CN-120851362-B - Dynamic weighing and data tracing method and system for Internet of things

CN120851362BCN 120851362 BCN120851362 BCN 120851362BCN-120851362-B

Abstract

The invention discloses a method and a system for dynamic weighing and data tracing of the Internet of things, which relate to the technical field of industrial Internet data processing and comprise the steps of acquiring dynamic weighing data of a weighing event and at least one group of auxiliary data synchronous with the dynamic weighing data; the method comprises the steps of generating a reliability weight value for dynamic weighing data through a preset reliability model based on auxiliary data, carrying out weighted statistical analysis on one or more dynamic weighing data based on the weight value to obtain a weighted statistical analysis result, fusing the weighted statistical analysis result and the change trend of the reliability weight value, carrying out two-dimensional fusion diagnosis to obtain a diagnosis result capable of accurately decoupling a problem root, and generating a high reliability traceability record or issuing a control instruction according to the diagnosis result. The invention realizes the intelligent distinction between the production process abnormality and the measurement system abnormality through the real-time quantification and management of the data reliability, and improves the reliability of the dynamic weighing system and the value of the traceable data.

Inventors

WANG BIN
ZHOU YUHUA
WANG WENJIE

Assignees

无锡西奈信息系统有限公司

Dates

Publication Date: 20260512
Application Date: 20250709

Claims (7)

1. The method for dynamically weighing and tracing data of the Internet of things is characterized by comprising the following steps of: Acquiring dynamic weighing data of a weighing event and at least one set of auxiliary data synchronous with the dynamic weighing data, wherein the at least one set of auxiliary data comprises a set of environmental state data used for representing the state of a measuring environment; based on the at least one group of auxiliary data, extracting auxiliary feature vectors, judging whether the auxiliary feature vectors meet rule conditions or not by traversing a preset attenuation rule base, executing corresponding attenuation operation, and generating a credibility weight value for the dynamic weighing data; based on the credibility weight value, carrying out weighted statistical analysis on one or more dynamic weighing data to obtain a weighted statistical analysis result; and fusing the weighted statistical analysis result and the credibility weight value to perform two-dimensional fusion diagnosis, wherein the performing of the two-dimensional fusion diagnosis comprises the following steps: When the weighted statistical analysis result shows that the process is abnormal and the credibility weight value is in a preset high credibility interval, determining that the diagnosis result is abnormal in the production process; When the weighted statistical analysis result shows that the process is abnormal and the credibility weight value is in a preset low credibility interval, determining that the diagnosis result is abnormal of the measurement system; And generating a traceability record or a control instruction according to the diagnosis result.
2. The method of claim 1, wherein the environmental status data comprises at least one of environmental vibration data, environmental acoustic data, temperature data, or humidity data, and the device status data comprises at least one of weighing device calibration status data, runtime data, or load history data.
3. The method for dynamic weighing and data tracing of the internet of things according to claim 1, wherein the step of performing weighted statistical analysis comprises the steps of: calculating a weighted average value or a weighted standard deviation of one or more dynamic weighing data according to the credibility weight value; and generating a weighted statistical process control diagram based on the weighted average or the weighted standard deviation.
4. The method for dynamic weighing and data tracing of Internet of things according to claim 3, wherein obtaining a weighted statistical analysis result further comprises applying at least one weighted adaptive criterion to judge a process state based on the weighted statistical process control diagram, wherein the weighted adaptive criterion additionally introduces consideration of the credibility weight value corresponding to one or more data points based on the classical criterion.
5. The method for dynamic weighing and data tracing of the internet of things according to claim 1, wherein the performing of the two-dimensional fusion diagnosis further comprises determining that the diagnosis result is a potential risk warning of the measurement system when the weighted statistical analysis result does not show process anomalies but the reliability weight value shows a decreasing trend or is in the preset low reliability interval.
6. The method for dynamically weighing and tracing data of the internet of things according to claim 1, wherein the generating of the tracing record comprises the steps of correlating the dynamic weighing data, the credibility weight value and the diagnosis result and storing the correlated dynamic weighing data, the credibility weight value and the diagnosis result into a tracing database to form a high-credibility tracing data chain.
7. The system for dynamic weighing and data tracing of the internet of things is characterized in that the system is used for executing the method for dynamic weighing and data tracing of the internet of things according to any one of claims 1-6, and comprises the following steps: The data acquisition module is used for acquiring dynamic weighing data of a weighing event and at least one group of auxiliary data synchronous with the dynamic weighing data; The weight generation module is used for extracting auxiliary feature vectors based on the at least one group of auxiliary data, judging whether the auxiliary feature vectors meet rule conditions or not by traversing a preset attenuation rule base, executing corresponding attenuation operation and generating credibility weight values for the dynamic weighing data; the analysis module is used for carrying out weighted statistical analysis on one or more dynamic weighing data based on the credibility weight value to obtain a weighted statistical analysis result; the diagnosis module is used for fusing the weighted statistical analysis result and the credibility weight value, and performing two-dimensional fusion diagnosis to obtain a diagnosis result; And the decision management module is used for generating a traceability record or a control instruction according to the diagnosis result.

Description

Dynamic weighing and data tracing method and system for Internet of things Technical Field The invention relates to the technical field of industrial Internet of things data processing, in particular to an Internet of things dynamic weighing and data tracing method and system. Background In modern automatic production lines, in particular in the manufacturing process of high-value products such as medicines, precise electronic components and the like, on-line dynamic weighing is a key quality control link. However, the prior art generally has a fundamental "diagnostic blind zone", wherein when weighing data is abnormal, the system cannot effectively distinguish whether the source of the abnormality is from "real fluctuation of the production process" or from "problems of the measuring system itself". The ambiguity causes huge economic loss, and in some high-value production lines, only the vibration interference cannot be effectively distinguished from insufficient filling quantity, the qualified products caused by each month are rejected by mistake and lost, and unnecessary production line shutdown check is caused for a plurality of times, so that the production efficiency and the quality control level are seriously affected. Disclosure of Invention The invention aims to provide a method and a system for dynamic weighing and data tracing of the Internet of things, which realize real-time quantification and management of the reliability of measured data and conduct intelligent root-cause diagnosis based on the method, so as to solve the problems that the quality of the data cannot be evaluated and the dimension of fault diagnosis is single in the prior art. In view of the foregoing, in a first aspect, the present invention provides a method for dynamic weighing and data tracing of the internet of things, including: Acquiring dynamic weighing data of a weighing event and at least one group of auxiliary data synchronous with the dynamic weighing data; Generating a credibility weight value for the dynamic weighing data through a preset credibility model based on the at least one group of auxiliary data; based on the credibility weight value, carrying out weighted statistical analysis on one or more dynamic weighing data to obtain a weighted statistical analysis result; fusing the weighted statistical analysis result and the credibility weight value, and performing two-dimensional fusion diagnosis to obtain a diagnosis result; And generating a traceability record or a control instruction according to the diagnosis result. In a second aspect, the present invention further provides an internet of things dynamic weighing and data tracing system, including: The data acquisition module is used for acquiring dynamic weighing data of a weighing event and at least one group of auxiliary data synchronous with the dynamic weighing data; The weight generation module is used for generating a credibility weight value for the dynamic weighing data through a preset credibility model based on the at least one group of auxiliary data; the analysis module is used for carrying out weighted statistical analysis on one or more dynamic weighing data based on the credibility weight value to obtain a weighted statistical analysis result; the diagnosis module is used for fusing the weighted statistical analysis result and the credibility weight value, and performing two-dimensional fusion diagnosis to obtain a diagnosis result; And the decision management module is used for generating a traceability record or a control instruction according to the diagnosis result. The technical scheme provided by the application has at least the following technical effects or advantages: according to the invention, a quantized credibility weight value is added for each piece of weight data, so that the data quality in a traceable chain can be objectively evaluated. When quality inspection is performed, the generation environment and the confidence coefficient of the data can be clearly known, and a firmer data basis is provided for decision making. The two-dimensional diagnosis logic can effectively distinguish whether the problem source comes from fluctuation of the production process or from faults or interference of the measurement system. This avoids ambiguity in conventional diagnostics, can guide more accurate maintenance and process adjustments, and reduces unnecessary downtime. By means of the weighted statistical analysis method, the system can automatically reduce the influence of low-reliability data in statistical calculation. The process control analysis can effectively inhibit noise interference such as environmental vibration, and the analysis result can more truly reflect the internal state of the production process, so that false alarm is reduced. By monitoring the long-term trend of the credibility weight value, the invention can provide early warning before the performance of the measurement system is obviously reduced or the measur