Production progress data acquisition method and system

Abstract

The invention relates to the field of data processing, in particular to a production progress data acquisition method and system. The method comprises the following steps: drawing a product quantity curve; presetting the length of the filtering window and the sliding step length of the filtering window; determining the relative fluctuation degree of each data point in the filtering window; determining the oscillation rate of the data segment of the filtering window; determining a loop characteristic of the data segment of the filtering window; the filtering window is optimized; and completing production schedule data acquisition. Due to factors such as market trend or manual operation, the production quantity has accidental peak or valley, the production schedule data comprises various periodic, trending and non-periodic changes and the like, the length of the optimized filtering window can be adjusted according to the local characteristics of the data, the trending and periodicity can be better smoothed, and the production schedule can be optimized. The accuracy of the pre-estimated plan completion time is improved, and the accuracy of the production progress data is further improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and particularly to a method and system for collecting production progress data. Background Art

[0002] With the continuous progress of society and the rapid development of technology, informatization and digitalization have penetrated into all aspects of industrial production. In this context, real-time monitoring of production progress and accurate data collection are particularly important. Traditional methods for collecting production progress data often have problems such as low efficiency and inaccurate data, and cannot meet the requirements of modern industrial production for efficient and precise management. Therefore, developing a new method and system for collecting production progress data has become an urgent need in the industry.

[0003] The patent document with the publication number CN106780826A discloses an automatic industrial production data collection system and method. By configuring a data collector and at least one motion sensor on each machine tool, the motion sensor is used to detect the motion trajectory and motion acceleration of the product on the current machine tool; the data collector performs real-time tracking and total quantity statistics on the product quantity of the current machine tool according to the motion trajectory and motion acceleration; the remote server is used to perform real-time tracking and total quantity statistics on the product quantities of all machine tools; during production, the data collector determines whether the actual motion trajectory and motion acceleration match the pre-stored simulated motion trajectory and motion acceleration. If they match, the product quantity is counted.

[0004] The production progress data can be intuitively reflected by the production quantity. During the process of an enterprise collecting production data, the completion time of the production plan is predicted based on the relationship between the current production quantity and the target task quantity, so as to obtain the production progress. However, due to factors such as market trends or human operations, there are occasional peaks or valleys in the production quantity, and this production trend will affect the accuracy of predicting the planned completion time. Therefore, during the process of predicting the planned completion time, it is necessary to perform filtering processing on it to smooth the trend. And during the process of using filtering to smooth the data, the length of the filtering window is a very important parameter, and the selection of the filtering window length will affect the final smoothing effect. The production progress data in different stages of production activities may lead to different change trends in the production quantity data. A fixed window length may cause overfitting or underfitting in some cases, affecting the authenticity of the data. Summary of the Invention

[0005] In order to solve the problem that the occasional peaks or valleys in the production quantity affect the accuracy of predicting the planned completion time, the present invention provides a method and system for collecting production progress data.

[0006] In a first aspect, the present invention provides a method for collecting production progress data, adopting the following technical solution: A method for collecting production progress data includes: plotting a product quantity curve, where each data point on the product quantity curve represents the quantity of products produced within each time period; presetting the length of a filtering window, with the sliding step length of the filtering window being equal to the length of the filtering window, and taking all the data points within the current filtering window as a data segment; determining the relative fluctuation degree of each data point based on the difference between each data point within the data segment and the mean value of the data points within this data segment, as well as the range of the data points within this data segment, where the relative fluctuation degree is positively correlated with the difference and negatively correlated with the range; when the relative fluctuation degree of a certain data point exceeds the mean value of the relative fluctuation degrees of the data points within this data segment, this data point is a fluctuation point; determining the oscillation rate of the data segment based on the number of fluctuation points within the data segment, where the oscillation rate is positively correlated with the number of fluctuation points; taking this data segment and its two adjacent data segments as data samples, performing clustering on the data samples, and marking the cluster containing data points from at least two data segments in the clustering result as a diversity cluster; taking the proportion of the number of diversity clusters in the total number of clusters as the cyclic feature of this data segment; optimizing the filtering window based on the oscillation rate and the cyclic feature, where the length of the optimized filtering window is positively correlated with the oscillation rate and the cyclic feature; filtering the data points according to the optimized filtering window, and performing a quantitative assessment of the production progress based on the filtered data points to complete the collection of production progress data.

[0007] The beneficial effects are as follows: By dynamically adjusting the filtering window to adapt to the fluctuation characteristics and periodic patterns of different production links, the pertinence and accuracy of data filtering are improved, ensuring the robustness of production progress assessment; by identifying the oscillation rate and cyclic feature of the data segment, effective identification of abnormal fluctuations in the production process and capture of periodic laws are achieved, optimizing the response speed and flexibility of production scheduling; comprehensively using clustering analysis to identify diversity clusters enhances the reliability of trend prediction in complex production scenarios, thereby accurately guiding the allocation of production resources and progress control, and improving the overall production efficiency and management level.

[0008] Further, the relative fluctuation degree of the data point satisfies the following relational expression: , where in the formula, is the relative fluctuation degree of the data point within the current filtering window, is the value of the data point within the current filtering window, is the mean value of the data points within the data segment of the current filtering window, is the maximum value of the data points within the data segment of the current filtering window, is the minimum value of the data points within the data segment of the current filtering window.

[0009] The beneficial effects are as follows: By calculating the ratio of the deviation of each data point from the mean within the window to the range of all data within the window, the relative fluctuation degree of the data points is quantified, which is conducive to accurately identifying abnormal fluctuation points in the production process, thereby improving the accuracy and efficiency of production data analysis.

[0010] Further, the oscillation rate of the data segment satisfies the following relational expression: , where is the oscillation rate of the data segment of the current filtering window, is the number of fluctuation points within the data segment of the current filtering window, is the number of data points within the data segment of the current filtering window.

[0011] The beneficial effects are as follows: By calculating the ratio of the fluctuation points within the data segment to determine the oscillation rate, it effectively reflects the instability degree of the production process, provides a quantitative evaluation index for production fluctuation management and optimization, and is conducive to timely adjusting production strategies and improving production efficiency.

[0012] Further, k-means clustering is adopted for the clustering.

[0013] Further, the length of the optimized filtering window satisfies the following relational expression: , where is the length of the optimized filtering window, is the length of the current filtering window, is the oscillation rate of the data segment of the current filtering window, is the cyclic feature of the data segment of the current filtering window, is the ceiling function, is the normalization function.

[0014] The beneficial effects are as follows: By dynamically adjusting the length of the filtering window by combining the oscillation rate and the cyclic feature, the adaptive matching of different fluctuation characteristics and periodicity in the production process is realized, thereby improving the pertinence of data filtering and the accuracy of production progress prediction.

[0015] Further, SG filtering is adopted for the filtering.

[0016] Furthermore, the quantitative evaluation of the production progress based on the filtered data points includes: based on the filtered data points, taking the day as the unit, obtaining the sum of the filtered data points for each day, that is, the total production quantity, forming a sequence with the total production quantity of each day, performing exponential smoothing prediction on the sequence to obtain the future daily production quantity, successively accumulating the total production quantity of each day and the future daily production quantity, stopping the accumulation when the accumulated value is not less than the target task quantity, at this time the date corresponding to the last daily production quantity is the expected completion time of the production target, and obtaining the production progress data according to the total production quantity and the expected completion time of the production target, thus completing the collection of production progress data.

[0017] The beneficial effects are as follows: By filtering to improve data quality and combining exponential smoothing prediction to accurately estimate the production completion time, the refined prediction management of production progress is realized, the adaptability and execution of the production plan are improved, and the production scheduling and decision-making optimization are effectively supported.

[0018] In the second aspect, the present invention provides a production progress data acquisition system, adopting the following technical solution: A production progress data acquisition system includes: a processor and a memory, and the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned production progress data acquisition method is implemented.

[0019] By adopting the above technical solution, the above-mentioned production progress data acquisition method is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0020] The present invention has the following technical effects: Due to factors such as market trends or human operations, there are occasional peaks or troughs in the production quantity. Therefore, the production progress data includes various periodic, trend, and non-periodic changes, etc. Optimizing the length of the filtering window can be adjusted according to the local characteristics of the data, which can better smooth out this trend and periodicity, improve the accuracy of estimating the planned completion time, and further improve the accuracy of production progress data; and by optimizing the length of the filtering window through the oscillation and cyclicity of the data segment of the filtering window, the filtering algorithm can be made more flexible and adaptable to different data characteristics, which helps to improve the generality and practicality of the algorithm, enabling it to be more widely applied to various production progress data acquisition scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown by way of illustration and not limitation, and like or corresponding reference numerals denote like or corresponding parts.

[0022] Figure 1 is a flowchart of a method for collecting production progress data in an embodiment of the present invention. Detailed implementation manners

[0023] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0024] It should be understood that when terms such as "first" and "second" are used in the claims, specifications, and drawings of the present invention, they are only used to distinguish different objects and not to describe a specific order. The terms "comprising" and "including" used in the specifications and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0025] An embodiment of the present invention discloses a method for collecting production progress data. Referring to Figure 1 , it includes steps S1 - S7: S1: Draw a product quantity curve; Collect the quantity of products produced in each time period through a counter. The time of each time period is equal. Draw a product quantity curve according to the quantity of products produced in each time period. Each data point on the product quantity curve is the quantity of products produced in each time period.

[0026] S2: Preset the length of the filtering window and the sliding step size of the filtering window; Preset the length of the filtering window. The sliding step size of the filtering window is equal to the length of the filtering window. All data points within the current filtering window are regarded as a data segment.

[0027] The implementer can set the length of the filtering window according to the actual implementation situation.

[0028] S3: Determine the relative fluctuation degree of each data point within the filtering window; Determine the relative fluctuation degree of each data point according to the difference between each data point in the data segment and the mean value of the data points in this data segment, and the range of the data points in this data segment. The relative fluctuation degree is positively correlated with the difference and negatively correlated with the range.

[0029] The relative fluctuation degree of the data point satisfies the following relational expression: ; In the formula, is the relative fluctuation degree of the data point within the current filtering window, is the value of the data point within the current filtering window, is the mean value of the data points within the data segment of the current filtering window, is the maximum value of the data points within the data segment of the current filtering window, is the minimum value of the data points within the data segment of the current filtering window.

[0030] Describe the degree of deviation of the data point from the central tendency by calculating the difference between each data point in the data segment of the current filtering window and the mean value of the data segment; in order to evaluate the relative size of the deviation of each data point in the entire data segment, a reference object is also needed. Here, the difference between the maximum value and the minimum value of the data segment is selected to describe the oscillation range of the data segment. By measuring the degree of deviation of each data point from the central tendency and the relative size of the oscillation range of the data segment, the relative fluctuation degree of the data point can be obtained.

[0031] S4: Determine the oscillation rate of the data segment of the filtering window; When the relative fluctuation degree of a certain data point exceeds the mean value of the relative fluctuation degrees of the data points within this data segment, this data point is a fluctuation point; determine the oscillation rate of the data segment according to the number of fluctuation points within the data segment. The oscillation rate is positively correlated with the number of fluctuation points.

[0032] The oscillation rate of the data segment satisfies the following relational expression: ; In the formula, is the oscillation rate of the data segment of the current filtering window, is the number of fluctuation points within the data segment of the current filtering window, is the number of data points within the data segment of the current filtering window.

[0033] Since the sales volume of the produced items will be adjusted to a certain extent due to seasonal changes or holiday effects, etc., which will lead to certain regular changes in the production schedule. Reflecting on the collected production quantity data, it means that the collected data has oscillation and cyclicity. For example, near shopping festivals such as 618 and Double 11, users will make purchases during the platform activities. At this time, the manufacturer will adjust the production schedule, which will lead to certain oscillations and periodicity in the collected production quantity data. Therefore, here, the oscillation of the data segment of the filtering window is used to describe the change characteristics of this segment of data. The more obvious this change characteristic is, the stronger the trend of this segment of data. Based on this, the filtering window is adjusted to better smooth the oscillation and cyclicity of this segment of data. The more obvious the oscillation of this segment of data is, the greater the adjustment degree of the filtering window to better smooth out this trend; the more obvious the cyclicity of this segment of data is, the greater the necessity to adjust the filtering window to avoid its impact on the final obtained result.

[0034] S5: Determine the cyclic characteristics of the data segment of the filtering window; Take this data segment and its two adjacent data segments as data samples, perform clustering on the data samples, and mark the clusters containing data points from at least two data segments in the clustering result as diverse clusters; take the proportion of the number of diverse clusters in the total number of clusters as the cyclic characteristic of this data segment.

[0035] When determining the cyclic characteristics of the data segment of the filtering window, traditional cyclicity detection algorithms, such as autocorrelation functions, Fourier analysis, etc., require a relatively long period of data for analysis. However, since the present invention needs to adjust the length of the current filtering window, that is, the cyclicity here belongs to local cyclicity. At this time, a clustering algorithm can be used to indirectly reflect the cyclic degree of the data segment corresponding to the current filtering window. Because cyclicity refers to a certain pattern or feature in time series data that repeats at fixed time intervals. Although clustering itself does not directly calculate the period length or frequency, it can identify similar patterns. If similar patterns repeat in adjacent time periods, then this may be an indication of a periodic or repetitive pattern. That is to say, clustering can be performed on the data segment of this filtering window and its adjacent data segments. The more clusters with data points from at least two data segments in the same cluster, it can be explained that similar patterns repeat in adjacent time periods, that is, this segment of data has cyclic characteristics.

[0036] The clustering uses K-means clustering.

[0037] The implementer can set the K value of K-means clustering according to the actual implementation situation, such as 5.

[0038] S6: Optimize the filtering window; Optimize the filtering window according to the oscillation rate and cyclic characteristics. After optimization, the length of the filtering window is positively correlated with the oscillation rate and cyclic characteristics.

[0039] The length of the optimized filtering window satisfies the following relational expression: ; In the formula, is the length of the optimized filtering window, is the length of the current filtering window, is the oscillation rate of the data segment of the current filtering window, is the cyclic characteristic of the data segment of the current filtering window, is the ceiling function, is the normalization function. Here, the maximum-minimum normalization method is adopted. is with as the base exponential function. Here, an exponential function with the length of the initial filtering window as the base is adopted to obtain the adjustment degree of the window, so as to ensure that the adjustment degree range of the filtering window is in [1, .

[0040] S7: Complete the acquisition of production progress data; Filter the data points according to the optimized filtering window, and conduct a quantitative evaluation of the production progress based on the filtered data points to complete the acquisition of production progress data.

[0041] The filtering adopts SG filtering.

[0042] SG filtering is a simple and effective filtering method, which is applicable to application fields such as signal processing and data smoothing; its principle is to fit a polynomial curve using the least squares method within a given data window, and then obtain the smoothed data points by calculating the derivative of this polynomial.

[0043] The quantitative evaluation of the production progress according to the filtered data points includes: According to the filtered data points, taking days as the unit, obtain the sum of the filtered data points for each day, that is, the total production quantity. Form a sequence with the total production quantity for each day, conduct exponential smoothing prediction on the sequence to obtain the future daily production quantity, accumulate the total production quantity for each day and the future daily production quantity in turn, and stop accumulating when the accumulated value is not less than the target task quantity. At this time, the date corresponding to the last daily production quantity is the expected completion time of the production target. According to the total production quantity and the expected completion time of the production target, obtain the production progress data to complete the acquisition of production progress data.

[0044] An embodiment of the present invention also discloses a production progress data acquisition system, which includes a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a production progress data acquisition method according to the present invention is implemented.

[0045] The above system also includes other components well-known to those skilled in the art, such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be described in detail here.

[0046] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and idea of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted in the process of practicing the present invention.

[0047] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for collecting production progress data, characterized in that, Including: Drawing a product quantity curve, where each data point on the product quantity curve represents the quantity of products produced within each time period; Presetting the length of a filtering window, with the sliding step length of the filtering window equal to the length of the filtering window, and taking all data points within the current filtering window as a data segment; Determining the relative fluctuation degree of each data point based on the difference between each data point within the data segment and the mean value of the data points within this data segment, as well as the range of the data points within this data segment. The relative fluctuation degree is positively correlated with the difference and negatively correlated with the range. When the relative fluctuation degree of a certain data point exceeds the mean value of the relative fluctuation degrees of the data points within this data segment, this data point is a fluctuation point. Determining the oscillation rate of the data segment based on the number of fluctuation points within the data segment, and the oscillation rate is positively correlated with the number of fluctuation points; Taking this data segment and its two adjacent data segments as data samples, performing clustering on the data samples, and marking the cluster containing data points from at least two data segments in the clustering result as a diversity cluster. Taking the proportion of the number of diversity clusters in the total number of clusters as the cyclic feature of this data segment; Optimizing the filtering window based on the oscillation rate and the cyclic feature. After optimization, the length of the filtering window is positively correlated with the oscillation rate and the cyclic feature. Filtering the data points according to the optimized filtering window, and performing a quantitative evaluation of the production progress based on the filtered data points to complete the acquisition of production progress data.

2. The production progress data acquisition method according to claim 1, characterized in that The relative fluctuation degree of the data point satisfies the following relationship: ； Wherein, is the relative fluctuation degree of the data points within the current filtering window, is the value of the data points within the current filtering window, is the average value of the data points within the data segment of the current filtering window, is the maximum value of the data points within the data segment of the current filtering window, is the minimum value of the data points within the data segment of the current filtering window.

3. The production progress data acquisition method according to claim 1, wherein The oscillation rate of the data segment satisfies the following relationship: ； Wherein, is the oscillation rate of the data segment of the current filtering window, is the number of fluctuation points within the data segment of the current filtering window, is the number of data points within the data segment of the current filtering window.

4. The method for collecting production progress data according to claim 1, wherein, The clustering uses k-means clustering.

5. A production progress data collection method according to claim 1, characterized in that, The length of the optimized filtering window satisfies the following relationship: ； In the formula, is the optimized filter window length, is the current filter window length, is the oscillation rate of the data segment of the current filter window, is the cyclic feature of the data segment of the current filter window, is the ceiling function, is the normalization function.

6. The production progress data acquisition method according to claim 1, characterized in that, The filtering uses SG filtering.

7. A method for collecting production progress data according to claim 1, characterized in that, The quantitative evaluation of the production progress based on the filtered data points includes: Based on the filtered data points, taking days as the unit, obtaining the sum of the filtered data points for each day, that is, the total production quantity. Constituting a sequence with the total production quantity for each day, performing exponential smoothing prediction on the sequence to obtain the future daily production quantity. Cumulatively adding the total production quantity for each day and the future daily production quantity in sequence. When the cumulative value is not less than the target task quantity, stop the accumulation. At this time, the date corresponding to the last daily production quantity is the estimated completion time of the production target. Obtaining the production progress data based on the total production quantity and the estimated completion time of the production target to complete the acquisition of production progress data.

8. A production progress data collection system, characterized in that, Including: A processor and a memory, where the memory stores computer program instructions, and when the computer program instructions are executed by the processor, it realizes a method for collecting production progress data according to any one of claims 1-7.

Images