A multi-sensor temperature sensor internal circulation monitoring system for aluminum foil billet casting and rolling mill
The multi-sensing temperature sensor system is used to accurately monitor and control the aluminum foil blank casting and rolling mill, which solves the problem that traditional temperature monitoring is difficult to capture tiny fluctuations, improves product quality and production efficiency, and reduces energy consumption and defect rate.
Patent Information
- Application Number
- CN202411153282.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-21
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-21
AI Technical Summary
In complex production environments, traditional temperature monitoring methods are difficult to capture slight temperature fluctuations, resulting in unstable product quality and may even cause production accidents.
The internal circulation monitoring system of aluminum foil blank casting and rolling mill adopts multi-sensor temperature sensor. Through temperature data acquisition, data preprocessing, multi-sensor data fusion, temperature fluctuation curve analysis, temperature interval division and abnormal outlier calculation modules, the aluminum foil blank casting and rolling mill is realized. Comprehensive and precise monitoring and control of internal temperature conditions.
Ensure that the quality, plate shape, tension and tension of the aluminum foil blank are within the preset range, provide a high-quality data foundation, quantitatively evaluate the temperature fluctuation characteristics, formulate accurate temperature control strategies, reduce energy consumption, and reduce product defect rate.
Smart Images

Figure CN118650013B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of aluminum deep processing, and more specifically to an internal circulation monitoring system of an aluminum foil billet casting and rolling mill with a multi-sensing temperature sensor. Background Art
[0002] As the pace of manufacturing industry's transformation towards intelligence accelerates, accurate temperature control and monitoring are particularly important in the production process of aluminum foil billets. The quality of aluminum foil billets directly affects the performance and market competitiveness of subsequent products. How to reduce energy consumption while ensuring product quality directly affects the performance and cost of the final product. Therefore, precise control of the internal circulation process of the aluminum foil billet casting and rolling mill, especially temperature control, is crucial to improving the quality and production efficiency of aluminum foil billets.
[0003] In recent years, with the advancement of sensor technology and the application of automatic control systems, the temperature control of aluminum foil billet casting and rolling mills has been significantly improved. Remote control technology is used to monitor and control the temperature distribution inside the casting and rolling mill in real time through multi-sensory temperature sensors, thereby optimizing rolling parameters and reducing energy consumption. This has greatly promoted the aluminum processing industry to develop in a more efficient and environmentally friendly direction. It can not only obtain real-time temperature data on the surface and inside of the billet during the casting and rolling process, and dynamically adjust process parameters based on these data, but also reduce energy consumption in the production process, reduce product defect rates caused by uneven temperature, and bring significant economic benefits and quality improvements to the manufacturing field of aluminum foil billets.
[0004] However, there are still some shortcomings in its actual use. For example, in a complex production environment, small fluctuations in temperature may have a significant impact on the performance of the final product, and traditional temperature monitoring methods often find it difficult to capture these subtle changes; the sensor's slow response to temperature fluctuations and insufficient monitoring accuracy under complex working conditions may lead to unstable product quality and even cause production accidents. In order to overcome these shortcomings, a multi-sensing temperature sensor internal circulation monitoring system for aluminum foil billet casting and rolling mill is proposed. By integrating multiple types of sensors, it can more comprehensively and accurately monitor the temperature state inside the casting and rolling mill, ensuring that the cast aluminum foil billet is kept within the preset balance value in terms of quality, plate shape, tension and pull, thereby further realizing fine control of the production process. Summary of the invention
[0005] In order to overcome the above defects of the prior art, the present invention provides an internal circulation monitoring system of an aluminum foil billet casting and rolling mill with multiple temperature sensors, and solves the problems raised in the above background technology through the following scheme.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] An aluminum foil billet casting and rolling mill internal circulation monitoring system with multiple temperature sensors, comprising:
[0008] Temperature data acquisition module: used to obtain the temperature data of each key point in the internal circulation process of the aluminum foil billet casting and rolling mill through various types of sensors, and transmit it to the data preprocessing module;
[0009] Data preprocessing module: used to preprocess the temperature data transmitted by the temperature data acquisition module through the self-diagnosis algorithm and transmit it to the multi-sensor data fusion module;
[0010] Multi-sensor data fusion module: used to perform multi-sensor data fusion processing on the temperature data transmitted by the data preprocessing module through the single-chip microcomputer, and transmit the fused temperature data to the temperature fluctuation curve analysis module;
[0011] Temperature fluctuation curve analysis module: used to analyze the data transmitted by the multi-sensor data fusion module, generate a temperature fluctuation curve composed of all temperature data in a unit time, further analyze the characteristic value of the temperature fluctuation curve, and transmit it to the temperature interval division module and the abnormal outlier calculation module; the unit time is a preset value; the characteristic value includes the temperature fluctuation characteristic value, the temperature change trend coefficient, the local temperature dynamic index, the temperature change rate index and the temperature change rate estimation;
[0012] Temperature interval division module: used to calculate the segmentation score value according to the characteristic value of the temperature fluctuation curve transmitted by the temperature fluctuation curve analysis module, and then divide different working intervals, and transmit them to the outlier calculation module; the working intervals include the start interval, the cutting interval, and the cooling interval;
[0013] Abnormal outlier calculation module: used to analyze the working interval transmitted by the temperature interval division module, generate abnormal outlier values, and transmit them to the abnormal data processing module;
[0014] Abnormal data processing module: used to monitor the abnormal outlier values of the abnormal outlier calculation module, and output or store the abnormal outlier values, and provide an alarm mechanism to remind the operation and maintenance personnel to take timely measures to deal with abnormal situations.
[0015] Preferably, the calculation model of the self-diagnosis algorithm is as follows:
[0016]
[0017] Among them, D i represents the i-th data point after temperature data point preprocessing, N represents the total number of data points transmitted by the temperature data acquisition module, and d i It represents the i-th data point transmitted by the temperature data acquisition module, and μ represents the mean value of the total data transmitted by the temperature data acquisition module.
[0018] Preferably, the calculation model of the multi-sensor data fusion is specifically expressed as:
[0019]
[0020] Where M represents the fusion data of temperature data points after preprocessing of all temperature sensors, and A i It is represented by the temperature subset of the ith measurement area after preprocessing of N-type thermocouples, B i It is represented by the temperature subset of the ith measurement area after preprocessing of the Pt100 thermal resistor, C i It is represented as the temperature subset of the i-th measurement area after thermistor is preprocessed, and K1 is represented as the temperature subset A i With temperature subset B i The conflict coefficient, K2 is expressed as the temperature subset A i With the temperature subset C i The conflict coefficient of K3 represents the temperature subset B i With the temperature subset C i The conflict coefficient, m(A i ) is represented as the temperature subset A i The distribution function, m(B i ) is represented as temperature subset B i The distribution function, m(C i ) is represented as a temperature subset C i The distribution function, m(A i ⊕B i ) is represented as the temperature subset A i With temperature subset B i The allocation function of the combination set, m(A i ⊕C i ) is represented as the temperature subset A i With the temperature subset C i The allocation function of the combination set, m(B i ⊕C i ) is represented as temperature subset B i With the temperature subset C i The allocation function for the combined set.
[0021] Preferably, the temperature fluctuation characteristic value of the temperature fluctuation curve is specifically expressed as:
[0022]
[0023] Among them, M TIt is represented as the temperature fluctuation characteristic value, M represents the fusion data transmitted by the multi-sensor data fusion module, a represents the scale sensitivity index, ψ(x) represents the calculation function of the temperature change trend coefficient, t represents the time point when the temperature changes, and b represents the time positioning index.
[0024] Preferably, the local temperature dynamic index of the temperature fluctuation curve is specifically expressed as:
[0025]
[0026] Among them, dM T / dt is the local temperature dynamic index, M T It is expressed as the temperature fluctuation characteristic value, t is the time point when the temperature changes, a is the scale sensitivity index, b is the time positioning index, and Δb is the difference of the time positioning index.
[0027] Preferably, the temperature change rate index of the temperature fluctuation curve is specifically expressed as:
[0028]
[0029] Among them, σ T It is represented as the temperature change rate indicator, T[k] is represented as the temperature change rate estimate, k is represented as a discrete time point, n is represented as the number of unit time curve segments that make up the final temperature fluctuation curve, and Δt is represented as the time interval corresponding to the discrete temperature characteristic value.
[0030] Preferably, the calculation model of the segmentation score value is specifically expressed as:
[0031] ξ i =(((dM T / dt)-(1 / 2)×(|M T |+|σ T |))+1) -1
[0032] Among them, ξ i It is expressed as the segment score value of the i-th unit time curve segment, dM T / dt is the local temperature dynamic index, t is the time point when the temperature changes, M T Expressed as a local temperature dynamic index, σ T Expressed as a temperature change rate indicator.
[0033] Preferably, the calculation model of the abnormal outlier is specifically expressed as:
[0034]
[0035] Among them, Φe represents the abnormal outlier value of the e-th temperature data, (dM T / dt) is expressed as the local temperature dynamic index, ξ i It is expressed as the segment score value of the i-th unit time curve segment, σ T Expressed as the temperature change rate index, Φ emax Expressed as the maximum value of abnormal outliers, Φ emin Represented as the abnormal outlier minimum.
[0036] Technical effects and advantages of the present invention:
[0037] 1. The present invention ensures that the temperature data in the internal circulation monitoring system of the aluminum foil billet casting and rolling mill is accurate and consistent through a multi-sensor data fusion module, providing a high-quality data foundation;
[0038] 2. The present invention calculates the characteristic value of the temperature fluctuation curve through the temperature fluctuation curve analysis module, quantitatively evaluates the characteristics of temperature fluctuation and its changes over time, and helps to formulate more accurate temperature control strategies and early warning mechanisms;
[0039] 3. The present invention compares the segmentation score values of adjacent segmentation points through the temperature interval division module, confirms and adjusts the preliminary interval division, ensures that each interval division is more accurate and reasonable, and further clarifies the scope of the start interval. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION
[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0042] As attached Figure 1 The internal circulation monitoring system of an aluminum foil billet casting and rolling mill with a multi-sensor temperature sensor shown includes a temperature data acquisition module, a data preprocessing module, a multi-sensor data fusion module, a temperature fluctuation curve analysis module, a temperature interval division module, an abnormal outlier calculation module and an abnormal data processing module.
[0043] The temperature data acquisition module is used to obtain the temperature data of each key point in the internal circulation process of the aluminum foil billet casting and rolling mill through various types of sensors, and transmit it to the data preprocessing module.
[0044] The temperature data acquisition module integrates various types of sensors, including but not limited to N-type thermocouples, Pt100 thermal resistors and thermistors, which are evenly distributed in different areas inside the casting and rolling mill to ensure that temperature information is collected from different positions and angles.
[0045] The temperature data acquisition module selects N-type thermocouples inside the heating furnace and around the heating elements to monitor the temperature changes during the heating process. N-type thermocouples can withstand higher temperatures and have good long-term stability. Pt100 thermal resistors are used at the inlet and outlet of the cooling system to monitor the temperature of the cooling medium to ensure that the cooling effect meets the process requirements. Low-cost thermistors are installed at the positions entering and leaving the casting and rolling mill to monitor changes in the billet temperature.
[0046] The data preprocessing module is used to perform data preprocessing on the temperature data transmitted by the temperature data acquisition module through a self-diagnosis algorithm, and transmit the data to the multi-sensor data fusion module.
[0047] The calculation model of the self-diagnosis algorithm is as follows:
[0048]
[0049] Among them, D i represents the i-th data point after temperature data point preprocessing, N represents the total number of data points transmitted by the temperature data acquisition module, and d i It represents the i-th data point transmitted by the temperature data acquisition module, and μ represents the mean value of the total data transmitted by the temperature data acquisition module.
[0050] The data preprocessing module preprocesses all temperature data, including removing invalid and erroneous data records, reducing random noise and abnormal fluctuations in the data, and standardizing the data, and classifying and storing the data according to the measurement area and the type of acquisition equipment, and finally obtaining all standardized temperature data in the circulation process of the aluminum foil billet casting and rolling mill.
[0051] The data preprocessing module identifies and deletes missing values, abnormal values or illogical data points through data cleaning, thereby improving data quality and reducing analysis errors caused by erroneous data; by removing high-frequency noise and sudden abnormal filtering, the data is smoothed to make the temperature trend more clearly visible; by converting the temperature data to the same numerical range, the data from different sensors can be directly compared and fused, avoiding misjudgment caused by dimensional differences; by grouping data according to measurement area and sensor type, the efficiency of data management is improved, which facilitates subsequent in-depth analysis of specific areas or sensors.
[0052] The multi-sensor data fusion module is used to perform multi-sensor data fusion processing on the temperature data transmitted by the data preprocessing module through the single-chip microcomputer, and transmit the fused temperature data to the temperature fluctuation curve analysis module.
[0053] The computational model of the multi-sensor data fusion is specifically expressed as follows:
[0054]
[0055] Where M represents the fusion data of temperature data points after preprocessing of all temperature sensors, and A i It is represented by the temperature subset of the ith measurement area after preprocessing of N-type thermocouples, B i It is represented by the temperature subset of the ith measurement area after preprocessing of the Pt100 thermal resistor, C i It is represented as the temperature subset of the i-th measurement area after thermistor is preprocessed, and K1 is represented as the temperature subset A i With temperature subset B i The conflict coefficient, K2 is expressed as the temperature subset A i With the temperature subset C i The conflict coefficient of K3 represents the temperature subset B i With the temperature subset C i The conflict coefficient, m(A i ) is represented as the temperature subset A i The distribution function, m(B i ) is represented as temperature subset B i The distribution function, m(C i ) is represented as a temperature subset C i The distribution function, m(A i ⊕B i ) is represented as the temperature subset A i With temperature subset B i The allocation function of the combination set, m(A i ⊕C i ) is represented as the temperature subset A i With the temperature subset C i The allocation function of the combination set, m(B i ⊕C i ) is represented as temperature subset B i With the temperature subset C i The allocation function for the combined set.
[0056] The calculation model of the conflict coefficient between the temperature subset of the N-type thermocouple after preprocessing and the temperature subset of the Pt100 thermal resistor after preprocessing in the calculation model of the multi-sensor data fusion is specifically expressed as follows:
[0057]
[0058] The calculation model of the conflict coefficient between the temperature subset of the N-type thermocouple after preprocessing and the temperature subset of the thermistor after preprocessing in the calculation model of the multi-sensor data fusion is specifically expressed as follows:
[0059]
[0060] The calculation model of the conflict coefficient between the preprocessed temperature subset of the Pt100 thermal resistor and the preprocessed temperature subset of the thermistor in the calculation model of the multi-sensor data fusion is specifically expressed as:
[0061]
[0062] in, Represents the empty set.
[0063] The allocation function in the calculation model of multi-sensor data fusion maps the corresponding subset to a real number in the interval [0, 1] to represent the credibility of each data point; the allocation function of the temperature subset of the i-th measurement area after preprocessing of the N-type thermocouple in the calculation model of multi-sensor data fusion is expressed as the credibility of each N-type thermocouple data point mapped to the temperature subset of the target measurement area, and the function satisfies the condition:
[0064]
[0065] Among them, Θ A It represents the complete set of temperature data of N-type thermocouple after preprocessing. is represented as an empty set; the distribution function of the temperature subset of the ith measurement area after the preprocessing of the Pt100 thermal resistor in the calculation model of multi-sensor data fusion is represented as the credibility of each Pt100 thermal resistor data point mapped to the temperature subset of the target measurement area, and the function satisfies the condition:
[0066]
[0067] Among them, Θ B It represents the complete set of temperature data of Pt100 thermal resistor after preprocessing. is represented as an empty set; the distribution function of the temperature subset of the i-th measurement area after thermistor preprocessing in the calculation model of multi-sensor data fusion is represented as the credibility of each thermistor data point mapped to the temperature subset of the target measurement area, and the function satisfies the condition:
[0068]
[0069] Among them, Θ C It represents the complete set of temperature data of the thermistor after preprocessing. is represented as an empty set; the allocation function of the combination set of the temperature subset of the ith measurement area after preprocessing of the N-type thermocouple and the temperature subset of the ith measurement area after preprocessing of the Pt100 thermal resistor in the calculation model of multi-sensor data fusion is represented as the credibility of the data points of each combination set of N-type thermocouple and Pt100 thermal resistor mapped to the temperature subset of the target measurement area, and the function satisfies the condition:
[0070]
[0071] Among them, Θ A⊕B It is represented as the complete set of N-type thermocouple and Pt100 thermal resistor combination sets in each target measurement temperature area. is represented as an empty set; the allocation function of the combination set of the temperature subset of the ith measurement area after preprocessing of the N-type thermocouple and the temperature subset of the ith measurement area after preprocessing of the thermistor in the calculation model of multi-sensor data fusion is represented as the credibility of the data points of each combination set of N-type thermocouple and thermistor mapped to the temperature subset of the target measurement area, and the function satisfies the condition:
[0072]
[0073] Among them, Θ A⊕C It is represented as the complete set of N-type thermocouple and thermistor combinations in each target measurement temperature region, is represented as an empty set; the allocation function of the temperature subset of the ith measurement area after preprocessing of the N-type thermocouple and the temperature subset of the ith measurement area after preprocessing of the thermistor in the calculation model of multi-sensor data fusion is represented as the credibility of the data points of each Pt100 thermal resistor and the thermistor combination set mapped to the temperature subset of the target measurement area, and the function satisfies the condition:
[0074]
[0075] Among them, Θ B⊕C It is represented as the complete set of Pt100 thermal resistors and thermistor combinations in each target measurement temperature region. Represents the empty set.
[0076] The multi-sensor data fusion module generates more accurate temperature measurement results by fusing data from N-type thermocouples, Pt100 thermal resistors and thermistors, and utilizes the complementary advantages of different sensors to reduce the limitations of a single sensor and improve the performance of the overall monitoring system; by calculating the conflict coefficients between N-type thermocouples and Pt100 thermal resistors, N-type thermocouples and thermistors, and Pt100 thermal resistors and thermistors, the conflict degree of data between different sensors is quantified to improve the consistency and credibility of data; by defining the distribution functions of N-type thermocouples, Pt100 thermal resistors and thermistors, and the distribution functions of the combination sets, the credibility of data from different sensors is quantified to provide a reliable mathematical basis for data fusion; by utilizing the computing power of the single-chip microcomputer, a large amount of temperature data is quickly processed to achieve real-time data fusion, making data fusion processing more efficient and meeting the needs of remote monitoring.
[0077] The temperature fluctuation curve analysis module is used to analyze the data transmitted by the multi-sensor data fusion module, generate a temperature fluctuation curve composed of all temperature data within a unit time, further analyze the characteristic value of the temperature fluctuation curve, and transmit it to the temperature interval division module and the abnormal outlier calculation module; the unit time is a preset value; the characteristic value includes the temperature fluctuation characteristic value, the temperature change trend coefficient, the local temperature dynamic index, the temperature change rate index and the temperature change rate estimation.
[0078] The generation of the temperature fluctuation curve composed of all temperature data within the unit time is based on the temperature data transmitted by the multi-sensor data fusion module being integrated and connected in chronological order to obtain a preset number of unit time curve segments, and all curve segments are merged in chronological order to obtain the final temperature fluctuation curve.
[0079] The temperature fluctuation characteristic value of the temperature fluctuation curve is specifically expressed as:
[0080]
[0081] Among them, M T It is represented as the temperature fluctuation characteristic value, M represents the fusion data transmitted by the multi-sensor data fusion module, a represents the scale sensitivity index, ψ(x) represents the calculation function of the temperature change trend coefficient, t represents the time point when the temperature changes, and b represents the time positioning index.
[0082] The calculation function of the temperature change trend coefficient is specifically expressed as:
[0083]
[0084] Among them, ψ(x) represents the calculation function of the temperature change trend coefficient, k represents the discrete time point, n represents the number of unit time curve segments that make up the final temperature fluctuation curve, and a k It is expressed as a scale sensitivity index at discrete time points, where x represents the parameter.
[0085] The local temperature dynamic index of the temperature fluctuation curve is specifically expressed as:
[0086]
[0087] Among them, dM T / dt is the local temperature dynamic index, M T It is expressed as the temperature fluctuation characteristic value, t is the time point when the temperature changes, a is the scale sensitivity index, b is the time positioning index, and Δb is the difference of the time positioning index.
[0088] The temperature change rate index of the temperature fluctuation curve is specifically expressed as:
[0089]
[0090] Among them, σ T It is represented as the temperature change rate indicator, T[k] is represented as the temperature change rate estimate, k is represented as a discrete time point, n is represented as the number of unit time curve segments that make up the final temperature fluctuation curve, and Δt is represented as the time interval corresponding to the discrete temperature characteristic value.
[0091] The temperature change rate of the temperature fluctuation curve is estimated, specifically expressed as:
[0092]
[0093] Where T[k] represents the estimated temperature change rate, k represents a discrete time point, and M T It is represented as the temperature fluctuation characteristic value, a is represented as the scale sensitivity index, t is represented as the time point when the temperature changes, and b is represented as the time positioning index.
[0094] The calculation function of the temperature fluctuation characteristic value and the temperature change trend coefficient is used to extract the fluctuation characteristics from the fused data transmitted by the multi-sensor data fusion module, and then evaluate the overall amplitude and trend of the temperature fluctuation; the scale sensitivity index is used to represent the sensitivity of the aluminum foil billet casting and rolling machine to temperature changes, and the degree of influence on the aluminum foil at different positions of the aluminum foil billet casting and rolling machine is different; the time positioning index is used to determine the time point when the temperature change occurs; the temperature change trend coefficient and the corresponding scale sensitivity index are used to identify the direction and speed of temperature change over time through calculation; the local temperature dynamic index is used to describe the dynamic characteristics of temperature change under specific conditions; the temperature change rate estimation is used to describe the process of converting the temperature transformation domain into the time domain, and quantify the speed and stability of temperature change.
[0095] The temperature interval division module is used to calculate the segmentation score value according to the characteristic value of the temperature fluctuation curve transmitted by the temperature fluctuation curve analysis module, and then divide it into different working intervals and transmit it to the outlier calculation module; the working interval includes a start interval, a cutting interval, and a cooling interval.
[0096] The calculation model of the segmentation score value is specifically expressed as:
[0097] ξ i =(((dM T / dt)-(1 / 2)×(|M T |+|σ T |))+1) -1 ,
[0098] Among them, ξ i It is expressed as the segment score value of the i-th unit time curve segment, dM T / dt is the local temperature dynamic index, t is the time point when the temperature changes, M T Expressed as a local temperature dynamic index, σ T Expressed as a temperature change rate indicator.
[0099] The temperature interval division module first performs preliminary division according to the unit time curve segment. The start interval selects the time interval corresponding to the first unit time curve segment in the stable working cycle. In the start interval, the aluminum foil billet casting and rolling mill starts to heat up to the preset working temperature; the cutting interval of the temperature interval division module selects all time intervals except the start interval and the cooling interval. In the cutting interval, the aluminum foil billet casting and rolling mill performs the main aluminum foil billet cutting work; the cooling interval of the temperature interval division module selects the time interval corresponding to the last unit time curve segment in the stable working cycle. In the cooling interval, the aluminum foil billet casting and rolling mill gradually cools down to a safe shutdown state.
[0100] The temperature interval division module then confirms and modifies the preliminary interval division by the segmentation score value. For two adjacent segmentation points, if their segmentation score values ξ i are all positive, they are identified and divided into the start interval; if their segment score values ξ i One positive and one negative are identified and divided into segment intervals; if their segment score values ξ i If they are all negative values, they are identified and classified into the cooling zone.
[0101] The abnormal outlier calculation module is used to analyze the working interval transmitted by the temperature interval division module, generate abnormal outlier values, and transmit them to the abnormal data processing module.
[0102] The calculation model of the abnormal outlier is specifically expressed as follows:
[0103]
[0104] Among them, Φ e It is represented as the abnormal outlier of the e-th temperature data, (dM T / dt) is expressed as the local temperature dynamic index, ξ i It is expressed as the segment score value of the i-th unit time curve segment, σ T Expressed as the temperature change rate index, Φ emax Expressed as the maximum value of abnormal outliers, Φ emin Represented as the abnormal outlier minimum.
[0105] In the abnormal outlier calculation formula, when (ξ i -σ T )>0, it means that the abnormal outlier degree of the e-th temperature data is greater than the abnormal outlier degree of all temperature data, and |ξ i -σ T The larger the value of |, the larger the abnormal outlier value of the corresponding e-th temperature data, and the more urgent measures need to be taken; when (ξ i -σ T )<0, it means that the outlier degree of the e-th temperature data is less than the outlier degree of all temperature data, and |ξ i -σ T The larger the value of | is, the smaller the abnormal outlier value of the corresponding e-th temperature data is, and appropriate preventive measures should be taken.
[0106] The abnormal outlier calculation module can identify abnormal temperature data within the working range by calculating abnormal outlier values, help discover problems that may affect the production process, and ensure the stability of temperature data in the production process; by judging and distinguishing whether the temperature data is higher or lower than the normal level, the most serious abnormal situation and the abnormal situation that deviates from the normal range but is of a lighter degree are identified, so as to take corresponding emergency measures and preventive measures.
[0107] The abnormal data processing module is used to monitor the abnormal outlier values of the abnormal outlier calculation module, and output or store the abnormal outlier values, and provide an alarm mechanism to remind operation and maintenance personnel to take measures to deal with abnormal situations in a timely manner.
[0108] The abnormal data processing module classifies abnormal situations to implement targeted data management and response strategies.
[0109] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the case of no conflict, the same embodiment and different embodiments of the present invention can be combined with each other;
[0110] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A multi-sensor temperature sensor internal circulation monitoring system for aluminum foil billet casting and rolling mill, characterized in that: include: Temperature data acquisition module: used to obtain the temperature data of each key point in the internal circulation process of the aluminum foil billet casting and rolling mill through various types of sensors, and transmit it to the data preprocessing module; Data preprocessing module: used to preprocess the temperature data transmitted by the temperature data acquisition module through the self-diagnosis algorithm and transmit it to the multi-sensor data fusion module; Multi-sensor data fusion module: used to perform multi-sensor data fusion processing on the temperature data transmitted by the data preprocessing module through the single-chip microcomputer, and transmit the fused temperature data to the temperature fluctuation curve analysis module; Temperature fluctuation curve analysis module: used to analyze the data transmitted by the multi-sensor data fusion module, generate a temperature fluctuation curve composed of all temperature data in a unit time, further analyze the characteristic value of the temperature fluctuation curve, and transmit it to the temperature interval division module and the abnormal outlier calculation module; the unit time is a preset value; the characteristic value includes the temperature fluctuation characteristic value, the temperature change trend coefficient, the local temperature dynamic index, the temperature change rate index and the temperature change rate estimation; Temperature interval division module: used to calculate the segmentation score value according to the characteristic value of the temperature fluctuation curve transmitted by the temperature fluctuation curve analysis module, and then divide different working intervals, and transmit them to the outlier calculation module; the working intervals include the start interval, the cutting interval, and the cooling interval; Abnormal outlier calculation module: used to analyze the working interval transmitted by the temperature interval division module, generate abnormal outlier values, and transmit them to the abnormal data processing module; Abnormal data processing module: used to monitor the abnormal outlier values of the abnormal outlier calculation module, and output or store the abnormal outlier values, and provide an alarm mechanism to remind the operation and maintenance personnel to take timely measures to deal with abnormal situations.
2. The aluminum foil billet casting and rolling mill internal circulation monitoring system with multiple temperature sensors according to claim 1 is characterized in that: The calculation model of the self-diagnosis algorithm is as follows: Among them, D i represents the i-th data point after temperature data point preprocessing, N represents the total number of data points transmitted by the temperature data acquisition module, and d i It represents the i-th data point transmitted by the temperature data acquisition module, and μ represents the mean value of the total data transmitted by the temperature data acquisition module.
3. The aluminum foil billet casting and rolling mill internal circulation monitoring system with multiple temperature sensors according to claim 1 is characterized in that: The computational model of the multi-sensor data fusion is specifically expressed as follows: Where M represents the fusion data of temperature data points after preprocessing of all temperature sensors, and A i It is represented by the temperature subset of the ith measurement area after preprocessing of N-type thermocouples, B i It is represented by the temperature subset of the ith measurement area after preprocessing of the Pt100 thermal resistor, C i It is represented as the temperature subset of the i-th measurement area after thermistor is preprocessed, and K1 is represented as the temperature subset A i With temperature subset B i The conflict coefficient, K2 is expressed as the temperature subset A i With the temperature subset C i The conflict coefficient of K3 represents the temperature subset B i With the temperature subset C i The conflict coefficient, m(A i ) is represented by the temperature subset A i The distribution function, m(B i ) is represented as temperature subset B i The distribution function, m(C i ) is represented as a temperature subset C i The distribution function, m(A i ⊕B i ) is represented as the temperature subset A i With temperature subset B i The allocation function of the combination set, m(A i ⊕C i ) is represented by the temperature subset A i With the temperature subset C i The allocation function of the combination set, m(B i ⊕C i ) is represented as temperature subset B i With the temperature subset C i The allocation function for the combined set.
4. The aluminum foil billet casting and rolling mill internal circulation monitoring system with multiple temperature sensors according to claim 1 is characterized in that: The temperature fluctuation characteristic value of the temperature fluctuation curve is specifically expressed as: Among them, M T It is represented by the temperature fluctuation characteristic value, M represents the fusion data transmitted by the multi-sensor data fusion module, a represents the scale sensitivity index, ψ(x) represents the calculation function of the temperature change trend coefficient, t represents the time point when the temperature changes, and b represents the time positioning index 5. The aluminum foil billet casting and rolling mill internal circulation monitoring system with multiple temperature sensors according to claim 1 is characterized in that: The local temperature dynamic index of the temperature fluctuation curve is specifically expressed as: Among them, dM T / dt is the local temperature dynamic index, M T It is expressed as the temperature fluctuation characteristic value, t is the time point when the temperature changes, a is the scale sensitivity index, b is the time positioning index, and Δb is the difference of the time positioning index.
6. The aluminum foil billet casting and rolling mill internal circulation monitoring system with multiple temperature sensors according to claim 1 is characterized in that: The temperature change rate index of the temperature fluctuation curve is specifically expressed as: Among them, σ T It is represented as the temperature change rate indicator, T[k] is represented as the temperature change rate estimate, k is represented as a discrete time point, n is represented as the number of unit time curve segments that make up the final temperature fluctuation curve, and Δt is represented as the time interval corresponding to the discrete temperature characteristic value.
7. The aluminum foil billet casting and rolling mill internal circulation monitoring system with multiple temperature sensors according to claim 1 is characterized in that: The calculation model of the segmentation score value is specifically expressed as: x i =(((dM T / dt)-(1 / 2)×(|M T |+|s T |))+1) -1 Among them, ξ i It is expressed as the segment score value of the i-th unit time curve segment, dM T / dt is the local temperature dynamic index, t is the time point when the temperature changes, M T Expressed as a local temperature dynamic index, σ T Expressed as a temperature change rate indicator.
8. The aluminum foil billet casting and rolling mill internal circulation monitoring system with multiple temperature sensors according to claim 1 is characterized in that: The calculation model of the abnormal outlier is specifically expressed as follows: Among them, Φe represents the abnormal outlier value of the e-th temperature data, (dM T / dt) is expressed as the local temperature dynamic index, ξ i It is expressed as the segment score value of the i-th unit time curve segment, σ T Expressed as the temperature change rate index, Φ emax Expressed as the maximum value of abnormal outliers, Φ emin Represented as the abnormal outlier minimum.
Citation Information
Patent Citations
System and method for uninterruptedly protecting bearing bush of high-speed wire finish rolling large synchronous motor
CN115189333A
Control method and equipment based on industrial process and storage medium
CN115305343A
Method and system for intelligently monitoring temperature of each part of finish rolling motor
CN115921547A
Control method of intelligent switch module based on multi-sensor information fusion
CN116599211A
