CN-122022338-A - Product processing data acquisition method and system based on sensor

CN122022338ACN 122022338 ACN122022338 ACN 122022338ACN-122022338-A

Abstract

The application relates to the technical field of industrial data acquisition, in particular to a sensor-based product processing data acquisition method and system, wherein the method comprises the steps of acquiring operation parameters of stirring equipment at each moment in each fermentation process at a preset high sampling rate in raw material fermentation of product processing, wherein the operation parameters at least comprise output power and vibration data; the method comprises the steps of calculating fluctuation coefficients of all operation parameters in each fermentation process to obtain coupling fluctuation degree of each fermentation process, calculating time domain evaluation values of each fermentation process, calculating frequency domain evaluation values of each fermentation process to obtain comprehensive evaluation values representing the integral vibration abnormality of equipment, and determining state discrimination values representing the instability of the operation state of the equipment to select and execute different data storage strategies. The application greatly reduces the data storage and transmission load on the premise of ensuring that the key data information is not lost.

Inventors

YANG BAOJUN
ZHANG HU
ZHAO QILEI
DONG CHUNYU

Assignees

天津全津食品有限公司

Dates

Publication Date: 20260512
Application Date: 20260130

Claims (10)

1. The product processing data acquisition method based on the sensor is characterized by comprising the following steps of: In the raw material fermentation of product processing, acquiring operation parameters of stirring equipment at each moment in each fermentation process at a preset high sampling rate, wherein the operation parameters at least comprise output power and vibration data; For each operation parameter, analyzing fluctuation characteristics of the operation parameters, which change in a single fermentation process, calculating fluctuation coefficients of each operation parameter in each fermentation process, and combining the change cooperativity of different operation parameters to obtain the coupling fluctuation degree of each fermentation process; calculating a frequency domain evaluation value of each fermentation process according to the concentration of energy distribution of vibration data on a frequency domain, and combining the time domain evaluation value to obtain a comprehensive evaluation value representing the integral vibration abnormality of equipment; And aiming at the current fermentation process, analyzing the trend change, the coupling fluctuation degree and the difference of the comprehensive evaluation value of vibration data between the current fermentation process and the adjacent fermentation process, and determining a state discrimination value for representing the instability of the running state of equipment so as to select and execute different data storage strategies.
2. The sensor-based product processing data collection method of claim 1, wherein said calculating the fluctuation coefficient of each operating parameter during each fermentation process comprises: calculating the discrete degree of the data of each operation parameter at all moments in each fermentation process; forward fusion is carried out on the difference of the data of all adjacent two moments under each operation parameter, so as to obtain the relative variation of each operation parameter; Calculating the difference between the data of each operation parameter at the first moment and the data at the last moment as the overall trend quantity; the fluctuation coefficient is the result of forward fusion of the discrete degree, the relative variation and the overall trend.
3. The sensor-based product processing data acquisition method of claim 1, wherein said deriving the coupling variability for each fermentation process comprises: calculating the output power and the correlation degree of vibration data at all moments in each fermentation process; and the coupling fluctuation degree and the fluctuation coefficient and the correlation degree of all the operation parameters are in positive correlation.
4. The sensor-based product processing data collection method of claim 1, wherein the calculating a time domain estimate for each fermentation process comprises: Aiming at each fermentation process, obtaining extreme points of vibration data at all moments, and carrying out forward fusion on differences of the vibration data corresponding to all two adjacent extreme points to serve as fluctuation difference quantity; marking the time corresponding to the maximum point as a significant time, counting the time interval between each significant time and the adjacent significant time, and carrying out forward fusion on the difference of the time intervals of all the two adjacent significant times to serve as an interval difference amount; and the time domain evaluation value and the fluctuation difference amount and the interval difference amount are in positive correlation.
5. The sensor-based product processing data collection method of claim 1, wherein the calculating the frequency domain estimate for each fermentation process comprises: Carrying out frequency domain analysis on vibration data at all moments in each fermentation process to obtain a spectrogram; Calculating the blade passing frequency of the fan blade in the stirring shaft, defining the blade passing frequency as a fundamental frequency, marking frequency components corresponding to all integer multiples of the fundamental frequency in a spectrogram as harmonic components, and calculating the sum of energy corresponding to all frequency components in the spectrogram as total energy; and counting the duty ratio of the sum value of the energy corresponding to the fundamental frequency and all harmonic components in the frequency chart in the total energy, and taking the duty ratio as a frequency domain evaluation value of each fermentation process.
6. The sensor-based product processing data acquisition method of claim 1, wherein the integrated evaluation value is in positive correlation with both the time domain evaluation value and the frequency domain evaluation value.
7. The sensor-based product processing data collection method of claim 1, wherein the calculating process of the state discrimination value is: Calculating the difference of vibration data at all moments between the current fermentation process and the previous fermentation process, and marking the difference as trend difference; respectively calculating the coupling fluctuation degree and the difference of the comprehensive evaluation value between the current fermentation process and the previous fermentation process, and respectively marking the differences as fluctuation differences and abnormal differences; the state discrimination value of the current fermentation process is the result of forward fusion of trend difference, fluctuation difference and abnormal difference.
8. The method of claim 1, wherein selecting and executing different data storage strategies includes executing a high-resolution storage strategy if the normalized state discrimination value is greater than or equal to a predetermined threshold, and executing a low-resolution storage strategy otherwise.
9. The sensor-based product processing data acquisition method of claim 8, wherein the high-resolution storage strategy is to directly transmit and store the raw data of the current fermentation process, and the low-resolution storage strategy is to downsample the raw data of the current fermentation process, and transmit and store the downsampled raw data.
10. Sensor-based product processing data acquisition system comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor implements the steps of the sensor-based product processing data acquisition method according to any one of claims 1-9 when the computer program is executed.

Description

Product processing data acquisition method and system based on sensor Technical Field The application relates to the technical field of industrial data acquisition, in particular to a sensor-based product processing data acquisition method and system. Background In product processing, monitoring the operation state of key equipment is an important means for guaranteeing process stability and product quality, and potential equipment faults are identified and prevented in advance by monitoring the operation state of the key equipment. However, the traditional collection mode of the equipment operation data generally carries out data collection through fixed sampling frequency, but because the quantity of equipment needing to be monitored and collected in a production scene is too large, if the lower sampling frequency is adopted, when the state is changed severely or abnormal occurs, key transient information is lost possibly due to insufficient sampling frequency, so that equipment faults and other conditions are not timely or accurately identified, and if the higher sampling frequency is adopted, huge data quantity and high transmission and storage cost are caused. Disclosure of Invention In order to solve the technical problems, a method and a system for acquiring product processing data based on a sensor are provided to solve the existing problems. The application provides a method and a system for acquiring product processing data based on a sensor, which comprise the following steps: in a first aspect, an embodiment of the present application provides a method for collecting sensor-based product processing data, the method comprising the steps of: In the raw material fermentation of product processing, acquiring operation parameters of stirring equipment at each moment in each fermentation process at a preset high sampling rate, wherein the operation parameters at least comprise output power and vibration data; For each operation parameter, analyzing fluctuation characteristics of the operation parameters, which change in a single fermentation process, calculating fluctuation coefficients of each operation parameter in each fermentation process, and combining the change cooperativity of different operation parameters to obtain the coupling fluctuation degree of each fermentation process; calculating a frequency domain evaluation value of each fermentation process according to the concentration of energy distribution of vibration data on a frequency domain, and combining the time domain evaluation value to obtain a comprehensive evaluation value representing the integral vibration abnormality of equipment; And aiming at the current fermentation process, analyzing the trend change, the coupling fluctuation degree and the difference of the comprehensive evaluation value of vibration data between the current fermentation process and the adjacent fermentation process, and determining a state discrimination value for representing the instability of the running state of equipment so as to select and execute different data storage strategies. Preferably, the calculating the fluctuation coefficient of each operation parameter in each fermentation process includes: calculating the discrete degree of the data of each operation parameter at all moments in each fermentation process; forward fusion is carried out on the difference of the data of all adjacent two moments under each operation parameter, so as to obtain the relative variation of each operation parameter; Calculating the difference between the data of each operation parameter at the first moment and the data at the last moment as the overall trend quantity; the fluctuation coefficient is the result of forward fusion of the discrete degree, the relative variation and the overall trend. Preferably, the obtaining the coupling fluctuation degree of each fermentation process includes: calculating the output power and the correlation degree of vibration data at all moments in each fermentation process; and the coupling fluctuation degree and the fluctuation coefficient and the correlation degree of all the operation parameters are in positive correlation. Preferably, the calculating the time domain evaluation value of each fermentation process includes: Aiming at each fermentation process, obtaining extreme points of vibration data at all moments, and carrying out forward fusion on differences of the vibration data corresponding to all two adjacent extreme points to serve as fluctuation difference quantity; marking the time corresponding to the maximum point as a significant time, counting the time interval between each significant time and the adjacent significant time, and carrying out forward fusion on the difference of the time intervals of all the two adjacent significant times to serve as an interval difference amount; and the time domain evaluation value and the fluctuation difference amount and the interval difference amount are in positive correlation