Method and system for predicting and correcting internal temperature of industrial equipment
By collecting and fitting the internal and housing temperature data of the motor, and creating a temperature prediction model, the problem that the existing technology cannot accurately monitor the internal temperature of the motor is solved, and the accuracy and safety of temperature monitoring are improved.
Patent Information
- Application Number
- CN202411850032.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-16
- Publication Date
- 2025-05-06
AI Technical Summary
The existing motor temperature monitoring methods cannot accurately reflect the internal temperature and rely on manual monitoring, which has hysteresis and potential dangers.
By setting device parameters and multiple sets of acquisition parameters, collecting internal and housing temperature data, performing linear fitting, and creating a temperature prediction model to predict the internal temperature of the motor from a long distance using a contactless infrared sensor.
It improves the accuracy of temperature abnormality monitoring, reduces the dependence of manual monitoring, and reduces hysteresis and potential dangers.
Smart Images
Figure CN119940597A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of temperature processing technology, and in particular to a method and system for predicting and correcting the internal temperature of industrial equipment. Background Art
[0002] With the rapid popularization of intelligent manufacturing technology around the world, automation equipment has been widely used in various manufacturing companies. As one of the key components of these automation equipment, the motor provides the necessary power support for the operation of these industrial equipment. Therefore, it is necessary to monitor the operating temperature of the motor in real time to prevent equipment damage and significant economic losses caused by overheating.
[0003] At present, the existing monitoring method mainly uses long-distance infrared sensors to obtain the motor shell temperature in real time at a long distance by taking advantage of its non-contact characteristics. However, this monitoring method has an obvious problem, that is, it cannot accurately reflect the actual temperature of the internal motor, because the internal temperature may have risen to an abnormal level, while the shell temperature is still within the normal range. This makes the abnormal temperature monitoring of the motor face certain challenges. In addition, the existing abnormal temperature monitoring method of the motor mainly relies on manual monitoring, which is not only inefficient, but also has certain lags and potential dangers. Summary of the invention
[0004] Based on this, it is necessary to provide a method and system for predicting and correcting the internal temperature of industrial equipment in order to address the problem that the existing monitoring method cannot accurately reflect the actual temperature of the internal motor and relies on manual monitoring, resulting in lag and potential danger.
[0005] On the one hand, the present application provides a method for predicting and correcting the internal temperature of industrial equipment, comprising:
[0006] Set device parameters and multiple groups of acquisition parameters, start the device and acquire device temperature data under each group of acquisition parameters to obtain multiple groups of device temperature data; the device temperature data includes the internal temperature of the device and the outer shell temperature of the device;
[0007] Based on the multiple sets of device temperature data, marking the data points corresponding to each set of device temperature data in the first plane rectangular coordinate system;
[0008] Perform linear fitting on the data points corresponding to each set of device temperature data to create a device temperature line corresponding to each set of device temperature data;
[0009] A temperature prediction model is created based on the slope of the device temperature line and the intercept of the device temperature line; the temperature prediction model includes a slope model and an intercept model.
[0010] On the other hand, the present application also provides a system for predicting and correcting the internal temperature of industrial equipment, the system comprising:
[0011] A collection component, through which temperature data of a target device is collected;
[0012] The processing component is communicatively connected with the acquisition component, and the temperature data of the target device acquired by the acquisition component is transmitted to the processing component, and the processing component executes the internal temperature prediction and correction method of the industrial equipment as mentioned above on the temperature data.
[0013] The present application relates to a method and system for predicting and correcting the internal temperature of industrial equipment. The method for predicting and correcting the internal temperature of industrial equipment sets equipment parameters and multiple sets of acquisition parameters. After starting the equipment, the equipment temperature data under each set of acquisition parameters is collected according to the acquisition parameters to obtain multiple sets of equipment temperature data. Then, based on the multiple sets of equipment temperature data, the data points corresponding to each set of equipment temperature data are marked in the first plane rectangular coordinate system, and the data points corresponding to each set of equipment temperature data are linearly fitted to create an equipment temperature line corresponding to each set of equipment temperature data. Finally, a temperature prediction model is created based on the slope of the equipment temperature line and the intercept of the equipment temperature line. The temperature prediction model includes a slope model and an intercept model. The present application helps to use a non-contact infrared sensor to remotely predict the real temperature inside the motor of an industrial equipment wrapped in a shell, thereby improving the accuracy of temperature anomaly monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 A schematic flow chart of a method for predicting and correcting the internal temperature of industrial equipment provided in one embodiment of the present application.
[0015] Figure 2 A schematic diagram of the structure of a system for predicting and correcting the internal temperature of industrial equipment provided in one embodiment of the present application.
[0016] Figure 3 A schematic diagram of linear fitting of a method for predicting and correcting the internal temperature of industrial equipment provided in one embodiment of the present application.
[0017] Reference numerals:
[0018] 100. Collection component; 200. Processing component. DETAILED DESCRIPTION
[0019] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0020] The present application provides a method and system for predicting and correcting the internal temperature of industrial equipment.
[0021] like Figure 1 As shown, in one embodiment of the present application, a method for predicting and correcting the internal temperature of the industrial equipment is provided, and the method for predicting and correcting the internal temperature of the industrial equipment includes:
[0022] S100, setting device parameters and multiple sets of acquisition parameters, starting the device and acquiring device temperature data under each set of acquisition parameters to obtain multiple sets of device temperature data. The device temperature data includes the device internal temperature and the device shell temperature.
[0023] S200 , based on multiple sets of device temperature data, marking data points corresponding to each set of device temperature data in a first plane rectangular coordinate system.
[0024] S300, performing linear fitting on the data points corresponding to each set of device temperature data, and creating a device temperature line corresponding to each set of device temperature data.
[0025] S400: Create a temperature prediction model based on the slope of the device temperature line and the intercept of the device temperature line. The temperature prediction model includes a slope model and an intercept model.
[0026] In this embodiment, by setting device parameters and multiple sets of acquisition parameters, after starting the device, the device temperature data under each set of acquisition parameters is collected according to the acquisition parameters, and multiple sets of device temperature data are obtained. Then, based on the multiple sets of device temperature data, the data points corresponding to each set of device temperature data are marked in the first plane rectangular coordinate system, and the data points corresponding to each set of device temperature data are linearly fitted to create a device temperature line corresponding to each set of device temperature data. Finally, a temperature prediction model is created based on the slope of the device temperature line and the intercept of the device temperature line. The temperature prediction model includes a slope model and an intercept model. The present application helps to use a non-contact infrared sensor to remotely predict the real temperature inside the motor of an industrial device wrapped in a shell, thereby improving the accuracy of temperature anomaly monitoring.
[0027] In one embodiment of the present application, the S100 includes:
[0028] S110, setting a collection threshold temperature and collection parameters.
[0029] Specifically, the acquisition threshold temperature is set to 35°C.
[0030] The acquisition parameters include an acquisition frequency and a total number of acquisitions. In the present application, for each target speed of a device, multiple sets of device data need to be acquired according to the acquisition parameters.
[0031] Specifically, the acquisition frequency in this application is set to 1 time / minute, and the total number of acquisitions is set to 20.
[0032] S120, setting target rotation speeds of multiple devices.
[0033] Specifically, the target speed of the device in the present application can be set to 10000RPM, 12000RPM, 13000RPM, 14000RPM, 15000RPM, 16000RPM, 17000RPM, 19000RPM, and 20000RPM.
[0034] S130, selecting a device target speed, and turning on the device until the actual speed of the device reaches the device target speed.
[0035] S140, determining whether the actual temperature of the device reaches a collection temperature threshold.
[0036] S150: If the actual temperature of the device reaches the collection temperature threshold, multiple device temperature data corresponding to the target rotation speed of the device are collected according to the collection parameters.
[0037] Specifically, the device temperature data includes the device internal temperature and the device outer shell temperature.
[0038] S160, return to S130, until the device temperature data corresponding to the target rotation speed of all devices are obtained.
[0039] In this embodiment, for each device target speed, multiple groups of device data need to be collected at the device target speed. Then, according to the collection parameters proposed in the previous embodiment, that is, the collection frequency is set to 1 time / minute, and the total number of collections is set to 20, 20 groups of device data can be collected for each device target speed.
[0040] In one embodiment of the present application, the S200 includes:
[0041] S210: Create a first plane rectangular coordinate system.
[0042] S220, selecting a device target speed.
[0043] S230, obtaining temperature data of all devices at a target rotation speed of the device.
[0044] S240, marking the corresponding position of each device temperature data on the first plane rectangular coordinate system, and recording each position as a data point.
[0045] S250, return to S220, until all device target speeds are selected, and multiple data points at each device target speed are obtained.
[0046] In this embodiment, as the device works, the temperature of the device will gradually rise over time. Therefore, the device temperature data collected at different collection nodes corresponding to each collection frequency will change. After marking these device temperature data in the first plane rectangular coordinate system, a close data temperature curve can be obtained based on multiple data points, thereby creating a temperature prediction model.
[0047] In one embodiment of the present application, the S300 includes:
[0048] S310, selecting a device target speed.
[0049] S320, performing linear fitting on all data points of the target rotation speed of the device based on the least square method to obtain an initial temperature prediction line.
[0050] Specifically, the least squares method is a mathematical optimization technique that finds the best function matching the data by minimizing the sum of squared errors.
[0051] The least squares method estimates the parameters of the model by minimizing the sum of squares of the errors, so that the difference between the predicted value and the actual value is minimized. This method has a wide range of applications in many fields, including parameter estimation, curve fitting, error estimation, system identification and prediction, etc.
[0052] S330, optimizing the initial temperature prediction line to obtain a device temperature line.
[0053] S340, returning to select a device target speed until all device target speeds are selected, and obtaining a device temperature line corresponding to each device target speed.
[0054] In this embodiment, Figure 3 As shown, by connecting multiple data points at each device target speed in sequence, it can be seen that the internal temperature of the device and the temperature of the device shell are roughly linearly related. Then, the least squares method can be used to perform linear fitting on all data points at a device target speed to obtain an initial temperature prediction line. Since the initial temperature prediction line is only obtained through linear fitting, it is also necessary to optimize the initial temperature prediction line to obtain the device temperature line.
[0055] Since there are differences between the device temperature data collected at each device target speed, an initial temperature prediction line can be obtained for each device target speed through the least squares method.
[0056] In one embodiment of the present application, the S320 includes:
[0057] S321, obtaining all data points at the target rotation speed of the device.
[0058] S22, create an initial linear model based on all data points using Formula 1.
[0059] y=mx+b formula 1.
[0060] Where y is the observed value, m is the slope of the linear model, b is the intercept of the linear model, and x is the independent variable.
[0061] Specifically, before executing S323, it is necessary to first define an objective function by using the residual sum of squares. The objective function defined by using the residual sum of squares is as described in the formula.
[0062]
[0063] Where y is the observed value, m is the slope of the linear model, b is the intercept of the linear model, x is the independent variable, n is the total number of initial temperature prediction lines, and i is the nth initial temperature prediction line.
[0064] The residual sum of squares is a quantity that measures the degree of model fit in a linear model. It is a data processing method that uses a continuous curve to approximately characterize or compare a group of discrete points on a plane to represent the functional relationship between coordinates.
[0065] S323, optimizing the slope of the initial linear model using Formula 2.
[0066]
[0067] Where m is the slope of the linear model, n is the total number of initial temperature prediction lines, xi represents the i-th independent variable, and yi represents the i-th dependent variable.
[0068] S324, optimizing the intercept of the initial linear model using Formula 3.
[0069]
[0070] Where m is the slope of the linear model, b is the intercept of the linear model, and n is the total number of initial temperature prediction lines.
[0071] S325 , combining the slope of the optimized linear model and the intercept of the optimized linear model, and establishing the device temperature line through Formula 4.
[0072] T in =m*T out +b Formula 4.
[0073] Among them, T in is the internal temperature of the device, T outis the device case temperature, m is the slope of the linear model, and b is the intercept of the linear model.
[0074] In this embodiment, an objective function is defined by the residual sum of squares, and the optimal slope m and intercept b can be solved by differentiating the objective function and setting the derivative equal to zero.
[0075] In one embodiment of the present application, the S400 includes:
[0076] S410: Create a second plane rectangular coordinate system, wherein the abscissa of the second plane rectangular coordinate system is the rotation speed of the device, and the ordinate of the second plane rectangular coordinate system is the slope.
[0077] S420, selecting target device rotation speeds in sequence, and marking a second data point corresponding to each device target rotation speed and its slope on a second plane rectangular coordinate system.
[0078] S430, creating a first fitting function according to the second data point, and recording the fitting function as z=a1x 2 +b1x+c1. Among them, m is the slope of the linear model, b is the intercept of the linear model, a1 is the square term coefficient of the first fitting function, b1 is the linear term coefficient of the first fitting function, and c1 is the constant term of the first fitting function.
[0079] S440, fitting the corresponding relationship between the rotation speed and the slope through a quadratic polynomial, thereby obtaining an actual value of the first fitting function.
[0080] In this embodiment, the relationship between the rotation speed r and the slope m is fitted by a quadratic polynomial, and the square term coefficient of the quadratic polynomial is obtained as a1, the linear term coefficient is b1, and the constant term coefficient is c1.
[0081] In one embodiment of the present application, the S440 includes:
[0082] S441, optimizing the residual sum of squares of the first fitting function using Formula 5.
[0083]
[0084] Wherein, a1 is the square term coefficient of the first fitting function, b1 is the linear term coefficient of the first fitting function, and c1 is the constant term of the first fitting function.
[0085] S442, references a1, b1 and c1, thereby constructing a linear equation system through formula 6.
[0086] Ap1=Y formula 6.
[0087] Where A is the function matrix of the first fitting function, Y is the dependent variable vector of the first fitting function, and p1 is the coefficient matrix of the first fitting function.
[0088] S443, calculate the actual values of a1, b1 and c1 using Formula 7.
[0089] p=(A T A) -1 A T Y formula 7.
[0090] Among them, A is the function matrix of the first fitting function, Y is the dependent variable vector of the first fitting function, p1 is the coefficient matrix of the first fitting function, and A T is the transposed matrix of the function matrix A.
[0091] S444, substituting the actual values of a1, b1 and c1 into the first fitting function, thereby creating a prediction model of the slope and the target speed of the device. The prediction model of the slope and the target speed of the device is shown in Formula 8.
[0092] m=a1r 2 +b1r+c1 formula 8.
[0093] Wherein, m is the slope of the linear model, r is the target device speed, a1 is the square term coefficient of the first fitting function, b1 is the linear term coefficient of the first fitting function, and c1 is the constant term of the first fitting function.
[0094] In this embodiment, the principle of quadratic polynomial fitting is the same as that of linear fitting, that is, based on the least squares method, the fitting process is similar to linear fitting, and the model parameters are determined by minimizing the residual square sum between the observed value and the model predicted value. Quadratic polynomial fitting is suitable for describing the curve relationship in the data, and compared with linear fitting, it can adapt to data changes more flexibly.
[0095] When the target speed of the device is set to 2000RPM, taking the device shell temperature as 35.3℃ as an example, according to Formula 8, the slope of the linear model can be calculated as m=2.49. According to Formula 12, the slope of the linear model can be calculated as b=-42.63.
[0096] Substituting the slope and intercept into Formula 4, we can obtain the internal temperature of the device as 45.18°C.
[0097] When the target speed of the device is set to 20000 RPM, and the device temperature data collected under the collection parameters described in this embodiment is shown in Table 1.
[0098] Table-1, Equipment temperature data table
[0099]
[0100]
[0101] In one embodiment of the present application, the S400 further includes:
[0102] S450: Create a third plane rectangular coordinate system, wherein the abscissa of the third plane rectangular coordinate system is the target rotation speed of the device, and the ordinate of the third plane rectangular coordinate system is the intercept.
[0103] S460, selecting target device rotation speeds in sequence, and marking a third data point corresponding to each device target rotation speed and its intercept on a third plane rectangular coordinate system.
[0104] S460: Create a second fitting function based on the third data point, and record the fitting function as q=a2x 2 +b2x+c2. Among them, m is the slope of the linear model, b is the intercept of the linear model, a2 is the square term coefficient of the second fitting function, b2 is the linear term coefficient of the second fitting function, and c2 is the constant term of the second fitting function.
[0105] S470, fitting the corresponding relationship between the rotation speed and the intercept by a quadratic polynomial, thereby obtaining an actual value of the third fitting function.
[0106] In this embodiment, similarly, after the relationship between the intercept and the rotational speed is solved by the least squares method, the formula of the slope and the rotational speed is also solved by the least squares method, so as to create a prediction model by combining the intercept and the slope.
[0107] In one embodiment of the present application, the S470 includes:
[0108] S471, optimizing the residual sum of squares of the second fitting function using Formula 9.
[0109]
[0110] Wherein, a2 is the square term coefficient of the second fitting function, b2 is the linear term coefficient of the second fitting function, and c2 is the constant term of the second fitting function.
[0111] S472, references a2, b2 and c2, thereby constructing a linear equation system through formula 10.
[0112] Bp2=Q formula 10.
[0113] Among them, B is the function matrix of the second fitting function, Q is the dependent variable vector of the second fitting function, and p2 is the coefficient matrix of the second fitting function.
[0114] S473, calculate the actual values of a2, b2 and c2 using formula 11.
[0115] p2=(B T B) -1 B T Q formula 11.
[0116] Among them, B is the function matrix of the second fitting function, Q is the dependent variable vector of the second fitting function, p2 is the coefficient matrix of the second fitting function, and B T is the transposed matrix of the function matrix B.
[0117] S474, substituting the actual values of a2, b2 and c2 into the second fitting function to create a prediction model of the intercept and the target speed of the device. The prediction model of the intercept and the target speed of the device is shown in Formula 12.
[0118] b=a2r 2 +b2r+c2 formula 12.
[0119] Where b is the intercept of the linear model and r is the target equipment speed.
[0120] In this embodiment, the "relationship between the slope and the rotational speed" and the "relationship between the intercept and the rotational speed" are solved using the same method, that is, they are both determined by the least squares method and the residual sum of squares, and a temperature prediction model is created based on the slope and intercept.
[0121] The absolute error and relative error at the target speed of each device as described in the above embodiment are shown in Table 1.
[0122] Table-2 Temperature Error Table
[0123] Speed RPM Absolute error (℃) Relative error 10000 0.69 1.80％ 12000 0.64 1.50％ 13000 0.23 0.57％ 14000 0.75 1.61％ 15000 0.21 0.48％ 16000 0.36 0.72％ 17000 0.22 0.40％ 18000 1.13 2.03％ 19000 0.15 0.26％ 20000 0.61 0.98％
[0124] It can be seen that most of the absolute errors are below 1°C, and most of the relative errors are below 2%, indicating the accuracy and reliability of the temperature prediction model created in this application.
[0125] like Figure 2 As shown, in one embodiment of the present application, a system for predicting and correcting the internal temperature of industrial equipment is provided. The system for predicting and correcting the internal temperature of industrial equipment includes a collection component 100 and a processing component 200 .
[0126] The temperature data of the target device is collected by the collection component 100. The collection component 100 is in communication with the processing component 200. The temperature data of the target device collected by the collection component 100 is transmitted to the processing component 200, and the processing component 200 performs the internal temperature prediction and correction method of the industrial device as described in the above embodiment on the temperature data.
[0127] In this embodiment, the acquisition component 100 acquires multiple sets of device temperature data at each device target speed, and all acquired device temperature data are input into the processing component 200, and the processing component 200 creates a temperature prediction model based on the device temperature data.
[0128] After creating the temperature prediction model, users can use a non-contact infrared sensor to remotely predict the actual temperature inside the motor of an industrial equipment wrapped in a casing based on the temperature prediction model.
[0129] The technical features of the above-described embodiments may be arbitrarily combined, and the execution order of the method steps is not limited. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0130] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for predicting and correcting the internal temperature of industrial equipment, characterized in that: The method for predicting and correcting the internal temperature of industrial equipment comprises: Set device parameters and multiple groups of acquisition parameters, start the device and acquire device temperature data under each group of acquisition parameters to obtain multiple groups of device temperature data; the device temperature data includes the internal temperature of the device and the outer shell temperature of the device; Based on the multiple sets of device temperature data, marking the data points corresponding to each set of device temperature data in the first plane rectangular coordinate system; Perform linear fitting on the data points corresponding to each set of device temperature data to create a device temperature line corresponding to each set of device temperature data; A temperature prediction model is created based on the slope of the device temperature line and the intercept of the device temperature line; the temperature prediction model includes a slope model and an intercept model.
2. The method for predicting and correcting the internal temperature of industrial equipment according to claim 1, characterized in that: The device parameters and multiple sets of acquisition parameters are set, the device is started, and the device temperature data under each set of acquisition parameters is acquired according to the set of acquisition parameters to obtain multiple sets of device temperature data, including: Set the acquisition threshold temperature and acquisition parameters; Set target speeds for multiple devices; Select a device target speed, and turn on the device until the actual speed of the device reaches the device target speed; Determine whether the actual temperature of the device reaches the acquisition temperature threshold; If the actual temperature of the device reaches the collection temperature threshold, multiple device temperature data corresponding to the target speed of the device are collected according to the collection parameters; Return and select a device target speed until the device temperature data corresponding to all device target speeds are obtained.
3. The method for predicting and correcting the internal temperature of industrial equipment according to claim 2, characterized in that: Based on the multiple sets of device temperature data, marking the data points corresponding to each set of device temperature data in the first plane rectangular coordinate system includes: Create a first plane rectangular coordinate system; Select a device target speed; Get the temperature data of all devices at the target speed of the device; Mark the corresponding position of each device temperature data on the first plane rectangular coordinate system, and record each position as a data point; Return to select a device target speed until all device target speeds are selected, and obtain multiple data points at each device target speed.
4. The method for predicting and correcting the internal temperature of industrial equipment according to claim 3, characterized in that: The performing linear fitting on the data points corresponding to each set of device temperature data to create a device temperature line corresponding to each set of device temperature data includes: Select a device target speed; Perform linear fitting on all data points of the target speed of the equipment based on the least square method to obtain the initial temperature prediction line; Optimize the initial temperature prediction line to obtain the equipment temperature line; Return to select a device target speed until all device target speeds are selected, and obtain the device temperature line corresponding to each device target speed.
5. The method for predicting and correcting the internal temperature of industrial equipment according to claim 4, characterized in that: The linear fitting of all data points of the target speed of the equipment based on the least squares method to obtain the initial temperature prediction line includes: Get all data points at the target speed of the device; Create an initial linear model based on all data points using Formula 1; y=mx+b Formula 1; Among them, y is the observed value, m is the slope of the linear model, b is the intercept of the linear model, and x is the independent variable; The slope of the initial linear model is optimized by formula 2; Where m is the slope of the linear model, n is the total number of initial temperature prediction lines, xi represents the i-th independent variable, and yi represents the i-th dependent variable; The intercept of the initial linear model is optimized by formula 3; Where m is the slope of the linear model, b is the intercept of the linear model, and n is the total number of initial temperature prediction lines; Combining the slope of the optimized linear model and the intercept of the optimized linear model, the device temperature line is established by formula 4; T in =m*T out +b Formula 4; Among them, T in is the internal temperature of the device, T out is the device case temperature, m is the slope of the linear model, and b is the intercept of the linear model.
6. The method for predicting and correcting the internal temperature of industrial equipment according to claim 5, characterized in that: The temperature prediction model is created based on the slope of the device temperature line and the intercept of the device temperature line; the temperature prediction model includes a slope model and an intercept model, including: A second plane rectangular coordinate system is created; the abscissa of the second plane rectangular coordinate system is the device rotation speed, and the ordinate of the second plane rectangular coordinate system is the slope; Select the target device speeds in turn, and mark the second data point corresponding to each device target speed and its slope on the second plane rectangular coordinate system; Create a first fitting function based on the second data point and record the fitting function as z=a1x 2 +b1x+c1; Wherein, m is the slope of the linear model, b is the intercept of the linear model, a1 is the square term coefficient of the first fitting function, b1 is the linear term coefficient of the first fitting function, and c1 is the constant term of the first fitting function; The corresponding relationship between the rotation speed and the slope is fitted by a quadratic polynomial, so as to obtain the actual value of the first fitting function.
7. The method for predicting and correcting the internal temperature of industrial equipment according to claim 6, characterized in that: The step of fitting the corresponding relationship between the rotation speed and the slope by a quadratic polynomial to obtain the actual value of the first fitting function includes: The residual sum of squares of the first fitting function is optimized by formula 5; Wherein, a1 is the square term coefficient of the first fitting function, b1 is the linear term coefficient of the first fitting function, and c1 is the constant term of the first fitting function; Refer to a1, b1 and c1 to construct a linear system of equations using Formula 6; Ap1=Y Formula 6; Where A is the function matrix of the first fitting function, Y is the dependent variable vector of the first fitting function, and p1 is the coefficient matrix of the first fitting function; The actual values of a1, b1 and c1 are calculated by formula 7; p = (A T A) -1 A T Formula 7 for Y; Among them, A is the function matrix of the first fitting function, Y is the dependent variable vector of the first fitting function, p1 is the coefficient matrix of the first fitting function, and A T is the transposed matrix of the function matrix A; Substitute the actual values of a1, b1 and c1 into the first fitting function to create a prediction model of the slope and the target speed of the device. The prediction model of the slope and the target speed of the device is shown in Formula 8; m=a1r 2 +b1r+c1 Formula 8; Wherein, m is the slope of the linear model, r is the target device speed, a1 is the square term coefficient of the first fitting function, b1 is the linear term coefficient of the first fitting function, and c1 is the constant term of the first fitting function.
8. The method for predicting and correcting the internal temperature of industrial equipment according to claim 7, characterized in that: The temperature prediction model is created based on the slope of the device temperature line and the intercept of the device temperature line; the temperature prediction model includes a slope model and an intercept model, and also includes: Creating a third plane rectangular coordinate system; the abscissa of the third plane rectangular coordinate system is the target speed of the device, and the ordinate of the third plane rectangular coordinate system is the intercept; Select the target device speeds in turn, and mark the third data point corresponding to each device target speed and its intercept on the third plane rectangular coordinate system; Create a second fitting function based on the third data point and record the fitting function as q=a2x 2 +b2x+c2; where m is the slope of the linear model, b is the intercept of the linear model, a2 is the square term coefficient of the second fitting function, b2 is the linear term coefficient of the second fitting function, and c2 is the constant term of the second fitting function; The corresponding relationship between the rotation speed and the intercept is fitted by a quadratic polynomial, so as to obtain the actual value of the third fitting function.
9. The method for predicting and correcting the internal temperature of industrial equipment according to claim 8, characterized in that: The step of fitting the corresponding relationship between the rotation speed and the intercept by a quadratic polynomial to obtain the actual value of the second fitting function includes: The residual sum of squares of the second fitting function is optimized by formula 9; Wherein, a2 is the square term coefficient of the second fitting function, b2 is the linear term coefficient of the second fitting function, and c2 is the constant term of the second fitting function; Refer to a2, b2 and c2 to construct a linear system of equations using formula 10; Bp2=Q formula 10; Wherein, B is the function matrix of the second fitting function, Q is the dependent variable vector of the second fitting function, and p2 is the coefficient matrix of the second fitting function; The actual values of a2, b2 and c2 are calculated by formula 11; p2=(B T B) -1 B T Q formula 11; Among them, B is the function matrix of the second fitting function, Q is the dependent variable vector of the second fitting function, p2 is the coefficient matrix of the second fitting function, and B T is the transposed matrix of the function matrix B; Substitute the actual values of a2, b2 and c2 into the second fitting function to create a prediction model of the intercept and the target speed of the device, wherein the prediction model of the intercept and the target speed of the device is as described in Formula 12; b=a2r 2 +b2r+c2 Formula 12; Wherein, b is the intercept of the linear model, r is the target device speed, a2 is the square term coefficient of the second fitting function, b2 is the linear term coefficient of the second fitting function, and c2 is the constant term of the second fitting function.
10. A system for predicting and correcting the internal temperature of industrial equipment, characterized in that: The internal temperature prediction and correction system of the industrial equipment comprises: A collection component, through which temperature data of a target device is collected; The processing component, the acquisition component is communicatively connected with the processing component, the temperature data of the target device acquired by the acquisition component is transmitted to the processing component, and the processing component executes the internal temperature prediction and correction method of the industrial equipment as claimed in any one of claims 1 to 9 on the temperature data.