A method and system for calibrating batching accuracy of batching equipment

Abstract

The present invention relates to the field of equipment calibration, and more specifically, to a method and system for calibrating the batching accuracy of batching equipment. The method comprises: obtaining the time sequence number and calibration times of the target equipment and the reference equipment in each sampling period, and calculating the required calibration degree of the equipment according to the time sequence number and the calibration times; calculating the difference between the reference equipment and the target equipment, and determining the phase compensation parameter according to the difference; compensating the required calibration degree using the phase compensation parameter to obtain the compensated required calibration degree; weighted averaging the compensated required calibration degree, and calculating the weighted required calibration degree in combination with the required calibration degree of the target equipment, and traversing to obtain the weighted required calibration degree of each sampling period to complete the calibration of the equipment batching accuracy. Through the technical solution of the present invention, the prediction calibration effect can be improved, and the waste of human, material and financial resources caused by inaccurate calibration time can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of equipment calibration, and more specifically, to a method and system for calibrating the batching accuracy of batching equipment. Background Art

[0002] In the production process of powder metallurgy, batching plays a vital role as the starting step. This step requires mixing various metal powders in strict proportions to ensure that the physical and chemical properties of the final product meet the design requirements. The accuracy of the batching directly affects the microstructure of the material, which in turn determines the key properties of the product such as strength, hardness, and toughness. Once the batching ratio deviates, it will not only cause unstable product quality, but may also cause the entire batch of products to be scrapped, bringing high cost losses to the company, including waste of raw materials, production delays, and possible loss of customer trust. Therefore, maintaining the high accuracy and stability of the batching equipment and avoiding batching errors by calibrating the batching equipment are the core of ensuring efficient production processes and reliable product quality.

[0003] The ARIMA model is widely used in time series forecasting scenarios. However, the ARIMA model is based on historical data for prediction, has high data volume requirements, and is sensitive to data outliers. If the input data is abnormal, it will greatly affect the accuracy of the ARIMA model output, resulting in poor prediction calibration results. Summary of the invention

[0004] In order to solve the problem of poor prediction calibration effect, the present invention proposes a calibration method and system for batching accuracy of batching equipment.

[0005] In a first aspect, the present invention discloses a calibration method for batching accuracy of batching equipment, comprising: taking any device as a target device, taking a device with the same model as the target device as a reference device, obtaining the time sequence number and the calibration number of the target device and the reference device in each sampling period, and calculating the calibration required degree of the device according to the time sequence number and the calibration number, wherein the device includes the target device and the reference device; calculating the absolute value of the difference between the calibration required degree of the reference device and the target device in the same sampling period, adding all the absolute values ​​of the difference to obtain the average value as the difference between the reference device and the target device, and determining a phase compensation parameter according to the difference; compensating the calibration required degree by using the phase compensation parameter to obtain the compensated calibration required degree; weighted averaging the compensated calibration required degree, and calculating the weighted calibration required degree in combination with the calibration required degree of the target device, traversing to obtain the weighted calibration required degree of each sampling period, so as to complete the calibration of the equipment batching accuracy; wherein the weighted calibration required degree satisfies the relationship:

[0006] , Indicates that the target device is The weighted calibration of each sampling period is required. represents the total number of reference devices, Indicates The weight of the reference device, Indicates The reference device is in After compensation of a sampling period, the calibration is required. Indicates that the target device is The calibration required for each sampling period.

[0007] By obtaining the calibration time sequence number and number of the target device and the reference device of the same model in each sampling period, the required calibration degree is calculated, providing basic data for device calibration. Then, by comparing the difference in the required calibration degree between the reference device and the target device in the same sampling period, the difference degree is calculated, and the phase compensation parameters are determined accordingly, which effectively eliminates the differences between devices and enhances the consistency and reliability of calibration. By introducing weights and compensation mechanisms, the balance and coordination of different devices during the calibration process are ensured.

[0008] Preferably, the required calibration degree satisfies the relationship: for any sampling period, the square of the difference between the sampling period number of the computing device and the calibration time number is negatively correlated to obtain the mapping value; the mapping value of each calibration is traversed to obtain the sum of all the mapping values ​​as the required calibration degree of the sampling period.

[0009] By calculating the square of the difference between the sampling period serial number and the calibration time serial number of the device, and converting these square differences into mapping values ​​using negative correlation mapping, the relative relationship between the sampling period and the calibration time is effectively quantified, which not only improves the calibration quality, but also reduces the impact of accidental errors and systematic deviations, providing a more accurate reference for equipment calibration.

[0010] Preferably, the calibration required also includes: taking the first sampling cycle of the device as the initial cycle, taking any sampling cycle as the research cycle, adding and normalizing the number of calibrations from the initial cycle to the research cycle as the calibration required for the research cycle.

[0011] Preferably, the calibration degree after compensation satisfies the relationship:

[0012] , Indicates The reference device is in After compensation of a sampling period, the calibration is required. Indicates Number of calibrations of reference devices, represents the sampling period, Indicates Reference device The time sequence number of the calibration. Indicates Phase compensation parameters of a reference device, Represents an exponential function.

[0013] By introducing phase compensation parameters, the phase difference between the reference device and the target device due to its own machine state is reduced, thereby improving the data referenceability of the reference device.

[0014] Preferably, determining the phase compensation parameter based on the difference degree includes: taking the difference between the time serial numbers of two adjacent calibrations of the device as the calibration interval, and taking the mean of all calibration intervals of the device as the average calibration interval; taking the maximum value between the average calibration interval of the target device and the average calibration interval of the reference device as the upper limit of the value range of the phase compensation parameter, and the lower limit of the value range is 0, traversing and calculating the calibration degree corresponding to each phase compensation parameter in the value range, calculating the difference degree between the reference device and the target device under each phase compensation parameter, and taking the phase compensation parameter corresponding to the minimum difference degree as the optimal phase compensation parameter.

[0015] By setting the value range of the phase compensation parameter, the rationality of the phase compensation parameter setting is ensured, the accuracy of equipment calibration is improved, and the representativeness and accuracy of the equipment calibration data in different sampling periods are ensured.

[0016] Preferably, the value range also includes: taking the difference between the time serial numbers of two adjacent calibrations of the device as the calibration interval, and using PCA to calculate the importance of each calibration interval of the device; taking the maximum value of the most important calibration interval of the target device and the most important calibration interval of the reference device as the upper limit of the value range of the phase compensation parameter, and the lower limit of the value range is 0.

[0017] Preferably, the weight includes: normalizing the difference between the number of calibrations of the target device and the reference device as the first difference; taking the difference in the time sequence numbers of two adjacent calibrations of the device as the calibration interval, and taking the average of all calibration intervals of the device as the average calibration interval; normalizing the difference between the average calibration intervals of the target device and the reference device as the second difference; calculating the product of the first difference, the second difference and the degree of difference, and taking the difference between 1 and the product as the weight.

[0018] The first difference reflects the relative deviation of the two devices in the calibration frequency, and the second difference quantifies the difference in the calibration regularity of the two devices. Using the difference between 1 and the product as a weight to adjust and optimize the calibration process not only improves the accuracy and adaptability of the calibration process, but also enhances the sensitivity to the differences in the calibration characteristics of the devices, ensuring the accuracy and reliability of the calibration results.

[0019] In a second aspect, the present invention discloses a system for calibrating the batching accuracy of a batching equipment, comprising: a processor; and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the system executes the above-mentioned method for calibrating the batching accuracy of a batching equipment.

[0020] Beneficial effects of the present invention:

[0021] 1. The present invention calculates the first difference and the second difference, and obtains a weight for weighting the degree of calibration according to the first difference, the second difference and the degree of difference. The calculation of this weight takes into account the relative changes in the calibration frequency and time interval, thereby more accurately reflecting the synchronization and consistency between devices.

[0022] 2. The present invention takes into account the influence of the calibration interval and enriches the determination method of the phase compensation parameter value interval, so as to adaptively obtain the optimal phase compensation parameter corresponding to each reference device. The calculation formula of the calibration degree required after compensation realizes accurate compensation of the calibration degree by summing the exponential decay function of the reference device calibration times and the time sequence number.

[0023] 3. The present invention improves the calibration efficiency of batching equipment, reduces the waste of resources caused by improper calibration, and ensures the accuracy and consistency of batching results. It can significantly improve production efficiency, reduce maintenance costs, and ensure product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] 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 accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0025] Figure 1 The present invention is a flowchart of a method for calibrating the batching accuracy of a batching device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0027] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description 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 collections.

[0028] The present invention provides a method for calibrating the batching accuracy of batching equipment. Figure 1 As shown, a method for calibrating the batching accuracy of a batching equipment includes steps S1 to S4, which are described in detail below.

[0029] S1, obtaining the time sequence number and calibration times of the target device and the reference device in each sampling period, and calculating the required calibration degree of the device according to the time sequence number and the calibration times.

[0030] It should be noted that studying a single device for batching accuracy calibration will usually result in poor calibration results due to the small amount of data. This is because other devices with the same model as the batching equipment to be predicted are similar in design, construction and performance, and their calibration cycles and performance degradation patterns often exhibit similar behaviors. Therefore, the database can be enriched with the historical calibration time of other devices with the same model as the batching equipment to be predicted.

[0031] In one embodiment, the batching equipment to be predicted is taken as the target equipment, and the equipment with the same model as the target equipment is taken as the reference equipment, and the time sequence number and calibration number of the target equipment and the reference equipment when they are calibrated at any time in the preset sampling total period are obtained.

[0032] Exemplarily, the preset total sampling period is set to 120 days, with each day being one sampling period. If the target device or the reference device is calibrated 5 times in the preset total sampling period, namely the 6th day, the 23rd day, the 48th day, the 70th day and the 105th day, then the time numbers are 6, 23, 48, 70 and 105 respectively. The specific values ​​can be determined by technicians in this field based on actual measurements.

[0033] The calibration degree required for the device is calculated according to the time sequence number and the number of calibrations, and the devices include the target device and the reference device.

[0034] The process of calculating the required calibration degree specifically includes: for any sampling period, calculating the square of the difference between the sampling period serial number of the device and the calibration time serial number, and performing negative correlation mapping on the square of the difference to obtain a mapping value; traversing to obtain the mapping value of each calibration, and taking the sum of all mapping values ​​as the required calibration degree of the sampling period. The negative correlation mapping can use an exponential function.

[0035] The calculation process of the calibration degree needs to satisfy the relationship:

[0036] , Indicates The reference device is in The calibration required for each sampling period is Indicates Number of calibrations of reference devices, represents the sampling period, Indicates Reference device The time sequence number of the calibration. Represents an exponential function.

[0037] The calibration degree required for the reference device in each sampling period is obtained by traversal.

[0038] The target device needs to be calibrated in each sampling period to meet the relationship:

[0039] , Indicates that the target device is The calibration required for each sampling period is Indicates the number of calibrations. represents the sampling period, Indicates the target device The time sequence number of the calibration. Represents an exponential function.

[0040] In one embodiment, the first sampling cycle of the device is taken as the initial cycle, any sampling cycle is taken as the research cycle, and the calibration times from the initial cycle to the research cycle are added and normalized to obtain the calibration required for the research cycle.

[0041] S2, calculating the absolute value of the difference between the reference device and the target device in the same sampling period, adding up all the absolute values ​​of the difference and taking the average as the difference between the reference device and the target device, and determining the phase compensation parameter according to the difference.

[0042] In one embodiment, the difference between the reference device and the target device is calculated, and the difference satisfies the relationship:

[0043] , Indicates The difference between the reference device and the target device, Represents the total sampling period, Indicates The reference device is in The calibration required for each sampling period is Indicates that the target device is The calibration required for each sampling period is Represents the normalization function.

[0044] The difference between the time serial numbers of two consecutive calibrations of the equipment is taken as the calibration interval, and the average of all calibration intervals of the equipment is taken as the average calibration interval.

[0045] It should be noted that when the difference between the average calibration intervals of the reference device and the target device is low, it means that the time sequence numbers of the calibration of the reference device and the target device are similar; when the difference between the reference device and the target device is high, it means that the calibration operations of the reference device and the target device are very different. In this case, the calibration data of the current reference device is of low reference value when the target device is subsequently predicted to calibrate the ingredients. If the difference between the average calibration intervals of the reference device and the target device is low and the difference is high, this is caused by the phase difference. At this time, the phase compensation parameters can be determined by the difference to reduce the situation where the difference between the reference device and the target device is high due to the phase difference.

[0046] The basic principle of phase compensation involves measuring and correcting the phase offset of the signal. Based on the measurement results, the phase offset is calculated and corrected. This process can be achieved through different technologies and algorithms such as digital filtering and frequency synthesis. In order to maintain the accurate phase of the signal in real time, a feedback control mechanism is usually used to adjust the phase compensation parameters in real time based on the measurement and correction results.

[0047] Determining the phase compensation parameter according to the difference includes: taking the difference of the time serial numbers of two adjacent calibrations of the device as the calibration interval, and taking the average of all the calibration intervals of the device as the average calibration interval.

[0048] The maximum value between the average calibration interval of the target device and the average calibration interval of the reference device is taken as the upper limit of the value range of the phase compensation parameter, and the lower limit of the value range is 0. The calibration degree corresponding to each phase compensation parameter in the value range is traversed and calculated, and the difference between the reference device and the target device under each phase compensation parameter is calculated. The phase compensation parameter corresponding to the minimum difference is taken as the optimal phase compensation parameter.

[0049] Exemplarily, the time numbers for calibration of the target device are 5, 7, 9, 11, 13 and 15, and the time numbers for calibration of the reference device are 6, 8, 10, 12, 14 and 16, respectively. The average calibration intervals of the target device and the reference device are both 2. Then the upper limit of the value range of the phase compensation parameter is 2, and the lower limit is 0. Then the values ​​of the phase compensation parameter are 0, 1 and 2, respectively.

[0050] When the phase compensation parameter value is 0, the time sequence number for calibration of the reference device is still 6, 8, 10, 12, 14 and 16, and the difference between the reference device and the target device is calculated; when the phase compensation parameter value is 1, the time sequence number for calibration of the reference device becomes 7, 9, 11, 13, 15 and 17, and the difference between the new reference device and the target device is calculated; when the phase compensation parameter value is 2, the time sequence number for calibration of the reference device becomes 8, 10, 12, 14, 16 and 18, and the difference between the new reference device and the target device is calculated.

[0051] The differences corresponding to the phase compensation parameters of 0, 1 and 2 are compared, and the phase compensation parameter corresponding to the minimum difference is taken as the optimal phase compensation parameter.

[0052] In one embodiment, the value range of the phase compensation parameter also includes: taking the difference between the time numbers of two adjacent calibrations of the device as the calibration interval, and using PCA to calculate the importance of each calibration interval of the device; taking the maximum value of the most important calibration interval of the target device and the most important calibration interval of the reference device as the upper limit of the value range of the phase compensation parameter, and the lower limit of the value range is 0.

[0053] S3, using the phase compensation parameter to compensate for the degree to be calibrated, and obtaining the degree to be calibrated after compensation.

[0054] In one embodiment, the calibration degree after compensation satisfies the relationship:

[0055] , Indicates The reference device is in After compensation of a sampling period, the calibration is required. Indicates Number of calibrations of reference devices, represents the sampling period, Indicates Reference device The time sequence number of the calibration. Indicates Phase compensation parameters of a reference device, Represents an exponential function.

[0056] S4, weighted average of the calibration required after compensation, and calculate the weighted calibration required in combination with the calibration required of the target equipment, and traverse to obtain the weighted calibration required for each sampling period to complete the equipment batching accuracy calibration.

[0057] It should be noted that the reference device may also have machine differences. When the calibration time difference with the target device is high, the reference device's reference for predicting the target device's batching accuracy is reduced. Therefore, when using the calibration time of the reference device to enrich the sample, the reference device with a high calibration time difference with the target device should be assigned a lower weight to ensure full use of existing data while reducing the inaccuracy of the data used for prediction due to machine differences. In this process, the weight can be set by those skilled in the art based on experience.

[0058] In one embodiment, calculating the weight includes: normalizing the difference between the number of calibrations of the target device and the reference device as a first difference; normalizing the difference between the average calibration intervals of the target device and the reference device as a second difference; calculating the product of the first difference, the second difference and the degree of difference, and using the difference between 1 and the product as the weight.

[0059] Calculate the weighted calibration required, the weighted calibration required satisfies the relationship:

[0060] , Indicates that the target device is The weighted calibration of each sampling period is required. represents the total number of reference devices, Indicates The weight of the reference device, Indicates The reference device is in After compensation of a sampling period, the calibration is required. Indicates that the target device is The calibration required for each sampling period.

[0061] The weighted calibration degree required for each sampling period is obtained by traversing, and a weighted calibration degree sequence is obtained. The weighted calibration degree sequence is input into the ARIMA model (Auto-Regressive Moving Average Model), and the future weighted calibration degree required for the future marked moment adjacent to the current moment is output. When the future weighted calibration degree required is greater than or equal to the preset calibration threshold, the future marked moment is marked as the time sequence number that needs calibration. Exemplarily, the preset calibration threshold is set to 0.6.

[0062] Exemplarily, according to the preset sampling total period of step S1, it is set to 120 days, and the weighted calibration degree sequence constructed by 120 weighted calibration degrees is input into the ARIMA model, and the future weighted calibration degree on the 121st day is output. If the future weighted calibration degree on the 121st day is 0.7, then the 121st day is marked as the time sequence number that needs to be corrected; if the calculated future weighted calibration degree on the 121st day is less than 0.6, then the future weighted calibration degree of subsequent days will continue to be predicted.

[0063] An embodiment of the present invention further discloses a system for calibrating the batching accuracy of a batching device, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for calibrating the batching accuracy of a batching device according to the present invention is implemented.

[0064] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0065] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0066] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0067] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for calibrating the batching accuracy of a batching equipment, characterized in that: include: Take any device as the target device and the device with the same model as the target device as the reference device, obtain the time sequence number and calibration times of the target device and the reference device in each sampling period, and calculate the required calibration degree of the device according to the time sequence number and calibration times, satisfying the relationship: For any sampling period, the square of the difference between the sampling period serial number of the device and the calibration time serial number is calculated, and the square of the difference is negatively correlated to obtain a mapping value; Traverse to obtain the mapping value of each calibration, and use the sum of all mapping values ​​as the calibration degree required for the sampling period; The calculation process of the required calibration degree satisfies the relationship: , Indicates The reference device is in The calibration required for each sampling period is Indicates Number of calibrations of reference devices, represents the sampling period, Indicates Reference device The time sequence number of the calibration. represents the exponential function; Traverse to obtain the calibration degree required for the reference device in each sampling period; The target device needs to be calibrated in each sampling period to meet the relationship: , Indicates that the target device is The calibration required for each sampling period is Indicates the number of calibrations. Indicates the target device The time sequence number of the calibration; The required calibration also includes: The first sampling cycle of the equipment is taken as the initial cycle, any sampling cycle is taken as the research cycle, and the calibration times from the initial cycle to the research cycle are added and normalized as the calibration required for the research cycle; Devices include target devices and reference devices; Calculate the absolute value of the difference between the reference device and the target device in the same sampling period, add all the absolute values ​​of the difference and take the average as the difference between the reference device and the target device, satisfying the relationship: , Indicates The difference between the reference device and the target device, Represents the total sampling period, represents the normalization function; The phase compensation parameters are determined according to the difference, including: The difference between the time serial numbers of two consecutive calibrations of the equipment is taken as the calibration interval, and the average of all calibration intervals of the equipment is taken as the average calibration interval; The maximum value between the average calibration interval of the target device and the average calibration interval of the reference device is taken as the upper limit of the value interval of the phase compensation parameter, and the lower limit of the value interval is 0. The calibration degree required corresponding to each phase compensation parameter in the value interval is traversed and calculated, and the difference between the reference device and the target device under each phase compensation parameter is calculated. The phase compensation parameter corresponding to the minimum difference is taken as the optimal phase compensation parameter. The phase compensation parameter is used to compensate the required calibration degree, and the required calibration degree after compensation is obtained, which satisfies the relationship: , Indicates The reference device is in After compensation of a sampling period, the calibration is required. Indicates Phase compensation parameters of a reference device; The weighted average of the calibration required after compensation is calculated, and the weighted calibration required is calculated in combination with the calibration required of the target equipment. The weighted calibration required for each sampling period is obtained by traversing to complete the equipment batching accuracy calibration. Among them, the weighted calibration degree satisfies the relationship: , Indicates that the target device is The weighted calibration of each sampling period is required. represents the total number of reference devices, Indicates The weight of a reference device.

2. The method for calibrating the batching accuracy of a batching equipment according to claim 1, characterized in that: The value range also includes: The time sequence difference between two consecutive calibrations of the equipment is taken as the calibration interval, and the importance of each calibration interval of the equipment is calculated using PCA; The maximum value of the most important calibration interval of the target device and the most important calibration interval of the reference device is used as the upper limit of the value interval of the phase compensation parameter, and the lower limit of the value interval is 0.

3. The method for calibrating the batching accuracy of a batching equipment according to claim 1, characterized in that: The weights include: Normalizing the difference between the calibration times of the target device and the reference device as a first difference; The difference between the time serial numbers of two consecutive calibrations of the equipment is taken as the calibration interval, and the average of all calibration intervals of the equipment is taken as the average calibration interval; Normalizing the difference between the average calibration intervals of the target device and the reference device as a second difference; The product of the first difference, the second difference and the degree of difference is calculated, and the difference between 1 and the product is used as a weight.

4. A calibration system for batching equipment batching accuracy, characterized in that: include: Processor; and A memory storing computer instructions, wherein when the computer instructions are executed by a processor, the system executes a method for calibrating the batching accuracy of a batching equipment according to any one of claims 1 to 3.

Images