Mold service life management system based on vehicle lamp production mold monitoring

Abstract

The invention discloses a mold life management system based on vehicle lamp production mold monitoring, which comprises a data acquisition module, a mold health assessment module and an early warning and decision module, and relates to the technical field of mold life management. According to the mold life management system based on vehicle lamp production mold monitoring, data are preprocessed, various characteristics of the temperature change rate, the pressure value, the strain amplitude and the vibration frequency are extracted for analysis and processing, and the extracted characteristic parameters are integrated to establish and form a mold life evaluation model; then real-time data is extracted and introduced into the mold life evaluation model to evaluate the health index of the mold, and the actual wear condition and performance change of the mold can be more accurately mastered by monitoring various physical quantity data of the mold in real time and utilizing an advanced algorithm and model to evaluate the life; and subjectivity and uncertainty of artificial experience judgment are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of mold life management, and in particular to a mold life management system based on monitoring of automobile lamp production molds. Background Art

[0002] In the automotive lighting industry, molds are key production tools. Their quality and service life directly affect the production efficiency, product quality, and production costs of automotive lighting. Currently, the management of automotive lighting production molds mainly relies on manual experience, and the mold life is determined through regular maintenance and simple estimates based on the number of uses.

[0003] The reference patent name is: A mold full life cycle management system (patent publication number: CN111695858A, patent publication date: 2020-09-22), including: a mold procurement module, a mold fault repair module and a mold inventory assessment management module; wherein: the mold inventory assessment management module applies the mold safety inventory assessment method to evaluate the mold inventory life, and the mold inventory assessment management module obtains relevant feature data input from the abnormality detection unit and industrial sensor of the mold fault repair module, applies the mold safety stock assessment method to calculate, outputs the mold inventory safety warning and the optimal inventory replenishment quantity, and finally notifies the mold procurement module of the optimal inventory replenishment quantity. The present invention effectively solves the problems of traditional mold management and mold inventory assessment, such as the lack of real-time monitoring, dynamic prediction of inventory life, and calculation of the optimal replenishment quantity, thereby improving the production efficiency and product yield of the enterprise.

[0004] Based on the description in the above-mentioned documents, existing automotive lamp production molds are easily affected by various factors during use, which affects the life of the mold. On the one hand, manual experience makes it difficult to accurately grasp the actual wear and tear and performance changes of the mold, which may cause the mold to be scrapped prematurely before reaching its theoretical life, resulting in a waste of resources; on the other hand, the failure to discover potential problems of the mold in time may cause the mold to malfunction during use, affecting the production progress and even causing product quality problems. For this reason, the present invention provides a mold life management system based on automotive lamp production mold monitoring. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a mold life management system based on the monitoring of car lamp production molds, which solves the problem that car lamp production molds are easily disturbed by various factors during use and mold problems cannot be discovered in time, which affects the life of the molds.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a mold life management system based on monitoring of automobile lamp production molds, comprising:

[0007] The data acquisition module is located in various parts of the headlight production mold and is equipped with various types of sensors to transmit the collected physical quantity data in real time and store them in the database;

[0008] The mold health assessment module receives the transmitted data, extracts historical data, performs pre-processing operations on the data, and extracts various characteristics such as temperature change rate, pressure value, strain amplitude and vibration frequency for analysis and processing. The extracted characteristic parameters are integrated to form a mold life assessment model. Then, real-time data is extracted and introduced into the mold life assessment model to evaluate the mold health index.

[0009] The early warning and decision-making module implements graded operations on the life status based on the evaluated mold health index, implements early warning operations through different levels, and matches the corresponding processing strategies to transmit to the execution unit to complete the control operation.

[0010] Preferably, the data acquisition module includes a temperature sensor, a pressure sensor, a strain sensor and a vibration sensor. The temperature sensor is used to monitor the temperature changes of the mold in real time when it is working. The pressure sensor measures the pressure that the mold is subjected to during the injection molding process. The strain sensor can detect the deformation of the mold when it is subjected to force. The vibration sensor is used to monitor the vibration frequency and amplitude of the mold during operation.

[0011] Preferably, the data preprocessing operation in the mold health assessment module is:

[0012] After extracting real-time data and historical data, set up the master node and slave node, which are used to implement indexing and tracing for subsequent data extraction;

[0013] By extracting the collection type content of each sensor, and taking the collection type content as the main node, and the main body of each sub-category content under the corresponding collection type as the sub-node, the corresponding data and numerical results are extracted through content search of the main node and sub-node.

[0014] Preferably, the mold health assessment module extracts the temperature change rate feature for analysis and processing by:

[0015] Identify the various processes in the production of automotive lamp molds and extract temperature data for each process;

[0016] Set the extraction cycle and establish a temperature change rate coordinate axis, with the number of extracted cycles as the horizontal axis of the temperature change rate coordinate axis, and the temperature change rate data under the corresponding number of cycles as the vertical axis of the temperature change rate coordinate axis. After the numerical value is introduced, a temperature change rate curve is formed, and then the temperature change rate threshold is introduced as a constant function into the temperature change rate coordinate axis to determine abnormal data, and determine whether it is problem data by analyzing the abnormal data;

[0017] And record the number of times the problem data appears and mark it as M.

[0018] Preferably, the specific operation of introducing the temperature change rate threshold as a constant function into the temperature change rate coordinate axis to determine abnormal data is:

[0019] Set the temperature change rate threshold to [A1, A2] and form a constant function with the vertical axis value equal to A1 or A2, and the constant function is parallel to the horizontal axis. If the constant function intersects the temperature change rate curve, abnormal data exists.

[0020] Then, the data of the timestamp node under the abnormal data is traced back to determine the temperature change value under the adjacent timestamp node. If there is a temperature change rate threshold [A1, A2] exceeded in the adjacent temperature change during the abnormal data period, the current abnormal data is problematic data;

[0021] The temperature change rate calculation formula is:

[0022] R n =|C t -C t-k | / C t ;

[0023] R n is the temperature change rate in the nth cycle, C t is the temperature value at the t-th timestamp node, C t-k is the temperature value at the tkth timestamp node;

[0024] The adjacent temperature changes are also obtained through the temperature change rate calculation formula.

[0025] Preferably, the operation of the mold health assessment module to extract pressure numerical features for analysis and processing is:

[0026] Extract the pressure data under the timestamp node and mark it as F1, and set the pressure threshold when the mold is not affected as F2;

[0027] When F1≤F2, the current pressure value used by the mold is normal, and when F1>F2, the current pressure value used by the mold is abnormal, and the number of times the abnormal pressure value occurs is recorded and marked as N.

[0028] Preferably, the operation of extracting strain amplitude features for analysis and processing by the mold health assessment module is:

[0029] The strain peak value (maximum strain value) and strain valley value (minimum strain value) in each cycle are extracted by the peak detection algorithm, and the strain amplitude of each cycle is calculated. The strain amplitude is obtained by subtracting the strain valley value from the strain peak value.

[0030] The extracted strain amplitude feature is compared with the preset strain threshold. If the strain amplitude feature is less than the preset strain threshold, the strain amplitude feature is normal. Otherwise, the strain amplitude feature is abnormal and affects the mold life. The number of times the abnormal strain amplitude feature is extracted is marked as L.

[0031] Preferably, the operation of the mold health assessment module to extract vibration frequency characteristics for analysis and processing is:

[0032] The obtained time domain vibration signal is converted into a frequency domain signal by fast Fourier transform, thereby forming a vibration frequency map;

[0033] The frequency curve is divided at the first maximum point and the second maximum point of the frequency curve, that is, the curve between the first maximum point and the second maximum point is a periodic curve;

[0034] Then, the natural frequency of the mold in the historical data is extracted and compared with the periodic curve. If the curves coincide, the vibration frequency characteristics are normal. Otherwise, if there is a deviation between the curves, the vibration frequency characteristics are abnormal. The number of abnormal vibration frequencies is extracted and marked as P.

[0035] Preferably, the operation of extracting real-time data from the mold health assessment module and introducing it into the mold life assessment model to implement mold health index assessment is as follows:

[0036] After extracting real-time data, the mold life assessment model is used to extract various features such as temperature change rate, pressure value, strain amplitude and vibration frequency;

[0037] Then, the number of abnormalities of each feature is extracted and weighted to evaluate the mold health index. The calculation formula is:

[0038] D = u × M + v × N + w × L + i × P;

[0039] D is the mold health index, u is the weighted value of the number of times the temperature change rate characteristic problem data is generated, v is the weighted value of the number of times the abnormal pressure value is generated, w is the weighted value of the number of times the abnormal strain amplitude feature is generated, and i is the weighted value of the number of times the abnormal vibration frequency data is generated.

[0040] Preferably, the operations for implementing early warning at different levels in the early warning and decision module are:

[0041] The different levels after setting the index division are: extremely poor level [0, a], poor level [a, b], good level [b, c], and excellent level [c, 100];

[0042] The mold health index D is then compared with different level thresholds, and the level is determined according to the mold health index D. The corresponding processing strategy is traced and the staff is warned of the mold situation.

[0043] The present invention provides a mold life management system based on monitoring of automotive lamp production molds. Compared with the existing technology, it has the following advantages:

[0044] 1. This mold life management system, based on monitoring automotive lamp production molds, preprocesses data and extracts characteristics such as temperature change rate, pressure value, strain amplitude, and vibration frequency for analysis and processing. The extracted characteristic parameters are then integrated to establish a mold life assessment model. Real-time data is then extracted and introduced into the mold life assessment model to evaluate the mold health index. By real-time monitoring of multiple physical quantity data of the mold and using advanced algorithms and models for life assessment, the actual wear and performance changes of the mold can be more accurately grasped, avoiding the subjectivity and uncertainty of manual judgment.

[0045] 2. The mold life management system based on the monitoring of automotive lamp production molds extracts real-time data and historical data and sets the main node and sub-node. The main node and sub-node are used to implement indexing and tracing during subsequent data extraction. The collection type content of each sensor is extracted, and the collection type content is used as the main node, and the main body of each sub-category content under the corresponding collection type is used as the sub-node. The corresponding data and numerical results are extracted through content search of the main node and sub-node, so as to achieve the close relationship between data and subsequent processing operations, and facilitate subsequent indexing and tracing, thereby better realizing mold life management operations.

[0046] 3. This mold life management system, based on monitoring of automotive lamp production molds, extracts real-time data and then uses the mold life assessment model to extract various features such as temperature change rate, pressure value, strain amplitude, and vibration frequency. It then extracts the number of abnormalities for each feature and assigns weights to it to evaluate the mold health index. The characteristic parameters provided by the data acquisition and processing module are input into the mold life assessment model. The model calculates and analyzes the input data and outputs the estimated remaining life of the mold and the current health status level, thereby better predicting and evaluating, and improving the efficiency of mold life management. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a principle block diagram of the mold life management system of the present invention;

[0048] Figure 2 This is an operational flow chart of data preprocessing of the present invention;

[0049] Figure 3 This is an operational flow chart for analyzing the temperature change rate characteristics of the present invention;

[0050] Figure 4 This is an operational flow chart of the pressure numerical characteristic analysis of the present invention;

[0051] Figure 5 This is an operational flow chart of the strain amplitude characteristic analysis of the present invention;

[0052] Figure 6 This is an operational flow chart of the vibration frequency characteristic analysis of the present invention. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0054] See also Figures 1-6 The present invention provides a technical solution: a mold life management system based on monitoring of automobile lamp production molds, comprising:

[0055] The data acquisition module is located in various parts of the headlight production mold and is equipped with various types of sensors to transmit the collected physical quantity data in real time and store them in the database;

[0056] The mold health assessment module receives the transmitted data, extracts historical data, performs pre-processing operations on the data, and extracts various characteristics such as temperature change rate, pressure value, strain amplitude and vibration frequency for analysis and processing. The extracted characteristic parameters are integrated to form a mold life assessment model. Then, real-time data is extracted and introduced into the mold life assessment model to evaluate the mold health index.

[0057] The early warning and decision-making module implements graded operations on the life status based on the evaluated mold health index, implements early warning operations through different levels, and matches the corresponding processing strategies to transmit to the execution unit to complete the control operation.

[0058] The generated data is displayed through a visual control interface.

[0059] Among them, by preprocessing the data, extracting the temperature change rate, pressure value, strain amplitude and vibration frequency characteristics for analysis and processing, and integrating the extracted characteristic parameters to establish a mold life assessment model, and then extracting real-time data and introducing it into the mold life assessment model to realize the assessment of the mold health index. By real-time monitoring of various physical quantity data of the mold and using advanced algorithms and models for life assessment, the actual wear and performance changes of the mold can be grasped more accurately, avoiding the subjectivity and uncertainty of manual experience judgment.

[0060] In an embodiment of the present invention, the data acquisition module includes a temperature sensor, a pressure sensor, a strain sensor and a vibration sensor. The temperature sensor is used to monitor the temperature changes of the mold in real time when it is working. The pressure sensor measures the pressure exerted on the mold during the injection molding process. The strain sensor can detect the deformation of the mold when it is subjected to force. The vibration sensor is used to monitor the vibration frequency and amplitude of the mold during operation.

[0061] In the embodiment of the present invention, the data preprocessing operation in the mold health assessment module is as follows:

[0062] After extracting real-time data and historical data, set up the master node and slave node, which are used to implement indexing and tracing for subsequent data extraction;

[0063] By extracting the collection type content of each sensor, and taking the collection type content as the main node, and the main body of each sub-category content under the corresponding collection type as the sub-node, the corresponding data and numerical results are extracted through content search of the main node and sub-node.

[0064] Among them, after extracting real-time data and historical data, and setting the main node and sub-node, the main node and sub-node are used to realize indexing and tracing during subsequent data extraction. The collection type content of each sensor is extracted, and the collection type content is used as the main node, and the main body of each sub-category content under the corresponding collection type is used as the sub-node. The corresponding data and numerical results are extracted through the content search of the main node and sub-node, so as to realize the close relationship between data and subsequent processing operations, and facilitate subsequent indexing and tracing, so as to better realize mold life management operations.

[0065] In the embodiment of the present invention, the mold health assessment module extracts the temperature change rate feature for analysis and processing as follows:

[0066] Identify the various processes in the production of automotive lamp molds and extract temperature data for each process;

[0067] Set the extraction cycle and establish a temperature change rate coordinate axis, with the number of extracted cycles as the horizontal axis of the temperature change rate coordinate axis, and the temperature change rate data under the corresponding number of cycles as the vertical axis of the temperature change rate coordinate axis. After the numerical value is introduced, a temperature change rate curve is formed, and then the temperature change rate threshold is introduced as a constant function into the temperature change rate coordinate axis to determine abnormal data, and determine whether it is problem data by analyzing the abnormal data;

[0068] And record the number of times the problem data appears and mark it as M.

[0069] In the embodiment of the present invention, the specific operation of introducing the temperature change rate threshold as a constant function into the temperature change rate coordinate axis to determine abnormal data is as follows:

[0070] Set the temperature change rate threshold to [A1, A2] and form a constant function with the vertical axis value equal to A1 or A2, and the constant function is parallel to the horizontal axis. If the constant function intersects the temperature change rate curve, abnormal data exists.

[0071] Then, the data of the timestamp node under the abnormal data is traced back to determine the temperature change value under the adjacent timestamp node. If there is a temperature change rate threshold [A1, A2] exceeded in the adjacent temperature change during the abnormal data period, the current abnormal data is problematic data;

[0072] The temperature change rate calculation formula is:

[0073] R n =|C t -C t-k | / C t ;

[0074] R n is the temperature change rate in the nth cycle, C t is the temperature value at the t-th timestamp node, C t-k is the temperature value at the tkth timestamp node;

[0075] The adjacent temperature changes are also obtained through the temperature change rate calculation formula.

[0076] In the embodiment of the present invention, the mold health assessment module extracts pressure numerical features for analysis and processing as follows:

[0077] Extract the pressure data under the timestamp node and mark it as F1, and set the pressure threshold when the mold is not affected as F2;

[0078] When F1≤F2, the current pressure value used by the mold is normal, and when F1>F2, the current pressure value used by the mold is abnormal, and the number of times the abnormal pressure value occurs is recorded and marked as N.

[0079] In the embodiment of the present invention, the operations of the mold health assessment module to extract strain amplitude features for analysis and processing are as follows:

[0080] The strain peak value (maximum strain value) and strain valley value (minimum strain value) in each cycle are extracted by the peak detection algorithm, and the strain amplitude of each cycle is calculated. The strain amplitude is obtained by subtracting the strain valley value from the strain peak value.

[0081] The extracted strain amplitude feature is compared with the preset strain threshold. If the strain amplitude feature is less than the preset strain threshold, the strain amplitude feature is normal. Otherwise, the strain amplitude feature is abnormal and affects the mold life. The number of times the abnormal strain amplitude feature is extracted is marked as L.

[0082] In the embodiment of the present invention, the mold health assessment module extracts vibration frequency characteristics for analysis and processing as follows:

[0083] The obtained time domain vibration signal is converted into a frequency domain signal by fast Fourier transform, thereby forming a vibration frequency map;

[0084] The frequency curve is divided at the first maximum point and the second maximum point of the frequency curve, that is, the curve between the first maximum point and the second maximum point is a periodic curve;

[0085] Then, the natural frequency of the mold in the historical data is extracted and compared with the periodic curve. If the curves coincide, the vibration frequency characteristics are normal. Otherwise, if there is a deviation between the curves, the vibration frequency characteristics are abnormal. The number of abnormal vibration frequencies is extracted and marked as P.

[0086] In the embodiment of the present invention, the operation of extracting real-time data from the mold health assessment module and introducing it into the mold life assessment model to implement mold health index assessment is as follows:

[0087] After extracting real-time data, the mold life assessment model is used to extract various features such as temperature change rate, pressure value, strain amplitude and vibration frequency;

[0088] Then, the number of abnormalities of each feature is extracted and weighted to evaluate the mold health index. The calculation formula is:

[0089] D = u × M + v × N + w × L + i × P;

[0090] D is the mold health index, u is the weighted value of the number of times the temperature change rate characteristic problem data is generated, v is the weighted value of the number of times the abnormal pressure value is generated, w is the weighted value of the number of times the abnormal strain amplitude feature is generated, and i is the weighted value of the number of times the abnormal vibration frequency data is generated.

[0091] Among them, after extracting real-time data, the mold life assessment model is used to extract the temperature change rate, pressure value, strain amplitude and vibration frequency characteristics, and then the abnormal number of each characteristic is extracted to implement the weight assignment operation to evaluate the mold health index. The characteristic parameters provided by the data acquisition and processing module are input into the mold life assessment model. The model calculates and analyzes according to the input data, and outputs the estimated remaining life of the mold and the current health status level, so as to better predict and evaluate and improve the efficiency of mold life management.

[0092] In the embodiment of the present invention, the operations for implementing early warning at different levels in the early warning and decision module are:

[0093] The different levels after setting the index division are: extremely poor level [0, a], poor level [a, b], good level [b, c], and excellent level [c, 100];

[0094] The mold health index D is then compared with different level thresholds, and the level is determined according to the mold health index D. The corresponding processing strategy is traced and the staff is warned of the mold situation.

[0095] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0096] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0097] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A mold life management system based on monitoring of automotive lamp production molds, characterized by: include: The data acquisition module is located in various parts of the headlight production mold and is equipped with various types of sensors to transmit the collected physical quantity data in real time and store them in the database; The mold health assessment module receives the transmitted data, extracts historical data, performs pre-processing operations on the data, and extracts various characteristics such as temperature change rate, pressure value, strain amplitude and vibration frequency for analysis and processing. The extracted characteristic parameters are integrated to form a mold life assessment model. Then, real-time data is extracted and introduced into the mold life assessment model to evaluate the mold health index. The early warning and decision-making module implements graded operations on the life status based on the evaluated mold health index, implements early warning operations through different levels, and matches the corresponding processing strategies to transmit to the execution unit to complete the control operation.

2. The mold life management system based on monitoring of automotive lamp production molds according to claim 1, characterized in that: The data acquisition module includes a temperature sensor, a pressure sensor, a strain sensor and a vibration sensor. The temperature sensor is used to monitor the temperature changes of the mold in real time when it is working. The pressure sensor measures the pressure the mold is subjected to during the injection molding process. The strain sensor can detect the deformation of the mold when it is under force. The vibration sensor is used to monitor the vibration frequency and amplitude during the operation of the mold.

3. The mold life management system based on monitoring of automotive lamp production molds according to claim 1, characterized in that: The data preprocessing operation in the mold health assessment module is as follows: After extracting real-time data and historical data, set up the master node and slave node, which are used to implement indexing and tracing for subsequent data extraction; By extracting the collection type content of each sensor, and taking the collection type content as the main node, and the main body of each sub-category content under the corresponding collection type as the sub-node, the corresponding data and numerical results are extracted through content search of the main node and sub-node.

4. The mold life management system based on monitoring of automotive lamp production molds according to claim 1, characterized in that: The mold health assessment module extracts the temperature change rate characteristics for analysis and processing as follows: Identify the various processes in the production of automotive lamp molds and extract temperature data for each process; Set the extraction cycle and establish a temperature change rate coordinate axis, with the number of extracted cycles as the horizontal axis of the temperature change rate coordinate axis, and the temperature change rate data under the corresponding number of cycles as the vertical axis of the temperature change rate coordinate axis. After the numerical value is introduced, a temperature change rate curve is formed, and then the temperature change rate threshold is introduced as a constant function into the temperature change rate coordinate axis to determine abnormal data, and determine whether it is problem data by analyzing the abnormal data; And record the number of times the problem data appears and mark it as M.

5. The mold life management system based on monitoring of automobile lamp production molds according to claim 4 is characterized by: The specific operation of introducing the temperature change rate threshold as a constant function into the temperature change rate coordinate axis to determine abnormal data is as follows: Set the temperature change rate threshold to [A1, A2] and form a constant function with the vertical axis value equal to A1 or A2, and the constant function is parallel to the horizontal axis. If the constant function intersects the temperature change rate curve, abnormal data exists. Then, the data of the timestamp node under the abnormal data is traced back to determine the temperature change value under the adjacent timestamp node. If there is a temperature change rate threshold [A1, A2] exceeded in the adjacent temperature change during the abnormal data period, the current abnormal data is problematic data; The temperature change rate calculation formula is: R n =|C t -C t-k | / C t ; R n is the temperature change rate in the nth cycle, C t is the temperature value at the t-th timestamp node, C t-k is the temperature value at the tkth timestamp node; The adjacent temperature changes are also obtained through the temperature change rate calculation formula.

6. The mold life management system based on monitoring of automobile lamp production molds according to claim 5, characterized in that: The mold health assessment module extracts pressure numerical features for analysis and processing as follows: Extract the pressure data under the timestamp node and mark it as F1, and set the pressure threshold when the mold is not affected as F2; When F1≤F2, the current pressure value used by the mold is normal, and when F1>F2, the current pressure value used by the mold is abnormal, and the number of times the abnormal pressure value occurs is recorded and marked as N.

7. The mold life management system based on monitoring of automotive lamp production molds according to claim 6, characterized in that: The mold health assessment module extracts strain amplitude features for analysis and processing as follows: The strain peak and strain valley values ​​in each cycle are extracted by the peak detection algorithm, and the strain amplitude of each cycle is calculated. The strain amplitude is obtained by subtracting the strain valley value from the strain peak value. The extracted strain amplitude feature is compared with the preset strain threshold. If the strain amplitude feature is less than the preset strain threshold, the strain amplitude feature is normal. Otherwise, the strain amplitude feature is abnormal and affects the mold life. The number of times the abnormal strain amplitude feature is extracted is marked as L.

8. The mold life management system based on monitoring of automobile lamp production molds according to claim 7 is characterized by: The mold health assessment module extracts vibration frequency characteristics for analysis and processing as follows: The obtained time domain vibration signal is converted into a frequency domain signal by fast Fourier transform, thereby forming a vibration frequency map; The frequency curve is divided at the first maximum point and the second maximum point of the frequency curve, that is, the curve between the first maximum point and the second maximum point is a periodic curve; Then, the natural frequency of the mold in the historical data is extracted and compared with the periodic curve. If the curves coincide, the vibration frequency characteristics are normal. Otherwise, if there is a deviation between the curves, the vibration frequency characteristics are abnormal. The number of abnormal vibration frequencies is extracted and marked as P.

9. The mold life management system based on monitoring of automobile lamp production molds according to claim 8, characterized in that: The operation of extracting real-time data from the mold health assessment module and introducing it into the mold life assessment model to implement mold health index assessment is as follows: After extracting real-time data, the mold life assessment model is used to extract various features such as temperature change rate, pressure value, strain amplitude and vibration frequency; Then, the number of abnormalities of each feature is extracted and weighted to evaluate the mold health index. The calculation formula is: D = u × M + v × N + w × L + i × P; D is the mold health index, u is the weighted value of the number of times the temperature change rate characteristic problem data is generated, v is the weighted value of the number of times the abnormal pressure value is generated, w is the weighted value of the number of times the abnormal strain amplitude feature is generated, and i is the weighted value of the number of times the abnormal vibration frequency data is generated.

10. The mold life management system based on monitoring of automobile lamp production molds according to claim 9, characterized in that: The operations for implementing early warning at different levels in the early warning and decision module are: The different levels after setting the index division are: extremely poor level [0, a], poor level [a, b], good level [b, c], and excellent level [c, 100]; The mold health index D is then compared with different level thresholds, and the level is determined according to the mold health index D. The corresponding processing strategy is traced and the staff is warned of the mold situation.

Images