A Data Analysis-Based Early Warning Method and System for Basic Nickel Carbonate Production Anomalies

Abstract

This invention discloses a data analysis-based method and system for early warning of anomalies in basic nickel carbonate production. The method includes: acquiring historical monitoring data within a preset time period; selecting key target data points by calculating data deviation; and extracting multiple historical monitoring data sequences with adjacent target data points as start and end points. During real-time monitoring, when the current monitoring data does not exceed a preset threshold, it is matched with the most similar historical sequence. By analyzing the subsequent data change rate trend of the sequence, it is determined whether there are potential anomalies in the current data. Combining static threshold early warning with dynamic trend early warning can identify risks that are still within the safe range but have abnormal development trends, realizing the transformation from post-event alarm to pre-event early warning. This significantly improves the timeliness and accuracy of early warning in the basic nickel carbonate production process, effectively ensuring production safety and stability.

Description

Technical Field

[0001] This invention belongs to the field of basic nickel carbonate production analysis technology, and particularly relates to a method and system for early warning of anomalies in basic nickel carbonate production based on data analysis. Background Technology

[0002] Basic nickel carbonate, as an important industrial raw material, is widely used in electroplating, battery materials, and catalyst preparation. Its production process typically involves complex chemical reactions and process control, with strict requirements on key process parameters such as reaction temperature, pH value, ion concentration, and feeding rate. If even minor anomalies in these parameters are not detected and addressed in a timely manner, they can easily lead to deviations in product composition, substandard purity, and even serious problems such as production interruptions and equipment scaling, resulting in significant economic losses.

[0003] In current production practices, monitoring and early warning of anomalies in the basic nickel carbonate production process mainly rely on two traditional technologies: First, alarm mechanisms based on fixed thresholds. This method sets a safety range for key parameters, and the system triggers an alarm once the monitored data exceeds the preset upper and lower limits. However, this method has significant lag and limitations. It can only trigger an alarm when an anomaly has already occurred and is relatively obvious, and cannot warn of "potential risks" that are still within the safety threshold but have shown an abnormal development trend, thus missing the best opportunity for early intervention. Second, it relies on the judgment of operators based on their experience. This method is highly subjective and difficult to handle massive amounts of high-speed production data, and is prone to missed judgments due to fatigue or negligence.

[0004] Furthermore, historical monitoring data generated during production contains rich information on process status, but effectively utilizing this data faces several challenges: First, due to sensor malfunctions, data transmission loss, and other reasons, historical data contains missing values, which can affect the accuracy of analysis if used directly. Second, the historical data volume is enormous, and most of it is in a normal and stable state. How to efficiently extract representative data patterns related to anomalies and quickly and accurately match them with current data is a technical challenge. Existing simple statistical analysis or fixed-time-window slicing methods are insufficient to capture the inherent laws of parameter dynamic evolution, resulting in low sensitivity and high false alarm rates in early warning models. Summary of the Invention

[0005] This invention provides a data analysis-based early warning method and system for basic nickel carbonate production anomalies, which addresses the technical problem of low sensitivity and high false alarm rate in early warning models due to the difficulty in capturing the inherent laws of dynamic parameter evolution.

[0006] In a first aspect, the present invention provides a method for early warning of anomalies in basic nickel carbonate production based on data analysis, comprising:

[0007] Historical monitoring data for a preset time period during the production of basic nickel carbonate are acquired, and at least one target historical monitoring data is selected within the preset time period based on the data deviation of each historical monitoring data and a preset data selection rule is adopted.

[0008] Using the historical monitoring data of two adjacent targets as the start and end points of the sequence, extract the historical monitoring data between the two adjacent historical monitoring data to obtain at least one historical monitoring data sequence.

[0009] Acquire the current monitoring data at the current moment during the basic nickel carbonate production process, and determine whether the monitoring value in the current monitoring data is greater than the corresponding preset monitoring threshold.

[0010] If the value is not greater than the corresponding preset monitoring threshold, then a target historical monitoring data sequence in the at least one historical monitoring data sequence is matched with the current monitoring data according to the preset matching strategy.

[0011] The current monitoring data is analyzed based on a certain historical monitoring data sequence, and the anomaly of the current monitoring data is determined based on the analysis results.

[0012] Secondly, the present invention provides a data analysis-based early warning system for anomalies in basic nickel carbonate production, comprising:

[0013] The acquisition module is configured to acquire historical monitoring data during a preset time period in the basic nickel carbonate production process, and select at least one target historical monitoring data within the preset time period based on the data deviation of each historical monitoring data and using preset data selection rules.

[0014] The interception module is configured to use the historical monitoring data of two adjacent targets as the start point and end point of the sequence, and intercept the historical monitoring data between the two adjacent targets to obtain at least one historical monitoring data sequence.

[0015] The judgment module is configured to acquire the current monitoring data at the current moment during the basic nickel carbonate production process, and to determine whether the monitoring value in the current monitoring data is greater than the corresponding preset monitoring threshold.

[0016] The matching module is configured to match the current monitoring data with a target historical monitoring data sequence from the at least one historical monitoring data sequence according to a preset matching strategy if the current monitoring data is not greater than the corresponding preset monitoring threshold.

[0017] The analysis module is configured to perform data analysis on the current monitoring data based on a certain historical monitoring data sequence, and determine whether the current monitoring data is abnormal based on the analysis results.

[0018] Thirdly, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the data analysis-based early warning method for anomalies in basic nickel carbonate production according to any embodiment of the present invention.

[0019] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the data analysis-based early warning method for basic nickel carbonate production anomalies according to any embodiment of the present invention.

[0020] This application discloses a data analysis-based method and system for early warning of anomalies in basic nickel carbonate production. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating an early warning method for anomalies in basic nickel carbonate production based on data analysis, provided as an embodiment of the present invention;

[0023] Figure 2 This is a structural block diagram of a data analysis-based early warning system for anomalies in basic nickel carbonate production, provided in an embodiment of the present invention.

[0024] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] Please see Figure 1 The diagram shows a flowchart of a data analysis-based early warning method for anomalies in basic nickel carbonate production, as described in this application.

[0027] like Figure 1 As shown, the data analysis-based early warning method for anomalies in basic nickel carbonate production specifically includes the following steps:

[0028] Step S101: Obtain historical monitoring data for a preset time period during the basic nickel carbonate production process, and select at least one target historical monitoring data within the preset time period based on the data deviation of each historical monitoring data and using preset data selection rules.

[0029] In one specific embodiment, before selecting at least one target historical monitoring data within a preset time period based on the data deviation of each historical monitoring data using a preset data selection rule, the process includes:

[0030] The historical monitoring data are sorted according to the chronological order of time points to obtain the total historical monitoring data sequence. It is then determined whether historical monitoring data exists at each time point within a preset time period. If no historical monitoring data exists at a certain time point, a subsequence of a preset length of historical monitoring data is extracted from the total historical monitoring data sequence, centered on that time point. A sliding window of the preset length slides across the total historical monitoring data sequence. Each time the window slides, the similarity between the sliding historical monitoring data sequence within the window and the subsequence is determined to be less than a preset similarity threshold. The sliding window moves in increments of one historical monitoring data point, and the sliding historical monitoring data sequence is the sequence obtained by sorting the historical monitoring data within the window according to the chronological order of time points. If the similarity is less than the preset threshold, the historical monitoring data at the center point of the sliding historical monitoring data sequence is used as the historical monitoring data at that time point, resulting in an updated target total historical monitoring data sequence. If the similarity is not less than the preset threshold, the average historical monitoring data of the subsequence is determined and used as the historical monitoring data at that time point, resulting in an updated target total historical monitoring data sequence.

[0031] It should be noted that before determining whether the sequence similarity between the sliding historical monitoring data sequence in the sliding window and a certain historical monitoring data sub-sequence is greater than a preset similarity threshold, the sliding historical monitoring data sequence and a certain historical monitoring data sub-sequence are aligned, and the absolute value of the data difference between a certain sliding historical monitoring data at the same position point and a certain historical monitoring data is calculated; the absolute values ​​of the data differences corresponding to each position point are added together to obtain the sequence similarity between the sliding historical monitoring data sequence in the sliding window and a certain historical monitoring data sub-sequence.

[0032] In the production of basic nickel carbonate, to achieve accurate early warning of production anomalies, it is first necessary to acquire historical monitoring data for a preset time period (e.g., the past 30 days). This data may include key process parameters such as reaction temperature, pH value, and nickel ion concentration. These parameters are usually recorded in time series form, and the sampling frequency can be hourly or daily. The core of step S101 lies in the preprocessing of historical monitoring data and the selection of key data points (i.e., target historical monitoring data), and the specific implementation method is as follows:

[0033] Export all historical monitoring data within a preset time period from the production database or monitoring system. This data may contain discontinuous or missing data points.

[0034] Historical monitoring data are sorted according to their chronological order (e.g., ascending order by timestamp) to form a complete historical monitoring data sequence. ,in Indicates the first Monitoring values ​​at each time point This represents the total number of data points.

[0035] Traversing the total sequence of historical monitoring data Check if data exists at each preset time point (e.g., one point per hour). If data is found at each time point... If no monitoring data is available, the point is marked as missing and data filling is required.

[0036] Extracting a local sequence: by time point Centered on the total sequence of historical monitoring data Extract a sequence of historical monitoring data of a preset length L (e.g., L=5). Note that, due to Missing Actually does not include The data includes L data points before and after it (total length 2L).

[0037] Sliding window search: Define a sliding window of length 2L, in Slide upwards with a step size of 1 data point. For each window position j, obtain the historical monitoring data sequence within the window.

[0038] Sequence similarity calculation: and Alignment is performed (based on time sequence), and the sum of the absolute values ​​of the data differences at the same location is used as the sequence similarity. .

[0039] If there exists some j such that (in (For the preset similarity threshold), then... Data at the center is used as a time point. The fill value. Otherwise, calculate. The average value, and use the average value as the time point. The fill value.

[0040] Repeat the above process until all missing time points are filled in, and obtain the updated target historical monitoring data sequence.

[0041] Specifically, the average historical monitoring data of the target is determined based on the historical monitoring data of each target in the total sequence of historical monitoring data of the target, and the difference between the historical monitoring data of each target and the average historical monitoring data of the target is calculated to obtain the data deviation of each historical monitoring data. At least one historical monitoring data of the target with a data deviation greater than a preset dynamic deviation threshold is selected in the total sequence of historical monitoring data of the target, wherein the preset dynamic deviation threshold is the average value of all data deviations.

[0042] In this embodiment, calculation The average of all data in ;

[0043] For each historical monitoring data Calculate its data deviation .

[0044] Calculate the average of all deviations As a preset dynamic deviation threshold.

[0045] Select all that satisfy The data points are used as historical monitoring data for the target to form a target data point set.

[0046] Through the above specific implementation methods, step S101 achieves efficient preprocessing of historical monitoring data and extraction of key data points, thus laying a solid foundation for subsequent anomaly early warning analysis. The achieved technical effects include:

[0047] Data integrity and quality improvement: By intelligently filling missing data, the analysis bias caused by missing data is avoided. By using sliding window and sequence similarity comparison methods, the filling value that is most similar to the local pattern can be adaptively selected, or the average value can be used as a backup strategy. This not only preserves the temporal characteristics of the data, but also reduces the introduction of noise and improves the overall reliability and consistency of the data.

[0048] Enhanced anomaly sensitivity: Based on a target data selection mechanism that focuses on data points that deviate significantly from the normal range, these points are often highly correlated with production anomalies (such as fluctuations in process parameters or equipment failures). Through a dynamic deviation threshold (i.e., average deviation), the method can adapt to changes in data distribution, avoiding false positives or false negatives caused by fixed thresholds, thus improving the sensitivity of anomaly detection.

[0049] Computational efficiency optimization: Setting the sliding window step size to one data point ensures the precision of local sequence matching, while quickly determining the similarity threshold reduces unnecessary computational overhead. The selection process for target data points is simple and efficient, providing a streamlined dataset for subsequent sequence truncation and matching steps, thus reducing overall computational complexity.

[0050] Provides reliable input for subsequent analysis: The updated target historical monitoring data sequence and target data point set serve as the basis for constructing the historical monitoring data sequence, which can more accurately reflect the abnormal patterns in the production process, thereby improving the accuracy and timeliness of abnormal early warning when matching with the current monitoring data in subsequent steps.

[0051] Step S102: Using the historical monitoring data of two adjacent targets as the start and end points of the sequence, extract the historical monitoring data between the two adjacent historical monitoring data to obtain at least one historical monitoring data sequence.

[0052] In this embodiment, the continuous historical monitoring data stream is dynamically divided into several historical monitoring data sequences that are representative of the event, with the boundary between two adjacent "target historical monitoring data" (i.e., high deviation data points).

[0053] Production anomalies often manifest as a series of related parameter fluctuations rather than isolated points. A sequence extracted by using two adjacent high-deviation data points as boundaries naturally captures a complete fluctuation cycle (e.g., the entire process from the start of one anomalous fluctuation to the occurrence of the next). This upgrades the basic unit of subsequent analysis (step S104) from an isolated "data point" to a "data story fragment" containing an evolutionary process, greatly enriching the analytical dimensions and contextual information.

[0054] Furthermore, by analyzing the trajectory, rate, and pattern of change in all data between two key points, the system can understand the typical behavior of parameters within a specific event interval. When current data matches a historical sequence, the system can not only determine the similarity of the values, but also make predictive assessments of the possible future trends of the current data based on the subsequent evolution history of that sequence.

[0055] When it is necessary to find reference patterns for current data, the system does not need to perform a global scan of the entire historical data stream. Instead, it can directly search within these predefined, high-information-density "key interval sequences." This significantly improves matching efficiency, and because these sequences themselves represent significant historical fluctuation ranges, the matching results are more focused and representative, thereby improving the accuracy and relevance of early warnings.

[0056] Step S103: Obtain the current monitoring data at the current moment during the basic nickel carbonate production process, and determine whether the monitoring value in the current monitoring data is greater than the corresponding preset monitoring threshold.

[0057] In one specific embodiment, after determining whether the monitored value in the current monitoring data is greater than the corresponding preset monitoring threshold, if it is greater than the corresponding preset monitoring threshold, it is directly determined that the current monitoring data is abnormal and an early warning signal is generated.

[0058] Step S104: If the value is not greater than the corresponding preset monitoring threshold, then match a target historical monitoring data sequence in the at least one historical monitoring data sequence with the current monitoring data according to the preset matching strategy.

[0059] In this step, it is determined whether there is historical monitoring data in each historical monitoring data sequence that is the same as the current monitoring data. If there is historical monitoring data in at least one target historical monitoring data sequence that is the same as the current monitoring data, then the target historical monitoring data sequence with the shortest interval time with the current monitoring data is selected as a target historical monitoring data sequence. If there is no historical monitoring data in at least one target historical monitoring data sequence that is the same as the current monitoring data, then the historical monitoring data sequence with the shortest interval time with the current monitoring data is directly selected as a target historical monitoring data sequence.

[0060] In this step, during the production of basic nickel carbonate, once the monitoring data for the current moment is acquired, if the monitored value does not exceed the preset monitoring threshold, the system will enter a deep analysis phase, identifying potential anomalies through historical data sequence matching. The specific implementation steps are as follows:

[0061] From at least one pre-constructed historical monitoring data sequence, select the target historical monitoring data sequence that is most relevant to the current monitoring data according to a preset matching strategy.

[0062] The matching strategy is implemented as follows: First, search each historical sequence for records that have the same value as the current monitoring data. If multiple matching sequences exist, select the sequence with the shortest interval between the timestamp and the current time. If there is no perfectly matching sequence, select the sequence with the closest time as the matching sequence.

[0063] Step S105: Perform data analysis on the current monitoring data based on a certain historical monitoring data sequence, and determine whether the current monitoring data is abnormal based on the analysis results.

[0064] In this step, the first target historical monitoring data that is identical to the current monitoring data is searched in a certain target historical monitoring data sequence. The first target historical monitoring data is the target historical monitoring data with the earliest time point in the certain target historical monitoring data sequence that is identical to the current monitoring data. Taking the time point of the first target historical monitoring data as the start time point and the time point of the last target historical monitoring data in the certain target historical monitoring data sequence as the end time point, the first target historical monitoring data sequence is extracted from the certain target historical monitoring data sequence. The data change rate between two adjacent target historical monitoring data in the first target historical monitoring data sequence is calculated, and it is determined whether the change rate of each data is greater than a preset change rate threshold. If the change rate of a data is greater than the preset change rate threshold, it is determined that there is a potential anomaly in the current monitoring data, and a potential anomaly signal is generated.

[0065] In this embodiment, in the selected target historical monitoring data sequence, the search proceeds forward along the time axis to locate the first target historical monitoring data with the same value as the current monitoring data, which is denoted as the first target historical monitoring data. This data point must meet two conditions: the monitoring value is completely consistent with the current data; and it is the earliest record of that value in the sequence.

[0066] Starting from the time point of the historical monitoring data of the first target and ending at the time point of the last data point in the historical sequence, all historical monitoring data of the target between the two are extracted to construct the historical monitoring data sequence of the first target.

[0067] Perform differential calculation on adjacent data points in the historical monitoring data sequence of the first target: traverse each data point in the sequence in chronological order, calculate the data change rate between two adjacent data points, data change rate = |value of the next data point - value of the previous data point| / time interval;

[0068] Each data change rate is compared with a preset change rate threshold, which is based on statistical analysis of historical normal production data and takes into account the characteristics of different production process stages to set differentiated thresholds.

[0069] This implementation method achieves effective identification of potential anomalies in the production process of basic nickel carbonate through refined sequence matching and trend analysis. Specific technical effects are reflected in:

[0070] Deep anomaly detection capability: Breaking through the limitations of traditional threshold detection, it establishes a correlation between current data and historical patterns through similarity matching of historical sequences. Even if the monitored values ​​are within the safe threshold range, it can identify potential anomalies in advance by analyzing their possible subsequent development trends, realizing the transformation from "static threshold judgment" to "dynamic trend early warning".

[0071] Precise pattern recognition: Employing an "earliest matching point" positioning strategy ensures the acquisition of complete historical evolution patterns. By calculating the rate of change of adjacent data points, it accurately captures abrupt changes in process parameters, effectively distinguishing between normal fluctuations and abnormal jumps, and significantly reducing false alarm rates;

[0072] An adaptive analysis mechanism dynamically selects matching sequences based on real-time data to adapt to the data analysis needs under different production conditions. Flexible setting of the rate of change threshold fully considers the characteristics of the production process, ensuring the accuracy and practicality of the analysis results.

[0073] Improved early warning timeliness: The mechanism for generating potential anomaly signals enables the system to issue warnings before anomalies fully manifest, providing maintenance personnel with a valuable response window. Early intervention effectively prevents production accidents and ensures the stable operation of the production line.

[0074] This implementation method upgrades traditional data monitoring to intelligent trend analysis, significantly enhancing the accuracy and foresight of anomaly warnings in the production of basic nickel carbonate, and providing reliable technical support for the safety management and control of industrial production.

[0075] In summary, the method of this application employs an intelligent data preprocessing strategy based on sliding windows and sequence similarity matching, effectively solving the problem of missing data in production data. While ensuring data integrity, it preserves temporal characteristics to the maximum extent. Secondly, by constructing a dual detection system of "static threshold real-time early warning" and "dynamic trend potential early warning," it breaks through the limitations of traditional single threshold judgment: when the monitored data does not exceed the threshold, the system can deeply explore the potential risks of normal values ​​but abnormal trends based on historical sequence matching and change rate analysis, realizing the key transformation from "post-event alarm" to "pre-event early warning." This provides maintenance personnel with a valuable time window for handling potential anomalies by discovering them early, effectively avoiding equipment damage and product quality problems, reducing unplanned downtime, and bringing considerable economic benefits while ensuring the continuous and stable operation of the production line.

[0076] Please see Figure 2The diagram shows a structural block diagram of an early warning system for abnormal production of basic nickel carbonate based on data analysis, as proposed in this application.

[0077] like Figure 2 As shown, the basic nickel carbonate production anomaly early warning system 200 includes an acquisition module 210, an interception module 220, a judgment module 230, a matching module 240, and an analysis module 250.

[0078] The acquisition module 210 is configured to acquire historical monitoring data during a preset time period in the basic nickel carbonate production process, and select at least one target historical monitoring data within the preset time period based on the data deviation of each historical monitoring data using a preset data selection rule; the interception module 220 is configured to intercept historical monitoring data between two adjacent target historical monitoring data as the sequence start point and sequence end point, to obtain at least one historical monitoring data sequence; the judgment module 230 is configured to acquire the current monitoring data at the current moment in the basic nickel carbonate production process, and determine whether the monitoring value in the current monitoring data is greater than the corresponding preset monitoring threshold; the matching module 240 is configured to match a target historical monitoring data sequence from the at least one historical monitoring data sequence with the current monitoring data according to a preset matching strategy if the value is not greater than the corresponding preset monitoring threshold; and the analysis module 250 is configured to perform data analysis on the current monitoring data based on the historical monitoring data sequence, and determine whether the current monitoring data is abnormal based on the analysis results.

[0079] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2 The various modules in the document will not be described in detail here.

[0080] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the data analysis-based early warning method for anomalies in basic nickel carbonate production as described in any of the above method embodiments.

[0081] In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows:

[0082] Historical monitoring data for a preset time period during the production of basic nickel carbonate are acquired, and at least one target historical monitoring data is selected within the preset time period based on the data deviation of each historical monitoring data and a preset data selection rule is adopted.

[0083] Using the historical monitoring data of two adjacent targets as the start and end points of the sequence, extract the historical monitoring data between the two adjacent historical monitoring data to obtain at least one historical monitoring data sequence.

[0084] Acquire the current monitoring data at the current moment during the basic nickel carbonate production process, and determine whether the monitoring value in the current monitoring data is greater than the corresponding preset monitoring threshold.

[0085] If the value is not greater than the corresponding preset monitoring threshold, then a target historical monitoring data sequence in the at least one historical monitoring data sequence is matched with the current monitoring data according to the preset matching strategy.

[0086] The current monitoring data is analyzed based on a certain historical monitoring data sequence, and the anomaly of the current monitoring data is determined based on the analysis results.

[0087] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created based on the use of the data analysis-based early warning system for basic nickel carbonate production anomalies. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely configured relative to a processor, which can be connected to the data analysis-based early warning system for basic nickel carbonate production anomalies via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0088] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby implementing the data analysis-based early warning method for anomalies in basic nickel carbonate production as described in the above embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the data analysis-based early warning system for anomalies in basic nickel carbonate production. The output device 340 may include a display screen or other display device.

[0089] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0090] In one implementation, the above-described electronic device is applied to a data analysis-based early warning system for anomalies in basic nickel carbonate production. As a client, it includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0091] Historical monitoring data for a preset time period during the production of basic nickel carbonate are acquired, and at least one target historical monitoring data is selected within the preset time period based on the data deviation of each historical monitoring data and a preset data selection rule is adopted.

[0092] Using the historical monitoring data of two adjacent targets as the start and end points of the sequence, extract the historical monitoring data between the two adjacent historical monitoring data to obtain at least one historical monitoring data sequence.

[0093] Acquire the current monitoring data at the current moment during the basic nickel carbonate production process, and determine whether the monitoring value in the current monitoring data is greater than the corresponding preset monitoring threshold.

[0094] If the value is not greater than the corresponding preset monitoring threshold, then a target historical monitoring data sequence in the at least one historical monitoring data sequence is matched with the current monitoring data according to the preset matching strategy.

[0095] The current monitoring data is analyzed based on a certain historical monitoring data sequence, and the anomaly of the current monitoring data is determined based on the analysis results.

[0096] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data analysis-based abnormality early warning method for basic nickel carbonate production, characterized by, The method comprises the following steps: acquiring historical monitoring data in a preset time period in a basic nickel carbonate production process, and selecting at least one target historical monitoring data in the preset time period according to the data deviation of each historical monitoring data and a preset data selection rule; sorting each historical monitoring data according to the sequence of time points to obtain a total sequence of historical monitoring data; judging whether there is historical monitoring data at each time point in the preset time period; if there is no historical monitoring data at a certain time point, a certain historical monitoring data sub-sequence of a preset length is intercepted in the total sequence of historical monitoring data with the certain time point as the center point; sliding a preset length sliding window on the total sequence of historical monitoring data, and judging whether the sequence similarity between a sliding historical monitoring data sequence in the sliding window and the certain historical monitoring data sub-sequence is less than a preset similarity threshold value each time the sliding window slides, wherein the step length of the sliding window is one historical monitoring data each time the sliding window slides, and the sliding historical monitoring data sequence is a historical monitoring data sequence sorted according to the sequence of time points in the sliding window; if the sequence similarity is less than the preset similarity threshold value, a historical monitoring data at the center point position in the sliding historical monitoring data sequence is taken as a certain historical monitoring data at a certain time point to obtain an updated total sequence of target historical monitoring data; if the sequence similarity is not less than the preset similarity threshold value, an average historical monitoring data of the certain historical monitoring data sub-sequence is determined and taken as a certain historical monitoring data at a certain time point to obtain an updated total sequence of target historical monitoring data; taking two adjacent target historical monitoring data as the sequence start point and the sequence end point, and intercepting historical monitoring data between the two adjacent target historical monitoring data to obtain at least one historical monitoring data sequence; acquiring current monitoring data at a current time in the basic nickel carbonate production process, and judging whether the monitoring value in the current monitoring data is greater than a corresponding preset monitoring threshold value; if the monitoring value is not greater than the corresponding preset monitoring threshold value, a certain target historical monitoring data sequence in the at least one historical monitoring data sequence is matched with the current monitoring data according to a preset matching strategy; performing data analysis on the current monitoring data according to a certain target historical monitoring data sequence, and determining whether the current monitoring data is abnormal according to the analysis result.

2. The method for early warning of abnormal production of basic nickel carbonate based on data analysis according to claim 1, characterized in that, Before judging whether the sequence similarity between the sliding historical monitoring data sequence in the sliding window and the certain historical monitoring data sub-sequence is greater than the preset similarity threshold value, the method further comprises the following steps: aligning the sliding historical monitoring data sequence with the certain historical monitoring data sub-sequence, and calculating the data difference absolute value between a certain sliding historical monitoring data and a certain historical monitoring data at the same position point; The absolute values of the data difference values corresponding to the respective position points are added to obtain a sequence similarity between the sliding historical monitoring data sequence in the sliding window and the certain historical monitoring data sequence.

3. The method for early warning of abnormal production of basic nickel carbonate based on data analysis according to claim 1, characterized in that, The data deviation degree of each historical monitoring data is determined, and at least one target historical monitoring data is selected in the preset time period according to a preset data selection rule. An average target historical monitoring data is determined according to each target historical monitoring data in the total sequence of target historical monitoring data, and the data deviation degree of each target historical monitoring data is obtained by subtracting the average target historical monitoring data from each target historical monitoring data. At least one target historical monitoring data with a data deviation degree greater than a preset dynamic deviation degree threshold is selected in the total sequence of target historical monitoring data, wherein the preset dynamic deviation degree threshold is the average of all data deviation degrees.

4. The method for early warning of abnormal production of basic nickel carbonate based on data analysis according to claim 1, characterized in that, The certain target historical monitoring data sequence in the at least one historical monitoring data sequence is matched with the current monitoring data according to a preset matching strategy, including: It is determined whether there is historical monitoring data in each historical monitoring data sequence that is the same as the current monitoring data; If there is historical monitoring data in at least one target historical monitoring data sequence that is the same as the current monitoring data, the target historical monitoring data sequence with the shortest interval time from the current monitoring data is selected as the certain target historical monitoring data sequence in the at least one target historical monitoring data sequence; If there is no historical monitoring data in at least one target historical monitoring data sequence that is the same as the current monitoring data, the historical monitoring data sequence with the shortest interval time from the current monitoring data is directly selected as the certain target historical monitoring data sequence.

5. The method for early warning of abnormal production of basic nickel carbonate based on data analysis according to claim 1, characterized in that, After determining whether the monitoring value in the current monitoring data is greater than the corresponding preset monitoring threshold, the method further includes: If it is greater than the corresponding preset monitoring threshold, it is directly determined that the current monitoring data is abnormal, and a warning signal is generated.

6. The method for early warning of abnormal production of basic nickel carbonate based on data analysis according to claim 1, characterized in that, The current monitoring data is analyzed according to the certain historical monitoring data sequence, and whether the current monitoring data is abnormal is determined according to the analysis result, including: The first target historical monitoring data that is the same as the current monitoring data is searched for in the certain target historical monitoring data sequence, wherein the first target historical monitoring data is the earliest target historical monitoring data in the certain target historical monitoring data sequence and is the same as the current monitoring data; The first target historical monitoring data sequence is intercepted in the certain target historical monitoring data sequence, with the time point of the first target historical monitoring data as the starting time point and the time point of the last target historical monitoring data in the certain target historical monitoring data sequence as the ending time point; The data change rate between adjacent two target historical monitoring data in the first target historical monitoring data sequence is calculated, and it is determined whether each data change rate is greater than a preset change rate threshold; If a certain data change rate is greater than the preset change rate threshold, it is determined that the current monitoring data has potential abnormality, and a potential abnormality signal is generated.

7. A data analysis-based abnormality early warning system for basic nickel carbonate production, characterized by, The method includes: The acquisition module is configured to acquire historical monitoring data in a preset time period in the production process of basic nickel carbonate, and select at least one target historical monitoring data in the preset time period according to the data deviation of each historical monitoring data and by using a preset data selection rule. Sort each historical monitoring data according to the order of time points to obtain a total sequence of historical monitoring data. Determine whether there is historical monitoring data at each time point in the preset time period. If there is no historical monitoring data at a certain time point, take the certain time point as a center point, and intercept a historical monitoring data sub-sequence of a preset length in the total sequence of historical monitoring data. Slide the preset length sliding window on the total sequence of historical monitoring data. At each sliding time, determine whether the sequence similarity between the sliding historical monitoring data sequence in the sliding window and the certain historical monitoring data sub-sequence is less than a preset similarity threshold, wherein the step length of the sliding window is one historical monitoring data at each sliding time, and the sliding historical monitoring data sequence is the historical monitoring data sequence obtained by sorting each historical monitoring data in the sliding window according to the order of time points. If it is less than the preset similarity threshold, take the historical monitoring data at the center point position in the sliding historical monitoring data sequence as the historical monitoring data at a certain time point to obtain an updated target historical monitoring data total sequence. If it is not less than the preset similarity threshold, determine the average historical monitoring data of the certain historical monitoring data sub-sequence, and take the average historical monitoring data as the historical monitoring data at a certain time point to obtain an updated target historical monitoring data total sequence. The interception module is configured to take two adjacent target historical monitoring data as sequence start point and sequence end point, intercept historical monitoring data between the two adjacent target historical monitoring data, and obtain at least one historical monitoring data sequence. The judgment module is configured to acquire current monitoring data at a current time in the production process of basic nickel carbonate, and determine whether the monitoring value in the current monitoring data is greater than a corresponding preset monitoring threshold. The matching module is configured to, if the monitoring value in the current monitoring data is not greater than the corresponding preset monitoring threshold, match a certain target historical monitoring data sequence in the at least one historical monitoring data sequence with the current monitoring data according to a preset matching strategy. The analysis module is configured to perform data analysis on the current monitoring data according to the certain target historical monitoring data sequence, and determine whether the current monitoring data is abnormal according to the analysis result.

8. An electronic device, comprising: The method comprises: At least one processor and a memory in communication with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program, when executed by the processor, implements the method of any one of claims 1 to 6.

Images