch to be mixed are obtained by: obtaining the average particle volume and the average density of all raw materials in the batch to be mixed; multiplying the average particle volume and the average density to obtain the raw material morphology feature of the batch to be mixed; obtaining the average stirring speed of the historical mixed batches in the matching historical batch cluster as the initial stirring speed, the mixing quality score of which is greater than the preset score threshold; obtaining the ratio between the volume of the mixing bin and the raw material morphology feature as the cutting efficiency; obtaining the final stirring time according to the initial stirring speed and the cutting efficiency; The speed control module comprises a stirring speed updating module, which is configured to obtain a speed adjustment coefficient according to the corresponding mixing difficulty and the matching degree of the matching historical batch cluster when the stirring process reaches the stirring time corresponding to each element in the mixing difficulty sequence, and update the initial stirring speed according to the speed adjustment coefficient.

2. The mixed breeding feed device according to claim 1, wherein, The historical feed mixing data analysis module further comprises a historical data classification unit; the historical data classification unit is configured to obtain the feature similarity of the raw material distribution features between the historical mixed batches, cluster the historical mixed batches based on the feature similarity using the Kmeans clustering algorithm, and obtain a plurality of historical batch clusters.

3. The mixed breeding feed device according to claim 1, wherein, The historical feed mixing data analysis module further comprises a raw material distribution feature extraction module, which is configured to: For each mixed batch, obtain the particle volume of each raw material in the mixed batch and the content proportion in the mixed batch; obtain the cutting probability of the raw material in the mixed batch according to the particle volume and the content proportion; construct a raw material combination feature curve of the mixed batch with the type number of the raw material as the horizontal axis and the cutting probability of the raw material as the vertical axis, and take the raw material combination feature curve as the raw material distribution feature.

4. A method of mixing a feed for aquaculture, characterized in that, The method uses the breeding feed mixing device according to any one of claims 1-3 to mix the breeding feed to be mixed.

Images