A Fault Prediction and Early Warning System for Aging Furnace

Abstract

The present invention discloses an aging furnace fault prediction and early warning system, relates to the technical field of aging furnace fault prediction, and solves the technical problem in the prior art that the fault early warning result is inaccurate due to the lack of complete analysis of the working conditions; the present invention collects temperature data and system data of the aging furnace during operation through a temperature sensor and a database, and obtains the temperature detection state by time matching a preset temperature range; obtains the fluctuation state according to the heating chamber temperature and the cavity temperature corresponding to the time node, thereby obtaining the temperature state; inputs the temperature state into a fault recognition model to obtain the system fault state, obtains the current thermal insulation performance and the current cooling performance according to the system fault state, the heating chamber temperature, the cavity temperature and the corresponding time node, and calculates the performance degradation rate in combination with the system data, compares the performance degradation rate with the preset degradation threshold to obtain the degradation degree of the material, and generates an early warning signal according to the degradation degree.

Description

Technical Field

[0001] The invention belongs to the field of aging furnace fault prediction, relates to fault prediction technology, and specifically is an aging furnace fault prediction early warning system. Background Art

[0002] In industrial production environments, aging ovens are used as a key processing equipment to accelerate the aging process of materials to evaluate their performance and durability. In the industrial testing process, the materials to be tested are sent into the aging oven. By running at high temperature for a certain period of time, potential manufacturing defects and reliability issues can be exposed in advance, ensuring that only qualified products that have been strictly screened can enter the market.

[0003] The invention patent with application number CN2014800258172 discloses a predictive fault algorithm for a refrigeration system. The invention collects the temperature of each component in the freezer by monitoring, and obtains the performance of each component in the freezer by comparing the temperature of each component with a preset predetermined value, and generates an alarm signal according to the performance. When obtaining the performance of each component, the invention only evaluates the performance of the corresponding component by comparing the temperature with the set value. This method can only evaluate whether the component can currently work normally, but cannot evaluate the overall system based on the status of each component, affecting the accuracy of fault warning.

[0004] The present invention provides an aging furnace fault prediction and early warning system to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an aging furnace fault prediction and warning system to solve the technical problem in the prior art that the fault warning results are inaccurate due to the lack of complete analysis of the working conditions.

[0006] To achieve the above-mentioned object, the first aspect of the present invention provides an aging furnace fault prediction and early warning system, comprising: a database, a data collection module, a temperature control detection module and a degradation prediction module;

[0007] Data collection module: used to collect temperature data and system data of the aging furnace during operation;

[0008] Temperature control detection module: used to obtain the temperature state of the aging furnace according to the temperature data; input the temperature state into the fault identification model to obtain the system fault state; wherein the fault identification model is constructed based on the neural network model;

[0009] Degradation prediction module: used to predict the degree of material degradation based on system fault status, temperature data and system data; generate early warning signals based on the degree of material degradation.

[0010] Preferably, obtaining the temperature state of the aging furnace according to the temperature data includes:

[0011] Extracting temperature data; the temperature data includes chamber temperature, heating chamber temperature and corresponding time;

[0012] Setting a preset temperature range corresponding to a preset time; the preset temperature range is set according to the chamber temperature range and the heating chamber temperature range of a normal aging furnace when the preset time is reached; the preset temperature range includes a preset chamber temperature range and a preset heating chamber temperature range;

[0013] Matching the corresponding time with the preset time, marking the chamber temperature and the heating chamber temperature that are the same as the preset time as the matching chamber temperature and the matching heating temperature respectively;

[0014] Determine whether the matching chamber temperature is included in the preset chamber temperature range; if yes, mark the corresponding chamber temperature state as a normal chamber state; if no, mark the corresponding chamber temperature state as an abnormal chamber state;

[0015] Determine whether the matching heating chamber temperature is included in the preset heating chamber temperature range; if yes, mark the corresponding heating chamber temperature state as a normal heating chamber temperature state; if no, mark the corresponding heating chamber temperature state as an abnormal heating chamber temperature state;

[0016] Marking the chamber temperature state and the heating chamber temperature state as temperature detection states;

[0017] Setting a fluctuation range; the fluctuation range is set according to the temperature fluctuation of the normal heating chamber when heating and the temperature fluctuation of the normal chamber when cooling; the fluctuation range includes the chamber fluctuation range and the heating chamber fluctuation range;

[0018] The fluctuation trend is obtained according to the fluctuation range, temperature data and corresponding time; the temperature detection state and the fluctuation trend are combined to obtain the temperature state.

[0019] Preferably, obtaining the fluctuation trend according to the fluctuation range, temperature data and corresponding time includes:

[0020] Extract fluctuation range, temperature data and corresponding time;

[0021] Setting a time extraction interval; the time extraction interval is set manually;

[0022] Obtaining a time node according to a time extraction interval; subtracting a chamber temperature corresponding to an n+1th time node from a chamber temperature corresponding to an nth time node to obtain a chamber temperature fluctuation at an nth time node; subtracting a heating chamber temperature corresponding to an n+1th time node from a heating chamber temperature corresponding to an nth time node to obtain a heating chamber temperature fluctuation at an nth time node;

[0023] Determine whether the chamber temperature fluctuation is greater than or equal to the chamber fluctuation range; if yes, mark the corresponding chamber fluctuation state as normal chamber fluctuation; if no, mark the corresponding chamber fluctuation state as abnormal chamber fluctuation;

[0024] Determine whether the heating chamber fluctuation is greater than or equal to the heating chamber fluctuation range; if yes, mark the corresponding heating chamber fluctuation state as normal heating chamber fluctuation; if no, mark the corresponding heating chamber fluctuation state as abnormal heating chamber fluctuation;

[0025] The chamber temperature fluctuation and the heating chamber temperature fluctuation are combined according to the time nodes to generate the chamber fluctuation graph and the heating chamber fluctuation graph; the chamber temperature trend and the heating chamber temperature trend are obtained according to the chamber fluctuation graph and the heating chamber fluctuation graph; the chamber fluctuation state, the heating chamber fluctuation state, the chamber temperature trend and the heating chamber temperature trend are combined to obtain the fluctuation trend.

[0026] Preferably, the step of obtaining the chamber temperature trend and the heating chamber temperature trend according to the chamber fluctuation graph and the heating chamber fluctuation graph comprises:

[0027] Extracting chamber fluctuation map and heating chamber fluctuation map;

[0028] The chamber temperature trend at the nth time node is obtained by subtracting the chamber temperature fluctuation at the nth time node from the chamber temperature fluctuation at the n+1th time node;

[0029] The heating chamber temperature trend at the mth time node is obtained by subtracting the heating chamber temperature fluctuation at the m+1th time node from the heating chamber temperature fluctuation at the mth time node; wherein n and m are positive integers.

[0030] Preferably, the fault identification model is constructed based on a neural network model, including:

[0031] Historical temperature states and corresponding historical system fault states are extracted from the database, and the historical temperature states and the corresponding historical system fault states are used as training data and test data. The neural network model is trained using the training data, and the trained neural network model is tested using the test data. The parameters of the neural network model are adjusted according to the test results to obtain a fault recognition model whose input data is the temperature state and whose output data is the corresponding system fault state.

[0032] Preferably, the predicting of the material degradation degree according to the system fault state, temperature data and system data includes:

[0033] Extracting system fault status, temperature data and system data; the system data includes initial insulation performance of insulation materials in the aging furnace, use time of insulation materials, initial cooling performance of cooling materials and use time of cooling materials;

[0034] When the system fault state is that the chamber rises abnormally, the cooling performance trend of the cooling material is marked as a downward trend; when the system fault state is that the heating chamber falls abnormally, the insulation performance trend of the insulation material is marked as a downward trend;

[0035] When the cooling performance trend and the thermal insulation performance trend show a downward trend, the thermal insulation performance decline rate and the cooling performance decline rate are calculated based on the system data, the current thermal insulation performance and the current cooling performance; the corresponding current thermal insulation performance and the current cooling performance are obtained based on the heating chamber temperature, the chamber temperature and the corresponding time node;

[0036] Setting a degradation threshold, wherein the degradation threshold is set according to whether the insulation material and the cooling material in the aging furnace meet the requirements of normal use; the degradation threshold includes a thermal insulation degradation threshold and a cooling degradation threshold;

[0037] The degree of material degradation is obtained based on the degradation threshold, the thermal insulation performance degradation rate, and the cooling performance degradation rate.

[0038] Preferably, the obtaining of the corresponding current heat preservation performance and current cooling performance according to the heating chamber temperature, the cavity temperature and the corresponding time node includes:

[0039] A1: Extract the heating chamber temperature, cavity temperature and corresponding time nodes;

[0040] A2: Set the thermal balance threshold; determine whether the difference between the heating chamber temperature at the q+1th time node and the heating chamber temperature at the qth time node is less than the thermal balance threshold; if yes, jump to A3; if no, add 1 to q and continue to determine; the thermal balance threshold is set according to the temperature fluctuation range after the heating chamber of the normal aging furnace reaches thermal balance;

[0041] A3: Determine whether the difference between the heating chamber temperature at the q+2th time node and the heating chamber temperature at the q+1th time node is less than the thermal balance threshold; if yes, mark the qth time node as the thermal balance time node, and the current thermal insulation performance is q minutes; if no, add 1 to q and continue to determine;

[0042] A4: Set the cold balance threshold; determine whether the difference between the chamber temperature at the p+1th time node and the chamber temperature at the pth time node is less than the cold balance threshold; if yes, jump to A5; if no, add one to p and continue to determine; the thermal balance threshold is set according to the temperature fluctuation range after the normal aging furnace chamber reaches cold balance;

[0043] A5: Determine whether the difference between the chamber temperature at the p+2th time node and the chamber temperature at the p+1th time node is less than the cold balance threshold; if yes, mark the pth time node as the cold balance time node, and the current cooling performance is p minutes; if no, add one to p and continue to determine.

[0044] Preferably, the step of calculating and obtaining the thermal insulation performance decrease rate and the cooling performance decrease rate according to the system data, the current thermal insulation performance and the current cooling performance includes:

[0045] Extract the initial thermal insulation performance, the use time of thermal insulation materials, the initial cooling performance, the use time of cooling materials, the current thermal insulation performance and the current cooling performance;

[0046] The initial thermal insulation performance is marked as CBX, the use time of the thermal insulation material is marked as CBT, the current thermal insulation performance is marked as CBY, the initial cooling performance is marked as CLX, the use time of the cooling material is marked as CLT, and the current cooling performance is marked as CLY;

[0047] The thermal insulation performance decrease rate CBP is calculated by the formula CBP= (CBX-CBY) / CBT; the cooling performance decrease rate CLP is calculated by the formula CLP= (CLX-CLY) / CLT.

[0048] Preferably, obtaining the degree of material degradation according to the degradation threshold, the thermal insulation performance degradation rate and the cooling performance degradation rate includes:

[0049] Extract the degradation threshold, the thermal insulation performance degradation rate, and the cooling performance degradation rate;

[0050] Determine whether the rate of decrease in thermal insulation performance is greater than or equal to the thermal insulation degradation threshold; if yes, mark the degree of degradation of the thermal insulation material as severe thermal insulation degradation; if no, mark the degree of degradation of the thermal insulation material as slight thermal insulation degradation;

[0051] Determine whether the cooling performance degradation rate is greater than or equal to the cooling degradation threshold; if yes, mark the degradation degree of the cooling material as severe cooling degradation; if no, mark the degradation degree of the cooling material as slight cooling degradation;

[0052] The degree of deterioration of the heat-insulating material and the degree of deterioration of the cooling material are marked as material deterioration degrees.

[0053] Preferably, generating a warning signal according to the degree of material degradation includes:

[0054] The degree of deterioration of the extracted material;

[0055] When the material degradation degree shows serious insulation degradation, a heating chamber warning signal is generated; when the material degradation degree shows serious cooling degradation, a chamber warning signal is generated;

[0056] The chamber warning signal and the heating chamber warning signal are marked as warning signals.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] 1. The present invention collects temperature data and system data when the aging furnace is running; analyzes the temperature data, and analyzes the temperature changes in the aging furnace according to the time and temperature data, so as to quickly locate the location of the fault, provide a direction for troubleshooting, and predict the possible future operating status of the equipment, which is helpful to take measures in advance to deal with potential problems; obtains the temperature change trend in the furnace according to the time and the fluctuation of the temperature in the furnace, and the temperature status of the heating chamber and the cavity when the aging furnace is running, which can provide early warning for equipment maintenance and avoid production interruption caused by sudden failure; inputs the temperature status into the fault identification model, which can quickly obtain the specific system fault status; obtains the corresponding current insulation performance and current cooling performance according to the heating chamber temperature, the cavity temperature and the corresponding time node Performance, determine the time nodes of thermal balance and cold balance, help to identify whether the equipment has performance degradation problems, and facilitate performance comparison and evaluation; calculate the insulation performance degradation rate and cooling performance degradation rate of the aging furnace based on system data, current insulation performance and current cooling performance, which can identify equipment performance degradation at an early stage, take maintenance measures in time, and avoid sudden failures. Preventive maintenance can effectively reduce the emergency repair cost of equipment, extend the service life of equipment, and reduce the total cost of ownership; by comparing the insulation performance degradation rate and cooling performance degradation rate with the set degradation threshold, the degree of degradation of the insulation and cooling materials in the aging furnace can be obtained; generate early warning signals according to the degree of degradation to help achieve preventive maintenance, reduce the occurrence of sudden failures, and avoid high emergency repair costs.

[0059] 2. The present invention analyzes the two different stages and locations in the aging furnace respectively, predicts faults for the heating chamber in the heating stage and the chamber in the cooling stage respectively, predicts the performance of the thermal insulation material in the heating chamber and the cooling material in the chamber, and compares them with preset thresholds. The location and type of possible failures are predicted in advance, and the aging state of the material can be judged more accurately, thereby identifying possible failure points in advance. Based on the prediction results, preventive maintenance strategies can be implemented to avoid unplanned downtime caused by sudden failures. Thermal insulation and cooling materials with good performance can reduce energy loss, improve energy utilization efficiency, reduce production costs, and are also more environmentally friendly. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 The following is a flowchart of an embodiment of the present invention.

[0062] Figure 2 It is a system composition diagram of the present invention.

[0063] Figure 3 The figure is a complete flow chart for obtaining the temperature detection status in one embodiment of the present invention. DETAILED DESCRIPTION

[0064] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0065] See also Figure 1-Figure 3 , the first aspect of the present invention provides an aging furnace fault prediction and early warning system, including: a database, a data collection module, a temperature control detection module and a degradation prediction module;

[0066] Data collection module: used to collect temperature data and system data during the operation of the aging furnace.

[0067] Exemplarily, the chamber temperature and the heating chamber temperature of the aging furnace when aging the items to be aged are collected through temperature sensors, and the corresponding time is recorded; it is extracted from the database that the initial cooling performance of the cooling material in the chamber of the aging furnace is 35 minutes, and the service life of the cooling material is 5 years; the initial insulation performance of the insulation material in the heating chamber of the aging furnace is 25 minutes, and the service life of the insulation material is 5 years.

[0068] It should be noted that this embodiment is to complete the data obtained from the aging process of the item to be aged. The item to be aged is heated in the heating chamber, and after the corresponding data is collected, it enters the chamber for cooling. During the heating process, the thermal insulation material retains the heat in the heating chamber to reduce heat loss and increase the temperature rise rate. The cooling material absorbs the heat in the heated item to be aged to cool the item to be aged. The thermal insulation performance can be represented by the time it takes for the temperature to reach thermal equilibrium, and the cooling performance can be represented by the time it takes for the temperature to reach cold equilibrium.

[0069] Temperature control detection module: used to obtain the temperature status of the aging furnace according to the temperature data; obtain the system fault status according to the temperature status.

[0070] For example, in this embodiment, the item to be aged is rubber. When the rubber is aged normally, a preset heating chamber temperature range corresponding to the estimated time of the heating stage and a preset chamber temperature range corresponding to the estimated time of the cooling stage are provided; the corresponding time is matched with the preset time, and the chamber temperature and the heating chamber temperature that are the same as the preset time are marked as the matching chamber temperature and the matching heating temperature, respectively. In this embodiment, thermal equilibrium is reached at the 20th minute of the heating stage, the matching heating chamber temperature in the heating chamber is 35 degrees, and the preset heating chamber temperature range at 20 minutes is 38 degrees-42 degrees; it is judged whether the matching heating chamber temperature is If the temperature is not within the preset heating chamber temperature range, it is determined that the matching heating chamber temperature is not within the preset chamber temperature range, and the heating chamber temperature state is marked as an abnormal heating chamber temperature state; at the 15th minute of the cooling stage, cold equilibrium is reached, the matching chamber temperature in the chamber is 15 degrees, and the preset chamber temperature range at 15 minutes is 12 degrees to 18 degrees. It is determined whether the matching chamber temperature is within the preset chamber temperature range, and it is determined that the matching chamber temperature is within the preset chamber temperature range, and the chamber temperature state is marked as a normal chamber state; the temperature detection states are abnormal heating chamber state and normal chamber state.

[0071] In this embodiment, the fluctuation range of the heating stage is set to 2 degrees, the fluctuation range of the cooling stage is set to 2 degrees, and the time extraction interval is 1 minute; the time nodes are obtained according to the time extraction interval, and a time node is extracted every one minute, and the heating chamber temperature corresponding to the 21st time node in the heating stage is 36 degrees, and the heating chamber temperature corresponding to the 20th time node is 35 degrees, and the heating chamber temperature fluctuation at the 20th time node is 1 degree; the time nodes are extracted to obtain the chamber temperature at the 16th time node is 13 degrees, and the chamber temperature at the 15th time node is 15 degrees, and the chamber temperature fluctuation at the 15th time node is 2 degrees; it is judged whether the heating chamber fluctuation is greater than or equal to the heating chamber fluctuation range, and it is judged that the heating chamber fluctuation is less than the heating chamber fluctuation range, and the heating chamber fluctuation state is marked as abnormal heating chamber fluctuation; it is judged whether the chamber temperature fluctuation is greater than or equal to the chamber fluctuation range, and it is judged that the chamber temperature fluctuation is equal to the chamber fluctuation range, and the chamber fluctuation state is marked as normal chamber fluctuation.

[0072] It should be noted that during the heating stage and the cooling stage, if the temperature fluctuation in the heating chamber or cavity is less than the preset fluctuation range, it means that the insulation effect of the insulation material in the heating chamber or the cooling effect of the cooling material in the cavity is lower than the normal level.

[0073] According to the time node, the chamber temperature fluctuation and the heating chamber temperature fluctuation are combined to generate a chamber fluctuation graph and a heating chamber fluctuation graph. The horizontal axis in the heating chamber fluctuation graph is the time node, and the vertical axis is the heating chamber temperature fluctuation. The horizontal axis in the chamber fluctuation graph is the time node, and the vertical axis is the chamber temperature fluctuation. The heating chamber temperature fluctuation at the 16th time node is subtracted from the heating chamber temperature fluctuation at the 15th time node, and the heating chamber temperature trend at the 15th time node is a downward trend. The chamber temperature fluctuation at the 15th time node is subtracted from the chamber temperature fluctuation at the 15th time node, and the chamber temperature trend at the 15th time node is an upward trend.

[0074] Historical temperature states and corresponding historical system fault states are extracted from the database, and the historical temperature states and corresponding historical system fault states are used as training data and test data. The neural network model is trained using the training data, and the trained neural network model is tested using the test data. The parameters of the neural network model are adjusted according to the test results to obtain a fault recognition model whose input data is the temperature state and whose output data is the corresponding system fault state; the temperature state is input into the fault recognition model to obtain the system fault state as an abnormal drop in the heating chamber.

[0075] In this embodiment, the system fault state is an abnormal decrease in the heating chamber, and the thermal insulation performance trend of the thermal insulation material is marked as a downward trend; in this embodiment, the thermal balance threshold is set to 1 degree, and it is judged whether the difference between the heating chamber temperature at the q+1th time node and the heating chamber temperature at the qth time node is less than or equal to the thermal balance threshold; it is judged that the difference between the heating chamber temperature at the 25th time node and the heating chamber temperature at the 24th time node is less than the thermal balance threshold; then it is continued to be judged whether the difference between the heating chamber temperature at the q+2th time node and the heating chamber temperature at the q+1th time node is less than the thermal balance threshold; it is judged that the difference between the heating chamber temperature at the 26th time node and the heating chamber temperature at the 25th time node is less than the thermal balance threshold, then the 24th time node is marked as a thermal balance time node, and the current thermal insulation performance is 24 minutes; the thermal insulation performance decrease rate CBP=2.2 is calculated by the formula CBP=(CBX-CBY) / CBT.

[0076] It should be noted that thermal equilibrium means that after the heating chamber reaches a certain temperature after heating, the temperature change no longer rises but fluctuates at a fixed value. This situation is thermal equilibrium; cold equilibrium means that after the chamber reaches a certain temperature after cooling, the temperature change no longer falls but fluctuates at a fixed value. This situation is cold equilibrium.

[0077] In another embodiment, when the system fault state is that the chamber temperature rises abnormally, the cooling performance trend of the cooling material is marked as a downward trend, and the cold balance threshold is set to 2 degrees, and it is determined whether the difference between the chamber temperature at the p+1th time node and the chamber temperature at the pth time node is less than or equal to the cold balance threshold; it is determined that the difference between the chamber temperature at the 17th time node and the chamber temperature at the 16th time node is less than the cold balance threshold; then it is continued to be determined whether the difference between the chamber temperature at the 18th time node and the chamber temperature at the 17th time node is less than the cold balance threshold; it is determined that the difference between the chamber temperature at the 18th time node and the chamber temperature at the 17th time node is less than the cold balance threshold, then the 16th time node is marked as a cold balance time node, and the current cooling performance is 16 minutes, and the cooling performance decrease rate CLP=1.8 is calculated by the formula CLP=(CLX-CLY) / CLT.

[0078] It should be noted that, under normal circumstances, system failures such as abnormal rising of the heating chamber and abnormal falling of the chamber will not occur. The abnormal rising of the heating chamber indicates that the heating chamber temperature fluctuation in the heating chamber is greater than the heating chamber temperature fluctuation range, and the temperature rising rate in the heating chamber is greater than the normal fluctuation range; the abnormal falling of the chamber indicates that the chamber temperature fluctuation in the chamber is greater than the chamber temperature fluctuation range, and the temperature falling rate in the chamber is greater than the normal fluctuation range.

[0079] In this embodiment, the thermal insulation degradation threshold is set to 2, and the cooling degradation threshold is set to 1.5; it is judged whether the thermal insulation performance degradation rate is greater than or equal to the thermal insulation degradation threshold. If it is judged that the thermal insulation performance degradation rate is greater than the thermal insulation degradation threshold, the degradation degree of the thermal insulation material is marked as severe thermal insulation degradation; it is judged whether the cooling performance degradation rate is greater than or equal to the cooling degradation threshold. If it is judged that the cooling performance degradation rate is less than the cooling degradation threshold, the degradation degree of the cooling material is marked as severe cooling degradation.

[0080] In this embodiment, if severe insulation degradation and severe cooling degradation are detected, a heating chamber warning signal and a cavity warning signal are generated, and the heating chamber warning signal and the cavity warning signal are sent to the management department to prepare a maintenance plan.

[0081] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0082] Working principle of the present invention:

[0083] The present invention collects temperature data and system data of the aging furnace during operation through a temperature sensor and a database, obtains the temperature detection state by matching the heating chamber temperature and the heating temperature corresponding to the preset heating chamber temperature range and the preset chamber temperature range through time matching and comparing; obtains the heating chamber temperature fluctuation and the chamber temperature fluctuation according to the heating chamber temperature and the chamber temperature corresponding to the time node, compares the heating chamber temperature fluctuation and the chamber temperature fluctuation with the preset fluctuation range, and obtains the fluctuation state; generates a chamber fluctuation graph and a heating chamber fluctuation graph according to the time node and the fluctuation state, analyzes the fluctuation graph to obtain the heating chamber temperature trend and the chamber temperature trend, and integrates them to obtain the temperature state of the aging furnace; inputs the temperature state into a fault identification model to obtain the system fault state; obtains the performance trend according to the system fault state; obtains the current thermal insulation performance and the current cooling performance according to the performance trend, the heating chamber temperature, the chamber temperature and the corresponding time node, calculates the performance degradation rate according to the system data, the current thermal insulation performance and the current cooling performance, compares the performance degradation rate with the preset degradation threshold to obtain the degree of material degradation, and generates an early warning signal according to the degree of degradation.

[0084] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An aging furnace failure prediction and early warning system, characterized in that: include: Database, data collection module, temperature control detection module and degradation prediction module; Data collection module: used to collect temperature data and system data of the aging furnace during operation; Temperature control detection module: used to obtain the temperature state of the aging furnace according to the temperature data; input the temperature state into the fault identification model to obtain the system fault state; wherein the fault identification model is constructed based on the neural network model; Deterioration prediction module: used to predict the degree of material degradation based on system fault status, temperature data and system data; generate early warning signals based on the degree of material degradation; The method of predicting the material degradation degree according to the system fault state, temperature data and system data includes: Extracting system fault status, temperature data and system data; the system data includes initial insulation performance of insulation materials in the aging furnace, use time of insulation materials, initial cooling performance of cooling materials and use time of cooling materials; When the system fault state is that the chamber rises abnormally, the cooling performance trend of the cooling material is marked as a downward trend; when the system fault state is that the heating chamber falls abnormally, the insulation performance trend of the insulation material is marked as a downward trend; The corresponding current thermal insulation performance and current cooling performance are obtained according to the heating chamber temperature, the cavity temperature and the corresponding time node; when the cooling performance trend and the thermal insulation performance trend show a downward trend, the thermal insulation performance decrease rate and the cooling performance decrease rate are calculated according to the system data, the current thermal insulation performance and the current cooling performance; Set the degradation threshold, which includes the thermal insulation degradation threshold and the cooling degradation threshold; The degree of material degradation is obtained based on the degradation threshold, the thermal insulation performance degradation rate, and the cooling performance degradation rate.

2. The aging furnace failure prediction and early warning system according to claim 1 is characterized in that: The step of obtaining the temperature state of the aging furnace according to the temperature data includes: Extracting temperature data; the temperature data includes chamber temperature, heating chamber temperature and corresponding time; Setting a preset temperature range corresponding to a preset time; the preset temperature range includes a preset chamber temperature range and a preset heating chamber temperature range; Matching the corresponding time with the preset time, marking the chamber temperature and the heating chamber temperature that are the same as the preset time as the matching chamber temperature and the matching heating temperature respectively; Determine whether the matching chamber temperature is included in the preset chamber temperature range; if yes, mark the corresponding chamber temperature state as a normal chamber state; if no, mark the corresponding chamber temperature state as an abnormal chamber state; Determine whether the matching heating chamber temperature is included in the preset heating chamber temperature range; if yes, mark the corresponding heating chamber temperature state as a normal heating chamber temperature state; if no, mark the corresponding heating chamber temperature state as an abnormal heating chamber temperature state; Marking the chamber temperature state and the heating chamber temperature state as temperature detection states; Set the fluctuation range; the fluctuation range includes the chamber fluctuation range and the heating chamber fluctuation range; The fluctuation trend is obtained according to the fluctuation range, temperature data and corresponding time; the temperature detection state and the fluctuation trend are combined to obtain the temperature state.

3. The aging furnace failure prediction and early warning system according to claim 2 is characterized in that: The obtaining of the fluctuation trend according to the fluctuation range, temperature data and corresponding time includes: Extract fluctuation range, temperature data and corresponding time; Set the time extraction interval; Obtaining a time node according to a time extraction interval; subtracting a chamber temperature corresponding to an n+1th time node from a chamber temperature corresponding to an nth time node to obtain a chamber temperature fluctuation at an nth time node; subtracting a heating chamber temperature corresponding to an n+1th time node from a heating chamber temperature corresponding to an nth time node to obtain a heating chamber temperature fluctuation at an nth time node; Determine whether the chamber temperature fluctuation is greater than or equal to the chamber fluctuation range; if yes, mark the corresponding chamber fluctuation state as normal chamber fluctuation; if no, mark the corresponding chamber fluctuation state as abnormal chamber fluctuation; Determine whether the heating chamber fluctuation is greater than or equal to the heating chamber fluctuation range; if yes, mark the corresponding heating chamber fluctuation state as normal heating chamber fluctuation; if no, mark the corresponding heating chamber fluctuation state as abnormal heating chamber fluctuation; The chamber temperature fluctuation and the heating chamber temperature fluctuation are combined according to the time nodes to generate the chamber fluctuation graph and the heating chamber fluctuation graph; the chamber temperature trend and the heating chamber temperature trend are obtained according to the chamber fluctuation graph and the heating chamber fluctuation graph; the chamber fluctuation state, the heating chamber fluctuation state, the chamber temperature trend and the heating chamber temperature trend are combined to obtain the fluctuation trend.

4. The aging furnace failure prediction and early warning system according to claim 3 is characterized in that: The step of obtaining the chamber temperature trend and the heating chamber temperature trend according to the chamber fluctuation diagram and the heating chamber fluctuation diagram comprises: Extracting chamber fluctuation map and heating chamber fluctuation map; The chamber temperature trend at the nth time node is obtained by subtracting the chamber temperature fluctuation at the nth time node from the chamber temperature fluctuation at the n+1th time node; The heating chamber temperature trend at the mth time node is obtained by subtracting the heating chamber temperature fluctuation at the m+1th time node from the heating chamber temperature fluctuation at the mth time node; wherein n and m are positive integers.

5. The aging furnace failure prediction and early warning system according to claim 1 is characterized in that: The fault identification model is constructed based on a neural network model, including: Historical temperature states and corresponding historical system fault states are extracted from the database, and the historical temperature states and corresponding historical system fault states are used as training data and test data. The neural network model is trained using the training data, and the trained neural network model is tested using the test data. The parameters of the neural network model are adjusted according to the test results to obtain a fault recognition model whose input data is the temperature state and whose output data is the corresponding system fault state.

6. The aging furnace failure prediction and early warning system according to claim 1 is characterized in that: The obtaining of the corresponding current heat preservation performance and current cooling performance according to the heating chamber temperature, the cavity temperature and the corresponding time node includes: A1: Extract the heating chamber temperature, cavity temperature and corresponding time nodes; A2: Set the thermal balance threshold; determine whether the difference between the heating chamber temperature at the q+1th time node and the heating chamber temperature at the qth time node is less than or equal to the thermal balance threshold; if yes, jump to A3; if no, add 1 to q and continue to determine; A3: Determine whether the difference between the heating chamber temperature at the q+2th time node and the heating chamber temperature at the q+1th time node is less than or equal to the thermal balance threshold; if yes, mark the qth time node as the thermal balance time node, and the current thermal insulation performance is q minutes; if no, add 1 to q and continue to determine; A4: Set the cold balance threshold; determine whether the difference between the chamber temperature at the p+1th time node and the chamber temperature at the pth time node is less than or equal to the cold balance threshold; if yes, jump to A5; if no, add one to p and continue to determine; A5: Determine whether the difference between the chamber temperature at the p+2th time node and the chamber temperature at the p+1th time node is less than or equal to the cold balance threshold; if yes, mark the pth time node as the cold balance time node, and the current cooling performance is p minutes; if no, add one to p and continue to determine.

7. The aging furnace failure prediction and early warning system according to claim 1 is characterized in that: The step of calculating and obtaining the thermal insulation performance decrease rate and the cooling performance decrease rate according to the system data, the current thermal insulation performance and the current cooling performance includes: Extract the initial thermal insulation performance, the use time of thermal insulation materials, the initial cooling performance, the use time of cooling materials, the current thermal insulation performance and the current cooling performance; The initial thermal insulation performance is marked as CBX, the use time of the thermal insulation material is marked as CBT, the current thermal insulation performance is marked as CBY, the initial cooling performance is marked as CLX, the use time of the cooling material is marked as CLT, and the current cooling performance is marked as CLY; The thermal insulation performance decrease rate CBP is calculated by the formula CBP= (CBX-CBY) / CBT; the cooling performance decrease rate CLP is calculated by the formula CLP= (CLX-CLY) / CLT.

8. The aging furnace failure prediction and early warning system according to claim 1 is characterized in that: The obtaining of the material degradation degree according to the degradation threshold, the thermal insulation performance degradation rate and the cooling performance degradation rate includes: Extract the degradation threshold, the thermal insulation performance degradation rate, and the cooling performance degradation rate; Determine whether the rate of decrease in thermal insulation performance is greater than or equal to the thermal insulation degradation threshold; if yes, mark the degree of degradation of the thermal insulation material as severe thermal insulation degradation; if no, mark the degree of degradation of the thermal insulation material as slight thermal insulation degradation; Determine whether the cooling performance degradation rate is greater than or equal to the cooling degradation threshold; if yes, mark the degradation degree of the cooling material as severe cooling degradation; if no, mark the degradation degree of the cooling material as slight cooling degradation; The degree of deterioration of the heat-insulating material and the degree of deterioration of the cooling material are marked as material deterioration degrees.

9. The aging furnace failure prediction and early warning system according to claim 1 is characterized in that: The generating of the early warning signal according to the degree of material degradation comprises: The degree of deterioration of the extracted material; When the material degradation degree shows serious insulation degradation, a heating chamber warning signal is generated; when the material degradation degree shows serious cooling degradation, a chamber warning signal is generated; The chamber warning signal and the heating chamber warning signal are marked as warning signals.

Images