Intelligent quality monitoring method for xylitol production
By dividing the xylitol production workshop into rectangular grids and conducting real-time biological density monitoring, combined with fluorescent labeling technology and regression models, the lag problem of traditional microbial culture methods was solved, real-time quality monitoring of the xylitol production process was achieved, and the safety of the production environment and product quality were guaranteed.
Patent Information
- Application Number
- CN202510849314.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-24
- Publication Date
- 2025-09-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional microbial culture methods have a lag in xylitol production and cannot achieve real-time monitoring, resulting in the inability to detect changes in microbial conditions during the production process in a timely manner, which may lead to the production of unqualified products.
By dividing the contact surface of the xylitol production workshop into rectangular grids, regional environmental indicators and biological density values are obtained in real time. Microbial distribution is predicted using fluorescent labeling technology and regression models. Warning areas are set up to prompt disinfection in a timely manner, and the detection cycle is dynamically adjusted to adapt to the growth conditions of microorganisms.
It realizes real-time monitoring of microbial growth conditions, avoids the production of unqualified products caused by detection delays, and improves the safety of the production environment and product quality.
Smart Images
Figure CN120629092A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of production quality monitoring, and in particular to an intelligent quality monitoring method for xylitol production. Background Art
[0002] In today's xylitol production industry, existing technologies involve multiple complex and sophisticated processes, among which microbial monitoring plays a crucial role. As a key raw material widely used in various industries, including food and medicine, xylitol's quality and safety are directly related to the quality of related products and the health of consumers.
[0003] Controlling the presence and abundance of microorganisms is a critical step in the xylitol production process. Microbial abundance can profoundly impact xylitol yield and safety. In actual xylitol production plants, accurate and timely monitoring of microorganisms is crucial for ensuring smooth production and consistent product quality. However, traditional microbial culture methods have numerous limitations in practical applications. These methods typically require hours to days to produce test results. During this time, the microbial landscape within the production process may have significantly changed, rendering the results inaccurately reflecting the current production environment. For products like xylitol, which require demanding production conditions, the lag inherent in traditional microbial culture methods makes them inadequate for real-time monitoring. For example, if the microbial count suddenly increases abnormally at some point during the production process, the delay in detection prevents personnel from detecting and taking appropriate action. This can lead to a large number of substandard products, resulting in significant economic losses for the company. Summary of the Invention
[0004] The purpose of the present invention is to provide an intelligent quality monitoring method for xylitol production to solve the following technical problems.
[0005] The purpose of the present invention can be achieved through the following technical solutions: The intelligent quality control method for xylitol production includes the following steps: Step S1: Obtaining a target microorganism, obtaining all environmental indicators required for the growth of the target microorganism, and the required indicator range of each environmental indicator; obtaining a xylitol production workshop, obtaining a contact surface within the production workshop, dividing the contact surface into a plurality of regions using a rectangular grid, and obtaining environmental indicators of the regions in real time; Step S2: Determine the environmental compliance of the area based on the index values of the environmental indicators of the area and the required index range of the target organisms; set an initial detection period, and modify the initial detection period based on the environmental compliance to obtain a modified detection period for the area; set a number of detection points, and the detection points obtain the biological density value of each area in real time based on the modified detection period; Step S3: Obtain the regional points and biological density values of each area, and obtain a density value gradient curve based on the biological density values of each regional point; obtain the gradient center, obtain several proliferation vectors, and obtain the distribution area of the target organism; and select a warning area on the contact surface. When the distribution area and the warning area intersect, it is prompted that the production workshop needs to be disinfected.
[0006] As a further embodiment of the present invention, the target organism is a microorganism that may cause pollution to the xylitol production workshop, which is determined manually; the environmental indicators include temperature and humidity, and the indicator range is the size range of the environmental indicators required for the survival of the target organism; The contact surfaces in the production workshop are the floor, walls, equipment surfaces and operating tables in the production workshop.
[0007] As a further solution of the present invention: the process of obtaining the environmental compliance of the area includes: If the index value of the environmental index of the area falls within the required index range, the index compliance of the environmental index is directly recorded as IC=1; If the index value of the environmental index of the area does not belong to the required index range, the median value of the required index range is obtained to obtain the index compliance at this time. , where λ is the preset first correction coefficient and λ>0, the approximate value of e is 2.71828, I is the index value of the environmental index of the area, I median is the median value of the desired metric range.
[0008] As a further solution of the present invention: the process of correcting the initial detection period includes: The modified detection cycle , where T is the initial detection period, k is the preset second correction coefficient and k>0; according to the correction detection period, the biological density value of the area is collected and obtained once every correction detection period.
[0009] As a further solution of the present invention: the process of obtaining the biomass density value includes: The detection point is based on fluorescent labeling technology to obtain the fluorescence signal intensity range of the detection point, divide the fluorescence signal intensity range into several signal intensity intervals, and sort each signal intensity interval from small to large according to the mean value of the fluorescence signal intensity of each signal intensity interval and number them; the numerical value of the number of the signal intensity interval is the biological density value of the area.
[0010] As a further solution of the present invention: the process of obtaining the density value gradient curve includes: The biological density value of each regional point is divided into several density value intervals, and the regional points in the same density value interval are connected in sequence with smooth curves to obtain a density value gradient curve.
[0011] As a further solution of the present invention: the process of obtaining the proliferation vector includes: Obtain the curve at the outermost edge of the density value gradient curve, record it as the outer line, obtain the regional points on the outermost edge, compare the biological density value of the regional points with the biological density value of the gradient center, record the side with higher biological density value as the starting point, and record the side with lower biological density value as the end point; connect the starting point and the end point with a straight line, with the direction pointing from the starting point to the end point, to obtain the proliferation vector.
[0012] As a further solution of the present invention: the process of obtaining the distribution area of the target organism includes: For any proliferation vector, obtain the modulus of the current proliferation vector, recorded as M, and obtain the modulus of the proliferation vector before a correction detection cycle, recorded as M′; obtain the increment M′-M of the proliferation vector in the previous correction detection cycle; based on the increment of the proliferation vector in each correction detection cycle, predict the increment of the proliferation vector in the next correction detection cycle based on the regression model, recorded as the predicted increment, and determine the modulus of the proliferation vector after the next correction detection cycle and the predicted modulus based on the predicted increment, and extend the proliferation vector according to the predicted modulus to obtain a predicted proliferation vector; The end points of the predicted proliferation vectors are connected with a smooth curve to obtain a predicted peripheral curve; the area encompassed by the predicted peripheral curve is recorded as the distribution area.
[0013] Beneficial effects of the present invention: The present invention obtains regional environmental indicators and biological density values in real time by dividing the contact surface of the production workshop into rectangular grids, which can timely grasp the growth status of microorganisms and environmental changes, change the lag problem of traditional microbial culture methods, reflect the microbial status in the production environment in real time, and avoid the production of a large number of unqualified products due to detection delays. The initial detection cycle is corrected according to the regional environmental compliance to make the detection more targeted. In areas with high environmental compliance, microorganisms are more likely to grow and reproduce. Shortening the detection cycle can timely detect changes in the number of microorganisms; in areas with low environmental compliance, the detection cycle is appropriately extended to reduce the detection workload and cost while ensuring the monitoring effect. The target biological distribution area is predicted by the density value gradient curve, proliferation vector and regression model, and the microbial distribution and diffusion trend can be accurately determined. Combined with the warning area setting, disinfection prompts can be given in time before the microorganisms spread to key areas, effectively controlling the scope of microbial contamination, ensuring the safety of the xylitol production environment, and improving product quality and safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] The present invention will be further described below with reference to the accompanying drawings.
[0015] Figure 1 It is a structural schematic diagram of the intelligent quality monitoring method for xylitol production of the present invention. DETAILED DESCRIPTION
[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.
[0017] See also Figure 1 As shown, the present invention is an intelligent quality monitoring method for xylitol production, comprising the following steps: Step S1: Obtaining a target microorganism, obtaining all environmental indicators required for the growth of the target microorganism, and the required indicator range of each environmental indicator; obtaining a xylitol production workshop, obtaining a contact surface within the production workshop, dividing the contact surface into a plurality of regions using a rectangular grid, and obtaining environmental indicators of the regions in real time; In a preferred embodiment of the present invention, the target organism is a microorganism that may cause pollution to the xylitol production workshop, which is determined manually; the environmental indicators include temperature and humidity, and the indicator range is the size range of the environmental indicators required for the survival of the target organism; As a preferred embodiment of the present invention, the contact surface in the production workshop is the floor, wall, equipment surface and operating table in the production workshop; It is understandable that the growth of target microorganisms is affected by a variety of environmental factors, such as temperature, humidity, pH value, and nutrient concentration. Obtaining these environmental indicators and their suitable ranges is the basis for understanding the growth requirements of microorganisms. Only by clarifying the required environmental conditions can subsequent monitoring and regulation be carried out in a targeted manner, providing a basis for judging the growth status of microorganisms in the production environment. The xylitol production workshop's contact surface is divided into rectangular grids to achieve refined, zoned monitoring of the production environment. Each grid area can be considered an independent monitoring unit, and real-time environmental indicators for each area can be obtained, enabling a more comprehensive and accurate understanding of the environmental conditions at different locations within the production environment. This allows for timely identification of areas with abnormal environmental indicators so that measures can be taken to prevent abnormal microbial growth caused by unsuitable local environments, which in turn affects xylitol production quality. Step S2: Determine the environmental compliance of the area based on the index values of the environmental indicators of the area and the required index range of the target organisms; set an initial detection period, and modify the initial detection period based on the environmental compliance to obtain a modified detection period for the area; set a number of detection points, and the detection points obtain the biological density value of each area in real time based on the modified detection period; As a preferred embodiment of the present invention, the process of obtaining the environmental compliance of the area includes: If the index value of the environmental index of the area falls within the required index range, the index compliance of the environmental index is directly recorded as IC=1; If the index value of the environmental index of the area does not belong to the required index range, the median value of the required index range is obtained to obtain the index compliance at this time. , where λ is the preset first correction coefficient and λ>0, the approximate value of e is 2.71828, I is the index value of the environmental index of the area, I median is the median value of the required indicator range; In a preferred embodiment of the present invention, the process of correcting the initial detection period includes: The modified detection cycle , where T is the initial detection period, k is a preset second correction coefficient and k>0; according to the correction detection period, the biological density value of the area is collected and obtained every other correction detection period; In a preferred embodiment of the present invention, the process of obtaining the biomass density value includes: The detection point is based on fluorescent labeling technology, and the fluorescence signal intensity range of the detection point is obtained. The fluorescence signal intensity range is divided into several signal intensity intervals. According to the mean value of the fluorescence signal intensity of each signal intensity interval, each signal intensity interval is sorted from small to large and numbered. The numerical value of the number of the signal intensity interval is the biological density value of the area; It is understandable that different environmental index values have different effects on the growth of target organisms. Comparing regional environmental index values with the index range required by the target organisms can quantify the environmental compliance. A high environmental compliance indicates that the current environment is conducive to the growth of the target organisms, while a low environmental compliance indicates that it is unfavorable. This serves as the basis for subsequent decision-making and clearly reflects the suitability of each regional environment for the growth of the target organisms. The initial detection cycle is a preset benchmark. When the environmental compliance is high, the target organisms are actively growing and may proliferate faster. Shortening the detection cycle can timely capture changes in biological density. When the environmental compliance is low, the growth of the target organisms is restricted and the proliferation is slow. Properly extending the detection cycle can reduce resource consumption and workload while ensuring monitoring results. Through this dynamic adjustment, the detection frequency is aligned with the actual growth trend of the target organisms. Data is collected in real time according to the revised detection cycle; the detection points are widely and scientifically distributed to ensure coverage of all areas, and can comprehensively and accurately obtain biological density values, providing reliable data support for subsequent analysis of target biological distribution and growth trends; the number of detection points is often smaller than the number of areas, in which case the same detection point detects biological density values in several areas; Step S3: Obtain the center point of each region, record it as the region point, and record the biological density value of the region as the biological density value of the region point; divide the biological density value of each region point into several density value intervals, and connect the region points in the same density value interval in sequence with a smooth curve to obtain a density value gradient curve; obtain the center point of the density value gradient curve, record it as the gradient center; A plurality of proliferation vectors are obtained on the density gradient curve according to the gradient center, and a distribution area of the target organism is predicted in the next correction detection cycle according to the proliferation vectors; and a warning area is selected on the contact surface. When the distribution area intersects with the warning area, a prompt is given to disinfect the production workshop; As a preferred embodiment of the present invention, the process of obtaining the proliferation vector includes: Obtaining the outermost curve of the density gradient curve as the outer line, obtaining regional points on the outermost curve, comparing the biological density value of the regional points with the biological density value of the gradient center, recording the side with the higher biological density value as the starting point, and recording the side with the lower biological density value as the end point; connecting the starting point and the end point with a straight line from the starting point to the end point, and obtaining a proliferation vector; In a preferred embodiment of the present invention, the process of obtaining the distribution area of the target organism includes: For any proliferation vector, obtain the modulus of the current proliferation vector, recorded as M, and obtain the modulus of the proliferation vector before a correction detection cycle, recorded as M′; obtain the increment M′-M of the proliferation vector in the previous correction detection cycle; based on the increment of the proliferation vector in each correction detection cycle, predict the increment of the proliferation vector in the next correction detection cycle based on the regression model, recorded as the predicted increment, and determine the modulus of the proliferation vector after the next correction detection cycle and the predicted modulus based on the predicted increment, and extend the proliferation vector according to the predicted modulus to obtain a predicted proliferation vector; Connecting the endpoints of each predicted proliferation vector with a smooth curve to obtain a predicted peripheral curve; recording the area encompassed by the predicted peripheral curve as the distribution area; As a preferred embodiment of the present invention, when the distribution area and the warning area do not have an intersection, the distribution area is continuously predicted after the next correction detection cycle; It can be understood that the center point of each region is used as the regional point, the corresponding biodensity value is divided into intervals, and the regional points in the same interval are connected to form a curve; this can intuitively present the changing trend and distribution of biodensity in different regions. The curve can clearly show the fluctuations and distribution pattern of biodensity, providing a visual basis for subsequent analysis; Find the center point of the density gradient curve (gradient center) and use it as a benchmark to obtain the proliferation vector. The proliferation vector reflects the proliferation trend and intensity of the target organism in different directions and is a key parameter for predicting its distribution changes. The prediction is based on the current biological density distribution and change direction. The target organism distribution area for the next detection cycle is predicted based on the proliferation vector. Warning areas are set on the contact surface. If the predicted distribution area overlaps with the warning area, it means that the microorganisms may spread to critical or easily contaminated areas, prompting disinfection, preventing and controlling microbial contamination in advance, and ensuring a safe production environment.
[0018] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.
Claims
1. An intelligent quality monitoring method for xylitol production, characterized in that: The following steps are involved: Step S1: Obtaining a target microorganism, obtaining all environmental indicators required for the growth of the target microorganism, and the required indicator range of each environmental indicator; obtaining a xylitol production workshop, obtaining a contact surface within the production workshop, dividing the contact surface into a plurality of regions using a rectangular grid, and obtaining environmental indicators of the regions in real time; Step S2: Determine the environmental compliance of the area based on the index values of the environmental indicators of the area and the required index range of the target organisms; set an initial detection period, and modify the initial detection period based on the environmental compliance to obtain a modified detection period for the area; set a number of detection points, and the detection points obtain the biological density value of each area in real time based on the modified detection period; Step S3: Obtain the regional points and biological density values of each area, and obtain a density value gradient curve based on the biological density values of each regional point; obtain the gradient center, obtain several proliferation vectors, and obtain the distribution area of the target organism; and select a warning area on the contact surface. When the distribution area and the warning area intersect, it is prompted that the production workshop needs to be disinfected.
2. The intelligent quality monitoring method for xylitol production according to claim 1, characterized in that: In step S1, the target organism is a microorganism that may cause pollution to the xylitol production workshop, which is determined manually; the environmental indicators include temperature and humidity, and the indicator range is the size range of the environmental indicators required for the survival of the target organism; The contact surfaces in the production workshop are the floor, walls, equipment surfaces and operating tables in the production workshop.
3. The intelligent quality monitoring method for xylitol production according to claim 1, characterized in that: In step S2, the process of obtaining the environmental compliance of the area includes: If the index value of the environmental index of the area falls within the required index range, the index compliance of the environmental index is directly recorded as IC=1; If the index value of the environmental index of the area does not belong to the required index range, the median value of the required index range is obtained to obtain the index compliance at this time. , where λ is the preset first correction coefficient and λ>0, the approximate value of e is 2.71828, I is the index value of the environmental index of the area, I median is the median value of the desired metric range.
4. The intelligent quality monitoring method for xylitol production according to claim 1, characterized in that: In step S2, the process of correcting the initial detection period includes: The modified detection cycle , where T is the initial detection period, k is the preset second correction coefficient and k>0; according to the correction detection period, the biological density value of the area is collected and obtained once every correction detection period.
5. The intelligent quality monitoring method for xylitol production according to claim 1, characterized in that: In step S2, the process of obtaining the biological density value includes: The detection point is based on fluorescent labeling technology to obtain the fluorescence signal intensity range of the detection point, divide the fluorescence signal intensity range into several signal intensity intervals, and sort each signal intensity interval from small to large according to the mean value of the fluorescence signal intensity of each signal intensity interval and number them; the numerical value of the number of the signal intensity interval is the biological density value of the area.
6. The intelligent quality monitoring method for xylitol production according to claim 1, characterized in that: In step S3, the process of obtaining the density gradient curve includes: The biological density value of each regional point is divided into several density value intervals, and the regional points in the same density value interval are connected in sequence with smooth curves to obtain a density value gradient curve.
7. The intelligent quality monitoring method for xylitol production according to claim 1, characterized in that: In step S3, the process of obtaining the proliferation vector includes: Obtain the curve at the outermost edge of the density value gradient curve, record it as the outer line, obtain the regional points on the outermost edge, compare the biological density value of the regional points with the biological density value of the gradient center, record the side with higher biological density value as the starting point, and record the side with lower biological density value as the end point; connect the starting point and the end point with a straight line, with the direction pointing from the starting point to the end point, to obtain the proliferation vector.
8. The intelligent quality monitoring method for xylitol production according to claim 1, characterized in that: In step S3, the process of obtaining the distribution area of the target organism includes: For any proliferation vector, obtain the modulus of the current proliferation vector, recorded as M, and obtain the modulus of the proliferation vector before a correction detection cycle, recorded as M′; obtain the increment M′-M of the proliferation vector in the previous correction detection cycle; based on the increment of the proliferation vector in each correction detection cycle, predict the increment of the proliferation vector in the next correction detection cycle based on the regression model, recorded as the predicted increment, and determine the modulus of the proliferation vector after the next correction detection cycle and the predicted modulus based on the predicted increment, and extend the proliferation vector according to the predicted modulus to obtain a predicted proliferation vector; The end points of the predicted proliferation vectors are connected with a smooth curve to obtain a predicted peripheral curve; the area encompassed by the predicted peripheral curve is recorded as the distribution area.