Sewage treatment equipment remote control system based on operation data statistics

Abstract

The invention discloses a sewage treatment equipment remote control system based on operation data statistics, and relates to the technical field of sewage treatment equipment management, and the system comprises a sewage treatment equipment operation data collection module which collects the operation parameters of sewage treatment equipment in real time; the state evaluation module is used for extracting abnormal factors, establishing a state evaluation model and judging whether operation abnormity exists or not based on output of the state evaluation model; the anomaly analysis module is used for carrying out anomaly reason analysis on the real-time operation data of the equipment based on the trained anomaly analysis model and proposing an optimal equipment repair suggestion scheme; and the remote control module is used for performing remote control on the equipment based on the equipment operation data and the health state. Through real-time data acquisition and anomaly analysis, fault early warning and repair suggestions are provided, the fault rate is reduced, the management efficiency is improved through remote control, the inspection requirements are reduced through automatic operation, the labor cost is saved, the service life of equipment is prolonged, stable operation of the equipment is ensured, and the maintenance cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sewage treatment equipment management, and particularly relates to a sewage treatment equipment remote control system based on operation data statistics. BACKGROUND

[0002] With the development of social economy, the sewage treatment industry is facing increasingly severe challenges, especially in equipment management, the operation state and efficiency of sewage treatment equipment directly affect water purification effect and environmental protection, therefore, real-time monitoring and intelligent management of sewage treatment equipment, especially using data analysis technology for fault detection and early warning, has become an important means to improve sewage treatment efficiency, reduce maintenance cost and prolong equipment service life.

[0003] Traditional sewage treatment equipment management mainly relies on manual inspection and manual recording, and there are problems such as equipment failure cannot be found in time, equipment damage caused by repair not in time, etc., with the development of Internet of Things, sensors, artificial intelligence and other technologies, remote monitoring and fault prediction combined with equipment operation data have become an important method to improve management efficiency and equipment health management. SUMMARY

[0004] To solve the above technical problems, a sewage treatment equipment remote control system based on operation data statistics is provided, which solves the above problems.

[0005] To achieve the above purposes, the technical scheme adopted by the present application is:

[0006] A sewage treatment equipment remote control system based on operation data statistics, comprising:

[0007] A sewage treatment equipment operation data acquisition module is used to acquire the operation parameters of the sewage treatment equipment in real time, extract statistical features and time sequence features, generate statistical information of the equipment operation state, and transmit the data to the fault detection module;

[0008] A state evaluation module is used to extract abnormal factors according to the data output by the fault detection module, establish a state evaluation model based on the abnormal factors, judge whether there is an operation abnormality based on the output of the state evaluation model, and if there is an abnormality, transmit the equipment state to the abnormality analysis module;

[0009] An abnormality analysis module is used to analyze the abnormal reasons of the real-time operation data of the equipment based on the trained abnormality analysis model, obtain abnormal reason data, quantify the abnormal reason data, obtain the score of each abnormal reason, establish a repair suggestion model based on the score of each abnormal reason, and propose an optimal equipment repair suggestion scheme based on the output of the repair suggestion model;

[0010] Remote control module: based on the device operation data and health status, the remote control of the device is carried out, including starting, stopping and adjusting, and the remote monitoring and operation of the sewage treatment device are carried out.

[0011] Preferably, the sewage treatment device operation data acquisition module specifically comprises:

[0012] Device operation parameter unit: based on the sensors in the sewage treatment device, the parameters of the device operation are obtained in real time, the frequency of collecting parameters is set to 1 time per second, the mobile average filtering algorithm is used to remove sensor noise, the values of different sensors are uniformly converted into standard dimensions and units, a time stamp is added to each collected data point, the data is arranged in time sequence, and the missing data is filled in through interpolation method;

[0013] Statistical feature and time sequence feature extraction unit: statistical analysis is carried out on real-time data to obtain mean, standard deviation, maximum value and minimum value, and analysis is carried out on the time sequence of data to extract trend, periodicity and mutation point time sequence features;

[0014] Device operation state statistical information generation unit: linear regression method is used to extract the trend of device data changing with time, wavelet transform is used to analyze the periodic change in data, change point detection algorithm is used to identify the mutation point in data, local statistical features such as mean, standard deviation, kurtosis and skewness are extracted in each time window to help analyze the local fluctuation of the device, and the collected real-time data is aggregated according to hours.

[0015] Preferably, the state evaluation module specifically comprises:

[0016] Abnormal factor extraction unit: abnormal factors in the device operation state statistical information generation unit are extracted, including temperature fluctuation abnormal factor, flow deviation abnormal factor, pressure fluctuation abnormal factor and device vibration abnormal factor;

[0017] State evaluation model establishment unit: the extracted abnormal factors are input, a state judgment model is established based on the abnormal factors, whether there is an operation abnormality is judged according to the output of the model, the state evaluation model is trained using historical data, whether the current state of the device belongs to the normal range is evaluated based on the trained model, the threshold value is set according to the historical data, if the result output by the state evaluation model exceeds the threshold value, it is determined that the state is abnormal, and if the state is abnormal, the state information of the device is transmitted to the abnormality analysis module.

[0018] Preferably, the state evaluation model establishment unit specifically comprises:

[0019] Based on the formula of weighted sum, a state evaluation model is established, the Pearson correlation coefficient method is used to evaluate the relationship strength between abnormal factors and abnormal state of the equipment, the correlation coefficients are used as the weights of the factors, and whether the equipment is in an abnormal state is judged by inputting the abnormal factors and the weights of the factors.

[0020] Preferably, the abnormality analysis module specifically comprises:

[0021] The abnormal reason analysis unit analyzes the real-time operation data of the equipment based on the trained abnormality analysis model, inputs the abnormal factor data under the abnormal state of the equipment at the current time, and identifies the reasons that may cause the equipment to be abnormal.

[0022] The abnormal reason scoring unit quantitatively processes the abnormal reasons obtained by analysis, scores each abnormal reason according to the operation state of the equipment, the detected abnormal factors and the historical data related to these factors, and outputs the abnormal reason scoring unit.

[0023] The repair suggestion model establishment unit constructs a repair suggestion model based on the score of each abnormal reason, automatically generates a repair suggestion for the equipment in combination with historical data and failure modes of the equipment, and calculates the priority of the repair suggestion according to the severity score of each abnormality.

[0024] The repair suggestion output unit obtains the priority of the repair suggestion based on the output of the repair suggestion model, and generates an optimal equipment repair suggestion scheme.

[0025] Preferably, the abnormal reason analysis unit specifically comprises:

[0026] Based on the correlation importance score, the key factors closely related to the abnormality of the equipment are screened out, the cosine similarity is obtained by comparing the current abnormal factors with the historical abnormal mode library, the two modes with the highest similarity are found out as candidates, whether the current abnormality belongs to a known category is judged by a clustering algorithm, and if it is a new category, it is marked as a new type of abnormality.

[0027] The Bayesian network is constructed, the probability of each potential reason causing the abnormality is obtained according to the historical failure frequency and the current abnormal data, and the causal relationship between variables is judged by Granger causality test for abnormal factors with time sequence characteristics.

[0028] Based on the weighted score, the similarity of the abnormal mode matching, the Bayesian probability and the weight of the fault propagation path are integrated to obtain the comprehensive score of each potential reason, and the final analysis result is output as the most likely reason in order of high to low score.

[0029] Preferably, the abnormal reason scoring unit specifically comprises:

[0030] Based on the device running state and the historical data of abnormal factors, key indicators affecting abnormal reasons are screened out, a score level is set for each scoring indicator, and the weight of each scoring indicator is obtained by using the analytic hierarchy process;

[0031] According to the current device running state and the detected abnormal factor data, each indicator of each abnormal reason is scored by comparing with the score level standard of each indicator;

[0032] Each indicator score of each abnormal reason is multiplied by the corresponding weight and then added to obtain the comprehensive score of the abnormal reason.

[0033] Preferably, the repair suggestion model establishment unit specifically comprises:

[0034] In combination with the abnormal reason score, the repair scheme is prioritized, wherein the priority calculation formula is:

[0035]

[0036] In the formula, P J is the priority of the Jth repair scheme, S is the comprehensive score of the abnormal reason, alpha is the weight of the comprehensive score of the abnormal reason, C J is the repair cost of the Jth repair scheme, T J is the estimated repair time of the Jth repair scheme.

[0037] Preferably, the output based on the repair suggestion model obtains the priority of the repair suggestion and generates an optimal device repair suggestion scheme specifically comprises: according to the priority value of each repair scheme given by the repair suggestion model, selecting the top n repair schemes with high priority from all schemes, arranging these schemes into a candidate scheme set, evaluating each repair scheme in the candidate scheme set from three important dimensions of repair cost, required repair time and repair effect, scoring each scheme with a comprehensive evaluation score, finding the scheme with the highest score from the comprehensive evaluation scores of all schemes in the candidate scheme set, and determining the scheme as the optimal device repair suggestion scheme.

[0038] Preferably, the remote control module specifically comprises: judging the operation required by the device according to the current running data and health state information of the sewage treatment device, and then generating corresponding start, stop and adjustment instructions, sending the generated control instructions to the device end based on the communication protocol, and receiving the feedback information returned by the device end.

[0039] Compared with the prior art, the beneficial effects of the present application are:

[0040] The present application provides accurate fault early warning and repair suggestions by real-time data acquisition, state evaluation and abnormality analysis, can identify device abnormalities in advance and reduce failure rate, remote control module improves device management efficiency, reduces manual intervention, improves management accuracy, prolongs device service life and reduces maintenance cost by repairing device abnormalities in time, ensures long-term stable operation of the device, reduces the need for manual inspection and manual operation through automated data acquisition, state evaluation, fault detection and analysis, reduces labor cost, and can focus on key issues, improves the accuracy and efficiency of device management. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 The system framework diagram of the present application is shown in the figure;

[0042] Figure 2 The internal system framework diagram of the sewage treatment equipment operation data acquisition module in the present application is shown in the figure;

[0043] Figure 3 The internal system framework diagram of the state evaluation module in the present application is shown in the figure;

[0044] Figure 4 The internal system framework diagram of the sewage abnormality analysis module in the present application is shown in the figure. DETAILED DESCRIPTION

[0045] The following description is used to disclose the present application so that those skilled in the art can implement the present application. The preferred embodiments in the following description are only as examples, and other obvious modifications can be made by those skilled in the art.

[0046] Referring to Figure 1 The sewage treatment equipment remote control system based on operation data statistics shown in the figure comprises:

[0047] The sewage treatment equipment operation data acquisition module is used for real-time acquisition of the operation parameters of the sewage treatment equipment, extraction of statistical characteristics and time sequence characteristics, generation of statistical information of the equipment operation state, and transmission of the data to the fault detection module;

[0048] The state evaluation module extracts abnormal factors according to the data output by the fault detection module, establishes a state evaluation model based on the abnormal factors, judges whether there is an operation abnormality based on the output of the state evaluation model, and if there is an abnormality, transmits the equipment state to the abnormality analysis module;

[0049] The abnormality analysis module analyzes the abnormal reasons of the real-time operation data of the equipment based on the trained abnormality analysis model, obtains abnormal reason data, quantizes the abnormal reason data, obtains the score of each abnormal reason, establishes a repair suggestion model based on the score of each abnormal reason, and proposes an optimal equipment repair suggestion scheme based on the output of the repair suggestion model.

[0050] Remote control module: based on the device operation data and health status, remote control of the device is carried out, including starting, stopping and adjusting, remote monitoring and operation of the sewage treatment device are carried out.

[0051] Referring to Figure 2 As shown in the figure, the sewage treatment device operation data acquisition module specifically includes:

[0052] Device operation parameter unit: based on the sensors in the sewage treatment device, the parameters of the device operation are obtained in real time, the frequency of collecting parameters is set to 1 time per second, the mobile average filtering algorithm is used to remove sensor noise, the values of different sensors are uniformly converted into standard dimensions and units, a time stamp is added to each collected data point, the data is arranged in time sequence, and the missing data is filled in through the interpolation method;

[0053] Statistical feature and time sequence feature extraction unit: statistical analysis is carried out on real-time data to obtain mean, standard deviation, maximum value and minimum value, and analysis is carried out on the time sequence of data to extract trend, periodicity and mutation point time sequence features;

[0054] Device operation state statistical information generation unit: linear regression method is used to extract the trend of device data changing with time, wavelet transform is used to analyze the periodic change in data, change point detection algorithm is used to identify the mutation point in data, local statistical features such as mean, standard deviation, kurtosis and skewness are extracted in each time window to help analyze the local fluctuation of the device, and the collected real-time data is aggregated according to hours, wherein the aggregation formula is:

[0055]

[0056] In the formula, μ h is the mean value of each hour, N o is the total number of data points in a certain hour, and x i is the value at the i-th data point;

[0057] By using the mobile average filtering algorithm, the interpolation method and the linear regression method, the collected real-time data is de-noised and the missing data is filled in, so that the accuracy and integrity of the data are guaranteed, and the method makes the operation data of the device more stable, providing reliable data support for subsequent analysis and evaluation.

[0058] Referring to Figure 3 As shown in the figure, the state evaluation module specifically includes:

[0059] Abnormal factor extraction unit: abnormal factors in the device operation state statistical information generation unit are extracted, including temperature fluctuation abnormal factor, flow deviation abnormal factor, pressure fluctuation abnormal factor and device vibration abnormal factor;

[0060] The state evaluation model establishment unit inputs the extracted abnormal factors, establishes a state judgment model based on the abnormal factors, judges whether there is an operation abnormality according to the output of the model, trains the state evaluation model using historical data, evaluates whether the current state of the equipment belongs to a normal range based on the trained model, sets a threshold value according to the historical data, and determines that the state is abnormal if the output result of the state evaluation model exceeds the threshold value. If the state is abnormal, the state information of the equipment is transmitted to the abnormality analysis module.

[0061] By extracting multi-dimensional abnormal factors and combining historical data for model training, the state evaluation model can accurately judge whether the equipment is in an abnormal state. By setting a dynamic threshold value, false positives caused by a static threshold value are avoided, and the intelligent level of the system is improved.

[0062] The state evaluation model establishment unit specifically includes:

[0063] Based on the weighted summation formula, the state evaluation model is established. The Pearson correlation coefficient method is used to evaluate the relationship strength between the abnormal factors and the abnormal state of the equipment. These correlation coefficients are used as the weights of the factors. The input abnormal factors and the weights of the factors are used to judge whether the equipment is in an abnormal state.

[0064] The weighted summation formula is:

[0065] G = L1X1 + L2X2 + L3X3 + … + LnXn n n

[0066] In the formula, G represents the state score of the equipment, X1 is the extracted temperature fluctuation abnormal factor, L1 is the weight coefficient of the temperature fluctuation abnormal factor, X2 is the flow deviation abnormal factor, L2 is the weight coefficient of the flow deviation abnormal factor, X3 is the pressure fluctuation abnormal factor, L3 is the weight coefficient of the pressure fluctuation abnormal factor, and Xn is the nth abnormal factor. n

[0067] According to the score distribution of the normal state and the abnormal state in the historical data, a threshold value is set. If the output score of the model exceeds the threshold value, it is determined that the state is abnormal. The threshold value calculation formula is:

[0068] T = mean(G n ) + kstd(G n )

[0069] In the formula, mean(G n ) is the mean of the score under the normal state, std(G n ) is the standard deviation of the score under the normal state, and k is a constant, which is 2. ​​

[0070] By combining the application of Pearson correlation coefficient through weighted summation formula, the weight of abnormal factors is more in line with the actual situation, improving the accuracy and sensitivity of the model, and more accurately identifying abnormal equipment status.

[0071] Referring to Figure 4 The abnormal analysis module specifically includes:

[0072] Abnormal reason analysis unit: based on the trained abnormal analysis model, the real-time running data of the equipment is analyzed, the abnormal factor data under the abnormal state of the equipment at the current time is input, and the reasons that may cause the equipment to appear abnormal are identified;

[0073] Abnormal reason scoring unit: quantitatively processing the abnormal reasons obtained by analysis, scoring each abnormal reason according to the running state of the equipment, the detected abnormal factors and the historical data related to these factors;

[0074] Repair suggestion model establishment unit: based on the score of each abnormal reason, a repair suggestion model is constructed, combined with historical data and equipment failure mode, to automatically generate repair suggestions for the equipment, and the priority of repair suggestions is calculated according to the severity score of each abnormality;

[0075] Repair suggestion output unit: based on the output of the repair suggestion model, the priority of the repair suggestion is obtained, and the optimal equipment repair suggestion scheme is generated;

[0076] The abnormal reason analysis adopts advanced statistical methods such as Bayesian network and Granger causality test, which can comprehensively evaluate the failure reasons of the equipment, and identify new abnormal patterns through clustering algorithm, improving the intelligence and flexibility of fault analysis.

[0077] The abnormal reason analysis unit specifically includes:

[0078] Based on the correlation importance score, the key factors closely related to the equipment abnormality are screened out, the current abnormal factor is compared with the historical abnormal mode library to obtain the cosine similarity, the two modes with the highest similarity are found as candidates, the clustering algorithm is used to judge whether the current abnormality belongs to the known category, and if it is a new category, it is marked as a new abnormality;

[0079] Build a Bayesian network, according to the historical failure frequency and the current abnormal data, get the probability of each potential reason leading to abnormality, for abnormal factors with time sequence characteristics, use Granger causality test to judge the causal relationship between variables;

[0080] Based on weighted scoring, the similarity of abnormal mode matching, Bayesian probability and the weight of fault propagation path are integrated to obtain the comprehensive score of each potential reason, and the final analysis result is output as the most likely reason according to the score.

[0081] By adopting the combination of various algorithms such as correlation importance score, cosine similarity, clustering algorithm and Bayesian network, the anomaly analysis module can quickly and accurately identify potential fault causes according to real-time data, and filter the most possible fault source through weighted scoring, thereby improving the accuracy of fault diagnosis.

[0082] The anomaly cause scoring unit specifically includes:

[0083] Based on the historical data of the device running state and the abnormal factors, the key indicators affecting the abnormal causes are screened out, the scoring levels are set for each scoring indicator, and the weights of each scoring indicator are obtained by using the analytic hierarchy process;

[0084] According to the current device running state and the detected abnormal factor data, the scoring levels of each indicator are compared, and each indicator of each abnormal cause is scored;

[0085] Each indicator score of each abnormal cause is multiplied by the corresponding weight and then added to obtain the comprehensive score of the abnormal cause;

[0086] Combined with the analytic hierarchy process and the weighted scoring strategy, the scoring unit can more objectively evaluate the importance of each abnormal cause, provide data support for subsequent repair recommendations, and improve the priority management capability of fault repair.

[0087] The repair recommendation model establishment unit specifically includes:

[0088] Combined with the anomaly cause scoring, the repair scheme is prioritized, wherein the priority calculation formula is:

[0089]

[0090] In the formula, P J is the priority of the Jth repair scheme, S is the comprehensive score of the abnormal cause, a is the weight of the comprehensive score of the abnormal cause, C J is the repair cost of the Jth repair scheme, and T J is the estimated repair time of the Jth repair scheme.

[0091] By considering factors such as the comprehensive score of the abnormal cause, the repair cost and the repair time, the repair recommendation model can comprehensively evaluate multiple repair schemes, provide the optimal repair scheme, and help maintenance personnel efficiently solve device problems.

[0092] Based on the output of the repair suggestion model, the priority of the repair suggestion is obtained, and the optimal device repair suggestion scheme is generated, specifically including: according to the priority value of each repair scheme given by the repair suggestion model, selecting the top n repair schemes from all schemes, arranging these schemes into a candidate scheme set, for each repair scheme in the candidate scheme set, evaluating from three important dimensions of repair cost, required repair time and repair effect, and giving a comprehensive evaluation score for each scheme, comparing the comprehensive evaluation scores of all schemes in the candidate scheme set, finding the scheme with the highest score, and determining it as the optimal device repair suggestion scheme;

[0093] The system can provide the optimal repair scheme for maintenance personnel by comprehensively evaluating multi-dimensional factors of the repair scheme such as repair cost, repair effect and required time, reduces resource waste caused by inaccurate decision-making, and improves maintenance efficiency.

[0094] The remote control module specifically includes: judging the operation required by the device according to the current operation data and health state information of the sewage treatment device, and then generating corresponding start, stop and adjustment instructions, sending the generated control instructions to the device end based on the communication protocol, and receiving the feedback information returned by the device end;

[0095] The remote control module can analyze the operation state and health information of the device in real time, generate operation instructions and perform remote operation, greatly improving the convenience and response speed of management, and making device maintenance and operation more intelligent and automated.

[0096] In summary, the advantages of the present application are:

[0097] The present application can obtain the key operation parameters of the device in real time through the operation data acquisition module of the sewage treatment device, and timely understand the operation state of the device, thereby providing accurate data support for fault early warning and maintenance;

[0098] Through the state evaluation module and the abnormality analysis module, the operation abnormality of the device can be accurately identified, helping the management personnel to take timely measures before the device failure occurs, reducing the device failure rate and downtime;

[0099] The abnormality cause analysis module can provide detailed repair suggestions for the maintenance personnel of the device through in-depth analysis of abnormal data, and prioritize the repair schemes, which helps to efficiently allocate resources for device repair and ensure long-term stable operation of the device;

[0100] Based on the health state and operation data of the device, the remote control module of the present application can remotely start, stop and adjust the device, greatly improving the flexibility and efficiency of device management, and avoiding the delay caused by manual intervention.

[0101] Through the automatic data acquisition, state evaluation, fault detection and analysis, the need of manual inspection and manual operation is reduced, the labor cost is reduced, and the energy can be concentrated on the key problems, the precision and efficiency of equipment management are improved;

[0102] The abnormal problems of the equipment are detected and repaired in time, the long-time equipment damage can be avoided, the service life of the equipment is prolonged, and the maintenance cost of the enterprise is reduced.

[0103] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above examples, and the above examples and descriptions in the specification are only the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection required by the present application is defined by the appended claims and their equivalents.

Claims

1. A remote control system for sewage treatment equipment based on operation data statistics, characterized in that: include: Sewage treatment equipment operation data acquisition module: used to collect the operating parameters of sewage treatment equipment in real time, extract statistical features and time series features, generate statistical information on the equipment operation status, and transmit the data to the fault detection module; Status assessment module: This module extracts abnormal factors based on the data output by the fault detection module, establishes a status assessment model based on the abnormal factors, and determines whether there is an operational abnormality based on the output of the status assessment model. If an abnormality exists, the device status is transmitted to the abnormality analysis module. Abnormal analysis module: Based on the trained abnormal analysis model, the module analyzes the causes of abnormalities in the real-time operation data of the equipment, obtains abnormal cause data, quantifies the abnormal cause data, and obtains a score for each abnormal cause. Based on the score of each abnormal cause, the module establishes a repair suggestion model. Based on the output of the repair suggestion model, the module proposes the optimal equipment repair plan. Remote control module: Based on the equipment operation data and health status, remote control of the equipment is carried out, including starting, stopping and adjusting, and remote monitoring and operation of the sewage treatment equipment is carried out.

2. A remote control system for sewage treatment equipment based on operation data statistics according to claim 1, characterized in that: The sewage treatment equipment operation data acquisition module specifically includes: Equipment operation parameter unit: Based on the sensors in the sewage treatment equipment, the equipment operation parameters are acquired in real time. The frequency of parameter acquisition is set to once per second. A moving average filter algorithm is used to remove sensor noise. The values ​​of different sensors are uniformly converted to standard dimensions and units. A timestamp is added to each collected data point, and the data is arranged in chronological order. Missing data is filled by interpolation. Statistical feature and time series feature extraction unit: performs statistical analysis on real-time data to obtain the mean, standard deviation, maximum value, and minimum value. It also analyzes the time series of the data to extract trend, periodicity, and mutation point time series features. Equipment operation status statistical information generation unit: uses linear regression method to extract the trend of equipment data changes over time, uses wavelet transform to analyze the periodic changes in the data, uses change point detection algorithm to identify mutation points in the data, and extracts local statistical features such as mean, standard deviation, kurtosis and skewness in each time window to help analyze the local fluctuations of the equipment, and aggregates the collected real-time data by hour.

3. A remote control system for sewage treatment equipment based on operation data statistics according to claim 1, characterized in that: The status assessment module specifically includes: Abnormal factor extraction unit: extracts abnormal factors in the equipment operation status statistical information generation unit, including temperature fluctuation abnormal factors, flow deviation abnormal factors, pressure fluctuation abnormal factors, and equipment vibration abnormal factors; Status assessment model establishment unit: inputs the extracted abnormal factors, establishes a status judgment model based on the abnormal factors, judges whether there is an operation abnormality according to the output of the model, uses historical data to train the status assessment model, and evaluates whether the current status of the equipment is within the normal range based on the trained model. According to the historical data, a threshold is set. If the result output by the status assessment model exceeds the threshold, it is judged to be an abnormal state. If it is in an abnormal state, the status information of the equipment is transmitted to the abnormality analysis module.

4. A remote control system for sewage treatment equipment based on operation data statistics according to claim 3, characterized in that: The state assessment model establishment unit specifically includes: establishing a state assessment model based on a weighted summation formula, using the Pearson correlation coefficient method to evaluate the strength of the relationship between abnormal factors and abnormal states of equipment, using these correlation coefficients as factor weights, and judging whether the equipment is in an abnormal state by inputting abnormal factors and factor weights.

5. A remote control system for sewage treatment equipment based on operation data statistics according to claim 1, characterized in that: The abnormality analysis module specifically includes: Abnormal cause analysis unit: Based on the trained abnormal analysis model, it analyzes the real-time operation data of the equipment, inputs the abnormal factor data of the abnormal state of the equipment at the current moment, and identifies the causes that may cause the equipment to abnormally occur; Abnormality cause scoring unit: Quantifies the abnormality causes obtained through analysis and scores each abnormality cause based on the equipment's operating status, detected abnormal factors, and historical data related to these factors; Repair suggestion model building unit: Based on the score of each abnormality cause, a repair suggestion model is built. By combining historical data and equipment failure modes, repair suggestions are automatically generated for the equipment. The priority of the repair suggestions is calculated based on the severity score of each abnormality. Repair suggestion output unit: Based on the output of the repair suggestion model, it obtains the priority of the repair suggestion and generates the optimal equipment repair suggestion plan.

6. A remote control system for sewage treatment equipment based on operation data statistics according to claim 5, characterized in that: The abnormal cause analysis unit specifically includes: Based on the relevance importance score, key factors closely associated with device anomalies are screened out. The current anomaly factor is compared with the historical anomaly pattern library to obtain cosine similarity. The two patterns with the highest similarity are selected as candidates. A clustering algorithm is used to determine whether the current anomaly belongs to a known category. If it belongs to a new category, it is marked as a new anomaly. Construct a Bayesian network to obtain the probability of each potential cause leading to an anomaly based on historical failure frequencies and current anomaly data. Use Granger causality tests to determine the causal relationship between variables for anomaly factors with time series characteristics. Based on weighted scoring, the similarity of abnormal pattern matching, Bayesian probability, and the weight of the fault propagation path are integrated to obtain a comprehensive score for each potential cause. The causes are sorted by score and the most likely cause is output as the final analysis result.

7. A remote control system for sewage treatment equipment based on operation data statistics according to claim 5, characterized in that: The abnormality cause scoring unit specifically includes: Based on the historical data of equipment operating status and abnormal factors, the key indicators that affect the causes of abnormalities are screened out, a scoring level is set for each scoring indicator, and the hierarchical analysis method is used to obtain the weight of each scoring indicator; Based on the current equipment operating status and the detected abnormal factor data, each indicator of each abnormal cause is scored separately according to the scoring standard of each indicator; Multiply the indicator scores of each abnormal cause by the corresponding weight and add them together to obtain the comprehensive score of the abnormal cause.

8. A remote control system for sewage treatment equipment based on operation data statistics according to claim 5, characterized in that: The repair suggestion model building unit specifically includes: Combined with the abnormality cause score, the repair plans are prioritized. The priority calculation formula is: Where, P J is the priority of the J-th repair plan, S is the comprehensive score of the abnormal cause, α is the weight of the comprehensive score of the abnormal cause, C J is the repair cost of the Jth repair plan, T J is the estimated repair time of the Jth repair plan.

9. A remote control system for sewage treatment equipment based on operation data statistics according to claim 5, characterized in that: The method of obtaining the priority of the repair suggestions based on the output of the repair suggestion model and generating the optimal equipment repair suggestion plan specifically includes: selecting n repair suggestions with the highest priority from all plans based on the priority values ​​of the repair suggestions given by the repair suggestion model, organizing these plans into a candidate plan set, evaluating each repair plan in the candidate plan set based on three important dimensions: repair cost, required repair time, and repair effect, and assigning a comprehensive evaluation score to each plan. By comparing the comprehensive evaluation scores of all plans in the candidate plan set, the plan with the highest score is found and determined as the optimal equipment repair suggestion plan.

10. A remote control system for sewage treatment equipment based on operation data statistics according to claim 1, characterized in that: The remote control module specifically includes: judging the operations that the equipment needs to perform based on the current operating data and health status information of the sewage treatment equipment, and then generating corresponding start, stop and adjustment instructions, sending the generated control instructions to the equipment end based on the communication protocol, and receiving feedback information returned by the equipment end.

Images