Sodium dihydrogen phosphate production monitoring method based on Internet of Things
By calculating the sensitivity and confidence of the temperature sensor and optimizing the installation position of the temperature sensor, the problem of inaccurate temperature monitoring in traditional methods is solved, the temperature stability and efficiency of sodium dihydrogen phosphate production is improved, and the production quality and efficiency are improved.
Patent Information
- Application Number
- CN202410691068.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-30
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-05-30
AI Technical Summary
In the traditional Internet of Things production monitoring method, the installation position of the temperature sensor is manually determined, resulting in some sensors being unable to accurately reflect the temperature changes in production, affecting the production quality and efficiency of sodium dihydrogen phosphate.
By collecting the temperature data sequence of the temperature sensor, the temperature data sensitivity and confidence of each numbered area are calculated, and combined with the correlation of adjacent areas, the installation location of the temperature sensor is optimized to achieve more accurate temperature monitoring.
It improves the accuracy and efficiency of temperature data, reduces the inconsistency caused by improper installation position of the sensor, ensures temperature stability and output in the sodium dihydrogen phosphate production process, and improves production quality and efficiency.
Smart Images

Figure CN118586548B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of data processing, and in particular to a sodium dihydrogen phosphate production monitoring method based on the Internet of Things. Background Art
[0002] In the production process of sodium dihydrogen phosphate, the temperature needs to be strictly controlled to ensure the quality of the product. The change of temperature will have a direct impact on the production process of sodium dihydrogen phosphate. If the temperature is too high, it will lead to a decrease in product quality and an increase in energy consumption. If the temperature is too low, it will lead to a decrease in output and incomplete crystallization. In the production process of sodium dihydrogen phosphate, it is very important to ensure the stability and suitability of the temperature, which can be achieved through appropriate temperature monitoring and control methods.
[0003] In the traditional Internet of Things-based sodium dihydrogen phosphate production monitoring method, a large number of temperature sensors are installed to collect temperature data. However, since the installation position of the temperature sensors is determined manually based on empirical values, the temperature data of some sensors cannot accurately reflect the temperature changes in production due to the structure of the production kettle, and the production quality and efficiency of sodium dihydrogen phosphate cannot be ensured. Summary of the invention
[0004] The invention provides a sodium dihydrogen phosphate production monitoring method based on the Internet of Things to solve the existing problems.
[0005] The method for monitoring sodium dihydrogen phosphate production based on the Internet of Things of the present invention adopts the following technical scheme:
[0006] One embodiment of the present invention provides a method for monitoring sodium dihydrogen phosphate production based on the Internet of Things, the method comprising the following steps:
[0007] Collect the temperature data sequence of each temperature sensor in the production process of several sodium dihydrogen hypophosphite, each temperature sensor corresponds to a numbered area to obtain the temperature data of each numbered area;
[0008] According to the change rate of each temperature data of each numbered area over time, the temperature data sensitivity of each numbered area is obtained;
[0009] According to the temperature data sensitivity difference between each numbered area and the adjacent numbered area, the temperature data confidence of the numbered area adjacent to each numbered area is obtained;
[0010] According to the temperature data sensitivity of each numbered area and the temperature data confidence of the numbered areas adjacent to each numbered area, the correlation between each numbered area and the adjacent numbered areas is obtained; and according to the correlation between each numbered area and the adjacent numbered areas, the final numbered area is obtained;
[0011] According to the number of times each numbered area is used as the final numbered area in different sodium dihydrogen phosphate production processes, the confidence of the temperature data of each numbered area is obtained;
[0012] The temperature sensors are removed according to the confidence level of the temperature data in each numbered area to optimize the production monitoring of sodium dihydrogen phosphate.
[0013] Furthermore, obtaining the temperature data sensitivity of each numbered area according to the change rate of each temperature data of each numbered area over time includes:
[0014] The specific calculation formula for the temperature data sensitivity of the i-th numbered area is:
[0015]
[0016] Among them, B i represents the temperature data sensitivity of the ith numbered area; m represents the number of sampled temperature data; m-1 represents the number of sampled temperature data other than the first sampled temperature data; T i,j represents the jth sampled temperature data of the i-th numbered area; T i,j-1 represents the j-1th sampled temperature data of the i-th numbered area; ΔS represents the time difference between adjacent sampled temperature data; T i ′ represents the first sampled temperature data of the ith numbered area; T i ″ represents the last sampled temperature data of the ith numbered area; norm() is a linear normalization function.
[0017] Furthermore, the specific method of obtaining the sampled temperature data is as follows:
[0018] m temperature data are uniformly selected from the production process of the i-th numbered area and recorded as the sampled temperature data of the i-th numbered area.
[0019] Furthermore, the specific acquisition method of the production process is:
[0020] The moment when the value of the temperature sensor begins to change is recorded as the start of production, and the moment when the values of all temperature sensors remain stable after the start of production is recorded as the end of production. The production process from the start of production to the end of production is regarded as a production process of the temperature sensor.
[0021] Further, the obtaining of the temperature data confidence of the numbered area adjacent to each numbered area according to the temperature data sensitivity difference between each numbered area and the adjacent numbered area includes:
[0022] Any numbered area adjacent to the ith numbered area is recorded as the dth numbered area, and the calculation formula for the temperature data confidence of the dth numbered area adjacent to the ith numbered area is:
[0023]
[0024] Among them, K i,d represents the confidence level of the temperature data of the dth numbered area adjacent to the ith numbered area; D i represents the number of numbered regions adjacent to the i-th numbered region; B i Indicates the temperature data sensitivity of the ith numbered area; B i,d represents the temperature data sensitivity of the dth numbered area adjacent to the ith numbered area; || represents the absolute value function; exp() represents the exponential function with a natural constant as the base.
[0025] Further, the obtaining of the correlation between each numbered region and the adjacent numbered regions according to the temperature data sensitivity of each numbered region and the temperature data confidence of the numbered regions adjacent to each numbered region includes:
[0026] The calculation formula for the association between the ith numbered region and the adjacent numbered region is:
[0027]
[0028] Among them, C i Indicates the association between the ith numbered region and the adjacent numbered regions; D i represents the number of numbered regions adjacent to the i-th numbered region; K i,d represents the confidence level of the temperature data of the dth numbered area adjacent to the ith numbered area; S i represents the time length of the production process of the ith numbered area; S i,d H represents the time length of the production process of the dth numbered area adjacent to the ith numbered area; i,d It represents the similarity between the ith numbered region and the adjacent dth numbered region; sigmoid() represents the Sigmoid function; || represents the absolute value function.
[0029] Furthermore, the specific method of obtaining the similarity degree is:
[0030] The difference between the ratio of the temperature data sensitivity of the ith numbered region and the adjacent dth numbered region and 1 is calculated, and the reciprocal of the absolute value of the difference is recorded as the similarity between the ith numbered region and the adjacent dth numbered region.
[0031] Furthermore, the obtaining of the final numbered region according to the association between each numbered region and an adjacent numbered region includes:
[0032] A correlation threshold is preset, and when the correlation between the ith numbered area and the adjacent numbered area is greater than the correlation threshold, the numbered area adjacent to the ith numbered area is deleted from all numbered areas, and the temperature data of the ith numbered area is used to represent the temperature data in the adjacent numbered areas;
[0033] When the correlation between the i-th numbered region and the adjacent numbered region is less than the correlation threshold, the i-th numbered region and the adjacent numbered region are retained and renumbered to obtain a new numbered region;
[0034] The correlation between each numbering region and the adjacent numbering region is calculated based on the new numbering region, and the numbering region whose correlation is greater than the correlation threshold is deleted from all numbering regions, and so on, until the correlation between each numbering region and the adjacent numbering region is less than or equal to the correlation threshold, all new numbering regions constitute the final numbering region of the current production process.
[0035] Furthermore, the specific method for obtaining the temperature data confidence of each numbered area is:
[0036] The number of times each numbered area is used as the final numbered area in all sodium dihydrogen hypophosphite production processes is counted, and the ratio of the number of times each numbered area is used as the final numbered area to the number of sodium dihydrogen phosphate production processes is recorded as the temperature data confidence of each numbered area.
[0037] Further, the removing of the temperature sensor according to the confidence level of the temperature data of each numbered area includes:
[0038] A confidence threshold is preset. For the i′th final numbered area, when the confidence of the temperature data of the i′th final numbered area is less than the confidence threshold, the temperature sensor of the i′th final numbered area is marked as a sensor to be removed, all sensors to be removed are obtained, and the sensors to be removed are removed.
[0039] The technical solution of the present invention has the following beneficial effects: a temperature data sequence of each temperature sensor in a number of sodium dihydrogen hypophosphite production processes is collected, each temperature sensor corresponds to a numbered area to obtain the temperature data of each numbered area, and the temperature data sensitivity of each numbered area is obtained according to the change rate of each temperature data of each numbered area over time, so that the temperature of the numbered area where the abnormal sensor is located will be reduced, which will manifest as the irregularity of temperature change, reduce the abnormal sensitivity that occurs in a specific stage, and improve the accuracy and efficiency level of the temperature data of the numbered area; according to the difference in temperature data sensitivity between each numbered area and the adjacent numbered area, the temperature data confidence of the numbered area adjacent to each numbered area is obtained, and the difference in data sensitivity of the adjacent numbered area and the temperature data sensitivity of the central numbered area caused by the installation position of the temperature sensors of some adjacent numbered areas being far away from the central numbered area is reduced. Inconsistency; According to the temperature data sensitivity of each numbered area and the temperature data confidence of the numbered areas adjacent to each numbered area, the correlation between each numbered area and the adjacent numbered areas is obtained, and the final numbered area is obtained according to the correlation between each numbered area and the adjacent numbered areas, so as to reduce the influence of inconsistent temperature changes between each numbered area and the adjacent numbered areas due to the special installation position; According to the number of times each numbered area is used as the final numbered area in different sodium dihydrogen phosphate production processes, the temperature data confidence of each numbered area is obtained, so as to reduce the influence of various environmental factors on the collected temperature data of the same temperature sensor; According to the temperature data confidence of each numbered area, the temperature sensor is removed to optimize the production monitoring of sodium dihydrogen phosphate, accurately reflect the temperature changes in the production of sodium dihydrogen phosphate, and improve the production quality and efficiency of sodium dihydrogen phosphate. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0041] Figure 1 The present invention is a flowchart of the steps of the sodium dihydrogen phosphate production monitoring method based on the Internet of Things. DETAILED DESCRIPTION
[0042] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the sodium dihydrogen phosphate production monitoring method based on the Internet of Things proposed by the present invention, its specific implementation method, structure, characteristics and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0043] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0044] The specific scheme of the sodium dihydrogen phosphate production monitoring method based on the Internet of Things provided by the present invention is described in detail below in conjunction with the accompanying drawings.
[0045] See also Figure 1 , which shows a flow chart of the steps of a sodium dihydrogen phosphate production monitoring method based on the Internet of Things provided by an embodiment of the present invention, the method comprising the following steps:
[0046] Step S001, collecting a temperature data sequence of each temperature sensor in a number of sodium dihydrogen hypophosphite production processes, wherein each temperature sensor corresponds to a numbered area and obtains temperature data of each numbered area.
[0047] In a single sodium dihydrogen phosphate production process, a temperature sensor based on the Internet of Things is installed every a centimeters inside the production kettle, and several temperature sensors are installed. By numbering the temperature sensors, the area collected by each temperature sensor is recorded as a numbered area. The temperature of each numbered area in the production process is collected by the temperature sensor and transmitted to the production monitoring system to obtain the temperature data of each numbered area. The installation distance threshold a=0.1 preset in this embodiment is described as an example, and can be set to other values in other implementations, which is not limited in this embodiment.
[0048] The number of temperature sensors set in this embodiment is described by taking 100 as an example, and every 1 minute is recorded as a moment. The collection interval and the number of temperature sensors in other embodiments can be set to other values, which will not be described in detail in this embodiment; each numbered area collects temperature data once at each moment, and the beginning of the change in the temperature of any sensor among all the sensors is recorded as the start of production, and the stabilization of the temperature of all sensors is recorded as the end of production. The period from the start of production to the end of production is regarded as a production process, and the temperature data at all moments in the production process are obtained to constitute the temperature data sequence of each numbered area.
[0049] Similarly, data of multiple sodium dihydrogen phosphate production processes are obtained. In this embodiment, the preset sodium dihydrogen phosphate production times z=20 are used as an example for description. Other implementations may be set to other values, which are not limited in this embodiment.
[0050] Step S002: Obtain the temperature data sensitivity of each numbered area according to the change rate of each temperature data of each numbered area over time.
[0051] It should be noted that the monitoring of the production of sodium dihydrogen phosphate based on the Internet of Things is mainly to reflect the production situation by monitoring the temperature changes in the production process of sodium dihydrogen phosphate. The production of sodium dihydrogen phosphate is an exothermic production. As the production of sodium dihydrogen phosphate proceeds, the temperature of the numbered area where each sensor is located will gradually change and increase, and the abnormality will manifest as irregular temperature changes and abnormal sensitivity at a specific stage. Therefore, this embodiment analyzes the sensitivity of temperature changes over time to evaluate the accuracy and efficiency level of the temperature data of the numbered area.
[0052] Specifically, in a production process, a coordinate system is constructed with the temperature data sequence of each numbered area, the horizontal axis of the coordinate system is the sampling time, and the vertical axis is the temperature value at each time. M temperature data are uniformly selected from a production process and recorded as sampled temperature data, and the temperature data sensitivity of the numbered area is obtained by the rate of change of the sampled temperature data over time. The number of sampled temperature data preset in this embodiment is m=20 as an example for description, and other values can be set in other implementations, which are not limited in this embodiment.
[0053] The calculation formula for the temperature data sensitivity of the i-th numbered area is:
[0054]
[0055] Among them, B i represents the temperature data sensitivity of the ith numbered area; m represents the number of sampled temperature data; m-1 represents the number of sampled temperature data other than the first sampled temperature data; T i,j represents the jth sampled temperature data of the i-th numbered area; T i,j-1 represents the j-1th sampled temperature data of the i-th numbered area; ΔS represents the time difference between adjacent sampled temperature data; T i ′ represents the first sampled temperature data of the ith numbered area; T i ″ represents the last sampled temperature data of the ith numbered area; norm() is a linear normalization function that normalizes the data value to the interval [0,1].
[0056] Indicates the rate of change of adjacent temperature data over time. The larger the value, the faster the rate of change of temperature data over time. It indicates the rate of change of temperature data over time during the entire production process. The larger the value, the greater the rate of change of temperature over time during the entire production process. It represents the difference between the rate of change of the jth temperature value in the ith numbered area over time and the mean rate of change of the temperature data over time in the entire production process. The larger the value is, the more sensitive the temperature is to changes over time during the production of sodium dihydrogen phosphate. When the temperature in the numbered area changes, the change can be recorded more quickly and accurately.
[0057] Step S003: Obtain the temperature data confidence of the numbered areas adjacent to each numbered area according to the temperature data sensitivity difference between each numbered area and the adjacent numbered areas.
[0058] It should be noted that the production of sodium dihydrogen phosphate is an exothermic production. Normally, as production occurs in a numbered area, the temperature of the surrounding numbered areas will rise accordingly, and the production rate will also increase accordingly. When the temperature gradually reaches a stable range, the production is in a state of equilibrium. Since each numbered area is producing sodium dihydrogen phosphate, it can be expected that the equilibrium production temperature of each numbered area is roughly the same. When calculating the time for each numbered area to reach the equilibrium production temperature and the sensitivity of the data, adjacent numbered areas reach the equilibrium production temperature in a similar time due to mutual influence between each other, and have similar data sensitivity.
[0059] It should be further explained that, due to heat transfer, adjacent numbered areas should have similar temperature data sensitivity. Since the installation positions of temperature sensors in some adjacent numbered areas are far away from the central numbered area, the data sensitivity of adjacent numbered areas is inconsistent with the temperature data sensitivity of the central numbered area. Their sensitivity to changes in the equilibrium production temperature over time is low, and the numbered areas have little impact on the temperature data of adjacent numbered areas, resulting in insufficient sensitivity to changes in temperature data.
[0060] The calculation formula for the temperature data confidence of the dth numbered area adjacent to the ith numbered area is:
[0061]
[0062] Among them, K i,d represents the confidence level of the temperature data of the dth numbered area adjacent to the ith numbered area; D i represents the number of numbered regions adjacent to the i-th numbered region; B i Indicates the temperature data sensitivity of the ith numbered area; Bi,d represents the temperature data sensitivity of the dth numbered area adjacent to the ith numbered area; || represents the absolute value function; exp() represents the exponential function with a natural constant as the base.
[0063] |B i,d -B i | represents the difference in temperature data sensitivity between the i-th numbered area and the adjacent d-th numbered area in the process of reaching the equilibrium production temperature. The larger the value is, the less the d-th numbered area adjacent to the i-th numbered area is affected by the i-th numbered area, and the lower the confidence of the temperature data of the d-th numbered area adjacent to the i-th numbered area is. It represents the average value of the difference in temperature data sensitivity between the ith numbered area and all adjacent numbered areas in the process of reaching the equilibrium production temperature. The larger the ratio of the difference to the average value, the smaller the influence of the ith numbered area on the numbered areas adjacent to the ith numbered area is, and the lower the confidence level of the temperature data of the dth numbered area adjacent to the ith numbered area is.
[0064] At this point, the confidence level of the temperature data of the numbered areas adjacent to each numbered area is obtained.
[0065] Step S004, obtaining the correlation between each numbered area and adjacent numbered areas according to the temperature data sensitivity of each numbered area and the temperature data confidence of the numbered areas adjacent to each numbered area; and obtaining the final numbered area according to the correlation between each numbered area and adjacent numbered areas.
[0066] It should be noted that each numbered area may show inconsistent temperature changes with the adjacent numbered area. When there is an adjacent numbered area that is closer to the numbered area in space, due to the special installation location, the temperature changes of the numbered area and the adjacent numbered area are inconsistent, which does not meet the research expectations. Therefore, based on the confidence of the temperature data of the adjacent numbered areas, the duration of the sodium dihydrogen phosphate production process and the temperature data sensitivity of each numbered area are linked to obtain the correlation between each numbered area and the adjacent numbered area.
[0067] By comparing the time when adjacent numbered areas reach the equilibrium production temperature and the temperature data sensitivity of adjacent numbered areas in the process of reaching the equilibrium production temperature, the correlation of the numbered areas is obtained. The calculation formula for the correlation between the i-th numbered area and the adjacent numbered area is:
[0068]
[0069] Among them, C i Indicates the association between the ith numbered region and the adjacent numbered regions; D irepresents the number of numbered regions adjacent to the i-th numbered region; K i,d represents the confidence level of the temperature data of the dth numbered area adjacent to the ith numbered area; S i represents the time length of the production process of the ith numbered area; S i,d H represents the time length of the production process of the dth numbered area adjacent to the ith numbered area; i,d It represents the similarity between the ith numbered region and the adjacent dth numbered region, and the similarity is obtained by subtracting the ratio of the temperature data sensitivity of the ith numbered region and the adjacent dth numbered region from 1, and inversely proportionally taking the absolute value of the difference as the similarity between the ith numbered region and the adjacent dth numbered region; sigmoid() represents the Sigmoid function; || represents the absolute value function.
[0070] |S i -S i,d | represents the difference in production time between the ith numbered area and the adjacent dth numbered area. The smaller the value, the stronger the correlation between the ith numbered area and the adjacent dth numbered area. i,d It means that the absolute value of the difference between the ratio of the temperature data sensitivity of the i-th numbered area and the adjacent d-th numbered area and 1 is inversely proportional. The smaller the value is, the smaller the similarity between the i-th numbered area and the adjacent d-th numbered area is, and the smaller the correlation between the i-th numbered area and the adjacent numbered area is.
[0071] The preset correlation threshold τ=0.5 in this embodiment is used as an example for description. Other values may be set in other implementations, which are not limited in this embodiment. When the correlation between the i-th numbered area and the adjacent numbered area is greater than the correlation threshold τ, it means that the correlation between the i-th numbered area and the adjacent numbered area is very strong, and the temperature change of the i-th numbered area can represent the temperature change of the adjacent numbered area. The numbered area adjacent to the i-th numbered area is deleted from all numbered areas, and the temperature data of the i-th numbered area is used to represent the temperature data in the adjacent numbered area; when the correlation between the i-th numbered area and the adjacent numbered area is less than the correlation threshold τ, it means that the correlation between the i-th numbered area and the adjacent numbered area is small, and the temperature change of the i-th numbered area cannot represent the temperature change of the adjacent numbered area. The i-th numbered area and the adjacent numbered area are retained and renumbered to obtain a new numbered area, and the correlation between each numbered area and the adjacent numbered area is calculated according to the new numbered area, and the numbered area whose correlation is greater than the correlation threshold is deleted from all numbered areas, and so on, until the correlation between each numbered area and the adjacent numbered area is less than or equal to the correlation threshold, all new numbered areas constitute the final numbered area of the current production process.
[0072] Step S005: Obtain the temperature data confidence of each numbered area according to the number of times each numbered area is used as the final numbered area in different sodium dihydrogen phosphate production processes.
[0073] It should be noted that in different sodium dihydrogen phosphate production processes, the same temperature sensor may be affected by various environmental factors, resulting in changes in the collected temperature data. On the one hand, if the area near the bottom of the production container may slow down the production speed due to the presence of impurities in the production raw materials, resulting in a slowdown in the trend of temperature change; on the other hand, if the concentration of the raw material solution is high, resulting in an accelerated trend of temperature change, these factors cause the temperature data recorded by the same temperature sensor to change in different production processes. Normally, when producing sodium dihydrogen phosphate, a small amount of impurities in the production raw materials or slight differences in solution concentrations are allowed. However, when these differences exceed a certain limit, the temperature data collected by the temperature sensor cannot accurately reflect the actual temperature changes.
[0074] Specifically, the number of times each numbered area is used as the final numbered area in all sodium dihydrogen hypophosphite production processes is counted, and the ratio of the number of times each numbered area is used as the final numbered area to the number of sodium dihydrogen phosphate production processes is recorded as the temperature data confidence of each numbered area.
[0075] Step S006: remove the temperature sensor according to the confidence level of the temperature data in each numbered area to optimize the production monitoring of sodium dihydrogen phosphate.
[0076] The confidence threshold ε=0.8 is preset in this embodiment, and is described by taking this as an example. Other values may be set in other implementations, and this embodiment does not limit this.
[0077] For the i′th final numbered area, when the confidence of the temperature data of the i′th final numbered area is greater than or equal to the confidence threshold ε, it means that the confidence of the data collected by the temperature sensor in this numbered area is relatively high, and the sensor in the i′th final numbered area is retained; when the confidence of the temperature data of the i′th final numbered area is less than the confidence threshold ε, it means that the confidence of the data collected by the temperature sensor in this numbered area is relatively low, and the temperature sensor in the i′th final numbered area is marked as a sensor to be removed.
[0078] Obtain all sensors to be removed and remove them, effectively avoiding a large amount of inaccurate and duplicate data from being uploaded to the cloud server, and performing a deep cleansing of the data, saving storage space on the cloud server. Secondly, as the accuracy of the data is improved and the amount of data is greatly reduced, the cloud server can process the uploaded data more efficiently and accurately, thus optimizing the production monitoring of sodium dihydrogen phosphate based on the Internet of Things.
[0079] It should be noted that the exp(-x) model used in this embodiment only indicates that the result of the negative correlation and constraint model output is in the interval (0,1], where x is the input of this model. It can be replaced by other models with the same purpose during specific implementation. This embodiment only takes the exp(-x) model as an example for description without making any specific limitation.
[0080] This is the end of the present invention.
[0081] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for monitoring the production of sodium dihydrogen phosphate based on the Internet of Things, characterized in that: The method comprises the following steps: Collect the temperature data sequence of each temperature sensor in the production process of several sodium dihydrogen hypophosphite, each temperature sensor corresponds to a numbered area to obtain the temperature data of each numbered area; According to the change rate of each temperature data of each numbered area over time, the temperature data sensitivity of each numbered area is obtained; According to the temperature data sensitivity difference between each numbered area and the adjacent numbered area, the temperature data confidence of the numbered area adjacent to each numbered area is obtained; According to the temperature data sensitivity of each numbered area and the temperature data confidence of the numbered areas adjacent to each numbered area, the correlation between each numbered area and the adjacent numbered areas is obtained; and according to the correlation between each numbered area and the adjacent numbered areas, the final numbered area is obtained; According to the number of times each numbered area is used as the final numbered area in different sodium dihydrogen phosphate production processes, the confidence of the temperature data of each numbered area is obtained; The temperature sensors are removed according to the confidence level of the temperature data in each numbered area to optimize the production monitoring of sodium dihydrogen phosphate; The step of obtaining the temperature data sensitivity of each numbered area according to the change rate of each temperature data of each numbered area over time includes: The specific calculation formula for the temperature data sensitivity of the i-th numbered area is: Among them, B i represents the temperature data sensitivity of the ith numbered area; m represents the number of sampled temperature data; m-1 represents the number of sampled temperature data other than the first sampled temperature data; T i,j represents the jth sampled temperature data of the i-th numbered area; T i,j-1 represents the j-1th sampled temperature data of the i-th numbered area; ΔS represents the time difference between adjacent sampled temperature data; T i ′ represents the first sampled temperature data of the ith numbered area; T i ″ represents the last sampled temperature data of the ith numbered area; norm() is a linear normalization function; The specific method of obtaining the sampled temperature data is as follows: Uniformly select m temperature data from the production process of the i-th numbered area and record them as the sampled temperature data of the i-th numbered area; The specific acquisition method of the production process is: The moment when the value of the temperature sensor starts to change is recorded as the start of production, and the moment when the values of all temperature sensors remain stable after the start of production is recorded as the end of production. The production process from the start of production to the end of production is regarded as a temperature sensor production process; The step of obtaining the temperature data confidence of the numbered area adjacent to each numbered area according to the temperature data sensitivity difference between each numbered area and the adjacent numbered area includes: Any numbered area adjacent to the ith numbered area is recorded as the dth numbered area, and the calculation formula for the temperature data confidence of the dth numbered area adjacent to the ith numbered area is: Among them, K i,d represents the confidence level of the temperature data of the dth numbered area adjacent to the ith numbered area; D i represents the number of numbered regions adjacent to the i-th numbered region; B i Indicates the temperature data sensitivity of the ith numbered area; B i,d represents the temperature data sensitivity of the dth numbered area adjacent to the ith numbered area; || represents the absolute value function; exp() represents the exponential function with a natural constant as the base; The step of obtaining the correlation between each numbered region and adjacent numbered regions according to the temperature data sensitivity of each numbered region and the temperature data confidence of the numbered regions adjacent to each numbered region includes: The calculation formula for the association between the ith numbered region and the adjacent numbered region is: Among them, C i Indicates the association between the ith numbered region and the adjacent numbered regions; D i represents the number of numbered regions adjacent to the i-th numbered region; K i,d represents the confidence level of the temperature data of the dth numbered area adjacent to the ith numbered area; S i represents the time length of the production process of the ith numbered area; S i,d H represents the time length of the production process of the dth numbered area adjacent to the ith numbered area; i,d Indicates the similarity between the ith numbered region and the adjacent dth numbered region; sigmoid() indicates the Sigmoid function; || indicates the absolute value function; The specific method of obtaining the similarity degree is: The difference between the ratio of the temperature data sensitivity of the ith numbered region and the adjacent dth numbered region and 1 is calculated, and the reciprocal of the absolute value of the difference is recorded as the similarity between the ith numbered region and the adjacent dth numbered region.
2. The method for monitoring sodium dihydrogen phosphate production based on the Internet of Things according to claim 1, characterized in that: The obtaining of the final numbered area according to the association between each numbered area and the adjacent numbered areas includes: A correlation threshold is preset, and when the correlation between the ith numbered area and the adjacent numbered area is greater than the correlation threshold, the numbered area adjacent to the ith numbered area is deleted from all numbered areas, and the temperature data of the ith numbered area is used to represent the temperature data in the adjacent numbered areas; When the correlation between the i-th numbered region and the adjacent numbered region is less than the correlation threshold, the i-th numbered region and the adjacent numbered region are retained and renumbered to obtain a new numbered region; The correlation between each numbering region and the adjacent numbering region is calculated based on the new numbering region, and the numbering region whose correlation is greater than the correlation threshold is deleted from all numbering regions, and so on, until the correlation between each numbering region and the adjacent numbering region is less than or equal to the correlation threshold, all new numbering regions constitute the final numbering region of the current production process.
3. The method for monitoring sodium dihydrogen phosphate production based on the Internet of Things according to claim 1, characterized in that: The specific method for obtaining the temperature data confidence of each numbered area is: The number of times each numbered area is used as the final numbered area in all sodium dihydrogen hypophosphite production processes is counted, and the ratio of the number of times each numbered area is used as the final numbered area to the number of sodium dihydrogen phosphate production processes is recorded as the temperature data confidence of each numbered area.
4. The method for monitoring sodium dihydrogen phosphate production based on the Internet of Things according to claim 1, characterized in that: The removing of the temperature sensor according to the confidence level of the temperature data of each numbered area comprises: A confidence threshold is preset. For the i′th final numbered area, when the confidence of the temperature data of the i′th final numbered area is less than the confidence threshold, the temperature sensor of the i′th final numbered area is marked as a sensor to be removed, all sensors to be removed are obtained, and the sensors to be removed are removed.
