CN-122022255-A - Grain and oil production line tracking detection method and system

CN122022255ACN 122022255 ACN122022255 ACN 122022255ACN-122022255-A

Abstract

The invention provides a grain and oil production line tracking detection method and system, and relates to the technical field of grain and oil production data analysis. The method comprises the steps of collecting historical grain and oil production data of a plurality of partitions in a grain and oil production line based on Internet of things equipment, and constructing a local accumulation chain of each partition. The method comprises the steps of identifying production acceleration events in historical grain and oil production data, generating congestion resistance data of each partition, carrying out real-time congestion detection on a plurality of partitions in a grain and oil production line, determining the production deviation state of each partition, constructing a real-time accumulation chain of each partition, determining candidate abnormal partitions, carrying out congestion diffusion influence detection on each candidate abnormal partition according to the congestion resistance data, and obtaining a congestion diffusion detection result of the grain and oil production line. The invention improves the accuracy and the reliability of the congestion detection of the grain and oil production line.

Inventors

WAN WENXIA
WANG ZHUOQIN
SUN QIULIAN

Assignees

江西工业贸易职业技术学院(江西省粮食干部学校、江西省粮食职工中等专业学校)

Dates

Publication Date: 20260512
Application Date: 20251225

Claims (7)

1. The grain and oil production line tracking and detecting method is characterized by comprising the following steps of: Collecting historical grain and oil production data of a plurality of partitions in a grain and oil production line based on Internet of things equipment, extracting product receiving data and product output data of each partition according to the historical grain and oil production data, and constructing a local accumulation chain of each partition based on the product receiving data and the product output data; Identifying production acceleration events in historical grain and oil production data by combining local accumulation chains, extracting the congestion response rate and the congestion response duration of each production acceleration event, and generating congestion resistance data of each partition according to the congestion response rate and the congestion response duration; real-time congestion detection is carried out on a plurality of subareas in the grain and oil production line, real-time grain and oil production data of each subarea are collected, a receiving interval sequence and an output interval sequence of each subarea are constructed, and the production deviation state of each subarea is determined based on the receiving interval sequence and the output interval sequence; And constructing a real-time accumulation chain of each partition according to the real-time grain and oil production data, determining candidate abnormal partitions based on the production deviation state and the real-time accumulation chain, and detecting the congestion diffusion influence of each candidate abnormal partition according to the congestion resistance data to obtain a congestion diffusion detection result of the grain and oil production line.
2. The grain and oil production line tracking detection method according to claim 1, wherein extracting the congestion response rate and the congestion response duration of each production acceleration event, and generating the congestion resistance data of each partition according to the congestion response rate and the congestion response duration comprises: The local accumulation chain comprises accumulation work-in-process quantity of the partitions in the plurality of sliding windows, partition basic production rate of each partition in the plurality of sliding windows is determined according to historical grain and oil production data, work-in-process accumulation rate of each sliding window is calculated based on the local accumulation chain, a plurality of abnormal windows of each partition are determined according to the partition basic production rate and the work-in-process accumulation rate, and a plurality of production acceleration events of each partition are constructed; The method comprises the steps of extracting the peak production rate of each production acceleration event as the congestion response rate of the production acceleration event, determining the duration of the production acceleration event under the peak production rate, obtaining the congestion response duration of the production acceleration event, aggregating the congestion response rates and the congestion response durations of a plurality of production acceleration events in the partitions, and generating congestion resistance data of each partition, wherein the congestion resistance data comprise short-term acceleration production rate and short-term acceleration production duration.
3. The grain and oil production line tracking detection method according to claim 2, wherein determining the production deviation status of each partition based on the reception interval sequence and the output interval sequence comprises: Each element in the receiving interval sequence is the difference value of the receiving rate of the product receiving data in the two adjacent sliding windows, and each element in the output interval sequence is the difference value of the output rate of the product output data in the two adjacent sliding windows; Calculating a receiving interval variation parameter of the subarea according to the receiving interval sequence, calculating an output interval variation parameter of the subarea according to the output interval sequence, detecting the production rhythm difference of the subarea based on the receiving interval sequence and the output interval sequence, calculating a production rhythm disorder parameter of the subarea, determining a production congestion state parameter of the subarea based on the receiving interval variation parameter, the output interval variation parameter and the production rhythm disorder parameter, and outputting production deviation state information of each subarea.
4. The grain and oil production line tracking detection method according to claim 3, wherein determining candidate abnormal partitions based on the production deviation state and the real-time accumulation chain, and performing congestion diffusion influence detection on each candidate abnormal partition according to congestion resistance data comprises: calculating the real-time accumulation rate of each partition according to the real-time accumulation chain, and carrying out abnormal marking on a plurality of partitions by combining the real-time accumulation rate of the partitions and the production congestion state parameters to obtain a plurality of candidate abnormal partitions; Determining a diffusion influence partition of each candidate abnormal partition, determining a congestion diffusion influence monitoring window and a diffusion influence yield of the candidate abnormal partition according to congestion resistance data of the diffusion influence partition, performing sliding influence monitoring on the candidate abnormal partition based on the congestion diffusion influence monitoring window, and generating diffusion influence early warning data of the candidate abnormal partition according to the diffusion influence yield.
5. The grain and oil production line tracking detection method according to claim 4, wherein the sliding influence monitoring is performed on the candidate abnormal partition based on the congestion diffusion influence monitoring window, and the generating diffusion influence early warning data of the candidate abnormal partition in combination with the diffusion influence yield comprises: And carrying out sliding window processing on the real-time grain and oil production data of the candidate abnormal partition based on the congestion diffusion influence monitoring window, calculating local yields of the real-time grain and oil production data in the areas of the plurality of congestion diffusion influence monitoring windows, and if the difference value between the diffusion influence yields of the candidate abnormal partition and the local yields is detected to be smaller than the diffusion influence early warning threshold value, generating diffusion influence early warning data of the candidate abnormal partition.
6. A grain and oil production line tracking and detecting method according to claim 3, wherein a cross correlation coefficient between the reception interval sequence and the output interval sequence of the partition is calculated as the production rhythm disorder parameter of the partition.
7. A grain and oil production line tracking and detecting system, characterized in that the system is used for realizing the grain and oil production line tracking and detecting method according to any one of claims 1-6, comprising: The grain and oil production data preprocessing module is used for acquiring historical grain and oil production data of a plurality of partitions in the grain and oil production line based on the Internet of things equipment, extracting product receiving data and product output data of each partition according to the historical grain and oil production data, and constructing a local accumulation chain of each partition based on the product receiving data and the product output data; The congestion resistance analysis module is used for identifying production acceleration events in the historical grain and oil production data by combining the local accumulation chains, extracting the congestion response rate and the congestion response duration of each production acceleration event, and generating congestion resistance data of each partition according to the congestion response rate and the congestion response duration; The production state deviation recognition module is used for carrying out real-time congestion detection on a plurality of subareas in the grain and oil production line, collecting real-time grain and oil production data of each subarea, constructing a receiving interval sequence and an output interval sequence of each subarea, and determining the production deviation state of each subarea based on the receiving interval sequence and the output interval sequence; The congestion diffusion detection module is used for constructing a real-time accumulation chain of each partition according to the real-time grain and oil production data, determining candidate abnormal partitions based on the production deviation state and the real-time accumulation chain, and detecting the congestion diffusion influence of each candidate abnormal partition according to the congestion resistance data to obtain a congestion diffusion detection result of the grain and oil production line.

Description

Grain and oil production line tracking detection method and system Technical Field The invention relates to the technical field of grain and oil production data analysis, in particular to a grain and oil production line tracking detection method and system. Background In the grain and oil production process, the production line is generally composed of a plurality of subareas in sequence, each subarea corresponds to different working procedures, such as cleaning, processing, cooling, split charging and the like, and the continuity and stability of the production line are critical to the production efficiency and the product quality. The same upstream input may produce different congestion responses in different partitions due to differences in factors such as process differences in each partition, equipment automation level, manual operating efficiency, and buffer capacity limitations. For example, for the same number of product stacks, a highly automated partition may be able to quickly digest backlog, while a lower automation or higher manual operation ratio partition may quickly reach an upper processing limit, resulting in product line delays, blocked downstream processes, and even affecting overall throughput and product quality. The partial production line monitoring and congestion detection methods treat each partition as the same processing unit, lack effective quantification on production capacity differences of different partitions, and cannot accurately judge whether congestion of one partition affects a downstream partition when the uncertainty such as transportation delay, buffer area retention and the like is faced, so that early warning delay or excessive intervention can be caused. How to accurately identify the actual processing capacity of a partition in a congestion state and the influence of the partition on a downstream partition on the premise of considering the production characteristic difference of each partition becomes a key problem of improving the real-time monitoring level of a production line and optimizing production scheduling. Disclosure of Invention In order to solve the technical problems, the invention provides a grain and oil production line tracking detection method for analyzing congestion response levels of different partitions based on historical data, and the potential congestion state of the partitions and the potential influence of the potential congestion state on the downstream are identified, so that a reliable basis is provided for real-time congestion early warning and scheduling optimization of the production line. In order to achieve the above purpose, the present invention provides the following technical solutions: a grain and oil production line tracking detection method comprises the following steps: Collecting historical grain and oil production data of a plurality of partitions in a grain and oil production line based on Internet of things equipment, extracting product receiving data and product output data of each partition according to the historical grain and oil production data, and constructing a local accumulation chain of each partition based on the product receiving data and the product output data; Identifying production acceleration events in historical grain and oil production data by combining local accumulation chains, extracting the congestion response rate and the congestion response duration of each production acceleration event, and generating congestion resistance data of each partition according to the congestion response rate and the congestion response duration; real-time congestion detection is carried out on a plurality of subareas in the grain and oil production line, real-time grain and oil production data of each subarea are collected, a receiving interval sequence and an output interval sequence of each subarea are constructed, and the production deviation state of each subarea is determined based on the receiving interval sequence and the output interval sequence; And constructing a real-time accumulation chain of each partition according to the real-time grain and oil production data, determining candidate abnormal partitions based on the production deviation state and the real-time accumulation chain, and detecting the congestion diffusion influence of each candidate abnormal partition according to the congestion resistance data to obtain a congestion diffusion detection result of the grain and oil production line. Preferably, extracting the congestion response rate and the congestion response time length of each production acceleration event, and generating the congestion resistance data of each partition according to the congestion response rate and the congestion response time length includes: The local accumulation chain comprises accumulation work-in-process quantity of the partitions in the plurality of sliding windows, partition basic production rate of each partition in the plurality of sliding windows is determi