A heating band temperature control monitoring method and system based on multi-channel data acquisition

Abstract

The application relates to the technical field of temperature control monitoring, and discloses a heating band temperature control monitoring method and system based on multi-channel data acquisition, which comprises the following steps: constructing a deviation coefficient matrix according to the time bending distance of multi-channel temperature data sequences in a sliding window in a monitoring area, and identifying an effective data sequence set in the multi-channel temperature data sequences; screening a reference channel in the effective data sequence set according to a data missing or distortion interval corresponding to an abnormal channel identifier; constructing a dynamic compensation mechanism through a temperature change trend in the reference channel and a linear regression relationship in a historical normal operation state, correcting the effective data sequence set, and obtaining temperature field data of the monitoring area; and performing correlation analysis on the temperature field data and real-time current data of the heating band, encoding analysis results into hierarchical control instructions, executing a temperature control task, and generating a monitoring record. The application can improve the efficiency of heating band temperature control monitoring.

Description

Technical Field

[0001] This invention relates to the field of temperature control monitoring technology, and in particular to a method and system for monitoring the temperature of heating belts based on multi-channel data acquisition. Background Technology

[0002] In existing technologies, temperature control monitoring of heating zones typically employs multiple temperature sensors to collect temperature data from different areas. When a sensor experiences data loss or distortion due to aging, poor contact, or electromagnetic interference, traditional anomaly detection methods often rely on fixed thresholds or single time-series differences for judgment. These methods lack the ability to measure the nonlinear time curvature distance between multiple data sequences, making it difficult to effectively distinguish between normal deviations caused by environmental fluctuations and genuine anomalies caused by sensor malfunctions. This results in low accuracy in identifying abnormal channels and a high rate of false rejection, leading to incomplete or erroneous data sequences used for subsequent temperature control decisions, thus affecting the accuracy of reconstructing the temperature field in the monitored area.

[0003] In existing technologies, conventional methods for handling identified abnormal channels often involve directly removing their data or filling them with simple linear interpolation of adjacent channels. These methods fail to consider the inherent linear regression relationship and temperature change ratio characteristics between abnormal channels and normal reference channels under historical normal operating conditions. This makes it difficult to establish a dynamic compensation mechanism based on weighted fusion of multiple reference channels within data gaps or distortion intervals. Furthermore, existing methods lack joint correlation analysis between multi-channel fused temperature field data and real-time current data from the heating zone, making it impossible to encode hierarchical control commands based on the joint temperature-current state. This results in coarse execution and delayed response of temperature control tasks. Therefore, there is an urgent need to develop a heating zone temperature control monitoring method and system based on multi-channel data acquisition. This system should construct a deviation coefficient matrix using time curvature distance to achieve accurate abnormal channel identification, establish a dynamic compensation mechanism using historical linear regression relationships to correct missing or distorted data, and output hierarchical control commands by combining temperature field and current correlation analysis. This would address the problems of inaccurate multi-source data anomaly identification, insufficient compensation for missing data, and low efficiency in temperature control response and monitoring record generation, thereby improving the reliability and intelligence level of heating zone temperature control monitoring. Summary of the Invention

[0004] This invention provides a heating belt temperature control monitoring method and system based on multi-channel data acquisition to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a heating belt temperature control monitoring method based on multi-channel data acquisition, comprising: Itm1: Based on the time curvature distance of multiple temperature data sequences within the sliding window in the monitoring area, construct the deviation coefficient matrix between multiple data sequences to identify the set of valid data sequences marked as abnormal channels in the multiple temperature data sequences; Itm2: Based on the data missing or distorted intervals corresponding to the abnormal channel identifiers, filter out the reference channels in the set of valid data sequences; Itm3: By using the linear regression relationship between the temperature change trend in the reference channel and the historical normal operation status, a dynamic compensation mechanism is constructed to correct the effective data sequence set and obtain multi-channel fused temperature field data of the monitoring area. Itm4 performs correlation analysis on the multi-channel fused temperature field data and the real-time current data of the heating belt, encodes the analysis results into hierarchical control commands, executes temperature control tasks, and generates monitoring records for the monitoring area.

[0006] In a preferred embodiment, constructing the deviation coefficient matrix among the multiple temperature data streams based on the time curvature distance of the multiple temperature data sequences within the sliding window in the monitoring area includes: Within the monitoring area, each temperature data sequence is divided into continuous sliding windows with a fixed time length; Within each sliding window, calculate the time curvature distance between the temperature data sequences aligned with the time axis; Using the two channel numbers corresponding to the time curvature distance values ​​as row and column indices, and the time curvature distance values ​​as matrix elements, construct a difference coefficient matrix.

[0007] In a preferred embodiment, identifying the set of valid data sequences marked as abnormal channels in a multi-channel temperature data sequence includes: The average deviation is generated by averaging all off-diagonal elements in each row of the statistical deviation coefficient matrix. The average deviation of each channel is compared with a preset tolerance threshold. If the average deviation exceeds the tolerance threshold for a preset judgment period, the channel is marked as an abnormal channel and a corresponding abnormal channel identifier is generated. Based on the abnormal channel identifier, the temperature data sequence corresponding to the marked abnormal channel is removed from the original multi-channel temperature data sequence, and the temperature data sequence of the remaining unmarked channels is retained; The retained temperature data sequences are re-associated and packaged with their corresponding channel identifiers to form a valid data sequence set.

[0008] In a preferred embodiment, the dynamic compensation mechanism is constructed by using the linear regression relationship between the temperature change trend in the reference channel and the historical normal operation status, including: Extract the temperature data sequences corresponding to all reference channels from the effective data sequence set, and retrieve the synchronous temperature records of the reference channels and abnormal channels under historical normal operating conditions from the historical database to form multiple sets of paired samples; The paired samples of the reference channel and the abnormal channel are compared at corresponding time points to determine the temperature change scaling factor and baseline offset between the reference channel and the abnormal channel. Based on the scaling factor and the baseline offset, a mapping rule is established to deduce the estimated temperature value of the abnormal channel from the current temperature value of the reference channel, serving as a dynamic compensation mechanism for the current abnormal channel.

[0009] In a preferred embodiment, the step of comparing the paired samples of the reference channel and the abnormal channel at corresponding time points to determine the temperature change scaling factor and reference offset between the reference channel and the abnormal channel includes: Select multiple sample points at different times from the paired samples, and read the historical temperature values ​​of the reference channel and the abnormal channel at the same time for each sample point; The difference between the temperature value of the abnormal channel and the temperature value of the reference channel in each sample point is used as the instantaneous offset, and the arithmetic mean of the instantaneous offsets of all sample points is used as the baseline offset. Subtract the baseline offset from the temperature value of the abnormal channel in each sample point to obtain the adjusted abnormal temperature value for each sample point. The ratio between the adjusted abnormal temperature value and the temperature value of the reference channel in the same sample point is used as the temperature change scaling factor.

[0010] In a preferred embodiment, obtaining multi-channel fused temperature field data of the monitoring area by correcting the effective data sequence set includes: For each moment within the data missing or distorted interval, obtain the current temperature value of the reference channel at the corresponding moment, and substitute it into the dynamic compensation mechanism to calculate the compensation temperature value of the abnormal channel. The original missing or distorted data in the interval of the abnormal channel in the effective data sequence set is replaced with the compensation temperature value to obtain the corrected single-channel temperature data sequence. The corrected single-channel temperature data sequence is spatially interpolated and fused with the uncorrected channel data sequence in the effective data sequence set according to the channel position to generate multi-channel fused temperature field data of the monitoring area.

[0011] In a preferred embodiment, the formula for calculating the compensation temperature value is as follows: ; In the formula, This represents the compensated temperature value for the abnormal channel at the current time t. This is the arithmetic mean of the reference offsets corresponding to all reference channels. The total number of reference channels in the reference channel set. This is the temperature change scaling factor between the i-th reference channel and the abnormal channel. Let be the current temperature value of the i-th reference channel at the current time t. Let be the confidence weight of the i-th reference channel.

[0012] In a preferred embodiment, the correlation analysis between the multi-channel fused temperature field data and the real-time current data of the heating zone includes: Extract the highest temperature value, lowest temperature value, and temperature change rate at the current moment from multi-channel fused temperature field data; Obtain the real-time current value and current change rate on the power supply circuit of the heating belt at the same moment; The highest temperature value is compared with the preset high temperature threshold in the first comparison, and the current change rate is compared with the preset current fluctuation threshold in the second comparison. Based on the combination of the results of the first comparison and the second comparison, the current working state category of the heating belt is determined. The working state categories include: normal temperature and stable current, slightly high temperature and stable current, normal temperature and sudden current change, and slightly high temperature and sudden current change.

[0013] In a preferred embodiment, encoding the analysis results into hierarchical control commands, executing temperature control tasks, and generating monitoring records for the monitored area includes: The operating status category is mapped to a preset category instruction association table to determine the corresponding instruction level, and hierarchical control instructions of power adjustment amount or start / stop flag are output according to the instruction level. While performing temperature control tasks, the system associates and stores hierarchical control commands, multi-channel fused temperature field data, real-time current data, and timestamps to form a monitoring record for the monitoring area.

[0014] To address the aforementioned problems, the present invention also provides a heating belt temperature control and monitoring system based on multi-channel data acquisition, the system comprising: The effective data filtering module is used to construct a deviation coefficient matrix between multiple temperature data sequences based on the time curvature distance of the multiple temperature data sequences within the sliding window in the monitoring area, and to identify the effective data sequence set marked as abnormal channel in the multiple temperature data sequences.

[0015] The reference channel filtering module is used to filter out reference channels in the set of valid data sequences based on the data missing or distorted intervals corresponding to the abnormal channel identifiers.

[0016] The temperature field fusion module is used to construct a dynamic compensation mechanism by using the linear regression relationship between the temperature change trend in the reference channel and the historical normal operation status, so as to correct the effective data sequence set and obtain multi-channel fused temperature field data of the monitoring area.

[0017] The hierarchical control module is used to perform correlation analysis on multi-channel fused temperature field data and real-time current data of the heating belt, encode the analysis results into hierarchical control commands, execute temperature control tasks, and generate monitoring records for the monitoring area.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention constructs a deviation coefficient matrix between multiple temperature data sequences by introducing time curvature distance, and judges the continuous over-limit duration based on the average deviation and tolerance threshold, significantly improving the accuracy and robustness of abnormal channel identification. Existing methods using fixed thresholds or single time-series differences easily misjudge environmental fluctuations as sensor malfunctions, leading to a high false rejection rate. This invention, however, utilizes a nonlinear time curvature distance metric within a sliding window to effectively distinguish between true anomalies and normal deviations, ensuring the integrity and reliability of the valid data sequence set. This provides a high-quality data foundation for subsequent temperature control decisions and avoids temperature field reconstruction deviations caused by false data rejection.

[0019] 2. This invention constructs a dynamic compensation mechanism including a scaling factor and a reference offset based on the linear regression relationship between reference channels and abnormal channels under historical normal operating conditions. It uses a weighted fusion formula for multiple reference channels to calculate the compensated temperature value. Compared to the coarse processing of simple elimination or linear interpolation of adjacent channels in existing technologies, this invention can more accurately restore the true temperature change trend of abnormal channels in areas with missing or distorted data, improving the accuracy and continuity of multi-channel fused temperature field data. Simultaneously, this invention performs joint correlation analysis with the fused temperature field data and the real-time current data of the heating element, automatically determining four operating state categories: normal / high temperature and stable / abrupt current. These are mapped to graded control commands, outputting power adjustment amounts or start / stop flags. This solves the problems of coarse and lagging temperature control response in existing technologies, achieving refined graded control. Furthermore, it automatically generates complete monitoring records while performing temperature control tasks, significantly improving the intelligence level and efficiency of heating element temperature control monitoring. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating a heating zone temperature control monitoring method based on multi-channel data acquisition, provided in an embodiment of the present invention. Figure 2 This is a functional block diagram of a heating belt temperature control monitoring system based on multi-channel data acquisition, provided in an embodiment of the present invention. The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0022] This application provides a heating zone temperature control monitoring method based on multi-channel data acquisition. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the heating zone temperature control monitoring method based on multi-channel data acquisition can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0023] Reference Figure 1 The diagram shown is a flowchart illustrating a heating zone temperature control monitoring method based on multi-channel data acquisition according to an embodiment of the present invention. In this embodiment, the heating zone temperature control monitoring method based on multi-channel data acquisition includes: Itm1: Based on the time curvature distance of multiple temperature data sequences within the sliding window in the monitoring area, construct the deviation coefficient matrix between multiple data sequences to identify the set of valid data sequences marked as abnormal channels in the multiple temperature data sequences; In this embodiment of the invention, constructing a deviation coefficient matrix between multiple temperature data streams based on the time curvature distance of the multiple temperature data sequences within a sliding window in the monitoring area includes: Within the monitoring area, each temperature data sequence is divided into continuous sliding windows with a fixed time length; Within each sliding window, calculate the time curvature distance between the temperature data sequences aligned with the time axis; Using the two channel numbers corresponding to the time curvature distance values ​​as row and column indices, and the time curvature distance values ​​as matrix elements, construct a difference coefficient matrix.

[0024] The set of valid data sequences marked as abnormal channels in the identified multi-channel temperature data sequences includes: The average deviation is generated by averaging all off-diagonal elements in each row of the statistical deviation coefficient matrix. The average deviation of each channel is compared with a preset tolerance threshold. If the average deviation exceeds the tolerance threshold for a preset judgment period, the channel is marked as an abnormal channel and a corresponding abnormal channel identifier is generated. Based on the abnormal channel identifier, the temperature data sequence corresponding to the marked abnormal channel is removed from the original multi-channel temperature data sequence, and the temperature data sequence of the remaining unmarked channels is retained; The retained temperature data sequences are re-associated and packaged with their corresponding channel identifiers to form a valid data sequence set.

[0025] Within the monitoring area, each temperature data sequence is divided into consecutive sliding windows of fixed time length. For each temperature sensor's data sequence consisting of temperature values ​​changing over time, the data sequence is cut into multiple consecutive, non-overlapping time segments according to a pre-set fixed time length, such as ten minutes. Each segment is a sliding window. As new data arrives, the sliding windows move sequentially forward to cover the latest temperature data.

[0026] Within each sliding window, the time warping distance between temperature data sequences aligned along the time axis is calculated. Each temperature data sequence within the sliding window is treated as a time series, and all sequences are aligned along the time axis to ensure that temperature values ​​at the same time point can be compared. After alignment, a dynamic time warping method is used to calculate the minimum distance between each pair of temperature data sequences. This distance measures the similarity in shape between the two sequences, accurately reflecting differences even if there is local stretching or compression along the time axis.

[0027] Using the channel numbers corresponding to the time curvature distance values ​​as row and column indices, and the time curvature distance values ​​as matrix elements, a deviation coefficient matrix is ​​constructed. All temperature channels within the monitoring area are numbered in a fixed order, and these numbers serve as the row and column indices of the matrix. For channel i and channel j, the calculated time curvature distance value is filled into the i-th row and j-th column position of the matrix, and the main diagonal elements are set to zero, ultimately forming a square matrix. This square matrix is ​​the deviation coefficient matrix, which completely records the degree of deviation between all pairs of channels.

[0028] The average deviation is generated by averaging all off-diagonal elements in each row of the deviation coefficient matrix. For each row of the deviation coefficient matrix, which corresponds to a specific channel, each matrix element represents the time warp distance between that channel and all other channels. Elements on the main diagonal of the row are excluded because they represent the channel's own distance, which is zero and not included in the deviation calculation. The remaining off-diagonal elements are summed and then divided by the total number of off-diagonal elements to obtain the average deviation for that channel. This average deviation measures the overall deviation of that channel relative to all other channels.

[0029] The system compares the average deviation of each channel with a preset tolerance threshold. If the average deviation exceeds the tolerance threshold for a preset judgment period, the channel is marked as an abnormal channel, and a corresponding abnormal channel identifier is generated. The system presets a tolerance threshold as the upper limit for judging normal fluctuations, and sets a judgment period to eliminate instantaneous noise interference. For each channel, the average deviation calculated within each sliding window is compared with the tolerance threshold in real time. Once the average deviation exceeds the tolerance threshold, the system starts recording the duration of the excess. If this duration accumulates to a preset judgment period, the channel is determined to be an abnormal channel, and a unique abnormal channel identifier is generated for it. This identifier is used for identification and processing of the channel in subsequent steps.

[0030] Based on the abnormal channel identifiers, the temperature data sequences corresponding to the channels marked as abnormal are removed from the original multi-channel temperature data sequences, retaining the temperature data sequences of the remaining unmarked channels. The system obtains the channel numbers indicated by all abnormal channel identifiers, and then accesses the original complete multi-channel temperature data sequences, which contain temperature data collected from all channels within the monitoring area. For each abnormal channel, its corresponding entire temperature data sequence is removed from the original dataset. For all channels not marked as abnormal, their corresponding temperature data sequences are all retained, forming a new dataset containing only normal channel data.

[0031] The retained temperature data sequences are re-associated and packaged with their corresponding channel identifiers to form a valid data sequence set. For each retained temperature data sequence, the system obtains its original channel number identifier and combines this identifier with the data sequence in a one-to-one correspondence. All such combinations are packaged together according to channel number order or any other determined order, and the resulting data set is called the valid data sequence set. This valid data sequence set no longer contains data from any abnormal channels, but only contains verified valid data that can be used for subsequent temperature control analysis.

[0032] The beneficial effect is that a deviation coefficient matrix is ​​constructed based on the time curvature distance of multiple temperature data sequences within a sliding window. This accurately measures the similarity of temperature change trends in each channel, overcoming the shortcomings of existing fixed threshold or single time-series difference methods that struggle to distinguish between environmental fluctuations and actual sensor malfunctions. By calculating the time curvature distance, even with local time shifts in temperature changes, the degree of deviation between channels can still be accurately reflected, thus constructing a complete deviation coefficient matrix. Based on this, the average deviation of each channel is statistically analyzed and dually judged using a tolerance threshold and continuous over-limit duration, effectively eliminating instantaneous noise interference and achieving high-accuracy identification of abnormal channels.

[0033] This process significantly reduces the false rejection rate, ensuring the integrity and authenticity of the data sequences upon which subsequent processing is based. Abnormal data sequences are removed by identifying abnormal channels, and the remaining normal channel data is re-associated and packaged with the channel identifiers to form a valid data sequence set, providing a high-quality data foundation for temperature control monitoring. Existing technologies often use simple rejection or linear interpolation methods, which frequently lose crucial information or introduce erroneous data. However, by using abnormal channel identifiers generated through time warping distance and continuous judgment, precise rejection is achieved, ensuring that the valid data sequence set contains only reliable temperature data. This valid data sequence set directly supports subsequent dynamic compensation, temperature field fusion, and hierarchical control, avoiding erroneous analysis results caused by abnormal data contamination, and significantly improving the reliability and data fusion accuracy of heated zone temperature control monitoring.

[0034] Itm2: Based on the data missing or distorted intervals corresponding to the abnormal channel identifiers, filter out the reference channels in the set of valid data sequences; Itm3: By using the linear regression relationship between the temperature change trend in the reference channel and the historical normal operation status, a dynamic compensation mechanism is constructed to correct the effective data sequence set and obtain multi-channel fused temperature field data of the monitoring area. In this embodiment of the invention, the step of constructing a dynamic compensation mechanism by means of the linear regression relationship between the temperature change trend in the reference channel and the historical normal operating conditions includes: Extract the temperature data sequences corresponding to all reference channels from the effective data sequence set, and retrieve the synchronous temperature records of the reference channels and abnormal channels under historical normal operating conditions from the historical database to form multiple sets of paired samples; The paired samples of the reference channel and the abnormal channel are compared at corresponding time points to determine the temperature change scaling factor and baseline offset between the reference channel and the abnormal channel. Based on the scaling factor and the baseline offset, a mapping rule is established to deduce the estimated temperature value of the abnormal channel from the current temperature value of the reference channel, serving as a dynamic compensation mechanism for the current abnormal channel.

[0035] The step of comparing the paired samples of the reference channel and the abnormal channel at corresponding time points to determine the temperature change scaling factor and baseline offset between the reference channel and the abnormal channel includes: Select multiple sample points at different times from the paired samples, and read the historical temperature values ​​of the reference channel and the abnormal channel at the same time for each sample point; The difference between the temperature value of the abnormal channel and the temperature value of the reference channel in each sample point is used as the instantaneous offset, and the arithmetic mean of the instantaneous offsets of all sample points is used as the baseline offset. Subtract the baseline offset from the temperature value of the abnormal channel in each sample point to obtain the adjusted abnormal temperature value for each sample point. The ratio between the adjusted abnormal temperature value and the temperature value of the reference channel in the same sample point is used as the temperature change scaling factor.

[0036] The process of obtaining multi-channel fused temperature field data of the monitoring area by correcting the effective data sequence set includes: For each moment within the data missing or distorted interval, obtain the current temperature value of the reference channel at the corresponding moment, and substitute it into the dynamic compensation mechanism to calculate the compensation temperature value of the abnormal channel. The original missing or distorted data in the interval of the abnormal channel in the effective data sequence set is replaced with the compensation temperature value to obtain the corrected single-channel temperature data sequence. The corrected single-channel temperature data sequence is spatially interpolated and fused with the uncorrected channel data sequence in the effective data sequence set according to the channel position to generate multi-channel fused temperature field data of the monitoring area.

[0037] The formula for calculating the compensation temperature value is as follows: ; In the formula, This represents the compensated temperature value for the abnormal channel at the current time t. This is the arithmetic mean of the reference offsets corresponding to all reference channels. The total number of reference channels in the reference channel set. This is the temperature change scaling factor between the i-th reference channel and the abnormal channel. Let be the current temperature value of the i-th reference channel at the current time t. Let be the confidence weight of the i-th reference channel.

[0038] The system extracts temperature data sequences corresponding to all reference channels from the valid data sequence set and retrieves synchronous temperature records of the reference channels and abnormal channels under historical normal operating conditions from the historical database, forming multiple sets of paired samples. First, the system accesses the valid data sequence set, which contains complete temperature data sequences of all reference channels not marked as abnormal channels, and extracts these reference channel data sequences one by one according to their channel identifiers. Simultaneously, the system accesses the historical database, retrieving synchronous temperature data recorded at the same time during historical normal operating conditions for the same reference channel and a marked abnormal channel. The historical temperature values ​​of the reference channels and abnormal channels are then matched one-to-one according to their time points. Each pair of temperature values ​​at the same time point constitutes a paired sample, and the set of paired samples from multiple different time points constitutes the required multiple sets of paired samples.

[0039] The system compares the values ​​of paired samples from the reference channel and the abnormal channel at corresponding time points to determine the temperature change scaling factor and baseline offset between the two channels. For each paired sample, the system reads the historical temperature values ​​of the reference channel and the abnormal channel at the same time, calculates the difference between the abnormal channel temperature value and the reference channel temperature value, and records it as the instantaneous offset. The arithmetic mean of the instantaneous offsets obtained from all paired samples is used to obtain the baseline offset, which reflects the average temperature deviation of the abnormal channel relative to the reference channel under normal operating conditions. Subsequently, the historical temperature value of the abnormal channel in each paired sample is subtracted from the baseline offset to obtain the adjusted abnormal temperature value. The ratio of the adjusted abnormal temperature value to the historical temperature value of the reference channel at the same sample point is then calculated. This ratio is the temperature change scaling factor corresponding to that paired sample, which reflects the rate of change of the abnormal channel temperature relative to the reference channel temperature.

[0040] Based on the scaling factor and the baseline offset, a mapping rule is established to estimate the temperature value of the abnormal channel from the current temperature value of the reference channel, serving as a dynamic compensation mechanism for the current abnormal channel. The system uses the calculated baseline offset as a constant offset term and the temperature change scaling factor as a multiplicative scaling coefficient to construct a mapping rule: when the current temperature value of the reference channel is obtained, it is first multiplied by the corresponding temperature change scaling factor, and then summed with the baseline offset. The result is the estimated temperature value of the abnormal channel at the current moment. This mapping rule is stored and bound to the current abnormal channel, forming a dynamic compensation mechanism specifically for this abnormal channel. Subsequently, whenever data loss or distortion occurs in the abnormal channel, the system calls this mapping rule to calculate the compensation temperature value using the real-time temperature value of the reference channel.

[0041] The system selects multiple sample points from paired samples at different times and reads the historical temperature values ​​of the reference channel and the abnormal channel at the same time for each sample point. The system accesses multiple sets of paired samples, each corresponding to a specific historical time, containing the temperature values ​​collected and stored by the reference channel and the temperature values ​​collected and stored by the abnormal channel at that time. The system selects multiple sample points from these paired samples in chronological order, covering different temperature change stages under normal operating conditions. For each selected sample point, the system reads the historical temperature values ​​of the reference channel and the abnormal channel, and uses these two values ​​as a set of original records for that sample point.

[0042] The difference between the temperature value of the abnormal channel and the temperature value of the reference channel at each sample point is used as the instantaneous offset, and the arithmetic mean of the instantaneous offsets of all sample points is used as the baseline offset. For each selected sample point, the system subtracts the historical temperature value of the reference channel from the historical temperature value of the abnormal channel, and the difference is recorded as the instantaneous offset of that sample point. After calculating the instantaneous offsets of all sample points, the system sums all the instantaneous offsets and divides them by the total number of sample points; the quotient is the baseline offset. This baseline offset represents the average temperature difference between the abnormal channel and the reference channel under historical normal operating conditions.

[0043] The system subtracts the baseline offset from the temperature value of the abnormal channel at each sample point to obtain the adjusted abnormal temperature value for each sample point. For each selected sample point, the system subtracts the calculated baseline offset from the previously read historical temperature value of the abnormal channel to obtain a new temperature value, which is called the adjusted abnormal temperature value. This operation is equivalent to removing the effect of the fixed offset from the original temperature reading of the abnormal channel, ensuring that the adjusted temperature value is compared with the temperature value of the reference channel at the same baseline level.

[0044] The ratio between the adjusted abnormal temperature value and the temperature value of the reference channel in the same sample point is used as the temperature change scaling factor. For each sample point, the system divides the calculated adjusted abnormal temperature value by the historical temperature value of the reference channel in the same sample point; the quotient is the temperature change scaling factor corresponding to that sample point. This scaling factor reflects the multiple relationship between the abnormal channel temperature and the temperature change when the reference channel temperature changes by one unit. The system can further process the scaling factors calculated from multiple sample points, such as taking an average value, to obtain a final temperature change scaling factor for use in the construction of subsequent dynamic compensation mechanisms.

[0045] For each moment within the data missing or distorted interval, the current temperature value of the reference channel at the corresponding moment is obtained and substituted into the dynamic compensation mechanism to calculate the compensated temperature value of the abnormal channel. The system first identifies the data missing or distorted intervals marked within the valid data sequence set for the abnormal channel. This interval encompasses a continuous time range, and each moment within the interval requires processing. For each moment within this interval, the system accesses the temperature data sequence of the reference channel and reads the current temperature value collected by the reference channel at the same moment. The system then invokes a pre-built dynamic compensation mechanism for the abnormal channel, which includes a baseline offset and a temperature change scaling factor. The system calculates the current temperature value of the reference channel according to the mapping rules defined in the dynamic compensation mechanism, i.e., multiplying it by the temperature change scaling factor and adding the baseline offset. The result is the compensated temperature value of the abnormal channel at that moment.

[0046] The system replaces the missing or distorted data within the interval of the abnormal channel in the valid data sequence set with compensated temperature values ​​to obtain a corrected single-channel temperature data sequence. The system accesses the valid data sequence set, locates the temperature data sequence corresponding to the abnormal channel, and finds the location of the missing or distorted data interval within that sequence. For each moment within that interval, the system removes the original missing markers or distorted values ​​and fills the corresponding data position with the calculated compensated temperature value. The system completes the replacement operation moment by moment in chronological order. After all moments within the interval have been replaced, the temperature data sequence of the abnormal channel no longer contains missing or distorted data, but instead consists of the original normal data segment and the compensated temperature value segment, forming a complete temperature data sequence. This sequence is called the corrected single-channel temperature data sequence.

[0047] The corrected single-channel temperature data sequence is spatially interpolated and fused with the uncorrected channel data sequence from the effective data sequence set according to channel location to generate multi-channel fused temperature field data for the monitoring area. The system acquires the corrected single-channel temperature data sequence and other uncorrected channel data sequences from the effective data sequence set. These uncorrected channels include a consistently functioning reference channel and other channels without data loss or distortion. The system obtains the physical location coordinates of each channel within the monitoring area and treats the temperature values ​​of each channel at the same time as discrete sampling points in space based on these coordinates. Using a spatial interpolation method, for any location point within the monitoring area without a temperature sensor, the system calculates the estimated temperature value of that location point through weighted calculation based on the temperature values ​​of the nearest few channels and their positional relationships. The system repeats the above spatial interpolation calculation for each time moment to generate continuous temperature distribution values ​​covering the entire monitoring area at each time moment. Organizing these temperature distributions in chronological order yields the multi-channel fused temperature field data.

[0048] The arithmetic mean of the baseline offsets is derived from the analysis of synchronized temperature records between multiple reference channels and abnormal channels under historical normal operating conditions. A baseline offset is calculated between each reference channel and the abnormal channel, and then the arithmetic mean of the baseline offsets corresponding to all reference channels is obtained. The total number of reference channels refers to the number of all reference channels selected from the valid data sequence set, which is determined by the data missing or distorted interval corresponding to the abnormal channel identifier. The temperature change scaling factor between each reference channel and the abnormal channel is derived from the historical paired samples of that reference channel and the abnormal channel, obtained by dividing the adjusted temperature value of the abnormal channel in each sample point by the temperature value of the reference channel. The current temperature value of each reference channel at the current moment refers to the temperature value collected in real time at the moment when the abnormal channel experienced data missing or distortion. The confidence weight of each reference channel is derived from the strength of the temperature correlation between that reference channel and the abnormal channel under historical normal operating conditions. The stronger the correlation, the greater the confidence weight is assigned to the reference channel. The sum of the confidence weights of all reference channels is used as the denominator for normalization.

[0049] This formula calculates the compensated temperature value of an anomaly channel at a specific moment within a data gap or distortion interval. Its core idea is to scale the current temperature values ​​of multiple reference channels according to their respective scaling factors relative to the anomaly channel, then perform a weighted average based on confidence weights, and finally add an overall baseline offset. The first part of the formula, the arithmetic mean of the baseline offsets, is used to correct for a fixed temperature deviation between the anomaly channel and the reference channels. The second part is a weighted average. The numerator first multiplies the current temperature value of each reference channel by its corresponding scaling factor to obtain a preliminary estimate of the anomaly channel value derived from that reference channel. Then, this preliminary estimate is multiplied by the confidence weight of that reference channel, and finally, the weighted results of all reference channels are summed. The denominator sums the confidence weights of all reference channels to normalize the numerator. Adding the first and second parts yields the anomaly channel compensated temperature value that comprehensively considers information from multiple reference channels. This formula, through a weighted fusion of multiple reference channels, reduces the impact of measurement errors or local temperature fluctuations that may exist in a single reference channel on the compensation result, improving the accuracy and stability of the compensated temperature value.

[0050] The beneficial effect is that a dynamic compensation mechanism is constructed based on the linear regression relationship between the reference channel and the abnormal channel under historical normal operating conditions, solving the problem of low compensation accuracy caused by simple elimination or linear interpolation in existing technologies. Synchronous temperature records are retrieved from the historical database to form paired samples. The baseline offset is obtained by calculating the arithmetic mean of the instantaneous offsets. Then, the ratio of the adjusted abnormal temperature value to the reference channel temperature value is calculated to obtain the temperature change scaling factor, accurately quantifying the relationship between the fixed temperature deviation and the rate of temperature change. For each moment within the data missing or distorted interval, the current temperature value of the reference channel is obtained and substituted into the dynamic compensation mechanism to calculate the compensation temperature value, replacing the original missing or distorted data, resulting in a corrected single-channel temperature data sequence. This ensures that the compensation result follows the historical temperature change pattern, significantly improving the restoration accuracy and avoiding erroneous temperature field reconstruction.

[0051] The corrected single-channel temperature data sequence is spatially interpolated and fused with the uncorrected channel data sequence in the effective data sequence set according to channel position to generate multi-channel fused temperature field data, overcoming the deficiency of existing technologies in the comprehensive utilization of multi-reference channel information. In the dynamic compensation mechanism, each reference channel is assigned a confidence weight, and the weighted results of all reference channels are normalized when calculating the compensated temperature value, effectively suppressing the interference of single reference channel measurement errors or local temperature fluctuations on the compensation results. Through spatial interpolation fusion, discrete channel temperature data is transformed into a continuous temperature distribution covering the entire monitoring area, providing a highly reliable data foundation for subsequent correlation analysis and hierarchical control, significantly improving the overall performance of temperature control monitoring in the heated zone.

[0052] Itm4 performs correlation analysis on the multi-channel fused temperature field data and the real-time current data of the heating belt, encodes the analysis results into hierarchical control commands, executes temperature control tasks, and generates monitoring records for the monitoring area.

[0053] In this embodiment of the invention, the correlation analysis between the multi-channel fused temperature field data and the real-time current data of the heating zone includes: Extract the highest temperature value, lowest temperature value, and temperature change rate at the current moment from multi-channel fused temperature field data; Obtain the real-time current value and current change rate on the power supply circuit of the heating belt at the same moment; The highest temperature value is compared with the preset high temperature threshold in the first comparison, and the current change rate is compared with the preset current fluctuation threshold in the second comparison. Based on the combination of the results of the first comparison and the second comparison, the current working state category of the heating belt is determined. The working state categories include: normal temperature and stable current, slightly high temperature and stable current, normal temperature and sudden current change, and slightly high temperature and sudden current change.

[0054] The process of encoding the analysis results into hierarchical control commands, executing temperature control tasks, and generating monitoring records for the monitored area includes: The operating status category is mapped to a preset category instruction association table to determine the corresponding instruction level, and hierarchical control instructions of power adjustment amount or start / stop flag are output according to the instruction level. While performing temperature control tasks, the system associates and stores hierarchical control commands, multi-channel fused temperature field data, real-time current data, and timestamps to form a monitoring record for the monitoring area.

[0055] The system extracts the highest, lowest, and rate of temperature change values ​​for the current moment from multi-channel fused temperature field data. The multi-channel fused temperature field data contains continuous temperature distribution values ​​for all locations within the monitored area at every moment. The system locates the temperature distribution data corresponding to the current moment, iterates through all temperature values ​​in the distribution, identifies the largest value as the current highest temperature, and the smallest value as the current lowest temperature. The system also reads the highest temperature value from the previous moment and the highest temperature value from the current moment, calculates the difference between them, divides it by the time interval between the two moments, and obtains the quotient, which is the rate of temperature change. This rate of change reflects the speed at which the overall temperature in the monitored area rises or falls.

[0056] The system acquires the real-time current value and current change rate of the heating element's power supply circuit at the same moment. The system connects to a current measuring device on the heating element's power supply circuit, directly reading the real-time current value flowing through the heating element at the current moment. Simultaneously, the system reads the real-time current value from the previous moment. Subtracting the previous moment's real-time current value from the current moment's value, and then dividing by the time interval between the two moments, yields the current change rate, which reflects the severity of the fluctuation in the heating element's power supply current.

[0057] The system performs a first comparison between the highest temperature value and a preset high-temperature threshold, and a second comparison between the current change rate and a preset current fluctuation threshold. The system pre-sets a high-temperature threshold as the boundary for judging whether the temperature is too high, and a current fluctuation threshold as the boundary for judging whether the current is stable. The system compares the extracted highest temperature value at the current moment with the high-temperature threshold. If the highest temperature value is greater than the high-temperature threshold, the first comparison result is that the temperature is too high; otherwise, the first comparison result is that the temperature is normal. The system then compares the calculated current change rate with the current fluctuation threshold. If the absolute value of the current change rate is greater than the current fluctuation threshold, the second comparison result is that the current has a sudden change; otherwise, the second comparison result is that the current is stable.

[0058] Based on the combination of the results of the first and second comparisons, the system determines the current operating state category of the heating element. The system combines the two results from the first comparison (temperature too high or normal) with the two results from the second comparison (current sudden change or current stable), generating a total of four possible combinations. When the first comparison result is normal temperature and the second comparison result is stable current, the operating state category is normal temperature and stable current. When the first comparison result is too high temperature and the second comparison result is stable current, the operating state category is too high temperature and stable current. When the first comparison result is normal temperature and the second comparison result is a sudden current change, the operating state category is normal temperature and a sudden current change. When the first comparison result is too high temperature and the second comparison result is a sudden current change, the operating state category is too high temperature and a sudden current change. The system outputs one of these four categories as the current operating state category of the heating element.

[0059] The system maps operating status categories to a pre-defined category instruction association table, determines the corresponding instruction level, and outputs hierarchical control instructions such as power adjustment or start / stop flags according to the instruction level. The system internally stores a category instruction association table, where each row corresponds to an operating status category and records the corresponding instruction level and the specific control content to be output at that level.

[0060] The system uses the current operating status category determined in the association analysis step as the query keyword, performs a matching search in the category instruction association table, finds the record that is exactly the same as the operating status category, and reads the instruction level and the corresponding power adjustment amount or start / stop flag from that record. The power adjustment amount is a value used to change the power supply of the heating element, and the start / stop flag is a switch signal used to control the heating element to start or stop heating. Based on the read instruction level and the corresponding power adjustment amount or start / stop flag, the system generates a hierarchical control instruction and sends the instruction to the power actuator of the heating element, which then performs the temperature control task.

[0061] While performing temperature control tasks, the system associates and stores hierarchical control commands, multi-channel fused temperature field data, real-time current data, and timestamps to form a monitoring record for the monitored area. The system initiates a data storage process simultaneously with sending hierarchical control commands to the power actuator. The system obtains the current time information as a timestamp, which accurately records the moment the temperature control task is executed. The system collects all data related to this temperature control task, including the generated hierarchical control commands themselves, the current multi-channel fused temperature field data, and the real-time current data read from the current measurement device. The system associates these data according to a fixed format, meaning each monitoring record contains a complete set of information under the same timestamp: the specific content of the hierarchical control command, all temperature distribution values ​​in the multi-channel fused temperature field data, and the value of the real-time current data. The system writes this associated monitoring record to a designated storage medium, forming an indivisible record entry. This process is repeated, generating a new monitoring record each time a temperature control task is performed. All records are organized chronologically to form a complete monitoring record archive for the monitored area.

[0062] The beneficial effect is that, based on the correlation analysis of multi-channel fused temperature field data and real-time current data of the heating element, it enables refined identification and hierarchical control of the heating element's operating status. Existing technologies rely solely on single data points such as temperature or current, making it difficult to distinguish the causes of excessively high temperatures. This method extracts the highest temperature value, lowest temperature value, and temperature change rate from the multi-channel fused temperature field data, while simultaneously acquiring the real-time current value and current change rate. The highest temperature value is compared with a high-temperature threshold, and the current change rate is compared with a current fluctuation threshold. Based on the comparison results, four operating status categories are determined, mapped to a category instruction association table, and then hierarchical control instructions are output. This allows the temperature control task to adopt differentiated adjustment strategies according to different fault modes, significantly improving the precision and response speed of temperature control.

[0063] While performing temperature control tasks, the system automatically generates monitoring records, solving the problems of data recording being separated from temperature control execution and low efficiency in generating monitoring records. The system associates and stores hierarchical control commands, multi-channel fused temperature field data, real-time current data, and timestamps to form a complete monitoring record. This record includes control commands and the temperature field distribution and current status at the time the commands are issued, providing data support for fault tracing and control optimization. It avoids data omissions and spatiotemporal mismatches, significantly improving the automation level and data management efficiency of heating zone temperature control monitoring.

[0064] like Figure 2 The diagram shown is a functional block diagram of a heating belt temperature control monitoring system based on multi-channel data acquisition, provided by an embodiment of the present invention.

[0065] The heating zone temperature control and monitoring system based on multi-channel data acquisition described in this invention can be installed in electronic devices. Depending on the functions implemented, the heating zone temperature control and monitoring system based on multi-channel data acquisition may include an effective data filtering module, a reference channel filtering module, a temperature field fusion module, and a hierarchical control module. The module described in this invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0066] In this embodiment, the functions of each module / unit are as follows: The effective data filtering module is used to construct a deviation coefficient matrix between multiple data streams based on the time curvature distance of multiple temperature data sequences within a sliding window in the monitoring area, and to identify the set of effective data sequences marked as abnormal channels in the multiple temperature data sequences.

[0067] The reference channel filtering module is used to filter out reference channels in the set of valid data sequences based on the data missing or distorted intervals corresponding to the abnormal channel identifiers.

[0068] The temperature field fusion module is used to construct a dynamic compensation mechanism by using the linear regression relationship between the temperature change trend in the reference channel and the historical normal operation status, so as to correct the effective data sequence set and obtain multi-channel fused temperature field data of the monitoring area.

[0069] The hierarchical control module is used to perform correlation analysis on multi-channel fused temperature field data and real-time current data of the heating belt, encode the analysis results into hierarchical control commands, execute temperature control tasks, and generate monitoring records for the monitoring area.

[0070] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0071] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0072] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0073] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0074] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for temperature control and monitoring of heating belts based on multi-channel data acquisition, characterized in that, The method includes: Itm1: Based on the time curvature distance of multiple temperature data sequences within the sliding window in the monitoring area, construct the deviation coefficient matrix between multiple data sequences to identify the set of valid data sequences marked as abnormal channels in the multiple temperature data sequences; Itm2: Based on the data missing or distorted intervals corresponding to the abnormal channel identifiers, filter out the reference channels in the set of valid data sequences; Itm3: By using the linear regression relationship between the temperature change trend in the reference channel and the historical normal operation status, a dynamic compensation mechanism is constructed to correct the effective data sequence set and obtain multi-channel fused temperature field data of the monitoring area. Itm4 performs correlation analysis on the multi-channel fused temperature field data and the real-time current data of the heating belt, encodes the analysis results into hierarchical control commands, executes temperature control tasks, and generates monitoring records for the monitoring area.

2. The heating belt temperature control monitoring method based on multi-channel data acquisition as described in claim 1, characterized in that, The step of constructing a deviation coefficient matrix among multiple temperature data streams based on the time curvature distance of the multiple temperature data sequences within a sliding window in the monitoring area includes: Within the monitoring area, each temperature data sequence is divided into continuous sliding windows with a fixed time length; Within each sliding window, calculate the time curvature distance between the temperature data sequences aligned with the time axis; Using the two channel numbers corresponding to the time curvature distance values ​​as row and column indices, and the time curvature distance values ​​as matrix elements, construct a difference coefficient matrix.

3. The heating belt temperature control monitoring method based on multi-channel data acquisition as described in claim 1, characterized in that, The set of valid data sequences marked as abnormal channels in the identified multi-channel temperature data sequences includes: The average deviation is generated by averaging all off-diagonal elements in each row of the statistical deviation coefficient matrix. The average deviation of each channel is compared with a preset tolerance threshold. If the average deviation exceeds the tolerance threshold for a preset judgment period, the channel is marked as an abnormal channel and a corresponding abnormal channel identifier is generated. Based on the abnormal channel identifier, the temperature data sequence corresponding to the marked abnormal channel is removed from the original multi-channel temperature data sequence, and the temperature data sequence of the remaining unmarked channels is retained; The retained temperature data sequences are re-associated and packaged with their corresponding channel identifiers to form a valid data sequence set.

4. The heating belt temperature control monitoring method based on multi-channel data acquisition as described in claim 1, characterized in that, The dynamic compensation mechanism is constructed by using the linear regression relationship between the temperature change trend in the reference channel and the historical normal operation status, including: Extract the temperature data sequences corresponding to all reference channels from the effective data sequence set, and retrieve the synchronous temperature records of the reference channels and abnormal channels under historical normal operating conditions from the historical database to form multiple sets of paired samples; The paired samples of the reference channel and the abnormal channel are compared at corresponding time points to determine the temperature change scaling factor and baseline offset between the reference channel and the abnormal channel. Based on the scaling factor and the baseline offset, a mapping rule is established to deduce the estimated temperature value of the abnormal channel from the current temperature value of the reference channel, serving as a dynamic compensation mechanism for the current abnormal channel.

5. The heating belt temperature control monitoring method based on multi-channel data acquisition as described in claim 4, characterized in that, The step of comparing the paired samples of the reference channel and the abnormal channel at corresponding time points to determine the temperature change scaling factor and baseline offset between the reference channel and the abnormal channel includes: Select multiple sample points at different times from the paired samples, and read the historical temperature values ​​of the reference channel and the abnormal channel at the same time for each sample point; The difference between the temperature value of the abnormal channel and the temperature value of the reference channel in each sample point is used as the instantaneous offset, and the arithmetic mean of the instantaneous offsets of all sample points is used as the baseline offset. Subtract the baseline offset from the temperature value of the abnormal channel in each sample point to obtain the adjusted abnormal temperature value for each sample point. The ratio between the adjusted abnormal temperature value and the temperature value of the reference channel in the same sample point is used as the temperature change scaling factor.

6. The heating belt temperature control monitoring method based on multi-channel data acquisition as described in claim 1, characterized in that, The process of obtaining multi-channel fused temperature field data of the monitoring area by correcting the effective data sequence set includes: For each moment within the data missing or distorted interval, obtain the current temperature value of the reference channel at the corresponding moment, and substitute it into the dynamic compensation mechanism to calculate the compensation temperature value of the abnormal channel. The original missing or distorted data in the interval of the abnormal channel in the effective data sequence set is replaced with the compensation temperature value to obtain the corrected single-channel temperature data sequence. The corrected single-channel temperature data sequence is spatially interpolated and fused with the uncorrected channel data sequence in the effective data sequence set according to the channel position to generate multi-channel fused temperature field data of the monitoring area.

7. The heating belt temperature control monitoring method based on multi-channel data acquisition as described in claim 6, characterized in that, The formula for calculating the compensation temperature value is as follows: ； In the formula, This represents the compensated temperature value for the abnormal channel at the current time t. This is the arithmetic mean of the reference offsets corresponding to all reference channels. The total number of reference channels in the reference channel set. This is the temperature change scaling factor between the i-th reference channel and the abnormal channel. Let be the current temperature value of the i-th reference channel at the current time t. Let be the confidence weight of the i-th reference channel.

8. The heating belt temperature control monitoring method based on multi-channel data acquisition as described in claim 1, characterized in that, The correlation analysis between the multi-channel fused temperature field data and the real-time current data of the heating zone includes: Extract the highest temperature value, lowest temperature value, and temperature change rate at the current moment from multi-channel fused temperature field data; Obtain the real-time current value and current change rate on the power supply circuit of the heating belt at the same moment; The highest temperature value is compared with the preset high temperature threshold in the first comparison, and the current change rate is compared with the preset current fluctuation threshold in the second comparison. Based on the combination of the results of the first comparison and the second comparison, the current working state category of the heating belt is determined. The working state categories include: normal temperature and stable current, slightly high temperature and stable current, normal temperature and sudden current change, and slightly high temperature and sudden current change.

9. The heating belt temperature control monitoring method based on multi-channel data acquisition as described in claim 1, characterized in that, The process of encoding the analysis results into hierarchical control commands, executing temperature control tasks, and generating monitoring records for the monitored area includes: The operating status category is mapped to a preset category instruction association table to determine the corresponding instruction level, and hierarchical control instructions of power adjustment amount or start / stop flag are output according to the instruction level. While performing temperature control tasks, the system associates and stores hierarchical control commands, multi-channel fused temperature field data, real-time current data, and timestamps to form a monitoring record for the monitoring area.

10. A heating belt temperature control and monitoring system based on multi-channel data acquisition, characterized in that, The system for implementing the heating belt temperature control monitoring method based on multi-channel data acquisition as described in claim 1 includes: The effective data filtering module is used to construct a deviation coefficient matrix between multiple data streams based on the time curvature distance of multiple temperature data sequences within a sliding window in the monitoring area, and to identify the set of effective data sequences marked as abnormal channels in the multiple temperature data sequences; The reference channel filtering module is used to filter out reference channels in the set of valid data sequences based on the data missing or distorted intervals corresponding to the abnormal channel identifiers. The temperature field fusion module is used to construct a dynamic compensation mechanism by using the linear regression relationship between the temperature change trend in the reference channel and the historical normal operation status, so as to correct the effective data sequence set and obtain multi-channel fused temperature field data of the monitoring area. The hierarchical control module is used to perform correlation analysis on multi-channel fused temperature field data and real-time current data of the heating belt, encode the analysis results into hierarchical control commands, execute temperature control tasks, and generate monitoring records for the monitoring area.

Images