CN115857461B

CN115857461B - Online monitoring method and system for production of premixed feed for piglets

Info

Publication number: CN115857461B
Application number: CN202310187340.9A
Authority: CN
Inventors: 张海梁; 袁冠华; 薛丹; 张楷雄; 罗轶华
Original assignee: Dongguan Zhengda Kangdi Feed Co ltd
Current assignee: Zhengda Kangdi Agriculture And Animal Husbandry Group Co ltd
Priority date: 2023-03-02
Filing date: 2023-03-02
Publication date: 2023-05-09
Anticipated expiration: 2043-03-02
Also published as: CN115857461A

Abstract

The embodiment of the application provides an online monitoring method and system for premixed feed production of a piglet, a fault tracing operation array is generated by combining feed production line observation data, then fault tracing operation in the fault tracing operation array is executed on the feed production line observation data, material mixed fault nodes for production monitoring subareas in the feed production line observation data are generated, the target material mixed fault nodes are generated by analyzing by combining the feed production line observation data, fault positioning fields of the material mixed fault nodes, fault positioning fields of a plurality of fault node relation networks and the fault tracing operation array, fault point repair is carried out on production monitoring subareas according to the target material mixed fault nodes, fault feature communication analysis on the feed production line observation data is realized because the fault node relation networks are the material mixed fault nodes carrying fault feature communication relations, and therefore fault point repair is carried out on the production monitoring subareas by combining the target material mixed fault nodes, and the reliability of fault point repair can be improved.

Description

Online monitoring method and system for production of premixed feed for piglets

Technical Field

The application relates to the technical field of online monitoring of feed production, in particular to an online monitoring method and an online monitoring system for premixed feed production of piglets.

Background

Because the formula of the piglet feed is complex, the feed raw materials are various, and the feed produced according to the formula needs a plurality of premixing procedures before entering the subsequent production link. Therefore, in the premixing stage, strict status monitoring needs to be performed on the production condition of the feed production line so as to ensure the production quality in the formal production link. For example, in particular, it is necessary to perform fault tracing and repair timely to ensure normal operation of the production line, however, in the related art, in the fault tracing process, the considered factors are too single, and the fault feature communication relationship is not considered, so that the accuracy of repairing the fault point is affected.

Disclosure of Invention

In order to at least overcome the defects in the prior art, the application aims to provide an online monitoring method and system for production of premixed feed for piglets.

In a first aspect, the present application provides an online monitoring method for production of premixed feed for piglets, applied to an online monitoring system for production of premixed feed for piglets, the method comprising:

acquiring feed production line observation data of a production monitoring partition, wherein the feed production line observation data are used for being tracked to material mixing fault nodes of the production monitoring partition;

Analyzing and generating a fault tracing operation array of the feed production line observation data by combining the feed production line observation data, wherein the fault tracing operation in the fault tracing operation array corresponds to different fault tracing events of the feed production line observation data;

performing fault tracing operation in the fault tracing operation array on the feed production line observation data to generate material mixing fault nodes of the production monitoring partition in the feed production line observation data;

analyzing and generating a target material mixing fault node by combining the feed production line observation data, the fault positioning field of the material mixing fault node, the fault positioning fields of a plurality of fault node relation networks and the fault tracing operation array, and repairing the fault point of the production monitoring partition by combining the target material mixing fault node, wherein the target material mixing fault node is a fault node relation network corresponding to the material mixing fault node in the plurality of fault node relation networks, and the fault node relation network is a material mixing fault node carrying a fault characteristic communication relation.

For some possible embodiments of the first aspect, the parsing the fault traceback operation array to generate the feed line observations in combination with the feed line observations includes:

And analyzing and generating a fault tracing operation array of the feed line observation data by combining the observation variable distribution of the feed line observation data in each feed line alarm event and a typical fault tracing operation array corresponding to each feed line alarm event, wherein the observation variable distribution represents production alarm characteristic points which are formed by production alarm characteristic points, linkage production alarm characteristic points and production alarm characteristic points which are not subjected to alarm processing in the feed line observation data in the corresponding feed line alarm event, and the typical fault tracing operation array is a fault tracing operation array determined by the feed line alarm event before the corresponding feed line alarm event.

For some possible embodiments of the first aspect, the analyzing the typical fault tracing operation array to generate the feed line observation data in combination with the observation variable distribution of the feed line observation data in each feed line alarm event and the typical fault tracing operation array corresponding to each feed line alarm event includes:

in any feed production line alarm event L, analyzing and generating observation variable distribution of the feed production line observation data in the feed production line alarm event L, wherein L is a positive integer;

Acquiring a typical fault tracing operation array determined by an alarm event L-1 in a feed production line;

analyzing and generating a fault tracing operation corresponding to the feed production line alarm event L by combining the observation variable distribution of the feed production line observation data at the feed production line alarm event L and a typical fault tracing operation array determined at the feed production line alarm event L-1;

and transmitting the fault tracing operation corresponding to the feed production line alarm event L to a typical fault tracing operation array determined by the feed production line alarm event L-1, and generating the fault tracing operation array corresponding to the feed production line alarm event L.

For some possible embodiments of the first aspect, the analyzing the typical fault tracing operation array determined by combining the observation variable distribution of the feed line observation data at the feed line alarm event L and the feed line alarm event L-1 to generate the fault tracing operation corresponding to the feed line alarm event L includes:

the method comprises the steps of combining production alarm feature point distribution, first production alarm feature point distribution and second production alarm feature point distribution of the feed production line observation data with head fault tracing operation in a typical fault tracing operation array determined by a feed production line alarm event L-1, analyzing and generating fault tracing operation corresponding to the feed production line alarm event L, wherein the production alarm feature point distribution comprises production alarm feature points formed by production alarm feature points which have executed alarm processing when the feed production line alarm event L, the first production alarm feature point distribution comprises production alarm feature points which are linked when the feed production line alarm event L, and the second production alarm feature point distribution comprises production alarm feature points which do not execute alarm processing in the feed production line observation data when the feed production line alarm event L.

For some possible embodiments of the first aspect, the analyzing and generating the fault tracing operation corresponding to the feed line alarm event L according to the production alarm feature point distribution, the first production alarm feature point distribution, the second production alarm feature point distribution, and the head fault tracing operation in the typical fault tracing operation array determined by the feed line alarm event L-1 includes:

converging two or more production alarm feature points with linkage relations in the production alarm feature point distribution, head production alarm feature points in the first production alarm feature point distribution, head production alarm feature points in the second production alarm feature point distribution and head fault tracing operation in a typical fault tracing operation array determined by the feed production line alarm event L-1 to generate a first production alarm relation space of the feed production line alarm event L;

updating the first production alarm relationship space by combining a predetermined first alarm influence matrix and a predetermined first alarm derivative matrix to generate a second production alarm relationship space of the feed production line alarm event L;

And carrying out fault tracing decision on the second production alarm relation space by combining a fault tracing decision model to generate fault tracing operation corresponding to the feed production line alarm event L.

For some possible embodiments of the first aspect, the analyzing the target material mixing fault node according to the feed line observation data, the fault location field of the material mixing fault node, the fault location fields of the plurality of fault node relation networks, and the fault tracing operation array includes:

acquiring a first linkage characteristic variable between a front production alarm characteristic point of the material mixing fault node and the material mixing fault node in the feed production line observation data and a second linkage characteristic variable between a rear production alarm characteristic point of the material mixing fault node and the material mixing fault node in the feed production line observation data by combining the feed production line observation data;

and analyzing and generating the target material mixed fault node by combining the first contact characteristic variable, the second contact characteristic variable, the fault positioning field of the material mixed fault node, the fault positioning fields of the multiple fault node relation networks and the fault tracing operation array.

For some possible embodiments of the first aspect, the parsing to generate the target material mixture fault node in combination with the first contact feature variable, the second contact feature variable, the fault location field of the material mixture fault node, the fault location fields of the plurality of fault node relationship networks, and the fault traceback operation array includes:

combining significance mining rules, respectively extracting significance characteristics of fault locating fields of the material mixed fault nodes and fault locating fields of each fault node relation network, and generating significance characteristics of the material mixed fault nodes and significance characteristics of each fault node relation network;

and analyzing and generating the target material mixed fault node by combining the first contact characteristic variable, the second contact characteristic variable, the significance characteristic of the material mixed fault node, the significance characteristic of each fault node relation network, the fault positioning field of each fault node relation network and the head fault tracing operation in the fault tracing operation array.

For some possible embodiments of the first aspect, the parsing the target material mixture fault node in combination with the first contact feature variable, the second contact feature variable, the saliency feature of the material mixture fault node, the saliency feature of each of the fault node relationship networks, the fault location field of each of the fault node relationship networks, and the head fault tracing operation in the fault tracing operation array includes:

Converging the first contact characteristic variable, the second contact characteristic variable, the salient features of the material mixed fault nodes, the salient features of each fault node relation network, the fault location field of each fault node relation network and head fault tracing operation in the fault tracing operation array to generate first fault location information;

processing the first fault location information by combining a second alarm influence matrix and a second alarm derivative matrix to generate second fault location information;

processing the second fault positioning information by combining a fault collecting model to generate fault collecting parameter values between each fault node relation network and the material mixed fault node;

and matching the fault collection parameter values in the plurality of fault node relation networks with the fault node relation network required by setting the fault collection parameter values, and analyzing and generating the fault node relation network into the target material mixed fault node.

In some possible embodiments of the first aspect, the method further comprises:

analyzing and generating fault locating fields of the plurality of fault node relation networks by combining the plurality of fault node relation networks and the communication fields among the plurality of fault node relation networks;

The method for analyzing and generating the fault location fields of the plurality of fault node relation networks comprises the steps of:

extracting the cycle significance characteristics of the first fault node relation network, the second fault node relation network and the third fault node relation network, and generating a first cycle significance characteristic of the first fault node relation network, a second cycle significance characteristic of the second fault node relation network and a third cycle significance characteristic of the third fault node relation network;

inputting the first cycle significance feature and the second cycle significance feature into a fault location model, combining the fault location model, and combining target nonlinear relation information to carry out nonlinear mapping on the second cycle significance feature to generate a fourth cycle significance feature of the second fault node relation network;

And processing the first cycle significance feature and the second cycle significance feature by combining first feature distance information between the first cycle significance feature and the fourth cycle significance feature and second feature distance information between the third cycle significance feature and the fourth cycle significance feature to generate a fault location field of the first fault node relation network and a fault location field of the second fault node relation network.

For example, in some possible embodiments of the first aspect, the fault point repairing of the production monitoring partition in combination with the target material mixing fault node specifically includes the following steps:

acquiring a production line operation example cluster of the production line plan of the target material mixing fault node corresponding to the production monitoring partition in a target production line period, wherein the production line operation example cluster corresponding to the target material mixing fault node comprises production line operation examples of all fault positioning child nodes in the target material mixing fault node;

and carrying out fault collaborative repair label extraction on the production line operation example cluster corresponding to the target material mixed fault node by combining a fault collaborative repair unit in a fault point repair model related to the current operation target material mixed fault node to obtain fault collaborative repair label information, updating the fault point repair model by combining the fault collaborative repair label information, and carrying out fault point repair on the production monitoring partition by combining the updated fault point repair model.

For example, in some possible embodiments of the first aspect, after the step of performing the fault point repair on the production monitoring partition in combination with the target material mixing fault node, the method further includes:

the method comprises the steps of combining first fault causal fault execution information and second fault causal fault execution information in a fault causal graph after fault point repair of the production monitoring partition, analyzing and generating a first fault penetration characteristic graph and first material production transaction information of the first fault causal fault execution information, and obtaining first continuous transaction information of the first fault causal fault execution information relative to a material production plan:

analyzing and generating a first fault tracing plan by combining a first fault penetration characteristic diagram, first material production transaction information and first continuous transaction information of fault execution information of the first fault cause and effect;

and judging whether invalid fault tracing information exists in the fault tracing evaluation data of the fault tracing activity corresponding to the first fault tracing plan according to the trained fault tracing portrait analysis model.

For example, for some possible embodiments of the first aspect, in combination with the first and second fault-causal fault-execution information in the fault-causal graph, parsing the first fault-penetration profile and the first material production profile to generate the first fault-causal fault-execution information includes: the method comprises the following steps of: for each first fault execution item in the first fault causal fault execution information and the second fault causal fault execution information, analyzing and generating a first fault execution characteristic associated with each first fault execution item by combining fault execution track data of each first fault execution item in the first fault causal fault execution information and the second fault causal fault execution information and first material production data corresponding to the fault causal graph, and determining a first fault execution characteristic graph of each first fault execution item and a first fault penetration characteristic graph of the first fault causal fault execution information; and resolving first material production abnormal information of the fault execution information for generating the first fault cause and effect according to the first fault execution characteristic diagram of each first fault execution item.

For example, for some possible embodiments of the first aspect, generating the first persistent transaction information for the first cause and effect of the fault relative to the material production plan includes: and analyzing and generating first continuous abnormal information of the fault execution information of the first fault cause and effect relative to the material production plan by combining the number of continuous abnormal conditions corresponding to the material production plan mapped by the fault execution characteristics of each first fault execution item in the fault execution flow.

In a second aspect, embodiments of the present application further provide a system for monitoring production of premixed feed for piglets on line, the system for monitoring production of premixed feed for piglets on line comprising a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores a computer program, and the computer program is loaded and executed based on the processor to realize the method for monitoring production of premixed feed for piglets on line of the first aspect.

According to the method, the system and the device, the fault tracing operation array of the feed production line observation data is generated through analyzing by combining the feed production line observation data, then fault tracing operation in the fault tracing operation array is carried out on the feed production line observation data, material mixed fault nodes of production monitoring partitions in the feed production line observation data are generated, the target material mixed fault nodes are generated through analyzing by combining the feed production line observation data, the fault positioning fields of the material mixed fault nodes, the fault positioning fields of a plurality of fault node relation networks and the fault tracing operation array, fault point repair is carried out on the production monitoring partitions according to the target material mixed fault nodes, fault feature communication analysis on the feed production line observation data is realized because the fault node relation networks are the material mixed fault nodes carrying fault feature communication relations, and therefore fault point repair is carried out on the production monitoring partitions by combining the target material mixed fault nodes, and reliability of fault point repair can be improved.

Drawings

For a clearer description of the technical solutions of the embodiments of the present application, the accompanying drawings, which are needed to be activated in the embodiments, will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and should therefore not be considered as limiting the scope, and that other related drawings may be obtained based on these drawings without the inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of an online monitoring method for production of premixed feed for piglets, which is provided by the embodiment of the application;

fig. 2 is a schematic block diagram of a monitoring system for on-line monitoring of a piglet premix feed production for implementing the above-mentioned method for on-line monitoring of a piglet premix feed production according to an embodiment of the present application.

Detailed Description

The following description is presented to enable one of ordinary skill in the art to make and use the application and is provided in the context of a particular application and its requirements. It will be apparent to those having ordinary skill in the art that various changes can be made to the disclosed embodiments and that the general principles defined herein may be applied to other embodiments and applications without departing from the principles and scope of the present application. Thus, the present application is not limited to the embodiments described, but is to be accorded the widest scope consistent with the claims.

The terminology used in the present application is for the purpose of describing particular example embodiments only and is not intended to limit the scope of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

These and other features, characteristics, and functions of related structural elements of the present application, as well as the methods of operation and combination of parts and economies of manufacture, will become more apparent upon consideration of the following description of the drawings, all of which form a part of this specification. It is to be understood, however, that the drawings are designed solely for the purposes of illustration and description and are not intended to limit the scope of the application. It should be understood that the figures are not drawn to scale.

Flowcharts are used in this application to describe the operations performed by systems according to some embodiments of the present application. It should be understood that the operations in the flow diagrams may be performed out of order. Rather, the various steps may be processed in reverse order or simultaneously. Further, one or more other operations may be added to the flowchart. One or more operations may also be deleted from the flowchart.

The following description is provided with reference to the accompanying drawings, and the specific operation method in the method embodiment may also be applied to the device embodiment or the system embodiment.

Fig. 1 is a schematic flow chart of an online monitoring method for production of premixed feed for piglets according to an embodiment of the application, and the online monitoring method for production of premixed feed for piglets is described in detail below.

Step 101, acquiring feed production line observation data of a production monitoring partition, wherein the feed production line observation data are used for tracking material mixing fault nodes of the production monitoring partition.

For some possible embodiments, the production monitoring partition is a production partition corresponding to any independent feed production line, and the feed production line observation data of the production monitoring partition is production behavior monitoring data of each material production device of the feed production line.

Step 102, analyzing and generating a fault tracing operation array of the feed production line observation data by combining the feed production line observation data, wherein the fault tracing operation in the fault tracing operation array corresponds to different fault tracing events of the feed production line observation data.

The fault tracing operation array comprises a plurality of fault tracing operations, and the plurality of fault tracing operations in the fault tracing operation array are in sequence of tracing, namely different fault tracing operations are correspondingly executed on different fault tracing events of the feed production line observation data. Each fault tracing operation may be used to trace fault information of different production stages in the feed line observation data, or fault information of different fault types, that is, one fault tracing operation may correspond to a certain production stage, or a certain fault type, but not limited thereto, and a person skilled in the art may determine different fault tracing operations from the feed line observation data in combination with an actual scenario.

And 103, performing fault tracing operation in the fault tracing operation array on the feed production line observation data to generate material mixing fault nodes of the production monitoring partition in the feed production line observation data.

The material mixing fault nodes of the production monitoring partition are specific fault positioning units in the observation data of the feed production line, and the fault positioning units are generally not associated with fault feature communication relations, namely, the material mixing fault nodes which do not carry the fault feature communication relations. For some possible embodiments, performing a fault tracing operation in the fault tracing operation array on the feed line observations, generating a material mixing fault node for the production monitoring zone in the feed line observations.

Step 104, analyzing and generating a target material mixing fault node by combining the feed production line observation data, the fault positioning field of the material mixing fault node, the fault positioning fields of a plurality of fault node relation networks and the fault tracing operation array, and repairing the fault point of the production monitoring partition by combining the target material mixing fault node, wherein the target material mixing fault node is a fault node relation network corresponding to the material mixing fault node in the plurality of fault node relation networks, and the fault node relation network is a material mixing fault node carrying a fault characteristic communication relation.

The target material mixing fault node is a communication relationship carrying fault characteristics corresponding to the material mixing fault node of the production monitoring partition in the observation data of the feed production line, and is used for representing association relationships carrying fault characteristics, such as causal relationships, scheduling relationships and the like.

By adopting the technical scheme, the embodiment analyzes and generates the fault tracing operation array of the feed production line observation data by combining the feed production line observation data, then performs fault tracing operation in the fault tracing operation array on the feed production line observation data, generates the material mixing fault node of the production monitoring partition in the feed production line observation data, analyzes and generates the target material mixing fault node by combining the feed production line observation data, the fault positioning field of the material mixing fault node, the fault positioning field of the multiple fault node relation network and the fault tracing operation array, and repairs the fault point of the production monitoring partition according to the analysis, and realizes fault feature communication analysis for the feed production line observation data because the fault node relation network is the material mixing fault node carrying the fault feature communication relation.

The above embodiments are described below in connection with further examples, e.g. the above method comprises the following steps.

Step 201, acquiring feed production line observation data of a production monitoring partition, wherein the feed production line observation data is used for tracking material mixing fault nodes of the production monitoring partition.

Step 202, analyzing and generating a fault tracing operation array of the feed production line observation data by combining the feed production line observation data, wherein the fault tracing operation in the fault tracing operation array corresponds to different fault tracing events of the feed production line observation data.

For some possible embodiments, the fault tracing operation array of the feed line observation data is generated by analyzing and combining the observation variable distribution of the feed line observation data in each feed line alarm event and the typical fault tracing operation array corresponding to each feed line alarm event, wherein the observation variable distribution represents production alarm feature points formed by production alarm feature points, linkage production alarm feature points and production alarm feature points which do not execute alarm processing in the feed line observation data in the corresponding feed line alarm event, and the typical fault tracing operation array is a fault tracing operation array determined by the feed line alarm event before the corresponding feed line alarm event.

The observation variable distribution is used for representing state information of production alarm feature points of the feed production line observation data, one feed production line alarm event is an alarm process, and after the corresponding fault tracing operation is executed on the feed production line observation data by one feed production line alarm event, the state information of the production alarm feature points of the feed production line observation data is changed, so that the observation variable distribution corresponding to the feed production line observation data is changed. The linkage production alarm feature points are production alarm feature points belonging to the material mixing fault node, and the production alarm feature points formed by the production alarm feature points which have been subjected to alarm processing are production alarm feature points belonging to the material mixing fault node.

Since the fault tracing operation array for resolving and generating the feed line observation data includes a plurality of feed line alarm events in combination with the feed line observation data, the above embodiment will be described by taking one feed line alarm event as an example.

For some possible embodiments, in any feed line alarm event L, the observed variable distribution of the feed line observation data at the feed line alarm event L is generated by parsing, and L is a positive integer. A typical fault trace-back operation array determined at a feed line alarm event L-1 is obtained. And analyzing and generating the fault tracing operation corresponding to the feed production line alarm event L by combining the observation variable distribution of the feed production line alarm event L and the typical fault tracing operation array determined by the feed production line alarm event L-1. And transmitting the fault tracing operation corresponding to the feed production line alarm event L to a typical fault tracing operation array determined by the feed production line alarm event L-1, and generating a fault tracing operation array corresponding to the feed production line alarm event L.

For some possible embodiments, the head fault tracing operation in the typical fault tracing operation array determined by the feed line alarm event L-1, in combination with the production alarm feature point distribution of the feed line observation data, the first production alarm feature point distribution, the second production alarm feature point distribution, and the head fault tracing operation in the typical fault tracing operation array determined by the feed line alarm event L-1, is analyzed to generate a fault tracing operation corresponding to the feed line alarm event L, the production alarm feature point distribution includes production alarm feature points composed of production alarm feature points that have performed alarm processing at the feed line alarm event L, the first production alarm feature point distribution includes production alarm feature points that are linked at the feed line alarm event L, and the second production alarm feature point distribution includes production alarm feature points that have not performed alarm processing at the feed line alarm event L in the feed line observation data.

For example, the first production alarm relation space of the feed production line alarm event L is generated by converging two or more production alarm feature points with linkage relations in the production alarm feature point distribution, head production alarm feature points in the first production alarm feature point distribution, head production alarm feature points in the second production alarm feature point distribution and head fault tracing operations in a typical fault tracing operation array determined by the feed production line alarm event L-1. And updating the first production alarm relation space by combining a predetermined first alarm influence matrix and a predetermined first alarm derivative matrix to generate a second production alarm relation space of the feed production line alarm event L. And carrying out fault tracing decision on the second production alarm relation space by combining a fault tracing decision model to generate fault tracing operation corresponding to the alarm event L of the feed production line.

And transmitting the fault tracing operation corresponding to the feed production line alarm event L to a typical fault tracing operation array determined by the feed production line alarm event L-1, and generating a fault tracing operation array corresponding to the feed production line alarm event L.

Thus, the determination and the adaptive updating of the fault tracing operation array are realized.

And 203, performing fault tracing operation in the fault tracing operation array on the feed production line observation data to generate material mixing fault nodes of the production monitoring partition in the feed production line observation data.

The operation of tracing the fault in the array of operation of tracing the fault is described in step 202 above, and step 203 will be described by some embodiments.

And 204, acquiring a fault location field of the material mixing fault node.

For some possible embodiments, fault location field extraction is performed on each production alarm feature point in the feed line observation data, and fault location fields of each production alarm feature point in the feed line observation data are generated. And summarizing the fault locating fields of the production alarm feature points in the material mixing fault node to generate the fault locating fields of the material mixing fault node.

By combining the design, the fault locating field of the material mixing fault node can be obtained through the fault locating field of the production alarm feature points in the feed production line observation data, the fault locating field of the material mixing fault node fuses the fault locating fields of all the production alarm feature points, and the feature expression performance of the fault locating field of the material mixing fault node is stronger.

In order to more clearly describe the above embodiments, the above embodiments will be described in two steps.

And step A, extracting the characteristics of each production alarm characteristic point in the observation data of the feed production line, and generating a fault locating field of each production alarm characteristic point in the observation data of the feed production line.

For some possible embodiments, for any production alarm feature point in the feed line observation data, convolving the production alarm feature point to generate a first production alarm feature point variable for the production alarm feature point. And carrying out cycle significance characteristic extraction on the production alarm characteristic points to generate second production alarm characteristic point variables of the production alarm characteristic points. And combining the production alarm characteristic point and a production alarm characteristic point associated with the production alarm characteristic point in the observation data of the feed production line to acquire a third production alarm characteristic point variable of the production alarm characteristic point, wherein the third production alarm characteristic point variable is a contact characteristic variable of the production alarm characteristic point. And splicing the first production alarm feature point variable, the second production alarm feature point variable and the third production alarm feature point variable to generate a fault locating field of the production alarm feature point.

And B, fusing fault locating fields of the production alarm feature points in the material mixing fault node to generate the fault locating field of the material mixing fault node.

For some possible embodiments, the fault location fields of the production alarm feature points in the material mixing fault node are spliced to generate the fault location fields of the material mixing fault node.

Step 205, analyzing and generating a target material mixing fault node by combining the feed production line observation data, the fault locating field of the material mixing fault node, the fault locating fields of a plurality of fault node relation networks and the fault tracing operation array, wherein the target material mixing fault node is a fault node relation network corresponding to the material mixing fault node in the plurality of fault node relation networks, and the fault node relation network is a material mixing fault node carrying a fault feature communication relation.

For some possible embodiments, a first linkage characteristic variable between a leading production alarm characteristic point of the material mixing fault node and the material mixing fault node in the feed line observation data and a second linkage characteristic variable between a trailing production alarm characteristic point of the material mixing fault node and the material mixing fault node in the feed line observation data are obtained in combination with the feed line observation data. And analyzing and generating the target material mixed fault node by combining the first contact characteristic variable, the second contact characteristic variable, the fault positioning field of the material mixed fault node, the fault positioning fields of the plurality of fault node relation networks and the fault tracing operation array.

And M, acquiring a first linkage characteristic variable between a front production alarm characteristic point of the material mixing fault node and the material mixing fault node in the feed production line observation data and a second linkage characteristic variable between a backward production alarm characteristic point of the material mixing fault node and the material mixing fault node in the feed production line observation data by combining the feed production line observation data.

For some possible embodiments, inputting the pre-production alarm feature point of the material mixing fault node and the material mixing fault node in the feed production line observation data into a connection feature variable extraction model, and performing feature extraction on the pre-production alarm feature point of the material mixing fault node and the material mixing fault node to generate the first connection feature variable.

And step N, analyzing and generating the target material mixed fault node by combining the first contact characteristic variable, the second contact characteristic variable, the fault positioning field of the material mixed fault node, the fault positioning fields of the multiple fault node relation networks and the fault tracing operation array.

For some possible embodiments, the significance mining rules are combined, and the significance feature extraction is respectively carried out on the fault location field of the material mixed fault node and the fault location field of each fault node relation network, so as to generate the significance feature of the material mixed fault node and the significance feature of each fault node relation network. And analyzing and generating the target material mixed fault node by combining the first contact characteristic variable, the second contact characteristic variable, the significance characteristic of the material mixed fault node, the significance characteristic of each fault node relation network, the fault location field of each fault node relation network and the head fault tracing operation in the fault tracing operation array.

The above embodiment will be described with two steps.

And a step a, combining a significance mining rule, respectively extracting significance characteristics of a fault locating field of the material mixed fault node and a fault locating field of each fault node relation network, and generating significance characteristics of the material mixed fault node and significance characteristics of each fault node relation network.

For some possible embodiments, a first saliency factor between the material mixture fault node and each fault node relationship network and a second saliency factor between each fault node relationship network and the material mixture fault node are obtained in combination with the fault location field of the material mixture fault node and the fault location field of each fault node relationship network. And fusing the fault locating field of the material mixing fault node with a corresponding first saliency factor to generate the saliency characteristic of the material mixing fault node, wherein the correspondence refers to the correspondence with the fault node relation network. And fusing the fault locating fields of each fault node relation network with the corresponding second saliency factors to generate the saliency characteristics of each fault node relation network.

And b, analyzing and generating the target material mixed fault node by combining the first contact characteristic variable, the second contact characteristic variable, the significance characteristic of the material mixed fault node, the significance characteristic of each fault node relation network, the fault positioning field of each fault node relation network and the head fault tracing operation in the fault tracing operation array.

For some possible implementations, the first connection feature variable, the second connection feature variable, the significance signature of the material-mixed fault node, the significance signature of each fault node relationship network, the fault location field of each fault node relationship network, and the head fault tracing operations in the fault tracing operation array are aggregated to generate first fault location information. And processing the first fault location information by combining a second alarm influence matrix and a second alarm derivative matrix to generate second fault location information. And processing the second fault positioning information by combining a fault collecting model to generate fault collecting parameter values between each fault node relation network and the material mixed fault node. And matching the fault collection parameter values in the plurality of fault node relation networks with the fault node relation network required by setting the fault collection parameter values, and analyzing and generating the fault node relation network into the target material mixed fault node.

For some possible embodiments, the plurality of fault node relationship networks and the connectivity fields between the plurality of fault node relationship networks are combined to parse and generate fault location fields of the plurality of fault node relationship networks.

For example, the plurality of fault node relationship networks includes a first fault node relationship network, a second fault node relationship network, and a third fault node relationship network, the first fault node relationship network being a pre-relationship network of the second fault node relationship network, a connectivity field not being present between the third fault node relationship network and the second fault node relationship network. And extracting the cycle significance characteristics of the first fault node relation network, the second fault node relation network and the third fault node relation network to generate a first cycle significance characteristic of the first fault node relation network, a second cycle significance characteristic of the second fault node relation network and a third cycle significance characteristic of the third fault node relation network. Inputting the first cycle significance feature and the second cycle significance feature into a fault location model, and carrying out nonlinear mapping on the second cycle significance feature by combining target nonlinear relation information through the fault location model to generate a fourth cycle significance feature of the second fault node relation network. And processing the first cycle significance feature and the second cycle significance feature in combination with first feature distance information between the first cycle significance feature and the fourth cycle significance feature and second feature distance information between the third cycle significance feature and the fourth cycle significance feature to generate a fault location field of the first fault node relation network and a fault location field of the second fault node relation network.

For example, for step 104, the process of performing a point of failure repair for the production monitoring partition in conjunction with the target material mixture failure node may be implemented by the following exemplary steps.

Step 301, obtaining a production line operation instance cluster of the production line plan of the target material mixing fault node corresponding to the production monitoring partition in the target production line period, where the production line operation instance cluster corresponding to the target material mixing fault node includes production line operation instances of each fault location sub-node in the target material mixing fault node.

Step 302, a fault collaborative repair label is extracted from a production line operation example cluster corresponding to the target material mixed fault node by combining a fault collaborative repair unit in a fault point repair model related to the target material mixed fault node in current operation to obtain fault collaborative repair label information, the fault point repair model is updated by combining the fault collaborative repair label information, and then the fault point repair is performed on the production monitoring partition by combining the updated fault point repair model.

For example, after the step of repairing the fault point of the production monitoring partition in conjunction with the target material mixing fault node, the method provided by the present embodiment may further include the following steps.

Step 401, resolving and generating a first fault penetration characteristic map and first material production abnormal information of the first fault causal fault execution information and first continuous abnormal information of the first fault causal fault execution information relative to a material production plan by combining the first fault causal fault execution information and the second fault causal fault execution information in the fault causal map after repairing the fault point of the production monitoring partition.

Step 402, analyzing and generating a first fault tracing plan through a first fault penetration feature map, first material production transaction information and first continuous transaction information of the fault execution information of the first fault cause and effect.

And step 403, judging whether invalid fault tracing information exists in the fault tracing evaluation data of the fault tracing activity corresponding to the first fault tracing plan according to the trained fault tracing portrait analysis model.

For example, in combination with the first and second fault-causal fault execution information in the fault-causal graph, resolving the first fault penetration feature graph and the first material production transaction information to generate the first fault-causal fault execution information, including: the method comprises the following steps of: for each first fault execution item in the first fault causal fault execution information and the second fault causal fault execution information, analyzing and generating a first fault execution characteristic associated with each first fault execution item by combining fault execution track data of each first fault execution item in the first fault causal fault execution information and the second fault causal fault execution information and first material production data corresponding to the fault causal graph, and determining a first fault execution characteristic graph of each first fault execution item and a first fault penetration characteristic graph of the first fault causal fault execution information; and resolving first material production abnormal information of the fault execution information for generating the first fault cause and effect according to the first fault execution characteristic diagram of each first fault execution item.

For example, generating the first persistent transaction information for the first cause and effect of the fault with respect to the material production plan includes: and analyzing and generating first continuous abnormal information of the fault execution information of the first fault cause and effect relative to the material production plan by combining the number of continuous abnormal conditions corresponding to the material production plan mapped by the fault execution characteristics of each first fault execution item in the fault execution flow.

Fig. 2 illustrates a hardware architecture diagram of the online monitor system 100 for premixed feed production of piglets for implementing the online monitor method for premixed feed production of piglets according to the embodiment of the present application, and as shown in fig. 2, the online monitor system 100 for premixed feed production of piglets may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.

In some embodiments, the piglet premix feed production online monitoring system 100 may be a single server or a group of servers. The server farm may be centralized or distributed (e.g., the piglet premix feed production online monitoring system 100 may be a distributed system). In some embodiments, the piglet premix feed production online monitoring system 100 may be local or remote. For example, the piglet premix feed production online monitoring system 100 may access information and/or data stored in the machine-readable storage medium 120 via a network. As another example, the piglet premix feed production online monitoring system 100 may be directly connected to the machine-readable storage medium 120 to access stored information and/or data. In some embodiments, the piglet premix feed production online monitoring system 100 may be implemented on a cloud platform. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, multiple clouds, or the like, or any combination thereof.

The machine-readable storage medium 120 may store data and/or instructions. In some embodiments, the machine-readable storage medium 120 may store the data from an external terminal. In some embodiments, the machine-readable storage medium 120 may store data and/or instructions that the piglet premix feed production online monitoring system 100 uses to perform or use to complete the exemplary methods described herein. In some embodiments, the machine-readable storage medium 120 may include mass storage, removable storage, volatile read-write memory, read-only memory (ROM), and the like, or any combination thereof. Exemplary mass storage devices may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, tape, and the like. Exemplary volatile read-write memory can include Random Access Memory (RAM). Exemplary RAM may include active random access memory (DRAM), double data rate synchronous active random access memory (DDR SDRAM), passive random access memory (SRAM), thyristor random access memory (T-RAM), zero capacitance random access memory (Z-RAM), and the like. Exemplary read-only memory may include mask read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (PEROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital versatile disk read-only memory, and the like. In some embodiments, the machine-readable storage medium 120 may be implemented on a cloud platform. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, etc., or any combination thereof.

In a specific implementation, the plurality of processors 110 execute computer executable instructions stored by the machine-readable storage medium 120, so that the processors 110 may execute the method for monitoring the production of the premixed feed for piglets according to the above method embodiment, the processors 110, the machine-readable storage medium 120 and the communication unit 140 are connected through the bus 130, and the processors 110 may be used to control the transceiving actions of the communication unit 140.

The specific implementation process of the processor 110 can be referred to each method embodiment executed by the above-mentioned piglet premix feed online monitoring system 100, and its implementation principle and technical effects are similar, and this embodiment will not be described herein again.

In addition, the embodiment of the application also provides a readable storage medium, wherein computer executable instructions are preset in the readable storage medium, and when a processor executes the computer executable instructions, the online monitoring method for the production of the premixed feed for the piglets is realized.

It is to be understood that the above description is intended to be illustrative only and is not intended to limit the scope of the present application. Many modifications and variations will be apparent to those of ordinary skill in the art based on the description herein. However, such modifications and variations do not depart from the scope of the present application.

While the basic concepts have been described above, it will be apparent to those of ordinary skill in the art after reading this application that the above disclosure is by way of example only and is not limiting of the present application. Although not explicitly described herein, various modifications, improvements, and adaptations of the present application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.

Meanwhile, the present application uses specific words to describe embodiments of the present application. For example, "one embodiment," "an embodiment," and/or "some embodiments" means a particular feature, structure, or characteristic in connection with various embodiments of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.

Furthermore, those of ordinary skill in the art will appreciate that aspects of the invention may be illustrated and described in terms of several patentable categories or circumstances, including any novel and useful processes, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, each aspect of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as a "unit," module, "or" system. Furthermore, aspects of the present disclosure may take the form of a computer program product embodied in one or more computer-readable media, wherein the computer-readable program code is embodied therein.

The computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer readable signal medium may be propagated through any suitable medium including radio, cable, fiber optic cable, RF, or the like, or any combination thereof.

The computer program code necessary for operation of portions of the present application may be written in any one or more programming languages, including a host-oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python, etc., a conventional programming language such as C language, visual Basic, forOPan 2003, perl, COBOL 2002, PHP, ABAP, an active programming language such as Python, ruby, and Groovy, or other programming languages, etc. The program code may execute entirely on the user's computer or as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or the use of services such as software as a service (SaaS) in a cloud computing environment.

Furthermore, the order in which the elements and sequences are presented, the use of numerical letters, or other designations are used in the application and are not intended to limit the order in which the processes and methods of the application are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present application. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed herein and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. Likewise, it should be noted that in order to simplify the presentation disclosed herein and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof.

Claims

1. An online monitoring method for the production of premixed feed for piglets, which is characterized by being applied to an online monitoring system for the production of premixed feed for piglets, comprises the following steps:

acquiring feed production line observation data of a production monitoring partition of the premixed feed of the piglets, wherein the feed production line observation data are used for being tracked to material mixing fault nodes of the production monitoring partition;

analyzing and generating a target material mixing fault node by combining the observation data of the feed production line, the fault positioning fields of the material mixing fault nodes, the fault positioning fields of a plurality of fault node relation networks and the fault tracing operation array, and repairing the fault point of the production monitoring partition by combining the target material mixing fault node, wherein the target material mixing fault node is a fault node relation network corresponding to the material mixing fault node in the plurality of fault node relation networks, and the fault node relation network is a material mixing fault node carrying a fault characteristic communication relation;

The method further comprises the steps of:

analyzing and generating fault positioning fields of the plurality of fault node relation networks by combining the plurality of fault node relation networks and communication fields among the plurality of fault node relation networks, wherein the plurality of fault node relation networks comprise a first fault node relation network, a second fault node relation network and a third fault node relation network, the first fault node relation network is a preposed relation network of the second fault node relation network, and no communication field exists between the third fault node relation network and the second fault node relation network;

the analyzing to generate the fault location fields of the plurality of fault node relation networks by combining the plurality of fault node relation networks and the communication fields among the plurality of fault node relation networks comprises the following steps:

Inputting the first cycle significance feature and the second cycle significance feature into a fault location model, and carrying out nonlinear mapping on the second cycle significance feature by combining target nonlinear relation information through the fault location model to generate a fourth cycle significance feature of the second fault node relation network;

2. The method of claim 1, wherein the analyzing the array of fault traceback operations to generate the feed line observations in combination with the feed line observations comprises:

3. The method for monitoring the premix feed production line of the piglets according to claim 2, wherein the analyzing and generating the fault tracing operation array of the feed production line observation data by combining the observation variable distribution of the feed production line observation data in each feed production line alarm event and the typical fault tracing operation array corresponding to each feed production line alarm event comprises:

4. A method of on-line monitoring of a pre-mixed feed production for piglets according to claim 3, wherein said parsing the array of typical traceback operations determined at said feed production line alarm event L-1 in combination with the distribution of observed variables of said feed production line observation data at said feed production line alarm event L comprises:

5. The method of claim 4, wherein the analyzing and generating the fault trace operations corresponding to the feed line alarm event L comprises:

6. The method of claim 1, wherein the parsing the target material mixture fault node in combination with the feed line observation data, the fault location field of the material mixture fault node, the fault location fields of the plurality of fault node relationship networks, and the fault traceback operation array comprises:

7. The method of on-line monitoring of piglet premix feed production of claim 6, wherein the parsing the combined first and second contact characteristic variables, fault location fields of the material mixing fault node, fault location fields of the plurality of fault node relationship networks, and the fault traceback operation array to generate the target material mixing fault node comprises:

8. The method of on-line monitoring of piglet premix feed production of claim 7, wherein the parsing to generate the target material mix fault node in combination with the first contact feature variable, the second contact feature variable, the saliency feature of the material mix fault node, the saliency feature of each of the fault node relationship networks, the fault location field of each of the fault node relationship networks, and the head fault traceback operation in the fault traceback operation array comprises:

9. An on-line monitoring system for the production of a pre-mixed feed of a piglet, characterized in that it comprises a processor and a machine-readable storage medium having stored therein machine-executable instructions loaded and executed by the processor to implement the on-line monitoring method for the production of a pre-mixed feed of a piglet of any one of claims 1 to 8.