Intelligent temperature control system for heating wire based on monitoring data analysis

Abstract

The present invention discloses an intelligent temperature control system for heating wires based on monitoring data analysis, which relates to the field of temperature control technology. The system includes: a task receiving module for obtaining heating tasks of a heating wire module, including heating target loads and load heating requirements; a load heating expectation analysis module for analyzing load heating requirements and determining multi-level temperature expectation curves; a temperature control decision module for formulating multi-level temperature control strategies according to temperature expectation curves and heating loss constraints; a temperature control monitoring module for executing temperature control strategies, heating the heating target loads, and monitoring the load temperature and heating wire status; and a monitoring data analysis module for performing temperature control compensation based on real-time data. Thus, the technical effect of improving the temperature control response speed and temperature control accuracy is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and in particular to an intelligent temperature control system for a heating wire based on monitoring data analysis. Background Art

[0002] Heating wires are widely used in temperature control systems in industries, home appliances, etc. The accuracy and stability of temperature control directly affect the performance and safety of the equipment. Existing temperature control technologies usually rely on simple temperature feedback control, which is prone to temperature overshoot in temperature fluctuation environments and difficult to achieve high-precision and intelligent temperature regulation. There are technical problems such as slow control response and low temperature control accuracy. Summary of the invention

[0003] The present invention provides an intelligent temperature control system for heating wires based on monitoring data analysis to solve the technical problems of slow control response and low temperature control accuracy in the prior art, and achieves the technical effect of improving the temperature control response speed and temperature control accuracy.

[0004] The intelligent temperature control system for heating wires based on monitoring data analysis provided by the present invention comprises:

[0005] A task receiving module is used to obtain a heating task of a heating wire module, wherein the heating wire module includes a plurality of heating wires, and the heating task includes a heating target load and a load heating requirement.

[0006] A load heating expectation analysis module is used to perform heating expectation analysis on the heating target load according to the load heating demand, and determine a multi-stage load temperature expectation curve.

[0007] A temperature control decision module is used to make a temperature control decision on the heating wire module according to the multi-stage load temperature expectation curve and in combination with the heating loss constraint to obtain a multi-stage temperature control strategy.

[0008] A temperature control monitoring module is used to heat the heating target load according to the multi-stage temperature control strategy and the heating wire module, and obtain real-time temperature data of the load and real-time monitoring data of the heating wire.

[0009] A monitoring data analysis module is used to perform temperature control compensation on the heating wire module according to the real-time temperature data of the load and the real-time monitoring data of the heating wire.

[0010] In a feasible implementation, the load heating expectation analysis module is used to perform heating expectation analysis on the heating target load according to the load heating demand and determine a multi-stage load temperature expectation curve, and the execution steps include:

[0011] An initial load temperature parameter of the heating target load is obtained.

[0012] The heating target load is divided into heating stages based on the initial load temperature parameter and the load heating requirement to obtain a plurality of load heating stages.

[0013] The material parameters and structural information of the heating target load are collected to obtain load basic data.

[0014] Based on the load basic data, heating expectation fitting is performed on the multiple load heating stages respectively, and the multi-stage load temperature expectation curve is output.

[0015] In a feasible implementation, based on the load basic data, heating expectation fitting is performed on the multiple load heating stages respectively, and the multi-stage load temperature expectation curve is output. The execution steps include:

[0016] A plurality of load normal temperature change record groups are retrieved, wherein each load temperature change record group has historical load basic data and historical load heating stages with corresponding identifiers.

[0017] Based on the multiple load heating stages, an nth load heating stage is extracted.

[0018] Based on the load basic data and the nth load heating stage, correlation evaluation is performed on the multiple load normal temperature change record groups to obtain multiple load stage correlation coefficients.

[0019] Based on the multiple load stage correlation coefficients, the multiple load normal temperature change record groups are selected according to a load stage correlation threshold to obtain an n-th stage load temperature change fitting set that is greater than / equal to the load stage correlation threshold.

[0020] Based on the n-stage load temperature change fitting set, a plurality of n-stage load temperature change fitting curves are constructed.

[0021] The plurality of n-stage load temperature change fitting curves are integrated to generate an n-stage load temperature expected curve, and the n-stage load temperature expected curve is added to the multi-stage load temperature expected curve.

[0022] In a feasible implementation, the temperature control decision module is used to make a temperature control decision on the heating wire module according to the multi-stage load temperature expectation curve and in combination with the heating loss constraint to obtain a multi-stage temperature control strategy, and the execution steps include:

[0023] According to the heating wire module, a sample stage load temperature expected curve set, a load basic data sample set and a temperature control solution sample set are retrieved.

[0024] Taking the sample stage load temperature expected curve set and the load basic data sample set as input data and the temperature control scheme sample set as output data, the BP neural network is trained to establish a temperature control decision channel, and the temperature control decision channel is embedded in the temperature control decision module.

[0025] Based on the load basic data and the expected load temperature curve of the nth stage, a temperature control plan of the nth stage is obtained according to the temperature control decision channel.

[0026] Based on the heating loss constraint, the temperature control scheme for the nth stage is optimized for heating loss to generate a temperature control strategy for the nth stage.

[0027] The nth stage temperature control strategy is added to the multi-stage temperature control strategy, and the temperature control decision is continued to be made on the heating wire module according to the multi-stage load temperature expected curve, the temperature control decision channel and the heating loss constraint to generate the multi-stage temperature control strategy.

[0028] In a feasible implementation, based on the heating loss constraint, the heating loss optimization is performed on the temperature control scheme of the nth stage to generate the temperature control strategy of the nth stage, and the execution steps include:

[0029] Based on the load basic data, heating loss prediction is performed according to the n-th stage temperature control scheme to obtain a predicted heating loss coefficient.

[0030] It is determined whether the predicted heating loss coefficient satisfies the heating loss constraint.

[0031] If the predicted heating loss coefficient satisfies the heating loss constraint, the n-stage temperature control scheme is added to the n-stage temperature control strategy.

[0032] If the predicted heating loss coefficient does not satisfy the heating loss constraint, a heating wire temperature control constraint space is activated, wherein the heating wire temperature control constraint space includes temperature control constraint information of the heating wire module.

[0033] Based on the heating loss constraint and the heating wire temperature control constraint space, the n-stage temperature control scheme is optimized to obtain the n-stage temperature control strategy.

[0034] In a feasible implementation, based on the heating loss constraint and the heating wire temperature control constraint space, the temperature control scheme of the nth stage is optimized to obtain the temperature control strategy of the nth stage, and the execution steps include:

[0035] The n-stage load temperature expected curve is used as the temperature control adjustment target, and the n-stage temperature control scheme is adjusted according to the heating wire temperature control constraint space to obtain the n-stage temperature control adjustment scheme.

[0036] Based on the load basic data, heating loss prediction is performed according to the temperature control adjustment scheme of the nth stage to obtain a heating loss coefficient of the adjustment scheme.

[0037] It is determined whether the heating loss coefficient of the adjustment scheme satisfies the heating loss constraint.

[0038] If the heating loss coefficient of the adjustment scheme satisfies the heating loss constraint, the n-th stage temperature control adjustment scheme is added to the n-th stage temperature control strategy.

[0039] In a feasible implementation, the monitoring data analysis module is used to perform temperature control compensation on the heating wire module according to the real-time temperature data of the load and the real-time monitoring data of the heating wire, and the execution steps include:

[0040] According to the multi-stage load temperature expectation curve, a current load temperature expectation curve is extracted.

[0041] A real-time load temperature curve is constructed according to the real-time load temperature data.

[0042] A deviation analysis is performed on the real-time load temperature curve based on the current load temperature expectation curve to generate a load temperature expectation deviation curve.

[0043] The heating wire module is subjected to temperature control compensation based on the load temperature expected deviation curve to generate a first temperature control compensation strategy.

[0044] The heating wire module is subjected to temperature control compensation based on the real-time monitoring data of the heating wire, and a second temperature control compensation strategy is generated.

[0045] The first temperature control compensation strategy and the second temperature control compensation strategy are integrated to generate a temperature control compensation scheme, and temperature control compensation is performed on the heating wire module according to the temperature control compensation scheme.

[0046] In a feasible implementation, the heating wire module is temperature-controlled and compensated based on the real-time monitoring data of the heating wire to generate a second temperature-controlled compensation strategy, and the execution steps include:

[0047] According to the multi-level temperature control strategy, a current temperature control strategy is extracted.

[0048] A temperature control offset comparison is performed based on the real-time monitoring data of the heating wire and the current temperature control strategy to generate a temperature control offset comparison result.

[0049] The heating wire module is subjected to temperature control compensation according to the temperature control offset comparison result to obtain the second temperature control compensation strategy.

[0050] The present invention discloses an intelligent temperature control system for heating wires based on monitoring data analysis, including: a task receiving module, which is used to obtain the heating task of the heating wire module, and the task content includes the composition of multiple heating wires, as well as the heating target load and the corresponding heating demand. A load heating expectation parsing module, which parses the heating expectation of the target load based on the heating demand of the load, and generates a multi-level load temperature expectation curve for guiding the subsequent heating control. A temperature control decision module, which makes decisions on the heating wire module according to the multi-level load temperature expectation curve and combines the heating loss constraint, and generates a multi-level temperature control strategy. A temperature control monitoring module, which controls the heating wire module according to the generated multi-level temperature control strategy, heats the target load, and monitors the load temperature and the state of the heating wire in real time during the process. A monitoring data analysis module, which performs temperature control compensation on the heating wire module by analyzing the real-time temperature of the load and the monitoring data of the heating wire, so as to ensure the accuracy and stability of the temperature control process. The intelligent temperature control system for heating wires based on monitoring data analysis disclosed by the present invention solves the technical problems of slow control response and low temperature control accuracy, and achieves the technical effect of improving the temperature control response speed and temperature control accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a structural schematic diagram of the intelligent temperature control system of the heating wire based on monitoring data analysis of the present invention;

[0052] Figure 2 The present invention is a flow chart of determining a multi-stage load temperature expected curve in the intelligent temperature control system of the heating wire based on monitoring data analysis.

[0053] Explanation of the reference numerals: task receiving module 11 , load heating expectation parsing module 12 , temperature control decision module 13 , heating wire module 14 , temperature control monitoring module 15 , monitoring data analysis module 16 . DETAILED DESCRIPTION

[0054] The technical solution provided in the embodiments of the present invention is to solve the technical problems of slow control response and low temperature control accuracy in the prior art. The overall idea adopted is as follows:

[0055] First, a task receiving module is used to receive a heating task of a heating wire module, wherein the heating wire module includes multiple heating wires, and the heating task includes a heating target load and a corresponding load heating requirement; then, a load heating expectation parsing module parses the heating target load according to the load heating requirement, and determines a multi-stage load temperature expectation curve; then, a temperature control decision module makes a temperature control decision on the heating wire module according to the multi-stage load temperature expectation curve and the constraint condition of heating loss, and generates a multi-stage temperature control strategy; then, the temperature control monitoring module controls the heating wire module according to the multi-stage temperature control strategy, heats the heating target load, and obtains the load temperature data and the monitoring data of the heating wire in real time; then, the monitoring data analysis module analyzes and performs temperature control compensation operations on the heating wire module according to the real-time temperature data of the load and the monitoring data of the heating wire.

[0056] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them.

[0057] Figure 1 The figure is a flow chart of the intelligent temperature control system for heating wires based on monitoring data analysis of the present invention, wherein the system comprises:

[0058] The task receiving module 11 is used to obtain a heating task of a heating wire module 14 , wherein the heating wire module 14 includes a plurality of heating wires, and the heating task includes heating a target load and a load heating requirement.

[0059] Specifically, the heating wire module 14 is composed of a plurality of heating wires, and the plurality of heating wires can be controlled individually or work in combination to heat a specific load, that is, each heating wire can adjust the power, temperature and working time according to the task requirements.

[0060] Specifically, the heating task describes the heating operation that the system needs to perform on the target load, including the heating target load that needs to be heated and the corresponding heating demand. The heating target load is the load that needs to be heated, including specific objects, liquids, gases, etc. The load heating demand includes a specific target temperature, heating rate (the temperature change rate and temperature gradient that needs to be applied to the load), time length, etc.

[0061] The load heating expectation analysis module 12 is used to perform heating expectation analysis on the heating target load according to the load heating demand, and determine a multi-level load temperature expectation curve.

[0062] Specifically, the multi-stage load temperature expectation curve characterizes the temperature change of the target load under ideal conditions, and the multiple levels correspond to the multiple heating stages expected by the target load. Among them, heating expectation analysis refers to identifying the heating requirements of the load from the heating task, including the final temperature that the load needs to reach and the staged requirements for existing temperature changes. For example, if the target temperature is heated to 300°C, there may be multi-stage heating requirements, such as slowly heating to 100°C, then quickly heating to 300°C, and maintaining it for a period of time. Through analysis, the system can better understand the heating requirements of the load at each stage.

[0063] Specifically, some loads may require a specific heating rate, ie, the rate at which the temperature changes over time, such as a temperature increase of 5° C. per minute, to avoid damage to the load material during the heating process.

[0064] In some embodiments, Figure 2 As shown, the heating expectation analysis is performed on the heating target load according to the load heating demand to determine a multi-level load temperature expectation curve, and the execution steps include:

[0065] Obtaining initial load temperature parameters of the heating target load; dividing the heating target load into heating stages based on the initial load temperature parameters and the load heating demand to obtain multiple load heating stages; collecting material parameters and structural information of the heating target load to obtain load basic data; based on the load basic data, performing heating expectation fitting on the multiple load heating stages respectively, and outputting the multi-stage load temperature expectation curve.

[0066] Specifically, the initial load temperature parameter of the heating target load refers to the starting temperature of the heating target load, which is obtained by a temperature sensor or other measuring device. Then, the load heating demand is analyzed to obtain heating constraints including target temperature, heating rate, time limit, etc., and the heating process is divided into multiple stages by combining the initial temperature parameter and the heating constraint. For example, if the initial load temperature parameter of the heating target load has reached the first platform temperature in the load heating demand, the actual first heating stage is determined directly based on the current initial load temperature parameter, such as the initial load temperature parameter to the second platform temperature.

[0067] Specifically, basic load data is collected, including material parameters and structural information. For example, material parameters include thermal conductivity, specific heat capacity, density, etc. of the target load. Structural information includes the geometry, size, thickness, etc. of the load. Different materials have different heat transfer characteristics, and different structural shapes also affect the transfer of heat in the load.

[0068] In some implementations, based on the load basic data, heating expectation fitting is performed on the multiple load heating stages respectively, and the multi-stage load temperature expectation curve is outputted. The execution steps include:

[0069] Retrieve multiple load normal temperature change record groups, wherein each load temperature change record group has correspondingly identified historical load basic data and historical load heating stages; extract the nth load heating stage based on the multiple load heating stages; perform correlation evaluation on the multiple load normal temperature change record groups based on the load basic data and the nth load heating stage to obtain multiple load stage correlation coefficients; based on the multiple load stage correlation coefficients, select the multiple load normal temperature change record groups according to the load stage correlation threshold to obtain the nth stage load temperature change fitting set greater than / equal to the load stage correlation threshold; based on the nth stage load temperature change fitting set, construct multiple nth stage load temperature change fitting curves; fuse the multiple nth stage load temperature change fitting curves to generate the nth stage load temperature expected curve, and add the nth stage load temperature expected curve to the multi-stage load temperature expected curve.

[0070] Specifically, normal temperature change record groups of multiple loads are retrieved from the historical database. Each normal temperature change record group of a load contains historical temperature change data of a load in a heating stage, as well as basic information of the load, such as load type, initial state, heating target, etc., which are the basic fitting data for subsequent heating expectation fitting.

[0071] Specifically, the nth load heating stage is any one of the multiple load heating stages, and each stage may have different temperature change targets, such as slow heating, rapid heating, constant temperature maintenance, etc. By extracting multiple load heating stages one by one, a corresponding load temperature expectation curve can be established for each load heating stage.

[0072] Specifically, the correlation evaluation is based on the basic data of the current load and the requirements of the nth heating stage, and evaluates which loads in the historical records have heating behaviors similar to the current load. The correlation coefficients of multiple load stages obtained through the correlation evaluation are then used to select relevant temperature change records. Among them, the multiple load stage correlation coefficients characterize the similarity between the historical load basic data, historical load heating stage and the load basic data, and the nth load heating stage of each load temperature change record group. The higher the value, the closer the temperature change behavior.

[0073] Optionally, the correlation evaluation is performed based on multiple dimensions such as load material, initial temperature, mass, heating rate, etc., and different dimensions have different evaluation weights. For example, if strict consistency is desired for the load material, the load material has a higher evaluation weight, or the relationship evaluation result for the load material dimension is set to a Boolean value. Through the correlation evaluation, the system can automatically filter out the historical temperature change records that are closest to the current load, providing a basis for subsequent fitting.

[0074] Specifically, the correlation threshold refers to the minimum standard that the correlation coefficient needs to meet. Only temperature change record groups with correlation coefficients higher than or equal to this threshold are allowed to be used for subsequent fitting. Multiple load normal temperature change record groups that meet the correlation threshold will be included in the temperature change fitting set of the nth stage to generate the expected temperature curve of the nth stage.

[0075] Specifically, the temperature change fitting curve is a temperature change model generated by a fitting algorithm based on the filtered historical temperature change record group, which is used to represent the expected trend of the temperature change of the load over time in this stage. Exemplarily, according to the historical data and the specific requirements of the heating stage, a suitable fitting algorithm (such as polynomial fitting, linear regression, nonlinear curve fitting, etc.) is selected to fit the filtered temperature change record group.

[0076] Specifically, the temperature change fitting set of the nth stage is fitted multiple times to obtain multiple load temperature change fitting curves of the nth stage, and then, a weighted average or other fusion algorithm is used to fuse the multiple fitting curves into a final temperature expectation curve. For example, a curve or curve segment with a higher correlation can be assigned a larger weight, and a curve or curve segment with a lower correlation can be assigned a smaller weight. The final generated temperature expectation curve describes the target temperature change of the load in the nth stage and is highly matched with the actual demand.

[0077] Furthermore, the above extraction and curve fitting process is repeated for multiple load heating stages, and corresponding fitting curves are generated for multiple load heating stages to ensure that the temperature change trend of the load under different conditions can be reflected. By constructing multiple fitting curves, the system can have a more comprehensive understanding of the temperature change process and generate an accurate temperature expectation model.

[0078] The temperature control decision module 13 is used to make a temperature control decision on the heating wire module 14 according to the multi-stage load temperature expectation curve and in combination with the heating loss constraint to obtain a multi-stage temperature control strategy.

[0079] In some embodiments, according to the multi-stage load temperature expectation curve, combined with the heating loss constraint, the temperature control decision of the heating wire module 14 is made to obtain a multi-stage temperature control strategy, and the execution steps include:

[0080] According to the heating wire module 14, retrieve the sample stage load temperature expected curve set, the load basic data sample set and the temperature control scheme sample set; use the sample stage load temperature expected curve set and the load basic data sample set as input data, and use the temperature control scheme sample set as output data to train the BP neural network, establish a temperature control decision channel, and embed the temperature control decision channel into the temperature control decision module; based on the load basic data and the n-th stage load temperature expected curve, obtain the n-th stage temperature control scheme according to the temperature control decision channel; based on the heating loss constraint, optimize the heating loss of the n-th stage temperature control scheme to generate the n-th stage temperature control strategy; add the n-th stage temperature control strategy to the multi-stage temperature control strategy, continue to make temperature control decisions on the heating wire module 14 according to the multi-stage load temperature expected curve, the temperature control decision channel and the heating loss constraint, and generate the multi-stage temperature control strategy.

[0081] Specifically, the sample stage load temperature expectation curve set is the historical load temperature expectation curve data, including the temperature changes in different stages. The load basic data sample set is the corresponding basic data sample related to the load, including material parameters, structural information, etc. The temperature control solution sample set refers to the historical temperature control solution data, including the application of different temperature control strategies under different conditions and their effects.

[0082] Specifically, the backpropagation (BP) neural network is trained with the load temperature expected curve set and the load basic data sample set in the sample stage as input data and the temperature control solution sample set as output data. Through multiple iterations of training, the network parameters are adjusted to minimize the prediction error, so that the BP neural network acquires the ability to make temperature control decisions based on the load temperature expected curve and the load basic data, and generates a temperature control decision channel. Then, the temperature control decision channel is embedded in the temperature control decision module so that temperature control decisions can be made in actual applications.

[0083] Specifically, the basic load data and the expected load temperature curve of the nth stage are input to the temperature control decision channel for temperature control decision making, and the temperature control plan of the nth stage is obtained; the temperature control plan is a specific heating control plan formulated by the system for the nth heating stage based on the basic load data and the expected temperature curve. The plan indicates how to control the working state of the heating wire in this stage to achieve the target temperature, including the heating power and heating time of multiple heating wires.

[0084] Specifically, the heating loss constraint refers to the heat loss factors that the system needs to consider during the heating process, including thermal radiation, convection heat dissipation, thermal conduction, etc. The heating loss constraint is determined based on the material properties of the load, ambient temperature, heating wire layout, etc. By combining the heating damage constraint, the heating power and heating time in the n-stage temperature control scheme and other control parameters, the heat loss generated during the heating process can be estimated, so as to adjust the n-stage temperature control scheme so that the effect in the actual heating operation is consistent with expectations and provide temperature control accuracy.

[0085] Furthermore, the multi-stage load temperature expectation curve is traversed to obtain the multi-stage temperature control strategy, and it is merged with the nth stage temperature control strategy to form a complete multi-stage temperature control strategy, ensuring that the temperature control strategy of each stage can be seamlessly connected, covering the different stages of the entire heating process, and avoiding temperature fluctuations or discontinuities.

[0086] In some implementations, based on the heating loss constraint, the temperature control scheme for the nth stage is optimized for heating loss to generate the temperature control strategy for the nth stage, and the execution steps include:

[0087] Based on the load basic data, heating loss prediction is performed according to the n-th stage temperature control scheme to obtain a predicted heating loss coefficient; whether the predicted heating loss coefficient satisfies the heating loss constraint is determined; if the predicted heating loss coefficient satisfies the heating loss constraint, the n-th stage temperature control scheme is added to the n-th stage temperature control strategy; if the predicted heating loss coefficient does not satisfy the heating loss constraint, the heating wire temperature control constraint space is activated, wherein the heating wire temperature control constraint space includes the temperature control constraint information of the heating wire module 14; based on the heating loss constraint and the heating wire temperature control constraint space, the n-th stage temperature control scheme is optimized to obtain the n-th stage temperature control strategy.

[0088] Specifically, according to the basic data of the load and the temperature control scheme, the heat loss that will be generated during the heating process is estimated, including energy losses in the form of heat conduction, convection, radiation, etc. First, based on the basic data of the load such as material, mass, initial temperature, surface area, etc., its heat transfer characteristics during the heating process are evaluated. Then, combined with the heat transfer principle, the heat loss of the load under the heating scheme is calculated. Exemplarily, the factors considered in the calculation include: Calculating the thermal radiation loss on the surface of the object according to the Stefan-Boltzmann law. Estimate the heat taken away from the load surface by the air or fluid medium according to the convection conditions of the heating environment. Evaluate the conduction of heat from the load material to the external environment. Then, combining the above-mentioned multi-part heat loss calculation results, generate a heating loss coefficient, which reflects the proportion of energy expected to be lost during the heating process.

[0089] Specifically, the predicted heating loss coefficient is compared with the preset heating loss constraint to determine whether the requirements of energy saving or efficient heating are met. If the predicted heating loss coefficient is less than or equal to the heating loss constraint value, the temperature control scheme is considered acceptable in terms of heat loss. If the predicted heating loss coefficient exceeds the constraint value, it indicates that the heat loss of the current heating scheme is large, which may affect the temperature control accuracy and requires further optimization. Among them, the heating loss constraint refers to the maximum heat loss value or ratio allowed by the system, which is determined according to the temperature control accuracy requirements of the target load.

[0090] Specifically, when the predicted heating loss coefficient meets the heating loss constraint, the system does not need further optimization, and directly adds the temperature control scheme of the nth stage to the temperature control strategy of the nth stage to guide the heating wire control of the nth stage.

[0091] Specifically, if the heating loss coefficient does not meet the constraint, the heating wire temperature control constraint space is activated. The heating wire temperature control constraint space contains the physical and performance limitation information of the heating wire module 14, such as the power range, temperature upper limit, turn-on time, heat distribution mode, etc. of the heating wire, to ensure effective optimization and adjustment within the working range of the heating wire.

[0092] Furthermore, based on the temperature control constraint space of the heating wires, the heat loss is compensated by adjusting the power of some heating wires or the number of heating wires called, ensuring that the optimized n-th stage temperature control strategy can operate within the heating loss constraint range while providing good temperature control accuracy.

[0093] Furthermore, based on the heating loss constraint and the heating wire temperature control constraint space, the temperature control scheme of the nth stage is optimized to obtain the temperature control strategy of the nth stage, and the execution steps include:

[0094] Taking the n-stage load temperature expected curve as the temperature control adjustment target, adjusting the n-stage temperature control scheme according to the heating wire temperature control constraint space, and obtaining the n-stage temperature control adjustment scheme; based on the load basic data, performing heating loss prediction according to the n-stage temperature control adjustment scheme, and obtaining the adjustment scheme heating loss coefficient; judging whether the adjustment scheme heating loss coefficient satisfies the heating loss constraint; if the adjustment scheme heating loss coefficient satisfies the heating loss constraint, adding the n-stage temperature control adjustment scheme to the n-stage temperature control strategy.

[0095] Specifically, the target temperature and heating rate are set based on the expected temperature curve of the nth stage. Then, the temperature control constraint space of the heating wire is used as the parameter adjustment space to compensate for the heat loss of the temperature control scheme of the nth stage, including increasing the heating power output, increasing the activation amount of the heating wire, adjusting the heating sequence, etc., to ensure that the adjusted temperature control scheme meets the requirements of the heating task.

[0096] Furthermore, based on the same principle as the heat loss prediction mentioned above, the heat loss prediction is iterated for the temperature control adjustment scheme of the nth stage obtained by adjustment, and the corresponding heating loss coefficient of the adjustment scheme is obtained. Then, the heating loss coefficient of the adjustment scheme is compared with the preset heating loss constraint. If the heating loss coefficient is less than or equal to the constraint value, it indicates that the scheme is acceptable in terms of energy consumption. The temperature control adjustment scheme of the nth stage is directly added to the temperature control strategy of the nth stage.

[0097] Specifically, if the heating loss coefficient is still greater than the constraint value, the temperature control adjustment scheme for the nth stage is iteratively optimized based on the heating loss coefficient of the adjustment scheme until the heating loss coefficient obtained by the heat loss prediction meets the heating loss constraint.

[0098] The temperature control monitoring module 15 is used to heat the heating target load according to the multi-stage temperature control strategy and the heating wire module 14, and obtain real-time temperature data of the load and real-time monitoring data of the heating wire.

[0099] Specifically, based on the generated multi-level temperature control strategy, the heating wire module 14 is controlled to perform temperature control operations for heating the target load, and the real-time temperature data of the load and the real-time monitoring data of the heating wire are monitored synchronously. Optionally, based on thermal imaging equipment or thermocouples, real-time temperature data of the load is collected; based on thermal imaging equipment or thermocouples, current and voltage meters, etc., real-time monitoring data of the heating wire is collected. Among them, the real-time monitoring data of the heating wire includes data of parameters such as the power output, current, voltage, and temperature of the heating wire.

[0100] The monitoring data analysis module 16 is used to perform temperature control compensation on the heating wire module 14 according to the real-time temperature data of the load and the real-time monitoring data of the heating wire.

[0101] In some embodiments, the heating wire module 14 is temperature-controlled and compensated according to the real-time temperature data of the load and the real-time monitoring data of the heating wire, and the execution steps include:

[0102] According to the multi-stage load temperature expectation curve, the current load temperature expectation curve is extracted; according to the load real-time temperature data, a real-time load temperature curve is constructed; based on the current load temperature expectation curve, the real-time load temperature curve is subjected to deviation analysis to generate a load temperature expectation deviation curve; based on the load temperature expectation deviation curve, the heating wire module 14 is subjected to temperature control compensation to generate a first temperature control compensation strategy; based on the real-time monitoring data of the heating wire, the heating wire module 14 is subjected to temperature control compensation to generate a second temperature control compensation strategy; the first temperature control compensation strategy and the second temperature control compensation strategy are integrated to generate a temperature control compensation scheme, and the heating wire module 14 is subjected to temperature control compensation according to the temperature control compensation scheme.

[0103] Specifically, the real-time load temperature curve is a temperature change curve based on the real-time temperature data of the load, reflecting the temperature fluctuation of the load during the heating process. The real-time load temperature curve is constructed based on the same coordinate space as the current load temperature expectation curve, which is convenient for subsequent comparison and deviation analysis.

[0104] Specifically, compare the current load temperature expected curve with the real-time load temperature curve to analyze whether there is a temperature deviation. For example, if the real-time load temperature curve is lower than the current load temperature expected curve, it means that the loss or conduction loss in heating is large, and the output power of the hot wire needs to be increased. The corresponding coordinate point of the load temperature expected deviation curve is located on the positive side of the coordinate axis. If the real-time load temperature curve is higher than the current load temperature expected curve, it may be necessary to reduce the heating power or shorten the heating time, depending on the position of the coordinate on the curve. If the coordinate point is at the inflection point of the curve, it is necessary to stop heating in advance to avoid temperature overshoot. According to the analysis results, the load temperature expected deviation curve generated by the system clarifies the temperature difference at each moment, which is used to guide subsequent temperature control compensation decisions.

[0105] In some implementations, the heating wire module 14 is temperature-controlled and compensated based on the real-time monitoring data of the heating wire to generate a second temperature-controlled and compensated strategy, and the execution steps include:

[0106] According to the multi-level temperature control strategy, the current temperature control strategy is extracted; based on the real-time monitoring data of the heating wire and the current temperature control strategy, a temperature control offset comparison is performed to generate a temperature control offset comparison result; according to the temperature control offset comparison result, the heating wire module 14 is temperature-controlled compensated to obtain the second temperature control compensation strategy.

[0107] Specifically, the real-time monitoring data of the heating wire reflects the difference between the control instructions received by the heating wire and the actual control results, which is caused by the physical differences of different heating wires in the heating wire module 14, the aging of the heating wires, the assembly differences of the heating wire module 14, etc.

[0108] Specifically, the current temperature control strategy is first extracted from the multi-level temperature control strategy, including the control parameters of the current, voltage, duration, output power, etc. of multiple heating wires. Then, the actual monitoring data of the heating wire is compared with the control instructions in the current temperature control strategy to check whether there is a deviation, and the temperature control offset comparison result is generated based on the comparison result. The temperature control offset comparison result quantitatively represents the deviation between the actual control effect of the heating wire and the expected instruction.

[0109] Furthermore, according to the temperature control offset comparison result, the power output (adjusting current, voltage) or working time of the heating wire is adjusted within the temperature control constraint space of the heating wire to ensure that the temperature control strategy can be implemented as expected. For example, for a heating wire with a lower actual temperature, it can be compensated by increasing the power. If the response speed of the heating wire is slow, its working start time is appropriately advanced to compensate for the temperature control delay. According to the compensation measures, an adjusted temperature control compensation second strategy is generated, and then the working state of the heating wire is dynamically adjusted to compensate for the actual deviation in the heating process, and further ensure the stability and consistency of the heating process.

[0110] In summary, the intelligent temperature control system for heating wires based on monitoring data analysis provided by the present invention has the following technical effects:

[0111] The task receiving module is used to obtain the heating task of the heating wire module 14. The task content includes the composition of multiple heating wires, the heating target load and the corresponding heating requirements. The load heating expectation parsing module, based on the heating requirements of the load, parses the heating expectations of the target load and generates a multi-level load temperature expectation curve to guide the subsequent heating control. The temperature control decision module makes decisions on the heating wire module 14 according to the multi-level load temperature expectation curve and combines the heating loss constraint to generate a multi-level temperature control strategy. The temperature control monitoring module controls the heating wire module 14 according to the generated multi-level temperature control strategy to heat the target load, and monitors the load temperature and the state of the heating wire in real time during the period. The monitoring data analysis module performs temperature control compensation on the heating wire module 14 by analyzing the real-time temperature of the load and the monitoring data of the heating wire to ensure the accuracy and stability of the temperature control process. The intelligent temperature control system for heating wires based on monitoring data analysis disclosed in the present invention solves the technical problems of slow control response and low temperature control accuracy, thereby achieving the technical effect of improving the temperature control response speed and temperature control accuracy.

[0112] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. Intelligent temperature control system for heating wire based on monitoring data analysis, characterized in that: The system comprises: A task receiving module, the task receiving module is used to obtain a heating task of a heating wire module, wherein the heating wire module includes a plurality of heating wires, and the heating task includes a heating target load and a load heating requirement; A load heating expectation analysis module, the load heating expectation analysis module is used to perform heating expectation analysis on the heating target load according to the load heating demand, and determine a multi-level load temperature expectation curve; A temperature control decision module, which is used to make a temperature control decision on the heating wire module according to the multi-stage load temperature expectation curve and in combination with the heating loss constraint to obtain a multi-stage temperature control strategy, wherein the multi-stage load temperature expectation curve represents the temperature change of the target load under ideal conditions, and the multiple stages correspond to the multiple heating stages expected by the target load; A temperature control monitoring module, which is used to heat the heating target load according to the multi-stage temperature control strategy and the heating wire module, and obtain real-time temperature data of the load and real-time monitoring data of the heating wire; A monitoring data analysis module, the monitoring data analysis module is used to perform temperature control compensation on the heating wire module according to the real-time temperature data of the load and the real-time monitoring data of the heating wire; The temperature control decision module is used to make a temperature control decision on the heating wire module according to the multi-stage load temperature expectation curve and in combination with the heating loss constraint to obtain a multi-stage temperature control strategy. The execution steps include: According to the heating wire module, retrieve the load temperature expected curve set, load basic data sample set and temperature control solution sample set in the sample stage; Taking the sample stage load temperature expected curve set and the load basic data sample set as input data and the temperature control scheme sample set as output data, training the BP neural network, establishing a temperature control decision channel, and embedding the temperature control decision channel into the temperature control decision module; Based on the load basic data and the expected load temperature curve of the nth stage, according to the temperature control decision channel, a temperature control plan for the nth stage is obtained; Based on the heating loss constraint, optimizing the heating loss of the temperature control scheme for the nth stage to generate a temperature control strategy for the nth stage; Adding the nth stage temperature control strategy to the multi-stage temperature control strategy, continuing to make temperature control decisions on the heating wire module according to the multi-stage load temperature expectation curve, the temperature control decision channel and the heating loss constraint, and generating the multi-stage temperature control strategy; Wherein, based on the heating loss constraint, the heating loss of the n-stage temperature control scheme is optimized to generate the n-stage temperature control strategy, and the execution steps include: Based on the load basic data, performing heating loss prediction according to the temperature control scheme of the nth stage to obtain a predicted heating loss coefficient; determining whether the predicted heating loss coefficient satisfies the heating loss constraint; If the predicted heating loss coefficient satisfies the heating loss constraint, adding the n-stage temperature control scheme to the n-stage temperature control strategy; If the predicted heating loss coefficient does not satisfy the heating loss constraint, activating a heating wire temperature control constraint space, wherein the heating wire temperature control constraint space includes temperature control constraint information of the heating wire module; Based on the heating loss constraint and the heating wire temperature control constraint space, optimizing the n-stage temperature control scheme to obtain the n-stage temperature control strategy; Among them, based on the heating loss constraint and the heating wire temperature control constraint space, the temperature control scheme of the nth stage is optimized to obtain the temperature control strategy of the nth stage, and the execution steps include: Taking the n-stage load temperature expected curve as the temperature control adjustment target, adjusting the n-stage temperature control plan according to the heating wire temperature control constraint space, and obtaining the n-stage temperature control adjustment plan; Based on the load basic data, a heating loss prediction is performed according to the temperature control adjustment scheme of the nth stage to obtain a heating loss coefficient of the adjustment scheme; Determining whether the heating loss coefficient of the adjustment scheme satisfies the heating loss constraint; If the heating loss coefficient of the adjustment scheme satisfies the heating loss constraint, adding the n-stage temperature control adjustment scheme to the n-stage temperature control strategy; The load heating expectation analysis module is used to perform heating expectation analysis on the heating target load according to the load heating demand, and determine a multi-level load temperature expectation curve, and the execution steps include: Obtaining an initial load temperature parameter of the heating target load; Dividing the heating target load into heating stages based on the initial load temperature parameter and the load heating requirement to obtain a plurality of load heating stages; Collecting material parameters and structural information of the heating target load to obtain basic load data; Based on the load basic data, respectively performing heating expectation fitting for the multiple load heating stages, and outputting the multi-stage load temperature expectation curve; Wherein, based on the load basic data, heating expectation fitting is performed on the multiple load heating stages respectively, and the multi-stage load temperature expectation curve is output, and the execution steps include: Retrieving multiple load normal temperature change record groups, wherein each load temperature change record group has historical load basic data and historical load heating stages with corresponding identifiers; Based on the multiple load heating stages, extracting the nth load heating stage; Based on the load basic data and the nth load heating stage, performing correlation evaluation on the multiple load normal temperature change record groups to obtain multiple load stage correlation coefficients; Based on the multiple load stage correlation coefficients, selecting the multiple load normal temperature change record groups according to the load stage correlation threshold, to obtain an n-th stage load temperature change fitting set that is greater than / equal to the load stage correlation threshold; Based on the n-stage load temperature change fitting set, construct a plurality of n-stage load temperature change fitting curves; The plurality of n-stage load temperature change fitting curves are integrated to generate an n-stage load temperature expected curve, and the n-stage load temperature expected curve is added to the multi-stage load temperature expected curve.

2. The intelligent temperature control system for heating wire based on monitoring data analysis according to claim 1, characterized in that: The monitoring data analysis module is used to perform temperature control compensation on the heating wire module according to the real-time temperature data of the load and the real-time monitoring data of the heating wire, and the execution steps include: Extracting a current load temperature expectation curve according to the multi-stage load temperature expectation curve; Constructing a real-time load temperature curve according to the real-time load temperature data; Performing deviation analysis on the real-time load temperature curve based on the current load temperature expected curve to generate a load temperature expected deviation curve; Performing temperature control compensation on the heating wire module based on the load temperature expected deviation curve to generate a first temperature control compensation strategy; Performing temperature control compensation on the heating wire module based on the real-time monitoring data of the heating wire, and generating a second temperature control compensation strategy; The first temperature control compensation strategy and the second temperature control compensation strategy are integrated to generate a temperature control compensation scheme, and temperature control compensation is performed on the heating wire module according to the temperature control compensation scheme.

3. The intelligent temperature control system for heating wire based on monitoring data analysis according to claim 2, characterized in that: The heating wire module is subjected to temperature control compensation based on the real-time monitoring data of the heating wire, and a second temperature control compensation strategy is generated. The execution steps include: According to the multi-level temperature control strategy, extract the current temperature control strategy; Performing a temperature control offset comparison based on the real-time monitoring data of the heating wire and the current temperature control strategy to generate a temperature control offset comparison result; The heating wire module is subjected to temperature control compensation according to the temperature control offset comparison result to obtain the second temperature control compensation strategy.

Images