Cutting oil preparation process management and control method and system based on cloud platform

Abstract

This invention relates to the field of process control technology and proposes a method and system for controlling the preparation process of cutting oil based on a cloud platform. The method includes: comparing the oil state feature vector of the cutting oil with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain a preparation state deviation sequence; based on the deviation evolution trend of adjacent time windows in the preparation state deviation sequence, extracting the evolution of the cutting oil preparation process to obtain a preparation state deviation subsequence; updating the boundary of the preparation state deviation subsequence to obtain the allowable fluctuation boundary of the preparation parameters; comparing the deviation value in the preparation state deviation sequence with the allowable fluctuation boundary of the preparation parameters to obtain a preparation parameter adjustment instruction, and sending the preparation parameter adjustment instruction to the cutting oil preparation execution terminal. This invention can improve the efficiency of controlling the preparation process of cutting oil based on a cloud platform.

Description

Technical Field

[0001] This invention relates to the field of process control technology, and in particular to a method and system for controlling the preparation process of cutting oil based on a cloud platform. Background Technology

[0002] Traditional cutting oil preparation processes often rely on manual offline testing and experience-based control, which cannot quantify and standardize the oil's state characteristics in real time. It is difficult to accurately obtain the degree of deviation between the preparation state and the standard formula, and it is even more impossible to form a time-series deviation sequence, resulting in delayed detection of anomalies in the preparation process and a lack of data support for state control.

[0003] Existing cloud platform-assisted management solutions can only achieve basic data upload and simple threshold judgment. They do not perform dynamic interception and analysis on the trend of deviation evolution, nor can they adaptively update parameter fluctuation boundaries according to the actual preparation process. The fixed boundary settings and rigid judgment logic cannot match the dynamic changes in cutting oil preparation, making it difficult to generate accurate parameter adjustment instructions. Ultimately, this leads to low preparation efficiency and low oil quality stability. Therefore, how to improve the generation efficiency of the cutting oil preparation process has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method and system for controlling the preparation process of cutting oil based on a cloud platform, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a cloud platform-based method for controlling the cutting oil preparation process, comprising: Z1. Compare the oil state feature vector of the cutting oil with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain the preparation state deviation sequence of the cutting oil. Z2. Based on the evolution trend of deviation between adjacent time windows in the preparation state deviation sequence, the cutting oil preparation process is extracted to obtain the preparation state deviation subsequence of the cutting oil preparation process. Z3. Update the boundary of the subsequence of the deviation of the preparation state to obtain the allowable fluctuation boundary of the preparation parameters of the cutting oil; Z4. The deviation value in the preparation state deviation sequence is compared with the allowable fluctuation boundary of the preparation parameters to determine the preparation parameters adjustment instruction of the cutting oil, and the preparation parameters adjustment instruction is sent to the preparation execution terminal of the cutting oil.

[0006] In a preferred embodiment, the oil state feature vector of the cutting oil is compared with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain the cutting oil preparation state deviation sequence, including: Based on the preset feature dimension order, the viscosity feature value, acid value feature value and impurity content feature value of the cutting oil are vectorized and encapsulated to obtain the oil state feature vector of the cutting oil. Based on the cutting oil formula identifier, retrieve the standard state feature vector of the same formula that matches the formula identifier from the cloud platform; By mapping the eigenvalues ​​in the oil condition feature vector to the standard eigenvalues ​​in the standard condition feature vector of the same formula, the comprehensive condition deviation of the cutting oil is obtained. The formula for calculating the comprehensive condition deviation is as follows: ; In the formula, The overall deviation from the state. The viscosity eigenvalues ​​are the characteristic values ​​of the oil's state feature vector. The standard viscosity value is the eigenvector of the standard state of the same formulation. The acid value is the characteristic value of the oil state feature vector. The standard acid value is the characteristic vector of the standard state of the same formulation. The impurity content feature value is the feature value of the oil state feature vector. The standard impurity content value is the characteristic vector of the standard state of the same formulation. The viscosity weighting coefficient is pre-stored in the cloud platform. The acid value weighting coefficients are pre-stored in the cloud platform. The impurity content weighting coefficient is pre-stored in the cloud platform; The overall state deviation is time-series aggregated to obtain the cutting oil preparation state deviation sequence.

[0007] In a preferred embodiment, based on the evolution trend of deviation between adjacent time windows in the preparation state deviation sequence, the cutting oil preparation process is truncated to obtain a subsequence of preparation state deviation of the cutting oil preparation process, including: The first deviation component, the second deviation component, and the third deviation component in the prepared state deviation sequence are combined by time-series correlation to obtain the trend judgment window of the cutting oil; The first deviation component and the second deviation component are compared to obtain the first comparison result of the cutting oil. The second deviation component and the third deviation component are compared to obtain the second comparison result of the cutting oil. When the first comparison result indicates that the second deviation component is greater than the first deviation component, and the second comparison result indicates that the third deviation component is greater than the second deviation component, the trend judgment window of the cutting oil is determined to show a monotonically increasing evolution trend. A continuous subsequence is extracted from the preparation state deviation sequence, with the starting time window of the trend judgment window as the boundary and the ending time window of the preparation state deviation sequence as the endpoint, and is taken as the preparation state deviation subsequence of the cutting oil preparation process.

[0008] In a preferred embodiment, a continuous subsequence is extracted from the prepared state deviation sequence, with the starting time window of the trend judgment window as the boundary and the ending time window of the prepared state deviation sequence as the endpoint, as the prepared state deviation subsequence, including: The window identifier of the first time window in the trend judgment window is used as the starting boundary window, and the window identifier of the last time window in the time sequence of the prepared state deviation sequence is used as the ending boundary window. The order of the window identifiers of the starting boundary window and the ending boundary window is determined to obtain the order determination result of the cutting oil preparation process. When the sequence determination result indicates that the window identifier of the starting boundary window is earlier than the window identifier of the ending boundary window, the preparation state deviation sequence is boundary-cut, and the missing window positions that occur during the boundary-cutting process are filled with null values ​​to obtain the preparation state deviation subsequence of the cutting oil preparation process.

[0009] In a preferred embodiment, the boundary of the preparation state deviation subsequence is updated to obtain the allowable fluctuation boundary of the cutting oil preparation parameters, including: Monotonic trend identification was performed on the subsequence of the deviation from the preparation state to obtain the monotonically increasing attribute identifier of the entire sequence of the cutting oil preparation process; The starting deviation value, ending deviation value and monotonically increasing attribute identifier of the entire sequence of the preparation state deviation subsequence are compiled to obtain the morphological feature set of the cutting oil preparation process; The morphological feature set is matched with the pre-stored standard evolutionary morphological template in the cloud platform to obtain the matching template for the cutting oil preparation process; Based on the template identifier of the matching template, the boundary parameter library of the cloud platform is identified and retrieved to obtain the pre-formed upper boundary value and pre-formed lower boundary value of the cutting oil preparation process; The pre-defined boundary interval, composed of the pre-defined upper boundary value and the pre-defined lower boundary value, is compared with the deviation component in the preparation state deviation subsequence to obtain the coverage verification result of the cutting oil preparation process. When the coverage verification result indicates complete coverage, the pre-set upper boundary value and pre-set lower boundary value are set as the allowable fluctuation boundaries of the cutting oil preparation parameters.

[0010] In a preferred embodiment, the morphological feature set is matched with a pre-stored standard evolutionary morphological template in the cloud platform to obtain a matching template for the cutting oil preparation process, including: Retrieve the standard evolutionary template corresponding to the cutting oil formulation from the cloud platform; Based on the standard evolutionary morphology template, the starting point deviation value, the ending point deviation value, and the monotonically increasing attribute identifier of the whole sequence were identified item by item to obtain three comparison results of the cutting oil preparation process; Based on the three comparison results, the standard evolution morphology templates were selected by optimization to obtain the matching templates for the cutting oil preparation process.

[0011] In a preferred embodiment, based on three comparison results, the standard evolutionary morphology template is selectively screened to obtain a matching template for the cutting oil preparation process, including: The three comparison results of the standard evolutionary morphology template are extracted in a targeted manner to obtain the total number of feature items that pass the comparison in the standard evolutionary morphology template; Extreme value screening is performed on the total number of feature items to determine the maximum total number of extreme value screening results, and the standard evolution morphology template corresponding to the maximum total number is used as the initial template for the cutting oil preparation process; When the number of initial templates is one, the initial template is determined as the matching template for the cutting oil preparation process; When the number of initial templates is greater than one, the deviation between the reference starting point value and the actual starting point value of the initial template is selected to obtain the matching template for the cutting oil preparation process.

[0012] In a preferred embodiment, the pre-defined boundary interval composed of the pre-defined upper boundary value and the pre-defined lower boundary value is compared with the interval verification in the preparation state deviation subsequence to obtain the coverage verification result of the cutting oil preparation process, including: Using the pre-defined upper boundary value as the upper limit of the interval and the pre-defined lower boundary value as the lower limit of the interval, a pre-defined boundary interval for the cutting oil preparation process is constructed. The deviation component of the prepared state deviation subsequence is compared with the lower limit and upper limit of the interval to determine the membership, and the single-point coverage judgment result of the cutting oil preparation process is obtained. When the single-point coverage judgment result shows that the deviation component belongs to the pre-made boundary interval, the deviation component is marked as coverage passed; When all deviation components in the deviation subsequence of the preparation state are marked as coverage passed, the coverage verification result indicating complete coverage during the cutting oil preparation process is obtained.

[0013] In a preferred embodiment, the deviation metric value in the preparation state deviation sequence is compared with the allowable fluctuation boundary of the preparation parameters to determine the preparation parameters adjustment instruction for the cutting oil, and the preparation parameter adjustment instruction is sent to the preparation execution terminal of the cutting oil, including: Read the real-time deviation metric value of the current time window from the prepared state deviation sequence; By performing a double-boundary verification between the real-time deviation measurement value and the upper and lower limits of the allowable fluctuation boundary of the preparation parameters, the result of the over-limit judgment in the cutting oil preparation process is obtained. The results of the over-limit judgment are conditionally diverted to obtain the cutting oil preparation parameter adjustment instructions; The preparation parameter adjustment command is sent to the cutting oil preparation execution terminal.

[0014] To address the above problems, this invention also provides a cloud-based cutting oil preparation process control system, the system comprising: The state comparison module is used to compare the oil state feature vector of the cutting oil with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain the preparation state deviation sequence of the cutting oil. The trend slicing module is used to extract the evolution of the cutting oil preparation process based on the deviation evolution trend of adjacent time windows in the preparation state deviation sequence, and obtain the preparation state deviation subsequence of the cutting oil preparation process. The boundary update module is used to update the boundary of the preparation state deviation subsequence to obtain the allowable fluctuation boundary of the preparation parameters of the cutting oil. The instruction issuing module is used to compare the deviation value in the preparation state deviation sequence with the allowable fluctuation boundary of the preparation parameters to determine the boundary, obtain the preparation parameter adjustment instruction of the cutting oil, and send the preparation parameter adjustment instruction to the preparation execution terminal of the cutting oil.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention compares the feature vector of the cutting oil product state with the feature vector of the same formula standard state state pre-stored on the cloud platform to generate a time-seriesed preparation state deviation sequence in real time, thereby achieving accurate quantitative characterization of the preparation state of the cutting oil. Relying on the data support of the cloud platform, it completes real-time tracking and accurate perception of the preparation state, allowing the state changes of the preparation process to be clearly presented, and improving the accuracy and response speed of preparation state monitoring.

[0016] 2. This invention extracts the evolution of the preparation process by analyzing the deviation trend, obtains a suitable deviation subsequence, and dynamically updates the allowable fluctuation boundary of the preparation parameters. This enables the construction of scientific control thresholds that conform to the actual preparation law of cutting oil. Then, through boundary comparison and judgment, precise preparation parameter adjustment instructions are generated and sent to the execution end, realizing closed-loop intelligent control of the preparation process. This effectively improves the control efficiency of the cutting oil preparation process, ensures stable and controllable oil preparation quality, simplifies the preparation control process, reduces the risk of abnormalities in the preparation process, and makes the control of cutting oil preparation more intelligent and efficient. Attached Figure Description

[0017] Figure 1This is a flowchart illustrating a cloud-based cutting oil preparation process control method according to an embodiment of the present invention. Figure 2 A functional block diagram of a cloud-based cutting oil preparation process control system provided in an embodiment of the present invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a method for controlling the cutting oil preparation process based on a cloud platform. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for controlling the cutting oil preparation process based on a cloud platform can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a cloud-based cutting oil preparation process control method according to an embodiment of the present invention. In this embodiment, the cloud-based cutting oil preparation process control method includes: Z1. Compare the oil state feature vector of the cutting oil with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain the preparation state deviation sequence of the cutting oil. In this embodiment of the invention, the oil state feature vector of the cutting oil is compared with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain the cutting oil preparation state deviation sequence, including: Based on the preset feature dimension order, the viscosity feature value, acid value feature value and impurity content feature value of the cutting oil are vectorized and encapsulated to obtain the oil state feature vector of the cutting oil. Based on the cutting oil formula identifier, retrieve the standard state feature vector of the same formula that matches the formula identifier from the cloud platform; By mapping the eigenvalues ​​in the oil condition feature vector to the standard eigenvalues ​​in the standard condition feature vector of the same formula, the comprehensive condition deviation of the cutting oil is obtained. The formula for calculating the comprehensive condition deviation is as follows: ; In the formula, The overall deviation from the state. The viscosity eigenvalues ​​are the characteristic values ​​of the oil's state feature vector. The standard viscosity value is the eigenvector of the standard state of the same formulation. The acid value is the characteristic value of the oil state feature vector. The standard acid value is the characteristic vector of the standard state of the same formulation. The impurity content feature value is the feature value of the oil state feature vector. The standard impurity content value is the characteristic vector of the standard state of the same formulation. The viscosity weighting coefficient is pre-stored in the cloud platform. The acid value weighting coefficients are pre-stored in the cloud platform. The impurity content weighting coefficient is pre-stored in the cloud platform; The overall state deviation is time-series aggregated to obtain the cutting oil preparation state deviation sequence.

[0021] Following the fixed characteristic dimension arrangement order of viscosity, acid value, and impurity content pre-set in the cloud platform, the viscosity characteristic value, acid value characteristic value, and impurity content characteristic value of the current preparation state are collected in real time by a dedicated testing device at the cutting oil preparation site. The three sets of collected characteristic values ​​are strictly combined and arranged in the order of the preset dimensions to construct a unified vector structure, thus completing the entire operation process of vectorization encapsulation and finally obtaining the oil state characteristic vector of the cutting oil.

[0022] Based on the unique formula identifier corresponding to the current batch of cutting oil, a precise search and matching operation is performed in the standard feature database built into the cloud platform. The standard data records stored in the database that are completely consistent with the formula identifier code are selected, and the pre-stored and solidified standard state feature vector of the same formula is directly retrieved from the successfully matched standard data record.

[0023] The viscosity characteristic value in the oil state characteristic vector is calculated and its relative difference is determined by comparing it with the standard viscosity value in the standard state characteristic vector of the same formulation. The acid value characteristic value is calculated and its relative difference is determined by comparing it with the standard acid value. The impurity content characteristic value is calculated and its relative difference is determined by comparing it with the standard impurity content value. The three sets of relative differences are multiplied one-to-one with the viscosity weighting coefficient, acid value weighting coefficient, and impurity content weighting coefficient pre-configured in the cloud platform. The values ​​obtained by multiplying the three sets are squared and then summed. The total value obtained by summing is then squared to obtain the comprehensive state deviation of the cutting oil.

[0024] According to the chronological order of the various data collection points during the cutting oil preparation process, the comprehensive state deviation calculated at each independent time point is sorted, ranked, and summarized in an orderly manner to complete all data processing operations of the time sequence aggregation. The comprehensive state deviation corresponding to all time points is combined into a continuous and complete data sequence, and finally the cutting oil preparation state deviation sequence is obtained.

[0025] The viscosity characteristic value is obtained by continuously sampling and detecting the cutting oil in the preparation pipeline within a fixed sampling period using an online viscosity detection sensor that has passed national metrological verification at the cutting oil preparation site. After the sensor converts the physical detection signal into a standard digital signal, it is obtained after being analyzed, calibrated, and converted by the data acquisition unit. This value is directly used as the measured data of the viscosity dimension in the oil state characteristic vector.

[0026] The standard viscosity value is calculated by the cloud platform based on the viscosity test data of all qualified production batches for the same formula of cutting oil for more than three consecutive years. Abnormal data that exceeds the allowable range of the process is first removed, and then the arithmetic mean of the remaining valid data is calculated. The calculation result is locked as a fixed benchmark value, pre-stored in the cloud platform database and used as the standard viscosity value in the standard state feature vector of the same formula.

[0027] The acid value characteristic value is obtained by using an online acid value analyzer calibrated on-site to sample and test the current cutting oil in real time according to the potentiometric titration method. After the analyzer completes the titration reaction and data calculation, it directly outputs a stable value, which serves as the measured characteristic data of the acid value dimension in the oil state characteristic vector.

[0028] The standard acid value is determined by the cloud platform by combining the current product quality standards of the cutting oil industry with the historical acid value test data of qualified batches of the same formula. After batch data statistics, mean fitting and process verification, a fixed benchmark value is determined and pre-stored in the cloud platform and incorporated into the standard state feature vector of the same formula as the standard data of the acid value dimension.

[0029] The impurity content characteristic value is detected in real time by an online impurity content detector at the preparation site using the light scattering method. The detector converts the impurity scattered light signal into a content value, and the stable value output after calibration is used as the measured data of the impurity content dimension in the oil state feature vector.

[0030] The standard impurity content value is determined by the cloud platform based on the purity requirements of the production process and the factory quality standards of the cutting oil with the same formula. It summarizes the impurity content test data of historical qualified batches, performs statistical calibration, determines a fixed benchmark value, and stores it as the standard impurity content value in the standard state feature vector of the same formula.

[0031] The viscosity weighting coefficient is determined by the cloud platform for cutting oils with the same formula. It analyzes the impact of viscosity index on the core performance of oil lubrication and cooling, and combines tens of thousands of sets of historical preparation data and process test results to perform weighted fitting calculations to determine the weight value of the viscosity dimension and permanently store it in advance. This is used to define the proportion of viscosity difference in the overall deviation.

[0032] The acid value weighting coefficient is determined by the cloud platform based on the influence level of acid value on oil stability and metal corrosion during the preparation of cutting oils with the same formula. It summarizes historical acid value fluctuation data and quality verification results, and determines a fixed coefficient after statistical analysis and weighting calculation. The coefficient is pre-stored in the cloud platform to calculate the contribution of acid value differences.

[0033] The impurity content weighting coefficient is calculated and pre-stored by the cloud platform based on the influence level of impurity content in the same formula cutting oil on metal processing accuracy and equipment wear, through correlation analysis of historical preparation data and multiple rounds of process verification tests. This is used to quantify the weight of impurity content differences in the overall deviation.

[0034] The formula first calculates the relative difference between the measured value of each feature and the corresponding standard value, then multiplies each relative difference by the corresponding preset weight, squares the results of the multiplication, and sums them up. Finally, it performs a square root operation on the summation value to obtain the comprehensive state deviation. This integrates the dispersed deviation information of the three dimensions of viscosity, acid value, and impurity content into a single quantitative index, providing a standardized numerical basis for the time-series aggregation of the preparation state deviation sequence. It accurately reflects the overall deviation degree between the current preparation state and the standard state of the same formula, and provides core data support for subsequent deviation evolution trend analysis, subsequence truncation, update of allowable fluctuation boundaries of preparation parameters, and generation of preparation parameter adjustment instructions.

[0035] The beneficial effects include the ability to accurately collect the viscosity, acid value, and impurity content characteristics of cutting oil in real time using dedicated on-site testing equipment. This data is then vectorized and encapsulated into an oil state feature vector along fixed dimensions. Based on the formula identifier, the system accurately matches and retrieves standard state feature vectors of the same formula from the cloud platform. Through standardized numerical calculations, the comprehensive state deviation is obtained and aggregated into a complete deviation sequence according to time. All feature values, standard values, and weighting coefficients are determined based on historical qualified data, industry standards, and process testing verification, ensuring scientific and stable sources. This allows for the integration of multi-dimensional oil state differences into a unified quantitative deviation index, providing accurate and reliable data support for subsequent trend analysis, data extraction, boundary updates, and parameter control in the preparation process, thus ensuring the accuracy and stability of the cutting oil preparation process control.

[0036] Z2. Based on the evolution trend of deviation between adjacent time windows in the preparation state deviation sequence, the cutting oil preparation process is extracted to obtain the preparation state deviation subsequence of the cutting oil preparation process. In this embodiment of the invention, based on the evolution trend of deviation between adjacent time windows in the preparation state deviation sequence, the cutting oil preparation process is truncated to obtain a subsequence of preparation state deviation of the cutting oil preparation process, including: The first deviation component, the second deviation component, and the third deviation component in the prepared state deviation sequence are combined by time-series correlation to obtain the trend judgment window of the cutting oil; The first deviation component and the second deviation component are compared to obtain the first comparison result of the cutting oil. The second deviation component and the third deviation component are compared to obtain the second comparison result of the cutting oil. When the first comparison result indicates that the second deviation component is greater than the first deviation component, and the second comparison result indicates that the third deviation component is greater than the second deviation component, the trend judgment window of the cutting oil is determined to show a monotonically increasing evolution trend. A continuous subsequence is extracted from the preparation state deviation sequence, with the starting time window of the trend judgment window as the boundary and the ending time window of the preparation state deviation sequence as the endpoint, and is taken as the preparation state deviation subsequence of the cutting oil preparation process.

[0037] A continuous subsequence is extracted from the prepared state deviation sequence, with the starting time window of the trend judgment window as the boundary and the ending time window of the prepared state deviation sequence as the endpoint, as the prepared state deviation subsequence, including: The window identifier of the first time window in the trend judgment window is used as the starting boundary window, and the window identifier of the last time window in the time sequence of the prepared state deviation sequence is used as the ending boundary window. The order of the window identifiers of the starting boundary window and the ending boundary window is determined to obtain the order determination result of the cutting oil preparation process. When the sequence determination result indicates that the window identifier of the starting boundary window is earlier than the window identifier of the ending boundary window, the preparation state deviation sequence is boundary-cut, and the missing window positions that occur during the boundary-cutting process are filled with null values ​​to obtain the preparation state deviation subsequence of the cutting oil preparation process.

[0038] According to the chronological order of the prepared state deviation sequence, the first deviation component, the second deviation component, and the third deviation component are extracted from the sequence. These three consecutive deviation components in chronological order are bound and combined to construct a time-series data window of fixed length, thus obtaining the trend judgment window of the cutting oil.

[0039] A one-to-one numerical comparison is performed between the first deviation component and the second deviation component within the trend judgment window. The numerical correspondence between the two deviation components is fully recorded, forming the first comparison result of the cutting oil. A one-to-one numerical comparison is also performed between the second deviation component and the third deviation component within the trend judgment window. The numerical correspondence between the two deviation components is fully recorded, forming the second comparison result of the cutting oil.

[0040] When the numerical relationship recorded in the first comparison result is that the value of the second deviation component is greater than the value of the first deviation component, and the numerical relationship recorded in the second comparison result is that the value of the third deviation component is greater than the value of the second deviation component, according to the preset trend judgment standard, it is confirmed that the deviation change in the trend judgment window is a continuously rising change pattern, and the trend judgment window of the cutting oil is determined to show a monotonically increasing evolution trend.

[0041] In the complete preparation state deviation sequence, the starting time window corresponding to the trend judgment window is determined as the starting boundary of the interception operation, and the last time window in the time dimension of the preparation state deviation sequence is determined as the endpoint of the interception operation. All deviation components corresponding to the continuous time windows between the starting boundary and the endpoint are extracted and combined to form a continuous and complete data sequence, which serves as the preparation state deviation subsequence of the cutting oil preparation process.

[0042] Read the unique window identifier corresponding to the first time window arranged in chronological order of preparation time within the trend judgment window, and directly determine this window identifier as the starting boundary window for cutting oil preparation process data interception. Read the unique window identifier corresponding to the last time window arranged in chronological order in the preparation state deviation sequence, and directly determine this window identifier as the ending boundary window for cutting oil preparation process data interception.

[0043] Based on the time progression logic of the cutting oil preparation process, the window identifiers carried by the starting boundary window and the window identifiers carried by the ending boundary window are compared one by one in terms of their temporal order to accurately determine the sequential arrangement of the two window identifiers on the preparation time axis, thus forming the sequence determination result of the cutting oil preparation process.

[0044] When the sequence determination result clearly shows that the preparation time corresponding to the window identifier of the starting boundary window is earlier than the preparation time corresponding to the window identifier of the ending boundary window, the preparation state deviation sequence is subjected to directional data cutting operation according to the range defined by the starting boundary window and the ending boundary window. If a time window position where deviation data is not collected is found during the data cutting process, a preset fixed null value is filled into the missing position to ensure the continuity of the sequence. After the continuous data sequence that has completed cutting and null value filling is integrated, the preparation state deviation subsequence of the cutting oil preparation process is obtained.

[0045] The beneficial effects are that it can extract continuous deviation components in chronological order to construct a trend judgment window, compare the values ​​of each component one by one to form corresponding comparison results, accurately determine the monotonically increasing evolution trend of deviation, determine the start and end boundaries of data interception based on window identifiers and determine the chronological order, extract data in a directional manner according to the defined range and fill the missing positions with fixed null values ​​to obtain a continuous and complete subsequence of preparation state deviation, providing a standardized and complete data foundation for the subsequent update of preparation parameter fluctuation boundaries, and improving the accuracy and reliability of trend analysis and data interception in the preparation process.

[0046] Z3. Update the boundary of the subsequence of the deviation of the preparation state to obtain the allowable fluctuation boundary of the preparation parameters of the cutting oil; In this embodiment of the invention, the boundary of the preparation state deviation subsequence is updated to obtain the allowable fluctuation boundary of the cutting oil preparation parameters, including: Monotonic trend identification was performed on the subsequence of the deviation from the preparation state to obtain the monotonically increasing attribute identifier of the entire sequence of the cutting oil preparation process; The starting deviation value, ending deviation value and monotonically increasing attribute identifier of the entire sequence of the preparation state deviation subsequence are compiled to obtain the morphological feature set of the cutting oil preparation process; The morphological feature set is matched with the pre-stored standard evolutionary morphological template in the cloud platform to obtain the matching template for the cutting oil preparation process; Based on the template identifier of the matching template, the boundary parameter library of the cloud platform is identified and retrieved to obtain the pre-formed upper boundary value and pre-formed lower boundary value of the cutting oil preparation process; The pre-defined boundary interval, composed of the pre-defined upper boundary value and the pre-defined lower boundary value, is compared with the deviation component in the preparation state deviation subsequence to obtain the coverage verification result of the cutting oil preparation process. When the coverage verification result indicates complete coverage, the pre-set upper boundary value and pre-set lower boundary value are set as the allowable fluctuation boundaries of the cutting oil preparation parameters.

[0047] The morphological feature set is matched with the pre-stored standard evolutionary morphological templates in the cloud platform to obtain a matching template for the cutting oil preparation process, including: Retrieve the standard evolutionary template corresponding to the cutting oil formulation from the cloud platform; Based on the standard evolutionary morphology template, the starting point deviation value, the ending point deviation value, and the monotonically increasing attribute identifier of the whole sequence were identified item by item to obtain three comparison results of the cutting oil preparation process; Based on the three comparison results, the standard evolution morphology templates were selected by optimization to obtain the matching templates for the cutting oil preparation process.

[0048] Based on the three comparison results, the standard evolutionary morphology templates were selected through a merit-based screening process to obtain matching templates for the cutting oil preparation process, including: The three comparison results of the standard evolutionary morphology template are extracted in a targeted manner to obtain the total number of feature items that pass the comparison in the standard evolutionary morphology template; Extreme value screening is performed on the total number of feature items to determine the maximum total number of extreme value screening results, and the standard evolution morphology template corresponding to the maximum total number is used as the initial template for the cutting oil preparation process; When the number of initial templates is one, the initial template is determined as the matching template for the cutting oil preparation process; When the number of initial templates is greater than one, the deviation between the reference starting point value and the actual starting point value of the initial template is selected to obtain the matching template for the cutting oil preparation process.

[0049] The pre-defined boundary interval, composed of the pre-defined upper and lower boundary values, is compared with the deviation subsequence of the preparation state to obtain the coverage verification results of the cutting oil preparation process, including: Using the pre-defined upper boundary value as the upper limit of the interval and the pre-defined lower boundary value as the lower limit of the interval, a pre-defined boundary interval for the cutting oil preparation process is constructed. The deviation component of the prepared state deviation subsequence is compared with the lower limit and upper limit of the interval to determine the membership, and the single-point coverage judgment result of the cutting oil preparation process is obtained. When the single-point coverage judgment result shows that the deviation component belongs to the pre-made boundary interval, the deviation component is marked as coverage passed; When all deviation components in the deviation subsequence of the preparation state are marked as coverage passed, the coverage verification result indicating complete coverage during the cutting oil preparation process is obtained.

[0050] Traverse all deviation components in the preparation state deviation subsequence arranged chronologically, and compare the value of each subsequent deviation component with the value of the preceding deviation component. When the value of all subsequent deviation components is greater than the value of the corresponding preceding deviation component, assign a fixed feature label to the sequence to obtain the monotonically increasing attribute identifier of the entire sequence of the cutting oil preparation process.

[0051] The deviation value at the earliest time position in the preparation state deviation subsequence is extracted as the starting deviation value, and the deviation value at the latest time position in the preparation state deviation subsequence is extracted as the ending deviation value. The starting deviation value, the ending deviation value, and the monotonically increasing attribute identifier of the whole sequence are integrated into a complete set of feature data according to a fixed combination rule to obtain the morphological feature set of the cutting oil preparation process.

[0052] All pre-stored standard evolutionary morphology templates are retrieved from the cloud platform's storage area. Each feature data in the morphological feature set is compared with the feature data of each standard evolutionary morphology template. The standard evolutionary morphology template with the highest matching degree with the morphological feature set data is selected to obtain the matching template for the cutting oil preparation process.

[0053] Extract the unique template identifier corresponding to the matching template, use the template identifier as the search condition, perform a precise search and matching operation in the boundary parameter library of the cloud platform, retrieve the pre-set boundary values ​​from the successfully matched parameter records, and obtain the pre-formed upper boundary value and pre-formed lower boundary value of the cutting oil preparation process.

[0054] The upper boundary value of the pre-made boundary is used as the upper limit value of the interval, and the lower boundary value of the pre-made boundary is used as the lower limit value of the interval to construct a complete pre-made boundary interval. Each deviation component in the deviation subsequence of the preparation state is compared with the position of the pre-made boundary interval to determine whether each deviation component is within the interval range. The final verification conclusion is formed based on the comparison of all deviation components, and the coverage verification result of the cutting oil preparation process is obtained.

[0055] When the coverage verification results clearly show that all deviation components in the deviation subsequence of the preparation state are within the range of the pre-defined boundary, the pre-defined upper boundary value is determined as the upper limit of the allowable fluctuation of the cutting oil preparation parameters, and the pre-defined lower boundary value is determined as the lower limit of the allowable fluctuation of the cutting oil preparation parameters. The boundary setting operation is completed, and the allowable fluctuation boundary of the cutting oil preparation parameters is obtained.

[0056] Based on the unique identifier of the formula used in the current cutting oil preparation, a precise search and matching is performed in the standard evolutionary form template library on the cloud platform. All standard evolutionary form templates that completely correspond to the formula identifier are selected and retrieved for subsequent feature comparison operations.

[0057] The preset starting point reference value, ending point reference value, and monotonically increasing attribute marker within each standard evolutionary morphology template obtained are compared one by one with the actual obtained starting point deviation value, ending point deviation value, and monotonically increasing attribute marker of the entire sequence. The verification and matching status of each feature is fully recorded, and the three sets of verification status are integrated into a unified verification conclusion to obtain the three comparison results of the cutting oil preparation process.

[0058] For each standard evolutionary morphology template, the total number of successfully matched features is counted. All standard evolutionary morphology templates are sorted from highest to lowest according to the total number of successfully matched features. The standard evolutionary morphology template with the highest number of successfully matched features is selected as the final template, thus obtaining the matching template for the cutting oil preparation process.

[0059] From the three comparison results corresponding to each standard evolutionary morphology template, the number of items that successfully match features is extracted individually. This number is the total number of feature items that the corresponding standard evolutionary morphology template has passed the comparison, ensuring that each template corresponds to a uniquely determined total number of feature items.

[0060] The total number of feature items of all standard evolution morphology templates is summarized, and the values ​​of each total are compared one by one. The total number of feature items with the largest value is determined, and all standard evolution morphology templates corresponding to the largest total number are selected as the initial templates for the cutting oil preparation process.

[0061] The number of initial templates is accurately counted. When the count shows that there is only one initial template, the unique initial template is directly selected as the final template, thus obtaining the matching template for the cutting oil preparation process.

[0062] When the statistical results show that the number of preliminary templates is greater than one, calculate the difference between the reference starting point value and the actual starting point deviation value of each preliminary template, and select the preliminary template with the smallest difference value as the final template to obtain the matching template for the cutting oil preparation process.

[0063] A predetermined upper boundary value is set as the maximum numerical limit of the interval, and a predetermined lower boundary value is set as the minimum numerical limit of the interval. Using the upper and lower boundary values ​​as the range boundaries, a continuous numerical range suitable for the cutting oil preparation process is constructed, forming a complete pre-defined boundary interval.

[0064] According to the time arrangement order of each deviation component in the deviation subsequence of the preparation state, the value of each deviation component is compared with the lower limit value and the upper limit value of the pre-made boundary interval one by one to determine whether the single deviation component is within the range between the lower limit and the upper limit of the interval. An independent judgment conclusion is generated for each deviation component to obtain the single-point coverage judgment result of the cutting oil preparation process.

[0065] When the single-point coverage judgment result clearly shows that the value of the current deviation component is greater than or equal to the lower limit of the interval and less than or equal to the upper limit of the interval, a fixed status flag is assigned to the deviation component, and the deviation component is marked as coverage passed.

[0066] The marking status of all deviation components in the preparation state deviation subsequence is checked in turn. After confirming that all deviation components are marked as covered, a verification conclusion indicating that all deviation components are within the pre-made boundary interval is generated, and the coverage verification result indicating complete coverage in the cutting oil preparation process is obtained.

[0067] The beneficial effects include the ability to accurately identify the monotonically increasing attribute of the deviation degree subsequence of the preparation state, compile a complete set of morphological features, retrieve the corresponding standard evolution morphological template based on formula matching, determine the optimal matching template through feature item-by-item verification, quantity statistics and difference optimization, retrieve the pre-made boundary values ​​based on the matching template, construct the boundary interval and complete the full component coverage verification, and finally determine the scientifically adapted allowable fluctuation boundary of the preparation parameters, providing accurate and reliable boundary basis for parameter control in the cutting oil preparation process, and improving the accuracy and standardization of the preparation process control.

[0068] Z4. The deviation value in the preparation state deviation sequence is compared with the allowable fluctuation boundary of the preparation parameters to determine the preparation parameters adjustment instruction of the cutting oil, and the preparation parameters adjustment instruction is sent to the preparation execution terminal of the cutting oil.

[0069] In this embodiment of the invention, the deviation value in the preparation state deviation sequence is compared with the allowable fluctuation boundary of the preparation parameters to determine the boundary, thereby obtaining the preparation parameter adjustment instruction for the cutting oil, and the preparation parameter adjustment instruction is sent to the preparation execution terminal of the cutting oil, including: Read the real-time deviation metric value of the current time window from the prepared state deviation sequence; By performing a double-boundary verification between the real-time deviation measurement value and the upper and lower limits of the allowable fluctuation boundary of the preparation parameters, the result of the over-limit judgment in the cutting oil preparation process is obtained. The results of the over-limit judgment are conditionally diverted to obtain the cutting oil preparation parameter adjustment instructions; The preparation parameter adjustment command is sent to the cutting oil preparation execution terminal.

[0070] In the entire time window data contained in the preparation state deviation sequence, based on the real-time progress sequence of the cutting oil preparation process, the time window data entry that completely corresponds to the current preparation time is accurately located. The stored deviation value is directly extracted and read from this data entry to obtain the real-time deviation measurement value of the current time window of the cutting oil.

[0071] The real-time deviation measurement value is first compared with the lower limit of the allowable fluctuation boundary of the preparation parameters, and then compared with the upper limit of the allowable fluctuation boundary of the preparation parameters. It is determined whether the real-time deviation measurement value meets the condition of being greater than or equal to the lower limit and less than or equal to the upper limit. Based on this judgment, a clear judgment information on whether it exceeds the allowable fluctuation range is formed, and the over-limit judgment result of the cutting oil preparation process is obtained.

[0072] Based on the different scenarios of the out-of-limit judgment result, a preset fixed processing rule is executed. If the out-of-limit judgment result does not exceed the allowable fluctuation boundary of the preparation parameters, an instruction to maintain the current preparation parameter operating state is generated. If the out-of-limit judgment result exceeds the allowable fluctuation boundary of the preparation parameters, an instruction to correct the corresponding preparation parameters is generated. The instruction generation is completed according to the rule to obtain the preparation parameter adjustment instruction for the cutting oil.

[0073] Through a dedicated data transmission channel established between the cloud platform and the cutting oil preparation execution terminal, the generated preparation parameter adjustment instructions are completely packaged and transmitted to the parameter control execution equipment terminal at the preparation site, ensuring that the instructions are delivered completely and received by the preparation execution terminal, thus completing the sending operation of the preparation parameter adjustment instructions.

[0074] The beneficial effects are that it can locate and read the deviation measurement value of the current time window in real time, obtain the over-limit judgment result by comparing it with the upper and lower limits of the allowable fluctuation boundary of the preparation parameters, generate the corresponding parameter adjustment command according to the preset rules, and then transmit the command stably to the preparation execution end through a dedicated data channel, so as to realize the real-time judgment and closed-loop control of the cutting oil preparation process, and improve the control response speed and execution accuracy.

[0075] like Figure 2 The diagram shown is a functional block diagram of a cloud-based cutting oil preparation process control system provided in an embodiment of the present invention.

[0076] The cutting oil preparation process control system 100 based on a cloud platform of the present invention can be installed in an electronic device. Depending on the functions implemented, the cutting oil preparation process control system 100 based on the cloud platform may include a state comparison module 101, a trend slicing module 102, a boundary update module 103, and an instruction issuance module 104. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0077] In this embodiment, the functions of each module / unit are as follows: The state comparison module 101 is used to compare the oil state feature vector of the cutting oil with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain the preparation state deviation sequence of the cutting oil. The trend slicing module 102 is used to extract the evolution of the cutting oil preparation process based on the deviation evolution trend of adjacent time windows in the preparation state deviation sequence, and obtain the preparation state deviation subsequence of the cutting oil preparation process. Boundary update module 103 is used to update the boundary of the preparation state deviation subsequence to obtain the allowable fluctuation boundary of the preparation parameters of the cutting oil; The instruction issuing module 104 is used to compare and determine the deviation value in the preparation state deviation sequence with the allowable fluctuation boundary of the preparation parameters, obtain the preparation parameter adjustment instruction of the cutting oil, and send the preparation parameter adjustment instruction to the preparation execution terminal of the cutting oil.

[0078] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0079] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0080] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0081] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0082] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for controlling the preparation process of cutting oil based on a cloud platform, characterized in that, The method includes: Z1. Compare the oil state feature vector of the cutting oil with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain the preparation state deviation sequence of the cutting oil. Z2. Based on the deviation evolution trend of adjacent time windows in the preparation state deviation sequence, the cutting oil preparation process is extracted to obtain the preparation state deviation subsequence of the cutting oil preparation process. Z3. Update the boundary of the prepared state deviation subsequence to obtain the allowable fluctuation boundary of the preparation parameters of the cutting oil; Z4. Compare the deviation value in the preparation state deviation sequence with the allowable fluctuation boundary of the preparation parameters to obtain the preparation parameter adjustment instruction of the cutting oil, and send the preparation parameter adjustment instruction to the preparation execution terminal of the cutting oil.

2. The method for controlling the cutting oil preparation process based on a cloud platform as described in claim 1, characterized in that, The step of comparing the oil state feature vector of the cutting oil with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain the preparation state deviation sequence of the cutting oil includes: Based on a preset feature dimension order, the viscosity feature value, acid value feature value, and impurity content feature value of the cutting oil are vectorized and encapsulated to obtain the oil state feature vector of the cutting oil. Based on the formula identifier of the cutting oil, retrieve the standard state feature vector of the same formula that matches the formula identifier from the cloud platform; The overall state deviation of the cutting oil is obtained by mapping the difference between the eigenvalues ​​in the oil state feature vector and the standard eigenvalues ​​in the standard state feature vector of the same formula. The formula for calculating the overall state deviation is as follows: ； In the formula, The deviation of the overall state. The viscosity characteristic value is the feature value of the oil state feature vector. The standard viscosity value is the characteristic vector of the standard state of the same formulation. The acid value is the characteristic value of the oil state feature vector. The standard acid value is the characteristic vector of the standard state of the same formulation. The impurity content feature value is the feature value of the oil state feature vector. The standard impurity content value is the standard state feature vector of the same formulation. The viscosity weighting coefficient is pre-stored in the cloud platform. The acid value weighting coefficient is pre-stored in the cloud platform. The impurity content weighting coefficient is pre-stored in the cloud platform; The overall state deviation is time-series aggregated to obtain the preparation state deviation sequence of the cutting oil.

3. The method for controlling the cutting oil preparation process based on a cloud platform as described in claim 2, characterized in that, The evolution trend of the deviation between adjacent time windows in the preparation state deviation sequence is used to extract the evolution of the cutting oil preparation process, resulting in a subsequence of the preparation state deviation of the cutting oil preparation process, including: The first deviation component, the second deviation component, and the third deviation component in the prepared state deviation sequence are combined in a time-series correlation to obtain the trend judgment window of the cutting oil; The first deviation component and the second deviation component are compared to obtain the first comparison result of the cutting oil. The second deviation component and the third deviation component are compared to obtain the second comparison result of the cutting oil. When the first comparison result indicates that the second deviation component is greater than the first deviation component, and the second comparison result indicates that the third deviation component is greater than the second deviation component, it is determined that the trend judgment window of the cutting oil shows a monotonically increasing evolution trend. A continuous subsequence is extracted from the preparation state deviation sequence, with the starting time window of the trend judgment window as the boundary and the ending time window of the preparation state deviation sequence as the endpoint, and is taken as the preparation state deviation subsequence of the cutting oil preparation process.

4. The method for controlling the cutting oil preparation process based on a cloud platform as described in claim 3, characterized in that, The step of extracting a continuous subsequence from the preparation state deviation sequence, with the starting time window of the trend judgment window as the boundary and the ending time window of the preparation state deviation sequence as the endpoint, as the preparation state deviation subsequence, includes: The window identifier of the first time window in the trend judgment window is used as the starting boundary window, and the window identifier of the last time window in the time sequence of the prepared state deviation sequence is used as the ending boundary window. The order of the window identifiers of the starting boundary window and the ending boundary window is determined to obtain the order determination result of the cutting oil preparation process. When the sequence determination result indicates that the window identifier of the starting boundary window is earlier than the window identifier of the ending boundary window, the preparation state deviation sequence is subjected to boundary cutting, and the missing window positions that occur during the boundary cutting process are filled with null values ​​to obtain the preparation state deviation subsequence of the cutting oil preparation process.

5. The method for controlling the cutting oil preparation process based on a cloud platform as described in claim 4, characterized in that, The step of updating the boundary of the deviation subsequence of the preparation state to obtain the allowable fluctuation boundary of the preparation parameters of the cutting oil includes: Monotonic trend identification is performed on the subsequence of the deviation of the preparation state to obtain the monotonically increasing attribute identifier of the entire sequence of the cutting oil preparation process; The starting deviation value and ending deviation value of the prepared state deviation subsequence are combined with the monotonically increasing attribute identifier of the whole sequence to obtain the morphological feature set of the cutting oil preparation process; The morphological feature set is matched with the pre-stored standard evolutionary morphological template in the cloud platform to obtain the matching template for the cutting oil preparation process; Based on the template identifier of the matching template, the boundary parameter library of the cloud platform is searched to obtain the pre-formed upper boundary value and pre-formed lower boundary value of the cutting oil preparation process; The pre-defined boundary interval, composed of the pre-defined upper boundary value and the pre-defined lower boundary value, is compared with the deviation component in the preparation state deviation subsequence to obtain the coverage verification result of the cutting oil preparation process. When the coverage verification result indicates complete coverage, the pre-set upper boundary value and the pre-set lower boundary value are set as the allowable fluctuation boundaries of the cutting oil preparation parameters.

6. The method for controlling the cutting oil preparation process based on a cloud platform as described in claim 5, characterized in that, The step of performing similarity matching between the morphological feature set and the pre-stored standard evolutionary morphological templates in the cloud platform to obtain the matching template for the cutting oil preparation process includes: Retrieve the standard evolutionary template corresponding to the cutting oil formulation from the cloud platform; Based on the standard evolutionary morphology template, the starting point deviation value, the ending point deviation value, and the monotonically increasing attribute identifier of the entire sequence are identified item by item to obtain the three comparison results of the cutting oil preparation process; Based on the three comparison results, the standard evolutionary morphology template is selected for optimal screening to obtain the matching template for the cutting oil preparation process.

7. The method for controlling the cutting oil preparation process based on a cloud platform as described in claim 6, characterized in that, Based on the three comparison results, the standard evolutionary morphology template is selectively screened to obtain a matching template for the cutting oil preparation process, including: The three comparison results of the standard evolutionary morphology template are extracted in a targeted manner to obtain the total number of feature items that pass the comparison in the standard evolutionary morphology template; Extreme value screening is performed on the total number of the feature items to determine the maximum total number of extreme value screening results, and the standard evolution morphology template corresponding to the maximum total number is used as the initial template for the cutting oil preparation process; When the number of the initial selection templates is one, the initial selection template is determined as the matching template for the cutting oil preparation process; When the number of the initial selection templates is greater than one, the deviation between the reference starting point value and the actual starting point value of the initial selection templates is optimized to obtain the matching template for the cutting oil preparation process.

8. The method for controlling the cutting oil preparation process based on a cloud platform as described in claim 7, characterized in that, The step of performing interval verification between the prefabricated boundary interval formed by the prefabricated upper boundary value and the prefabricated lower boundary value and the deviation subsequence of the preparation state to obtain the coverage verification result of the cutting oil preparation process includes: Using the pre-defined upper boundary value as the upper limit of the interval and the pre-defined lower boundary value as the lower limit of the interval, a pre-defined boundary interval for the cutting oil preparation process is constructed. The deviation component of the prepared state deviation subsequence is compared with the lower limit and upper limit of the interval to determine the membership, thereby obtaining the single-point coverage judgment result of the cutting oil preparation process. When the single-point coverage determination result shows that the deviation component belongs to the pre-defined boundary interval, the deviation component is marked as covered. When all deviation components in the deviation subsequence of the preparation state are marked as coverage passed, the coverage verification result indicating complete coverage during the preparation of the cutting oil is obtained.

9. The method for controlling the cutting oil preparation process based on a cloud platform as described in claim 1, characterized in that, The step of comparing the deviation value in the preparation state deviation sequence with the allowable fluctuation boundary of the preparation parameters to determine the preparation parameters adjustment instruction for the cutting oil, and sending the preparation parameter adjustment instruction to the preparation execution terminal of the cutting oil, includes: Read the real-time deviation metric value of the current time window from the prepared state deviation sequence; The real-time deviation measurement value is compared with the upper and lower limits of the allowable fluctuation boundary of the preparation parameters to obtain the over-limit judgment result of the cutting oil preparation process. The result of the over-limit judgment is conditionally split to obtain the adjustment command for the preparation parameters of the cutting oil; The preparation parameter adjustment command is sent to the cutting oil preparation execution terminal.

10. A cloud-based cutting oil preparation process control system, characterized in that, The system for implementing the cloud-based cutting oil preparation process control method of claim 1 includes: The state comparison module is used to compare the oil state feature vector of the cutting oil with the pre-stored standard state feature vector of the same formula in the cloud platform to obtain the preparation state deviation sequence of the cutting oil. The trend slicing module is used to extract the evolution trend of the cutting oil preparation process based on the deviation evolution trend of adjacent time windows in the preparation state deviation sequence, and obtain the preparation state deviation subsequence of the cutting oil preparation process. The boundary update module is used to update the boundary of the preparation state deviation subsequence to obtain the allowable fluctuation boundary of the preparation parameters of the cutting oil; The instruction issuing module is used to compare the deviation value in the preparation state deviation sequence with the allowable fluctuation boundary of the preparation parameters to determine the boundary, obtain the preparation parameter adjustment instruction of the cutting oil, and send the preparation parameter adjustment instruction to the preparation execution terminal of the cutting oil.

Images