A sewage treatment process monitoring method and system based on data recognition

Abstract

The application discloses a sewage treatment process monitoring method and system based on data identification, and the method comprises the following steps: judging whether isolated second abnormal pollution sub-data exist in a second abnormal pollution sub-data sequence; if not, performing first abnormal analysis on each sewage treatment stage by adopting a preset abnormal sewage analysis strategy according to a first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence, obtaining a first abnormal analysis result, correcting the first abnormal analysis result by adopting a preset result correction rule according to other abnormal pollution sub-data sequences in an abnormal pollution sub-data sequence set, obtaining a second abnormal analysis result, and generating early warning information containing the second abnormal analysis result; and the method can identify the case that the sewage treatment reaches an upper limit, so that the sewage treatment stage with equipment abnormality can be determined more accurately, and the precision of monitoring and alarm is effectively improved.

Description

Technical Field

[0001] This invention belongs to the field of wastewater monitoring technology, and in particular relates to a wastewater treatment process monitoring method and system based on data identification. Background Technology

[0002] Wastewater treatment refers to the removal or reduction of harmful substances from domestic sewage, industrial wastewater, and other sources of wastewater to a certain level, enabling them to meet water quality standards for discharge or reuse. The wastewater treatment process typically includes physical, chemical, and biological treatment stages.

[0003] In actual wastewater treatment processes, due to the uncertainty of wastewater treatment volume and composition, one or more wastewater treatment stages may become oversaturated, resulting in wastewater data exceeding standards after one or more treatment stages. This situation can lead to deviations in the monitoring of whether wastewater treatment equipment is working properly during the treatment stages, thus causing false alarms. Summary of the Invention

[0004] This invention provides a wastewater treatment process monitoring method and system based on data recognition, which solves the technical problem of being unable to accurately alarm and locate abnormal wastewater treatment equipment.

[0005] In a first aspect, the present invention provides a wastewater treatment process monitoring method based on data identification, comprising:

[0006] Acquire wastewater data at various collection times within a preset time period, wherein the wastewater data at a certain collection time includes wastewater sub-data at each wastewater treatment stage at that collection time.

[0007] Based on the preset wastewater data thresholds for each wastewater treatment stage, the pollution sub-data at each collection time is filtered, and at least one abnormal pollution sub-data at the same collection time is sorted according to the order of each wastewater treatment stage to obtain a set of abnormal pollution sub-data sequences, wherein one abnormal pollution sub-data sequence corresponds to one collection time.

[0008] Determine whether the first abnormal contaminated sub-data sequence and the second abnormal contaminated sub-data sequence are the same sequence, wherein the first abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the most abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences, and the second abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the fewest abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences;

[0009] If they are not the same sequence, then determine whether the number of second abnormal polluting sub-data in the second abnormal polluting sub-data sequence is greater than a preset number threshold.

[0010] If the number exceeds a preset threshold, it is determined whether there is an isolated second abnormal pollution sub-data in the second abnormal pollution sub-data sequence. When a certain wastewater treatment stage corresponding to a certain second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is not continuous with other wastewater treatment stages corresponding to other second abnormal pollution sub-data, the certain second abnormal pollution sub-data is defined as an isolated second abnormal pollution sub-data.

[0011] If not, then based on the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence, a preset abnormal wastewater analysis strategy is used to perform a first abnormal analysis on each wastewater treatment stage to obtain the first abnormal analysis result.

[0012] Based on other abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set, the first abnormal analysis result is corrected using a preset result correction rule to obtain a second abnormal analysis result, and an early warning message containing the second abnormal analysis result is generated. The other abnormal pollution sub-data sequences are the abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set excluding the first and second abnormal pollution sub-data sequences.

[0013] Secondly, the present invention provides a wastewater treatment process monitoring system based on data identification, comprising:

[0014] The acquisition module is configured to acquire wastewater data at various collection times within a preset time period, wherein the wastewater data at a certain collection time includes wastewater sub-data at each wastewater treatment stage at that collection time.

[0015] The filtering module is configured to filter the pollution sub-data at each collection time according to the preset sewage data threshold of each sewage treatment stage, and sort at least one abnormal pollution sub-data at the same collection time according to the order of each sewage treatment stage to obtain a set of abnormal pollution sub-data sequences, wherein one abnormal pollution sub-data sequence corresponds to one collection time.

[0016] The first judgment module is configured to judge whether the first abnormal contaminated sub-data sequence and the second abnormal contaminated sub-data sequence are the same sequence, wherein the first abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the most abnormal contaminated sub-data in the abnormal contaminated sub-data sequence set, and the second abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the fewest abnormal contaminated sub-data in the abnormal contaminated sub-data sequence set.

[0017] The second judgment module is configured to determine whether the number of second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is greater than a preset number threshold if they are not the same sequence.

[0018] The third judgment module is configured to determine whether there is an isolated second abnormal pollution sub-data in the second abnormal pollution sub-data sequence if the number is greater than a preset threshold. Specifically, when a certain wastewater treatment stage corresponding to a certain second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is not continuous with other wastewater treatment stages corresponding to other second abnormal pollution sub-data, the certain second abnormal pollution sub-data is defined as an isolated second abnormal pollution sub-data.

[0019] The analysis module is configured to perform a first anomaly analysis on each wastewater treatment stage based on the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence, using a preset abnormal wastewater analysis strategy, and obtain the first anomaly analysis result if it does not exist.

[0020] The correction module is configured to correct the first anomaly analysis result based on other anomaly contaminated sub-data sequences in the set of anomaly contaminated sub-data sequences using a preset result correction rule, to obtain a second anomaly analysis result, and to generate a warning message containing the second anomaly analysis result, wherein the other anomaly contaminated sub-data sequences are the anomaly contaminated sub-data sequences in the set of anomaly contaminated sub-data sequences excluding the first anomaly contaminated sub-data sequence and the second anomaly contaminated sub-data sequence.

[0021] 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 wastewater treatment process monitoring method based on data identification according to any embodiment of the present invention.

[0022] 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 wastewater treatment process monitoring method based on data identification according to any embodiment of the present invention.

[0023] The wastewater treatment process monitoring method and system based on data identification of this application determines whether a first abnormal pollution sub-data sequence and a second abnormal pollution sub-data sequence are the same sequence. If they are not the same sequence, it determines whether the number of second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is greater than a preset number threshold. If it is greater than the preset number threshold, it determines whether there is an isolated second abnormal pollution sub-data in the second abnormal pollution sub-data sequence. If not, it performs a first abnormal analysis on each wastewater treatment stage based on the first and second abnormal pollution sub-data sequences using a preset abnormal wastewater analysis strategy to obtain a first abnormal analysis result. Based on other abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set, it corrects the first abnormal analysis result using a preset result correction rule to obtain a second abnormal analysis result and generates an early warning message containing the second abnormal analysis result. This method can identify situations where wastewater treatment has reached its limit, thereby more accurately determining the wastewater treatment stage where equipment malfunctions, facilitating rapid location and maintenance by subsequent staff. Attached Figure Description

[0024] 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.

[0025] Figure 1 A flowchart illustrating a wastewater treatment process monitoring method based on data identification, provided in an embodiment of the present invention;

[0026] Figure 2 A structural block diagram of a wastewater treatment process monitoring system based on data recognition is provided in one embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0028] 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.

[0029] Please see Figure 1The diagram shows a flowchart of a wastewater treatment process monitoring method based on data identification, as described in this application.

[0030] like Figure 1 As shown, the wastewater treatment process monitoring method based on data identification specifically includes the following steps:

[0031] Step S101: Obtain wastewater data at each collection time within a preset time period, wherein the wastewater data at a certain collection time includes wastewater sub-data at each wastewater treatment stage at that collection time.

[0032] In this step, the system automatically calculates the usage time of the load devices and prioritizes starting the device with the shortest usage time each time it is started. Furthermore, the number of load devices is appropriately selected based on the actual liquid level. Finally, wastewater data is acquired at each collection point within a preset time period.

[0033] Step S102: Based on the preset wastewater data thresholds for each wastewater treatment stage, the pollution sub-data at each collection time is filtered, and at least one abnormal pollution sub-data at the same collection time is sorted according to the order of each wastewater treatment stage to obtain a set of abnormal pollution sub-data sequences, wherein one abnormal pollution sub-data sequence corresponds to one collection time.

[0034] In this step, a preset wastewater data threshold is set for each wastewater treatment stage; a pollution sub-data corresponding to a certain wastewater treatment stage at a certain moment is obtained, and it is determined whether the pollution sub-data is greater than a preset wastewater data threshold, wherein the preset wastewater data threshold is the preset wastewater data threshold corresponding to the certain wastewater treatment stage; if it is not greater than the preset wastewater data threshold, the pollution sub-data is defined as normal; otherwise, the pollution sub-data is defined as abnormal pollution sub-data; the defined abnormal pollution sub-data are sorted according to the order of each wastewater treatment stage to obtain a set of abnormal pollution sub-data sequences.

[0035] Step S103: Determine whether the first abnormal contamination sub-data sequence and the second abnormal contamination sub-data sequence are the same sequence.

[0036] In this step, the first abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the largest number of abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences, and the second abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the smallest number of abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences.

[0037] In one specific embodiment, after determining whether the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence are the same sequence, if they are the same sequence, then a first abnormal analysis is performed on each wastewater treatment stage according to the set of abnormal pollution sub-data sequences using a preset abnormal wastewater analysis strategy, to obtain the first abnormal analysis result, and a warning message containing the first abnormal analysis result is directly generated.

[0038] Step S104: If they are not the same sequence, determine whether the number of second abnormal polluting sub-data in the second abnormal polluting sub-data sequence is greater than a preset number threshold.

[0039] In one specific embodiment, after determining whether the number of second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is greater than a preset number threshold, if it is not greater than the preset number threshold, the sewage treatment stage corresponding to the second abnormal pollution sub-data in the second abnormal pollution sub-data is defined as an abnormal sewage treatment stage, and an early warning information containing the abnormal sewage treatment stage is generated.

[0040] Step S105: If the number exceeds a preset threshold, determine whether there is an isolated second abnormal pollutant sub-data in the second abnormal pollutant sub-data sequence.

[0041] In this step, when a certain wastewater treatment stage corresponding to a certain second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is not continuous with other wastewater treatment stages corresponding to other second abnormal pollution sub-data, the certain second abnormal pollution sub-data is defined as an isolated second abnormal pollution sub-data.

[0042] In one specific embodiment, after determining whether there is an isolated second abnormal pollution sub-data in the second abnormal pollution sub-data sequence, if there is, the normal sewage treatment stage is directly determined based on the isolated second abnormal pollution sub-data, and a preset abnormal sewage analysis strategy is used to perform a first abnormal analysis on other sewage treatment stages to obtain a first abnormal analysis result, and a warning message containing the first abnormal analysis result is directly generated.

[0043] Step S106: If it does not exist, then based on the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence, a preset abnormal wastewater analysis strategy is used to perform a first abnormal analysis on each wastewater treatment stage to obtain the first abnormal analysis result.

[0044] In this step, a first set of anomalous stages is extracted from the first anomalous pollution sub-data sequence, wherein the first set of anomalous stages contains the wastewater treatment stages corresponding to each anomalous pollution sub-data in the first anomalous pollution sub-data sequence; a second set of anomalous stages is extracted from the second anomalous pollution sub-data sequence, wherein the second set of anomalous stages contains the wastewater treatment stages corresponding to each anomalous pollution sub-data in the second anomalous pollution sub-data sequence; the intersection of the first set of anomalous stages and the second set of anomalous stages is calculated to obtain a common set of anomalous stages; the union of the first set of anomalous stages and the second set of anomalous stages is calculated to obtain a complete set of anomalous stages; the wastewater treatment stages in the common set of anomalous stages are identified as anomalous wastewater treatment stages, and the wastewater treatment stages in the complete set of anomalous stages other than the common set of anomalous stages are identified as potentially anomalous wastewater treatment stages; based on the anomalous wastewater treatment stages and the potentially anomalous wastewater treatment stages, a first anomaly analysis result is generated.

[0045] In this embodiment, all wastewater treatment stages where anomalies occurred are first extracted from the first abnormal pollution sub-data sequence (i.e., the sequence with the most abnormal data), forming the first abnormal stage set. This set represents all potentially affected links in the entire treatment process at the moment when the problem is most severe.

[0046] Simultaneously, the system extracts all wastewater treatment stages exhibiting anomalies from the second abnormal pollution sub-data sequence (i.e., the sequence with the fewest abnormal data points), forming the second abnormal stage set. This set represents the most persistent anomalies that persist even when the problem is relatively minor.

[0047] Calculating the intersection of the two sets yields a common set of abnormal stages. The wastewater treatment stages in this set exhibited anomalies at both the most severe and mildest stages, indicating that they are the core abnormal links with the highest persistence and strongest correlation in the problem.

[0048] Next, the system calculates the union of the two sets to obtain the complete set of abnormal stages. This set encompasses all stages where anomalies occurred under extreme conditions, providing a global perspective on the scope of the problem's impact.

[0049] The system explicitly identifies all stages in the common anomaly stage set as "abnormal wastewater treatment stages." These stages are high-confidence anomaly sources in the analysis conclusions.

[0050] For the set of all abnormal stages, the remaining parts after removing the common abnormal stages mentioned above are classified by the system as "questionable abnormal wastewater treatment stages". These stages may only be affected intermittently or occasionally or generate false alarms, and their anomaly confidence is relatively low.

[0051] Finally, by combining information from both the "abnormal wastewater treatment stage" and the "questionable abnormal wastewater treatment stage," the first anomaly analysis result was generated. This result not only identified confirmed anomalies but also highlighted potential risks requiring further attention, providing a clear priority for subsequent decision-making.

[0052] By comprehensively comparing and analyzing the two extreme sequences with the most and least abnormal data, and using set operations to accurately extract their common and all abnormal stages, intelligent locking and classification of core abnormal links are achieved. Ultimately, this method achieves significant benefits in improving the accuracy of abnormal early warning, optimizing the allocation of operation and maintenance resources, and enhancing the robustness of system decision-making. Specifically, this method can effectively filter transient noise interference, significantly improve the accuracy of localization by identifying common abnormal stages that appear stably under different severity levels, provide clear guidance for processing priorities by classifying "abnormal" and "suspected" levels, and reveal the potential propagation path of abnormalities in the process flow by analyzing the union of abnormal stages.

[0053] Step S107: Based on other abnormal contamination sub-data sequences in the abnormal contamination sub-data sequence set, the first abnormal analysis result is corrected using a preset result correction rule to obtain a second abnormal analysis result, and an early warning message containing the second abnormal analysis result is generated. The other abnormal contamination sub-data sequences are the abnormal contamination sub-data sequences in the abnormal contamination sub-data sequence set excluding the first abnormal contamination sub-data sequence and the second abnormal contamination sub-data sequence.

[0054] In this step, the abnormal wastewater treatment stages and suspected abnormal wastewater treatment stages in the first anomaly analysis results are obtained. For each abnormal wastewater treatment stage, a certain frequency of occurrence of the abnormal wastewater treatment stage in the other abnormal pollution sub-data sequences is calculated. If the certain frequency of occurrence is greater than or equal to a first preset frequency threshold, the abnormal wastewater treatment stage is retained as the final target abnormal wastewater treatment stage; otherwise, the abnormal wastewater treatment stage is downgraded to a suspected abnormal wastewater treatment stage. For each suspected abnormal wastewater treatment stage, the frequency of occurrence of the suspected abnormal wastewater treatment stage in the other abnormal pollution sub-data sequences is calculated. If the frequency of occurrence is greater than or equal to a second preset frequency threshold, the suspected abnormal wastewater treatment stage is upgraded to a target abnormal wastewater treatment stage; otherwise, the suspected abnormal wastewater treatment stage is removed from the abnormal stages. Based on all target abnormal wastewater treatment stages, a second anomaly analysis result is generated.

[0055] In this embodiment, the first anomaly analysis result generated in step S106 is read. This result contains two key lists: a high-confidence "abnormal wastewater treatment stage" and a low-confidence "questionable abnormal wastewater treatment stage".

[0056] Next, a two-stage frequency verification and dynamic correction process begins:

[0057] Confirmatory verification of "abnormal wastewater treatment stages": The system iterates through each stage that has been initially identified as "abnormal" and calculates its frequency of occurrence in "other abnormal pollution sub-data sequences" (i.e., how many remaining sequences also show this stage as abnormal). This frequency is compared with a higher first preset frequency threshold (e.g., 80%).

[0058] If the frequency meets the standard (≥ the first threshold): it indicates that the abnormal stage has continued to appear in most time series, verifying the stability and severity of the anomaly, and therefore it is officially confirmed as the "target abnormal wastewater treatment stage".

[0059] If the frequency does not meet the standard (< the first threshold): This indicates that although this stage shows abnormalities in extreme sequences, it is not a common phenomenon and may be sporadic. Therefore, the system will downgrade it from the "abnormal" category to the "questionable" category for further observation.

[0060] Discovery verification of “questionable abnormal wastewater treatment stage”: Similarly, traverse each “questionable” stage, calculate its frequency of occurrence in “other sequences”, and compare it with a relatively low second preset frequency threshold (e.g., 50%).

[0061] If the frequency meets the standard (≥ the second threshold): this indicates that the suspicious stage occurs frequently in the remaining sequence, and its anomaly is somewhat common and should not be ignored. Therefore, it is upgraded to "target anomaly wastewater treatment stage".

[0062] If the frequency does not meet the standard (< the second threshold): it indicates that the abnormal phenomenon in this stage is relatively rare, and it is likely to be a false alarm or instantaneous fluctuation at a particular moment. The system will then decisively remove it from the list of abnormal stages to avoid interfering with the final judgment.

[0063] Finally, all the "target abnormal wastewater treatment stages" determined after the above verification and correction are summarized to generate the final second abnormality analysis results, and based on this, accurate early warning information is generated to directly guide the operation and maintenance personnel to carry out targeted handling.

[0064] By introducing a dynamic correction mechanism based on frequency thresholds, a one-time preliminary judgment based on extreme scenarios is transformed into a highly reliable final conclusion verified by data throughout the entire time period. This significantly improves the anti-interference capability, statistical significance, and practical operational guidance value of the anomaly diagnosis results, effectively avoiding misjudgments and omissions caused by occasional noise or data fluctuations, ensuring accurate and reliable early warning information, and ultimately driving the operation and maintenance management of the sewage treatment process to shift from passive response to proactive, precise, and intelligent decision-making.

[0065] In summary, the method of this application determines whether the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence are the same sequence. If they are not the same sequence, it determines whether the number of second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is greater than a preset number threshold. If it is greater than the preset number threshold, it determines whether there is an isolated second abnormal pollution sub-data in the second abnormal pollution sub-data sequence. If not, it performs a first abnormal analysis on each sewage treatment stage based on the first and second abnormal pollution sub-data sequences using a preset abnormal sewage analysis strategy to obtain a first abnormal analysis result. Based on other abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set, it corrects the first abnormal analysis result using a preset result correction rule to obtain a second abnormal analysis result and generates an early warning message containing the second abnormal analysis result. This method can identify situations where sewage treatment has reached its limit, thereby more accurately determining the sewage treatment stage where equipment malfunctions, facilitating rapid location and maintenance by subsequent staff.

[0066] Please see Figure 2 The diagram shows a structural block diagram of a wastewater treatment process monitoring system based on data identification, according to this application.

[0067] like Figure 2 As shown, the wastewater treatment process monitoring system 200 includes an acquisition module 210, a screening module 220, a first judgment module 230, a second judgment module 240, a third judgment module 250, an analysis module 260, and a correction module 270.

[0068] The acquisition module 210 is configured to acquire wastewater data at various collection times within a preset time period, wherein the wastewater data at a certain collection time includes wastewater sub-data of each wastewater treatment stage at that collection time; the filtering module 220 is configured to filter the pollution sub-data at each collection time according to a preset wastewater data threshold for each wastewater treatment stage, and sort at least one abnormal pollution sub-data at the same collection time according to the chronological order of each wastewater treatment stage to obtain a set of abnormal pollution sub-data sequences, wherein one abnormal pollution sub-data sequence corresponds to one collection time; the first judgment module 230 is configured to determine whether the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence are the same sequence, wherein the first abnormal pollution sub-data sequence is the abnormal pollution sub-data sequence with the most abnormal pollution sub-data in the set of abnormal pollution sub-data sequences, and the second abnormal pollution sub-data sequence is the abnormal pollution sub-data sequence with the fewest abnormal pollution sub-data in the set of abnormal pollution sub-data sequences; the second judgment module 240 is configured to determine whether the number of second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is greater than a preset number if they are not the same sequence. The threshold; the third judgment module 250 is configured to determine whether there is an isolated second abnormal pollution sub-data in the second abnormal pollution sub-data sequence if the threshold is greater than a preset number threshold. Specifically, when a wastewater treatment stage corresponding to a certain second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is not continuous with other wastewater treatment stages corresponding to other second abnormal pollution sub-data, the certain second abnormal pollution sub-data is defined as an isolated second abnormal pollution sub-data. The analysis module 260 is configured to perform a first abnormal analysis on each wastewater treatment stage according to the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence using a preset abnormal wastewater analysis strategy, and obtain a first abnormal analysis result. The correction module 270 is configured to correct the first abnormal analysis result according to other abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set using a preset result correction rule, obtain a second abnormal analysis result, and generate a warning message containing the second abnormal analysis result. The other abnormal pollution sub-data sequences are the abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set excluding the first and second abnormal pollution sub-data sequences.

[0069] It should be understood that Figure 1 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 1 The various modules in the document will not be described in detail here.

[0070] 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 wastewater treatment process monitoring method based on data identification in any of the above method embodiments.

[0071] In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows:

[0072] Acquire wastewater data at various collection times within a preset time period, wherein the wastewater data at a certain collection time includes wastewater sub-data at each wastewater treatment stage at that collection time.

[0073] Based on the preset wastewater data thresholds for each wastewater treatment stage, the pollution sub-data at each collection time is filtered, and at least one abnormal pollution sub-data at the same collection time is sorted according to the order of each wastewater treatment stage to obtain a set of abnormal pollution sub-data sequences, wherein one abnormal pollution sub-data sequence corresponds to one collection time.

[0074] Determine whether the first abnormal contaminated sub-data sequence and the second abnormal contaminated sub-data sequence are the same sequence, wherein the first abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the most abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences, and the second abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the fewest abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences;

[0075] If they are not the same sequence, then determine whether the number of second abnormal polluting sub-data in the second abnormal polluting sub-data sequence is greater than a preset number threshold.

[0076] If the number exceeds a preset threshold, it is determined whether there is an isolated second abnormal pollution sub-data in the second abnormal pollution sub-data sequence. When a certain wastewater treatment stage corresponding to a certain second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is not continuous with other wastewater treatment stages corresponding to other second abnormal pollution sub-data, the certain second abnormal pollution sub-data is defined as an isolated second abnormal pollution sub-data.

[0077] If not, then based on the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence, a preset abnormal wastewater analysis strategy is used to perform a first abnormal analysis on each wastewater treatment stage to obtain the first abnormal analysis result.

[0078] Based on other abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set, the first abnormal analysis result is corrected using a preset result correction rule to obtain a second abnormal analysis result, and an early warning message containing the second abnormal analysis result is generated. The other abnormal pollution sub-data sequences are the abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set excluding the first and second abnormal pollution sub-data sequences.

[0079] 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 identification-based wastewater treatment process monitoring system, etc. 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 identification-based wastewater treatment process monitoring system 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.

[0080] 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 3 Taking 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 wastewater treatment process monitoring method based on data recognition 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 wastewater treatment process monitoring system based on data recognition. The output device 340 may include a display screen or other display device.

[0081] 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.

[0082] In one implementation, the above-described electronic device is applied to a wastewater treatment process monitoring system based on data identification, for a client, and 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, the instructions being executed by the at least one processor to enable the at least one processor to:

[0083] Acquire wastewater data at various collection times within a preset time period, wherein the wastewater data at a certain collection time includes wastewater sub-data at each wastewater treatment stage at that collection time.

[0084] Based on the preset wastewater data thresholds for each wastewater treatment stage, the pollution sub-data at each collection time is filtered, and at least one abnormal pollution sub-data at the same collection time is sorted according to the order of each wastewater treatment stage to obtain a set of abnormal pollution sub-data sequences, wherein one abnormal pollution sub-data sequence corresponds to one collection time.

[0085] Determine whether the first abnormal contaminated sub-data sequence and the second abnormal contaminated sub-data sequence are the same sequence, wherein the first abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the most abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences, and the second abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the fewest abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences;

[0086] If they are not the same sequence, then determine whether the number of second abnormal polluting sub-data in the second abnormal polluting sub-data sequence is greater than a preset number threshold.

[0087] If the number exceeds a preset threshold, it is determined whether there is an isolated second abnormal pollution sub-data in the second abnormal pollution sub-data sequence. When a certain wastewater treatment stage corresponding to a certain second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is not continuous with other wastewater treatment stages corresponding to other second abnormal pollution sub-data, the certain second abnormal pollution sub-data is defined as an isolated second abnormal pollution sub-data.

[0088] If not, then based on the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence, a preset abnormal wastewater analysis strategy is used to perform a first abnormal analysis on each wastewater treatment stage to obtain the first abnormal analysis result.

[0089] Based on other abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set, the first abnormal analysis result is corrected using a preset result correction rule to obtain a second abnormal analysis result, and an early warning message containing the second abnormal analysis result is generated. The other abnormal pollution sub-data sequences are the abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set excluding the first and second abnormal pollution sub-data sequences.

[0090] 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.

[0091] 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 wastewater treatment process monitoring method based on data identification, characterized in that, include: Acquire wastewater data at various collection times within a preset time period, wherein the wastewater data at a certain collection time includes wastewater sub-data at each wastewater treatment stage at that collection time. Pollution sub-data at each collection time is filtered according to preset wastewater data thresholds for each wastewater treatment stage, and at least one abnormal pollution sub-data at the same collection time is sorted according to the chronological order of each wastewater treatment stage to obtain a set of abnormal pollution sub-data sequences. Each abnormal pollution sub-data sequence corresponds to one collection time. The process of filtering pollution sub-data at each collection time according to preset wastewater data thresholds for each wastewater treatment stage and sorting at least one abnormal pollution sub-data at the same collection time according to the chronological order of each wastewater treatment stage to obtain the set of abnormal pollution sub-data sequences includes: Set preset wastewater data thresholds for each wastewater treatment stage; Obtain a pollution sub-data point at a certain moment corresponding to a certain wastewater treatment stage, and determine whether the pollution sub-data point is greater than a certain preset wastewater data threshold, wherein the certain preset wastewater data threshold is a preset wastewater data threshold corresponding to the certain wastewater treatment stage; If the value is not greater than a certain preset wastewater data threshold, then a certain pollution sub-data is defined as normal; otherwise, a certain pollution sub-data is defined as abnormal pollution sub-data. Based on the sequential order of each wastewater treatment stage, the defined abnormal pollution sub-data are sorted to obtain a set of abnormal pollution sub-data sequences. Determine whether the first abnormal contaminated sub-data sequence and the second abnormal contaminated sub-data sequence are the same sequence, wherein the first abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the most abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences, and the second abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the fewest abnormal contaminated sub-data in the set of abnormal contaminated sub-data sequences; If they are not the same sequence, then determine whether the number of second abnormal polluting sub-data in the second abnormal polluting sub-data sequence is greater than a preset number threshold. If the number exceeds a preset threshold, then determine whether there is an isolated second abnormal pollutant sub-data in the second abnormal pollutant sub-data sequence; If not, then based on the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence, a preset abnormal wastewater analysis strategy is used to perform a first abnormal analysis on each wastewater treatment stage to obtain the first abnormal analysis result. Based on other abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set, the first abnormal analysis result is corrected using a preset result correction rule to obtain a second abnormal analysis result, and an early warning message containing the second abnormal analysis result is generated. The other abnormal pollution sub-data sequences are the abnormal pollution sub-data sequences in the abnormal pollution sub-data sequence set excluding the first and second abnormal pollution sub-data sequences.

2. The wastewater treatment process monitoring method based on data identification according to claim 1, characterized in that, After determining whether the first abnormal contaminated sub-data sequence and the second abnormal contaminated sub-data sequence are the same sequence, the method further includes: If they are the same sequence, then a first anomaly analysis is performed on each wastewater treatment stage according to the set of abnormal pollution sub-data sequences using a preset abnormal wastewater analysis strategy, to obtain the first anomaly analysis result, and a warning message containing the first anomaly analysis result is directly generated.

3. The wastewater treatment process monitoring method based on data identification according to claim 1, characterized in that, After determining whether the number of second abnormal contaminated sub-data in the second abnormal contaminated sub-data sequence is greater than a preset number threshold, the method further includes: If the number is not greater than a preset threshold, the wastewater treatment stage corresponding to the second abnormal pollution sub-data in the second abnormal pollution sub-data is defined as an abnormal wastewater treatment stage, and an early warning message containing the abnormal wastewater treatment stage is generated.

4. The wastewater treatment process monitoring method based on data identification according to claim 1, characterized in that, in, When a wastewater treatment stage corresponding to a certain second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is not continuous with other wastewater treatment stages corresponding to other second abnormal pollution sub-data, the certain second abnormal pollution sub-data is defined as an isolated second abnormal pollution sub-data. After determining whether an isolated second anomalous contamination sub-data segment exists in the second anomalous contamination sub-data sequence, the method further includes: If present, the normal wastewater treatment stage is directly determined based on the isolated second abnormal pollution sub-data, and a preset abnormal wastewater analysis strategy is used to perform a first abnormal analysis on other wastewater treatment stages to obtain the first abnormal analysis result, and a warning message containing the first abnormal analysis result is directly generated.

5. The wastewater treatment process monitoring method based on data identification according to claim 1, characterized in that, The step of performing a first anomaly analysis on each wastewater treatment stage based on the first and second abnormal pollution sub-data sequences using a preset abnormal wastewater analysis strategy, and obtaining the first anomaly analysis results includes: Extract a first set of abnormal stages from the first abnormal pollution sub-data sequence, wherein the first set of abnormal stages includes the wastewater treatment stage corresponding to each abnormal pollution sub-data in the first abnormal pollution sub-data sequence; Extract a second set of abnormal stages from the second abnormal pollution sub-data sequence, wherein the second set of abnormal stages contains the wastewater treatment stage corresponding to each abnormal pollution sub-data in the second abnormal pollution sub-data sequence; Calculate the intersection of the first abnormal stage set and the second abnormal stage set to obtain the common abnormal stage set; Calculate the union of the first abnormal stage set and the second abnormal stage set to obtain the complete abnormal stage set; The wastewater treatment stages in the common abnormal stage set are identified as abnormal wastewater treatment stages, and the wastewater treatment stages in the full abnormal stage set other than the common abnormal stage set are identified as suspected abnormal wastewater treatment stages. Based on the abnormal wastewater treatment stage and the suspected abnormal wastewater treatment stage, a first anomaly analysis result is generated.

6. The wastewater treatment process monitoring method based on data identification according to claim 1, characterized in that, The step of correcting the first anomaly analysis result based on other anomaly contamination sub-data sequences in the set of anomaly contamination sub-data sequences, using a preset result correction rule, to obtain the second anomaly analysis result includes: Obtain the abnormal wastewater treatment stage and the suspected abnormal wastewater treatment stage from the first anomaly analysis results; For each abnormal wastewater treatment stage, calculate the frequency of occurrence of a certain abnormal wastewater treatment stage in the other abnormal pollution sub-data sequences. If the frequency of occurrence is greater than or equal to a first preset frequency threshold, then retain the certain abnormal wastewater treatment stage as the final target abnormal wastewater treatment stage; otherwise, downgrade the certain abnormal wastewater treatment stage to a questionable abnormal wastewater treatment stage. For each suspected abnormal wastewater treatment stage, the frequency of occurrence of a suspected abnormal wastewater treatment stage in the other abnormal pollution sub-data sequences is calculated. If the frequency of occurrence is greater than or equal to a second preset frequency threshold, the suspected abnormal wastewater treatment stage is upgraded to a target abnormal wastewater treatment stage; otherwise, the suspected abnormal wastewater treatment stage is removed from the abnormal stages. Based on all the target abnormal wastewater treatment stages, a second abnormality analysis result is generated.

7. A wastewater treatment process monitoring system based on data recognition, characterized in that, include: The acquisition module is configured to acquire wastewater data at various collection times within a preset time period, wherein the wastewater data at a certain collection time includes wastewater sub-data at each wastewater treatment stage at that collection time. The filtering module is configured to filter pollution sub-data at each collection time according to preset wastewater data thresholds for each wastewater treatment stage, and sort at least one abnormal pollution sub-data at the same collection time according to the chronological order of each wastewater treatment stage to obtain a set of abnormal pollution sub-data sequences. Each abnormal pollution sub-data sequence corresponds to one collection time. The steps of filtering pollution sub-data at each collection time according to preset wastewater data thresholds for each wastewater treatment stage and sorting at least one abnormal pollution sub-data at the same collection time according to the chronological order of each wastewater treatment stage to obtain the set of abnormal pollution sub-data sequences include: Set preset wastewater data thresholds for each wastewater treatment stage; Obtain a pollution sub-data point at a certain moment corresponding to a certain wastewater treatment stage, and determine whether the pollution sub-data point is greater than a certain preset wastewater data threshold, wherein the certain preset wastewater data threshold is a preset wastewater data threshold corresponding to the certain wastewater treatment stage; If the value is not greater than a certain preset wastewater data threshold, then a certain pollution sub-data is defined as normal; otherwise, a certain pollution sub-data is defined as abnormal pollution sub-data. Based on the sequential order of each wastewater treatment stage, the defined abnormal pollution sub-data are sorted to obtain a set of abnormal pollution sub-data sequences. The first judgment module is configured to judge whether the first abnormal contaminated sub-data sequence and the second abnormal contaminated sub-data sequence are the same sequence, wherein the first abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the most abnormal contaminated sub-data in the abnormal contaminated sub-data sequence set, and the second abnormal contaminated sub-data sequence is the abnormal contaminated sub-data sequence with the fewest abnormal contaminated sub-data in the abnormal contaminated sub-data sequence set. The second judgment module is configured to determine whether the number of second abnormal pollution sub-data in the second abnormal pollution sub-data sequence is greater than a preset number threshold if they are not the same sequence. The third judgment module is configured to determine whether there is an isolated second abnormal pollution sub-data in the second abnormal pollution sub-data sequence if the number is greater than a preset threshold. The analysis module is configured to perform a first anomaly analysis on each wastewater treatment stage based on the first abnormal pollution sub-data sequence and the second abnormal pollution sub-data sequence, using a preset abnormal wastewater analysis strategy, and obtain the first anomaly analysis result if it does not exist. The correction module is configured to correct the first anomaly analysis result based on other anomaly contaminated sub-data sequences in the set of anomaly contaminated sub-data sequences using a preset result correction rule, to obtain a second anomaly analysis result, and to generate a warning message containing the second anomaly analysis result, wherein the other anomaly contaminated sub-data sequences are the anomaly contaminated sub-data sequences in the set of anomaly contaminated sub-data sequences excluding the first anomaly contaminated sub-data sequence and the second anomaly contaminated sub-data sequence.

8. An electronic device, characterized in that, include: 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 to enable the at least one processor to perform the method according to any one of claims 1 to 6.

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

Images