Cloud-based bulk liquid storage tank information analysis method and system and storage medium

Abstract

The invention relates to the technical field of liquid batching management, and discloses a cloud-based bulk liquid storage tank information analysis method and system and a storage medium, and the method comprises the steps: S1, collecting real-time field data of a device end in real time through an edge end, and carrying out the cleaning, edge calculation and preprocessing of the real-time field data; s2, based on an MQTT protocol, establishing a bidirectional interaction data link between the device end and the factory end and a bidirectional interaction data link between the factory end and the cloud end; and S3, acquiring real-time field data of all equipment ends under the factory end through the cloud end, acquiring operation data of the factory end, and performing early warning analysis on the operation state of the factory end based on the operation data of the factory end and the real-time field data of the equipment ends. According to the method, through the process of cleaning and edge calculation of real-time field data and the process of pressure fluctuation analysis, quantitative analysis can be carried out on the pressure fluctuation risk according to comparison of the reference pressure change curve and the real-time pressure of the liquid storage tank, and pressure early warning is carried out when the risk is high.

Description

Technical Field

[0001] This application relates to the technical field of liquid batching management, and in particular to cloud-based methods, systems and storage media for analyzing information from bulk liquid storage tanks. Background Technology

[0002] In the process of animal feed production, various liquids need to be added, such as liquid methionine, lysine, choline, and oils. In the management of these liquids, it is necessary to record the liquids' entry, exit, and transfer in real time to provide complete inventory reports. With the development and application of Internet of Things (IoT) technology, the management of bulk liquids is becoming increasingly intelligent. By setting up various sensors inside and around the bulk liquid storage tanks, various data of the bulk liquid storage tanks can be monitored. At the same time, the data collected by the sensors can be processed through edge devices to realize the management process of the bulk liquid storage tanks.

[0003] Existing bulk liquid storage tank management systems mainly collect data on the feeding and discharging of bulk liquid storage tanks and monitor key environmental parameters. When environmental parameters exceed safe limits, they notify management personnel through timely warnings, enabling timely handling of risk factors and ensuring the safety of bulk liquid storage tanks. However, this method has poor monitoring accuracy and cannot promptly assess potential risks of bulk liquid storage tanks. Therefore, how to conduct accurate and timely risk analysis based on bulk liquid storage tank information is the fundamental problem that this invention aims to solve. Summary of the Invention

[0004] In order to conduct accurate and timely risk analysis based on information from bulk liquid storage tanks, this application provides a cloud-based method, system, and storage medium for analyzing information from bulk liquid storage tanks.

[0005] Firstly, this application provides a cloud-based method for analyzing information on bulk liquid storage tanks, employing the following technical solution: Cloud-based methods for analyzing information on bulk liquid storage tanks include: S1. Real-time field data is collected from the device at the edge, and the real-time field data is cleaned, edge-computed and preprocessed. S2. Establish bidirectional interactive data links between the device and the factory, and between the factory and the cloud, based on the MQTT protocol. S3. Obtain real-time field data from all equipment in the factory via the cloud, acquire factory operation data, and perform early warning analysis on the factory operation status based on the factory operation data and the real-time field data from the equipment.

[0006] By adopting the above technical solutions, accurate and timely risk analysis can be conducted based on information about bulk liquid storage tanks.

[0007] Optionally, the real-time field data includes the real-time liquid level of the liquid storage tank, the real-time pressure of the liquid storage tank, and the real-time temperature of the environment in which the liquid storage tank is located; The process of cleaning real-time field data includes: Remove invalid data from real-time field data based on preset rules; High-frequency noise in real-time field data is removed based on a low-pass filtering algorithm. Missing values ​​are handled using prefix and denominator interpolation.

[0008] By adopting the above technical solutions, invalid data is removed to ensure the accuracy of subsequent edge analysis; stable and accurate measurement values ​​are obtained through low-pass filtering; missing values ​​are processed using preceding and following value interpolation to ensure the continuity of the acquired data; and missing values ​​are estimated using adjacent data in time or sequence, which can ensure the authenticity and continuity of the acquired data.

[0009] Optionally, the process of performing edge computing on real-time field data includes: Obtain the liquid level h(t) at the current time t and the liquid level h(t-Δt) at t-Δt. Obtain the absolute value Δh of the difference between h(t) and h(t-Δt). S / △t is compared with the preset value of the liquid storage tank. When △h If S / △t is greater than the preset value of the liquid storage tank, an early warning message will be issued; where S is the cross-sectional area of ​​the liquid storage tank and △t is the unit time period.

[0010] By adopting the above technical solution, it is possible to make anomaly judgments on the feeding or discharging process of liquid storage tanks, and issue early warning information when the judgment result is abnormal, so as to realize timely handling of abnormal problems of liquid storage tanks.

[0011] Optionally, the process of performing edge computing on real-time field data also includes: The real-time pressure of the liquid storage tank is compared with the preset pressure range of the liquid storage tank. If the real-time pressure of the liquid storage tank is within the preset pressure range, pressure fluctuation analysis is performed, and a pressure warning is issued based on the pressure fluctuation analysis. If the real-time pressure of the liquid storage tank is not within the preset pressure range, a pressure warning is issued for the liquid storage tank.

[0012] By adopting the above technical solution, a real-time monitoring and early warning process for the pressure of liquid storage tanks can be achieved.

[0013] Optionally, the pressure fluctuation analysis process includes: The closing time and opening time of the breather valve of the liquid storage tank are used as the analysis period. The liquid discharge period and liquid injection period are obtained within the analysis period. The pressure change curve of the liquid discharge period is determined according to the liquid discharge rate, and the pressure change curve of the liquid injection period is determined according to the liquid injection rate. The standard pressure of the liquid storage tank is added to the pressure change curves of the liquid discharge period and the liquid injection period to obtain the first reference pressure change curve P1(t). The reference pressure change curve Pr(t) is obtained according to the first reference pressure change curve P1(t) and the real-time temperature of the environment where the liquid storage tank is located. The real-time pressure P(t) of the liquid storage tank and the reference pressure change curve Pr(t) are placed in the same coordinate system. The real-time difference between P(t) and Pr(t) at different time points is collected at fixed time intervals. The sum of squares of the real-time differences at all time points is calculated. The mean of the sum of squares at each time point is compared with the preset fluctuation threshold. When the mean of the sum of squares is greater than or equal to the preset fluctuation threshold, a pressure warning is issued.

[0014] By adopting the above technical solution, the closing time and opening time of the breather valve of the liquid storage tank are used as the analysis period. The liquid discharge period and liquid injection period are obtained within the analysis period. Based on the characteristics that the pressure changes of the liquid storage tank during the liquid discharge period and the liquid injection period are different and related to the liquid discharge rate, the relationship between the liquid discharge rate and the pressure change rate in different ranges is fitted according to the test data. The corresponding pressure change rate is determined according to the different ranges of the liquid discharge rate. Then, the pressure change curve of the liquid discharge period can be determined according to the liquid discharge rate. By comparing the real-time pressure of the liquid storage tank with the reference pressure change curve, the sum of squares and mean values ​​are obtained. The magnitude of the sum of squares and mean values ​​is used to judge the pressure fluctuation risk. When the sum of squares and mean values ​​are greater than or equal to the preset fluctuation threshold, a pressure warning is issued to notify the management personnel to promptly investigate the pressure risk of the liquid storage tank.

[0015] Optionally, the process of obtaining the reference pressure change curve Pr(t) includes: The real-time temperature of the environment where the liquid storage tank is located is compared with a preset range group. The pressure influence coefficient is determined according to the range of the real-time temperature of the environment at different times, and the pressure influence coefficient changes over time curve is obtained. The product of the first reference pressure change curve P1(t) and the pressure influence coefficient change curve over time is used as the reference pressure change curve Pr(t).

[0016] By adopting the above technical solution, based on the characteristic that temperature changes cause pressure changes in the liquid storage tank, different preset interval groups are established based on the test temperature data. Different temperature intervals correspond to different pressure influence coefficients. The real-time temperature of the environment where the liquid storage tank is located is compared with the preset interval group. The pressure influence coefficient is determined according to the interval where the real-time temperature of the environment is located at different times. Then, the pressure influence coefficient change curve over time is obtained. The product of the first reference pressure change curve and the pressure influence coefficient change curve over time is used as the reference pressure change curve, thus realizing the process of obtaining the reference pressure change curve.

[0017] Optionally, the early warning analysis process includes: Production change curves are collected from factory operation data. Consumption curves for each liquid are calculated based on real-time liquid levels and injection volumes in liquid storage tanks. Correlation coefficients between production change curves and consumption curves for each liquid are calculated. Early warning analysis of factory operation status is conducted based on the magnitude of the correlation coefficients.

[0018] By adopting the above technical solution, it is possible to conduct early warning analysis of the factory's operating status based on the magnitude of the correlation coefficient.

[0019] Secondly, this application provides a cloud-based information analysis system for bulk liquid storage tanks, employing the following technical solution: The system is a cloud-based information analysis system for bulk liquid storage tanks, wherein the system employs any one of the cloud-based information analysis methods for bulk liquid storage tanks described above.

[0020] Thirdly, this application provides a storage medium, which adopts the following technical solution: A storage medium storing a program for the cloud-based bulk liquid storage tank information analysis method described in any one of the above-mentioned methods.

[0021] In summary, this application includes at least one of the following beneficial technical effects: This invention, through the process of cleaning and edge computing of real-time field data, can promptly issue early warning information when abnormalities occur in the feeding or discharging process of liquid storage tanks, enabling timely handling of abnormal problems in liquid storage tanks. Through pressure fluctuation analysis, it can quantify the pressure fluctuation risk by comparing the reference pressure change curve with the real-time pressure of the liquid storage tank, and issue pressure warnings when the risk is high. Management personnel can conduct technical investigations into the pressure risks of liquid storage tanks to ensure their safe use. By using the correlation coefficient between the production change curve and the consumption curve of each type of liquid, it can accurately determine the abnormality of various liquid consumption states. Attached Figure Description

[0022] Figure 1This is a flowchart of the steps involved in cloud-based information analysis methods for bulk liquid storage tanks. Detailed Implementation

[0023] The embodiments of this application are described in detail below, and examples of the embodiments are shown in the accompanying drawings.

[0024] In the description of this specification, the references to "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with the described embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0025] This application discloses a cloud-based method for analyzing information on bulk liquid storage tanks, referring to... Figure 1 This includes: S1. Real-time field data from the device end is collected at the edge, and the real-time field data is cleaned, edge-computed, and preprocessed; S2. Two-way interactive data links are established between the device end and the factory end, and between the factory end and the cloud, based on the MQTT protocol; S3. Real-time field data from all devices under the factory end is obtained through the cloud, and the factory end operation data is obtained. Based on the factory end operation data and the real-time field data from the device end, the factory end operation status is analyzed and warned.

[0026] The edge computing layer includes various sensors, such as level sensors, flow sensors, pressure sensors, and temperature sensors, distributed across base stations in various feed mills. These sensors collect real-time field data from the equipment. The data is then cleaned, processed, and pre-processed using edge computing devices. Data cleaning primarily removes invalid data and high-frequency noise. Pre-defined rules, utilizing domain knowledge to set logical thresholds, are used to remove invalid data. For example, if the level data exceeds its range or is negative, it indicates an anomaly. Removing this invalid data ensures the accuracy of subsequent edge analysis. Next, a low-pass filtering algorithm removes high-frequency noise from the real-time data. The core of low-pass filtering is to allow components below a certain frequency (cutoff frequency) to pass through while significantly attenuating components above that frequency (i.e., high-frequency noise). The output signals of pressure, temperature, and level sensors often contain high-frequency electrical noise; low-pass filtering provides stable and accurate measurements. Finally, interpolation is used to process missing values, ensuring data continuity. Missing values ​​are estimated using adjacent data in time or sequence. Therefore, this process guarantees the authenticity and continuity of the acquired data.

[0027] In one embodiment, real-time field data includes real-time liquid level of the liquid storage tank, real-time pressure of the liquid storage tank, and real-time temperature of the environment in which the liquid storage tank is located. The process of performing edge computing on the real-time field data includes first obtaining the liquid level h(t) at the current time point t and the liquid level h(t-Δt) at t-Δt, where Δt is a unit time period, so t-Δt represents the time point corresponding to Δt before the current time point, obtaining the absolute value Δh of the difference between h(t) and h(t-Δt), and then... The value of S / Δt is compared with the preset value of the liquid storage tank, where S is the cross-sectional area of ​​the liquid storage tank and Δh is the cross-sectional area of ​​the liquid storage tank. S / △t reflects the injection or discharge rate of the liquid storage tank. The preset value is set according to the ultimate performance limit of the liquid storage tank. Therefore, when △h If S / △t is greater than the preset value of the liquid storage tank, it indicates that there is an abnormality in the feeding or discharging process of the liquid storage tank. Therefore, an early warning message is issued to enable timely handling of abnormal problems in the liquid storage tank.

[0028] Furthermore, regarding pressure risks in liquid storage tanks, the edge computing process for real-time field data includes comparing the real-time pressure of the liquid storage tank with its preset pressure range. This preset pressure range is set according to the performance standards of the liquid storage tank. Therefore, if the real-time pressure of the liquid storage tank is outside its preset pressure range, a pressure warning is issued. It should be noted that the liquid storage tank is equipped with a breather valve. When the real-time pressure exceeds the preset pressure range, the breather valve opens to regulate the pressure. However, if the breather valve malfunctions, the real-time pressure will continuously exceed the preset pressure range. If the real-time pressure of the liquid storage tank falls within the preset pressure range, a pressure warning is required to notify management personnel for timely handling. If the real-time pressure of the liquid storage tank falls within the preset pressure range, pressure fluctuation analysis is performed to determine whether a pressure warning should be issued. Pressure fluctuation analysis primarily assesses the stability of the liquid storage tank pressure. The specific process includes: using the closing and opening times of the liquid storage tank's breather valve as the analysis period, obtaining the outflow and injection periods within this period. Since the pressure changes during the outflow and injection periods differ and are related to the outflow rate, the pressure during the outflow period... As the pressure decreases during the liquid inlet period, the relationship between the liquid outlet rate and the pressure change rate is fitted based on the test data. The corresponding pressure change rate is determined according to the different ranges of the liquid outlet rate. Therefore, the pressure change curve during the liquid outlet period can be determined based on the liquid outlet rate. The standard pressure of the liquid storage tank is then added to the pressure change curves during the liquid outlet and injection periods to obtain the first reference pressure change curve P1(t). Simultaneously, since increases and decreases in temperature also cause changes in the pressure inside the liquid storage tank, different preset interval groups are established based on the test temperature data. Different temperature intervals correspond to different pressures. The influence coefficient is determined by comparing the real-time temperature of the environment where the liquid storage tank is located with a preset range group. The pressure influence coefficient is determined according to the range of the real-time temperature of the environment at different times, and the pressure influence coefficient changes over time curve is obtained. The product of the first reference pressure change curve P1(t) and the pressure influence coefficient change curve over time is used as the reference pressure change curve Pr(t). Therefore, the reference pressure change curve Pr(t) can reflect the normal pressure change and fluctuation in the liquid storage tank. By comparing the reference pressure change curve Pr(t) with the real-time pressure P(t) of the liquid storage tank, the analysis of pressure fluctuation risk can be realized.

[0029] The process of comparing the reference pressure change curve Pr(t) with the real-time pressure P(t) of the liquid storage tank includes: placing the real-time pressure P(t) of the liquid storage tank and the reference pressure change curve Pr(t) in the same coordinate system; collecting the real-time difference between P(t) and Pr(t) at different time points at fixed time intervals; summing the squares of the real-time differences at all time points; and comparing the mean of the sum of squares at each time point with a preset fluctuation threshold. The preset fluctuation threshold is set based on the critical data of the liquid storage tank. The larger the mean of the sum of squares, the greater the degree of fluctuation of the pressure parameter. Therefore, when the mean of the sum of squares is greater than or equal to the preset fluctuation threshold, a pressure warning is issued to notify the management personnel to promptly investigate the pressure risk of the liquid storage tank.

[0030] In one embodiment, a warning analysis process is provided, which includes: collecting production change curves from factory operation data; calculating the consumption curve of each liquid based on the real-time liquid level and injection volume of the liquid storage tank; calculating the correlation coefficient between the production change curve and the consumption curve of each liquid; since the consumption of each liquid is positively correlated with the production, the factory operation status can be warned based on the magnitude of the correlation coefficient; when the correlation coefficient approaches 1, it indicates that the consumption status of each liquid is normal; otherwise, it indicates that the consumption status of each liquid is abnormal.

[0031] This application also discloses a cloud-based information analysis system for bulk liquid storage tanks, wherein the system is any of the cloud-based information analysis methods for bulk liquid storage tanks described above.

[0032] This application also discloses a storage medium storing a program for the cloud-based bulk liquid storage tank information analysis method described in any one of the above embodiments.

[0033] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A cloud-based bulk liquid storage tank information analysis method, characterized by, include: S1. Real-time field data is collected from the device at the edge, and the real-time field data is cleaned, edge-computed and preprocessed. S2. Establish bidirectional interactive data links between the device and the factory, and between the factory and the cloud, based on the MQTT protocol. S3. Obtain real-time field data from all equipment in the factory via the cloud, acquire factory operation data, and perform early warning analysis on the factory operation status based on the factory operation data and the real-time field data from the equipment.

2. The cloud-based method for analyzing information on bulk liquid storage tanks according to claim 1, characterized in that, The real-time field data includes the real-time liquid level of the liquid storage tank, the real-time pressure of the liquid storage tank, and the real-time temperature of the environment in which the liquid storage tank is located. The process of cleaning real-time field data includes: Remove invalid data from real-time field data based on preset rules; High-frequency noise in real-time field data is removed based on a low-pass filtering algorithm. Missing values ​​are handled using prefix and denominator interpolation.

3. The cloud-based method for analyzing information on bulk liquid storage tanks according to claim 1, characterized in that, The process of performing edge computing on real-time field data includes: Obtain the liquid level h(t) at the current time t and the liquid level h(t-Δt) at t-Δt. Obtain the absolute value Δh of the difference between h(t) and h(t-Δt). S / △t is compared with the preset value of the liquid storage tank. When △h If S / △t is greater than the preset value of the liquid storage tank, an early warning message will be issued; where S is the cross-sectional area of ​​the liquid storage tank and △t is the unit time period.

4. The cloud-based method for analyzing information on bulk liquid storage tanks according to claim 3, characterized in that, The process of performing edge computing on real-time field data also includes: The real-time pressure of the liquid storage tank is compared with the preset pressure range of the liquid storage tank. If the real-time pressure of the liquid storage tank is within the preset pressure range, pressure fluctuation analysis is performed, and a pressure warning is issued based on the pressure fluctuation analysis. If the real-time pressure of the liquid storage tank is not within the preset pressure range, a pressure warning is issued for the liquid storage tank.

5. The cloud-based method for analyzing information on bulk liquid storage tanks according to claim 4, characterized in that, The process of pressure fluctuation analysis includes: The closing time and opening time of the breather valve of the liquid storage tank are used as the analysis period. The liquid discharge period and liquid injection period are obtained within the analysis period. The pressure change curve of the liquid discharge period is determined according to the liquid discharge rate, and the pressure change curve of the liquid injection period is determined according to the liquid injection rate. The standard pressure of the liquid storage tank is added to the pressure change curves of the liquid discharge period and the liquid injection period to obtain the first reference pressure change curve P1(t). The reference pressure change curve Pr(t) is obtained according to the first reference pressure change curve P1(t) and the real-time temperature of the environment where the liquid storage tank is located. The real-time pressure P(t) of the liquid storage tank and the reference pressure change curve Pr(t) are placed in the same coordinate system. The real-time difference between P(t) and Pr(t) at different time points is collected at fixed time intervals. The sum of squares of the real-time differences at all time points is calculated. The mean of the sum of squares at each time point is compared with the preset fluctuation threshold. When the mean of the sum of squares is greater than or equal to the preset fluctuation threshold, a pressure warning is issued.

6. The cloud-based method for analyzing information on bulk liquid storage tanks according to claim 5, characterized in that, The process of obtaining the reference pressure change curve Pr(t) includes: The real-time temperature of the environment where the liquid storage tank is located is compared with a preset range group. The pressure influence coefficient is determined according to the range of the real-time temperature of the environment at different times, and the pressure influence coefficient changes over time curve is obtained. The product of the first reference pressure change curve P1(t) and the pressure influence coefficient change curve over time is used as the reference pressure change curve Pr(t).

7. The cloud-based method for analyzing information on bulk liquid storage tanks according to claim 2, characterized in that, The early warning analysis process includes: Production change curves are collected from factory operation data. Consumption curves for each liquid are calculated based on real-time liquid levels and injection volumes in liquid storage tanks. Correlation coefficients between production change curves and consumption curves for each liquid are calculated. Early warning analysis of factory operation status is conducted based on the magnitude of the correlation coefficients.

8. A cloud-based information analysis system for bulk liquid storage tanks, characterized in that: The system employs the cloud-based bulk liquid storage tank information analysis method as described in any one of claims 1-7.

9. A storage medium, characterized in that, The program stores a cloud-based method for analyzing information on bulk liquid storage tanks as described in any one of claims 1-7.

Images