An abnormality diagnosis method, device and equipment of a flavoring and seasoning pump and a medium

Abstract

This invention discloses a method, apparatus, equipment, and medium for diagnosing anomalies in a flavoring and additive pump. The method includes: acquiring in real-time inverter operating data, flow parameters, and valve status corresponding to the target flavoring and additive pump; calculating the inverter statistical characteristics corresponding to the target flavoring and additive pump based on the inverter operating data, and judging the abnormal state of the target flavoring and additive pump based on the inverter statistical characteristics to determine the abnormal state type corresponding to the target flavoring and additive pump; determining the target expert rule corresponding to the abnormal state type based on a preset expert rule base and preset logical priority, and performing anomaly diagnosis on the flow parameters or valve status based on the target expert rule to determine the anomaly diagnosis result corresponding to the target flavoring and additive pump. Through the technical solution of this invention, second-level automatic fault diagnosis and precise location can be achieved, improving the efficiency and accuracy of anomaly diagnosis for flavoring and additive pumps.

Description

Technical Field

[0001] This invention relates to the field of tobacco processing technology, and in particular to a method, apparatus, equipment and medium for diagnosing abnormalities in a flavoring and additive pump. Background Technology

[0002] In tobacco processing, the flavoring and additive process is a core element in shaping the sensory quality of cigarette products and ensuring their stylistic consistency. This process requires the precise and uniform application of trace amounts of flavorings or liquids to continuously and dynamically conveyed tobacco leaves or shredded tobacco in extremely high proportions. To achieve this precision control, modern production lines commonly employ closed-loop systems based on ratio control. In this control loop, the rotational speed of the flavoring and additive pump, typically characterized by the output frequency of a frequency converter, is the final execution variable. The stability of its operating state is directly related to the setpoint tracking capability and anti-interference capability of the control system; therefore, the stability of the pump frequency is a key indicator for evaluating the control quality of the entire flavoring and additive system.

[0003] Currently, the industry primarily relies on two solutions for diagnosing abnormal frequency of flavoring and additive pumps. The first is a Supervisory Control and Data Acquisition (SCADA) or Human-Machine Interface (HMI) combined with manual experience for troubleshooting. SCADA or HMI collects and displays process variables, triggering upper and lower limit alarms. Once an alarm is triggered, the diagnostic work depends entirely on the manual judgment of the on-site operation or maintenance engineer. Engineers need to simultaneously review multiple scattered monitoring screens or historical trend charts, building a possible fault tree in their minds based on their accumulated experience, and then manually verifying each item on-site. The second solution is a manual checklist based on a fixed process. When an abnormal pump frequency is detected, technicians check and troubleshoot item by item according to a pre-listed checklist.

[0004] However, the efficiency, accuracy, and effectiveness of the entire diagnostic process in the first type of solution highly depend on the experience level of individual engineers, resulting in slow response times, high risk of misjudgment, and difficulty in standardizing and sharing valuable experience. The second type of solution has a fixed and rigid troubleshooting path, failing to dynamically focus on the most likely fault branch based on the specific characteristics of the current anomaly, leading to low troubleshooting efficiency, especially when multiple faults occur concurrently or hidden faults exist. Therefore, how to achieve second-level automatic fault diagnosis and precise location, improving the efficiency and accuracy of anomaly diagnosis for flavoring and dispensing pumps, is a problem that urgently needs to be solved. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, and medium for diagnosing malfunctions in flavoring and dispensing pumps, which can solve the problem of low efficiency and accuracy in diagnosing malfunctions in flavoring and dispensing pumps.

[0006] According to one aspect of the present invention, a method for diagnosing malfunctions in a flavoring and dispensing pump is provided, comprising: Real-time acquisition of inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump; Based on the inverter operating data, the inverter statistical characteristics corresponding to the target odor-adding pump are calculated, and based on the inverter statistical characteristics, the abnormal state of the target odor-adding pump is judged to determine the abnormal state type of the target odor-adding pump. Based on a preset expert rule base and preset logical priority, the target expert rule corresponding to the abnormal state type is determined, and the abnormality diagnosis of the flow parameter or valve state is performed based on the target expert rule to determine the abnormal diagnosis result corresponding to the target flavoring and feeding pump.

[0007] According to another aspect of the present invention, an abnormality diagnosis device for a flavoring and additive pump is provided, comprising: The data acquisition module is used to acquire in real time the inverter operating data, flow parameters and valve status corresponding to the target flavoring and feeding pump; The status judgment module is used to calculate the inverter statistical characteristics corresponding to the target odor-adding pump based on the inverter operating data, and to judge the abnormal status of the target odor-adding pump based on the inverter statistical characteristics, and determine the abnormal status type of the target odor-adding pump. The anomaly diagnosis module is used to determine the target expert rule corresponding to the anomaly state type based on the preset expert rule library and preset logical priority, and to perform anomaly diagnosis on the flow parameter or valve state based on the target expert rule, and determine the anomaly diagnosis result corresponding to the target flavoring and feeding pump.

[0008] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the abnormal diagnosis method for the flavoring and dispensing pump according to any embodiment of the present invention.

[0009] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the abnormal diagnosis method for the flavoring and dispensing pump described in any embodiment of the present invention.

[0010] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the abnormal diagnosis method for the flavoring and dispensing pump described in any embodiment of the present invention.

[0011] The technical solution of this invention acquires the inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump in real time. Further, based on the inverter operating data, statistical characteristics of the inverter corresponding to the target flavoring and feeding pump are calculated, and based on these statistical characteristics, anomaly status judgment is performed on the target flavoring and feeding pump to determine the type of anomaly status. Finally, based on a preset expert rule base and preset logical priorities, target expert rules corresponding to the anomaly status type are determined, and anomaly diagnosis is performed on the flow parameters or valve status based on the target expert rules to determine the anomaly diagnosis result for the target flavoring and feeding pump. Because the diagnosis is automatically triggered using statistical characteristics, and reverse reasoning is performed by calling an expert rule base built based on material balance and signal transmission relationships, the problem of low efficiency and accuracy in anomaly diagnosis of flavoring and feeding pumps is solved. This enables second-level automatic fault diagnosis and precise location, improving the efficiency and accuracy of anomaly diagnosis for flavoring and feeding pumps.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of a flavoring and ingredient adding process based on existing technology; Figure 2 This is a schematic diagram of a flavoring and additive pipeline based on existing technology; Figure 3 This is a flowchart of an abnormal diagnosis method for a flavoring and additive pump according to Embodiment 1 of the present invention; Figure 4This is a flowchart of an abnormality diagnosis method for a flavoring and additive pump according to Embodiment 2 of the present invention; Figure 5 This is a flowchart of an optional malfunction diagnosis method for a flavoring and additive pump according to Embodiment 2 of the present invention; Figure 6 This is a schematic diagram of the abnormal diagnosis device for a flavoring and additive pump according to Embodiment 3 of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device that implements the abnormal diagnosis method of the flavoring and adding pump according to an embodiment of the present invention. Detailed Implementation

[0015] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0017] Figure 1 The diagram shows a flavoring and additive process provided by the prior art. Specifically, the closed-loop process for controlling the flavoring and additive ratio in this flavoring and additive process is as follows: after the tobacco material is measured and the flow is controlled by the electronic scale 1, it is sent to the flavoring and additive machine 3 through the first vibrating conveyor 2 for flavoring and additive. The flavored and additive material is then sent to the subsequent process through the second vibrating conveyor 4 and the belt conveyor 5.

[0018] Figure 2The diagram shows a schematic of a flavoring and feeding pipeline provided by the prior art. Specifically, the flavoring and feeding pipeline includes: a material tank 7, a feeding pipe 8, a filter 9, a flavoring and feeding pump 10, a mass flow meter 11, a test valve 12, a nozzle 13, and a compressed air / steam pipeline 14. Its working process is as follows: the liquid material flows out of the material tank 7 under the power of the flavoring and feeding pump 10, passes through the feeding pipe 8, and sequentially passes through the filter 9, the flavoring and feeding pump 10, and the mass flow meter 11 before entering the nozzle 13. At the nozzle 13, the liquid material is atomized by compressed air or steam supplied by the compressed air / steam pipeline 14 and then sprayed out to flavor and feed the tobacco material in the flavoring and feeding machine 3. The test valve 12 is used to test the feeding pipeline system during equipment maintenance. It is normally in the closed state; if it is accidentally opened during production, it will cause leakage and affect normal flavoring and feeding.

[0019] The system control flow can be as follows: The real-time tobacco flow signal detected by the electronic scale 1 is sent to the electrical control cabinet 6, which processes it to generate a set flow rate for the feeding amount; the electrical control cabinet 6 compares the set flow rate with the actual feeding flow rate detected by the mass flow meter 11, and the resulting deviation is calculated by the electrical control cabinet 6 and outputs a frequency control command to the frequency converter of the flavoring and feeding pump 10; the frequency converter adjusts its output frequency accordingly, driving the flavoring and feeding pump 10 to change its speed, thereby achieving precise proportional control of the feeding flow rate. The actual feeding flow rate signal detected by the mass flow meter 11 is fed back to the electrical control cabinet 6, thus forming a closed-loop control circuit.

[0020] In this closed loop, the rotational speed of the flavoring and dispensing pump, controlled by the frequency converter output, is the final execution variable, and its stability directly characterizes the system's control quality. However, during production, pump frequencies often experience abnormal fluctuations, remaining consistently high or low. The root causes are complex and multifaceted, potentially involving equipment failures in any of the following stages: upstream (e.g., unstable electronic scale signals), midstream (e.g., pipe blockage, filter clogging, valve malfunction), or downstream (e.g., leakage after the flow meter). Quickly and accurately locating these root causes is crucial for ensuring production continuity and product quality, and is a long-standing industry pain point. Therefore, this application provides a method for diagnosing anomalies in flavoring and dispensing pumps to address the low efficiency and accuracy of such diagnoses.

[0021] Example 1 Figure 3 This is a flowchart of a method for diagnosing malfunctions in a flavoring and dispensing pump according to Embodiment 1 of the present invention. This embodiment is applicable to situations where malfunctions in a flavoring and dispensing pump are automatically diagnosed. This method can be executed by a malfunction diagnosis device for the flavoring and dispensing pump, which can be implemented in hardware and / or software and can be configured in an electronic device. For example... Figure 3 As shown, the method includes: S110: Real-time acquisition of inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump.

[0022] In this context, "flavoring and adding ingredients" refers to the process of adding flavorings and liquids to processed tobacco leaves or shreds during the tobacco processing. A flavoring and adding pump can refer to a precision metering pump driven by a motor whose speed is controlled by a frequency converter. A target flavoring and adding pump can refer to a pre-selected flavoring and adding pump used for anomaly diagnosis. For example, the target flavoring and adding pump can be any flavoring and adding pump in the tobacco processing workshop. Typically, the target flavoring and adding pump can be determined based on actual application requirements; this embodiment of the invention does not specifically limit its selection.

[0023] The inverter operating data can refer to parameter data used to represent the operating status of the inverter corresponding to the target odor-adding pump. For example, inverter operating data can be output power. Flow parameters can refer to data used to represent various flow states corresponding to the target odor-adding pump. For example, flow parameters can be flow data corresponding to an electronic scale or flow data corresponding to a mass flow meter. Valve status can refer to data used to represent the opening and closing status of the test manual valve corresponding to the target odor-adding pump. For example, valve status can be valve open or valve closed.

[0024] S120. Calculate the inverter statistical characteristics corresponding to the target odor-adding pump based on the inverter operating data, and determine the abnormal state type of the target odor-adding pump based on the inverter statistical characteristics.

[0025] The statistical characteristics of a frequency converter can refer to numerical indicators calculated from a set of frequency converter operating data that represent certain core properties of the data. Optionally, the statistical characteristics of a frequency converter include: target standard deviation and moving average. Standard deviation can refer to a statistical measure used to measure the dispersion or fluctuation of a set of data. For example, standard deviation can describe the average deviation of a data point from its mean. Generally, the larger the standard deviation, the more volatile the data; the smaller the standard deviation, the more stable the data. Target standard deviation can refer to the standard deviation corresponding to the target odor-adding pump. Moving average can refer to a data value used to analyze the trend of time series data. Abnormal state type can refer to a system fault mode with specific causal orientation identified by real-time calculation and analysis of the statistical characteristics of the odor-adding pump frequency, combined with its relationship with the system setpoint.

[0026] S130. Based on the preset expert rule base and preset logical priority, determine the target expert rule corresponding to the abnormal state type, and perform abnormal diagnosis on the flow parameter or valve state based on the target expert rule to determine the abnormal diagnosis result corresponding to the target flavoring and feeding pump.

[0027] Among these, expert rules refer to rules that formalize and structure the understanding of control principles and troubleshooting experience of domain experts, such as senior equipment engineers and process engineers. Typically, each expert rule is based on "IF (condition) THEN (conclusion)" logic, associating specific abnormal data patterns with specific fault causes. Preset expert rules refer to pre-defined expert rules used for a deep understanding and judgment of how key parameters of a flavoring and additive dosing closed-loop system should change under various fault modes. A preset expert rule library refers to a set of rules composed of various preset expert rules for the same abnormality diagnosis scenario. Preset logical priority refers to pre-defined rules used to classify the importance of different abnormal state types. Target expert rules refer to expert rules in the preset expert rule library that match the abnormal state type. Anomaly diagnosis results refer to the diagnostic results obtained after using target expert rules to diagnose anomalies in flow parameters or valve states. Typically, anomaly diagnosis results may include the cause of the anomaly, the anomaly level, and handling suggestions.

[0028] In an optional implementation, after acquiring the inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump in real time, the method further includes: acquiring the pressure sensor data corresponding to the target flavoring and feeding pump in real time; calculating the confidence level of the anomaly diagnosis result based on the pressure sensor data and a preset index trend, and determining the confidence score corresponding to the anomaly diagnosis result. Here, the filter is a device used to filter impurities in the liquid. When it becomes clogged, it increases pipeline resistance, causing the pump to require a higher frequency to reach the set flow rate, which is one of the typical causes of increased pump frequency. Pressure sensor data can refer to data used to represent the pressure situation in the flavoring and feeding pipeline. For example, pressure sensor data can include pipeline pressure sensor data and / or filter differential pressure sensor data. Typically, pipeline pressure sensor data representing pipeline pressure can be read by a pressure transmitter installed on the main pipeline after the pump, and filter differential pressure sensor data representing filter pressure difference can be read by a differential pressure sensor connected across the filter. The preset index trend can refer to pre-set rules used to limit the changing trends of various pressure sensor data under different abnormal conditions. For example, the preset indicator trend can include the matching relationship between different abnormal conditions and the corresponding pressure sensor data change trends. The confidence score can refer to a score used to intuitively represent the accuracy of the anomaly diagnosis results. Specifically, pressure sensor data can be acquired simultaneously with inverter operating data, flow parameters, and valve status. Therefore, after obtaining the anomaly diagnosis results, the pressure sensor data can be used to cross-validate the anomaly diagnosis results, improving the accuracy of the diagnosis.

[0029] The technical solution of this invention acquires the inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump in real time. Further, based on the inverter operating data, statistical characteristics of the inverter corresponding to the target flavoring and feeding pump are calculated, and based on these statistical characteristics, anomaly status judgment is performed on the target flavoring and feeding pump to determine the type of anomaly status. Finally, based on a preset expert rule base and preset logical priorities, target expert rules corresponding to the anomaly status type are determined, and anomaly diagnosis is performed on the flow parameters or valve status based on the target expert rules to determine the anomaly diagnosis result for the target flavoring and feeding pump. Because the diagnosis is automatically triggered using statistical characteristics, and reverse reasoning is performed by calling an expert rule base built based on material balance and signal transmission relationships, the problem of low efficiency and accuracy in anomaly diagnosis of flavoring and feeding pumps is solved. This enables second-level automatic fault diagnosis and precise location, improving the efficiency and accuracy of anomaly diagnosis for flavoring and feeding pumps.

[0030] Example 2 Figure 4 This is a flowchart of an abnormal diagnosis method for a flavoring and additive pump provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Specifically, this embodiment refines the step of "judging the abnormal state of the target flavoring and additive pump based on the statistical characteristics of the frequency converter and determining the abnormal state type corresponding to the target flavoring and additive pump". Specifically, it may include: performing a threshold judgment on the target standard deviation based on a first stability threshold; if the target standard deviation exceeds the first stability threshold, then the drastic fluctuation type is taken as the abnormal state type corresponding to the target flavoring and additive pump; performing a threshold judgment on the moving average based on a second stability threshold and a reference operating frequency; if the moving average exceeds the sum of the second stability threshold and the reference operating frequency, then the pump frequency increase type is taken as the abnormal state type corresponding to the target flavoring and additive pump; performing a threshold judgment on the moving average based on a third stability threshold and a reference operating frequency; if the moving average is lower than the difference between the reference operating frequency and the third stability threshold, then the pump frequency decrease type is taken as the abnormal state type corresponding to the target flavoring and additive pump. Figure 4 As shown, the method includes: S210: Real-time acquisition of inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump.

[0031] Specifically, the electronic scale is a key upstream detection device used to measure the instantaneous flow rate of tobacco leaves in real time. Its signal serves as the feedforward input for the control system to generate the feeding setpoint, and its stability directly affects the stability of the entire loop. The mass flow meter is a precision measuring instrument installed on the feeding pipeline, used to detect the actual feeding flow rate in real time and calculate instantaneous accuracy. Its measured value, as a feedback signal, is compared with the setpoint, forming the core of closed-loop control and a key reference point for determining whether the flow rate has actually arrived during diagnostics. The flavoring and feeding pump and its frequency converter are the core actuators of the system. The pump provides the conveying power, and the frequency converter, by receiving instructions from the controller, adjusts the output frequency to steplessly regulate the pump speed, thereby achieving precise flow control. The test manual valve is a manual valve installed on the pipeline after the mass flow meter and must be closed during normal production. Its on / off state is a key Boolean variable in diagnostics. If accidentally opened, it will create a legitimate bypass, leading to an abnormal decrease in pump frequency and material leakage. Therefore, in the abnormal diagnosis process of the flavoring and feeding pump, the output frequency of the flavoring and feeding pump frequency converter can be collected at the output end of the frequency converter, the instantaneous flow rate of the electronic scale can be collected at the signal output end of the electronic scale, the instantaneous flow rate, set flow rate, and instantaneous flow rate accuracy of the mass flow meter can be collected at the mass flow meter, and the on / off status of the test valve can be collected at the test valve. This provides a valid basis for subsequent operations.

[0032] S220. Based on preset data processing rules, perform data cleaning on the inverter operating data to determine the target operating data corresponding to the inverter operating data.

[0033] The preset data processing rules refer to pre-defined rules that define the data processing flow. For example, preset data processing rules may include rules for data cleaning and filtering / noise reduction. Thus, data cleaning ensures data accuracy, signal filtering ensures data usability, and highlights relevant information. The target operating data can refer to the inverter's operating data after data preprocessing.

[0034] S230. Calculate the standard deviation of the target operating data based on the first time period to determine the target standard deviation corresponding to the target flavoring and feeding pump.

[0035] Here, the time period can refer to a numerical value used to define the time interval for data processing. The first time period can refer to the time period involved in calculating the standard deviation. For example, the first time period can be 30 seconds.

[0036] Specifically, with a first time period of 30 seconds, the target running data Pump_Freq is a sample containing n data points {x1, x2, ..., x...}. nFor example, the target standard deviation can be calculated every 30 seconds using the following process: First, use the formula μ=(x1+x2+...+x) n Calculate the average value using (x1-μ) / n. Then, use the formula (x1-μ) 2 ,(x2-μ) 2 ,...,(x n -μ) 2 Calculate the difference between each data point and the mean, then square it. Further, according to the formula σ... 2 =[(x1-μ) 2 +(x2-μ) 2 +...+(x n -μ) 2 The average of the squared differences, i.e., the variance, is calculated using the formula ] / n. Finally, the square root of the variance is taken to obtain the target standard deviation. It is worth noting that the number of data samples, n, can be determined based on the actual application; this embodiment of the invention does not impose a specific limitation on this.

[0037] S240. Calculate the average value of the target operating data based on the second time period and the preset time window to determine the moving average value corresponding to the target flavoring and feeding pump.

[0038] The second time period can refer to the time period involved in calculating the moving average. For example, the second time period can be 10 seconds. The preset time window can refer to a pre-set value used to limit the number of data samples to be processed. For example, the preset time window can be 60 seconds.

[0039] Specifically, taking a second time period of 10 seconds, a preset time window of 60 seconds, a sampling frequency of 1 Hz, and a current sampling time of t as an example, the moving average can be calculated every 10 seconds using the following formula: Where N can represent the number of data points within a preset time window, i.e., 60. This can represent the pump frequency value at the i-th second before the current time t. The summation range is 60 data points backward from the current time t, i.e., the past 60 seconds.

[0040] S250. Based on the first stability threshold, a threshold judgment is made on the target standard deviation. If the target standard deviation exceeds the first stability threshold, the drastic fluctuation type is taken as the abnormal state type corresponding to the target flavoring and feeding pump.

[0041] The stability threshold can refer to a pre-set value used to assess the stability of the data. The first stability threshold can refer to a stability threshold used to assess whether the fluctuation is severe. For example, the first stability threshold can be set to 0.5 Hz. The severe fluctuation type can refer to information used to describe an abnormal situation where the pump's operating frequency fluctuates wildly in a short period of time, indicating extreme instability. Typically, when the fluctuation intensity of the target standard deviation exceeds the first stability threshold, it is judged as severe fluctuation.

[0042] S260. Based on the second stable threshold and the reference operating frequency, the moving average value is judged. If the moving average value exceeds the sum of the second stable threshold and the reference operating frequency, the pump frequency increase type is taken as the abnormal state type corresponding to the target flavoring and feeding pump.

[0043] The second stability threshold can refer to a stability threshold used to assess the magnitude of a significantly higher pump frequency. For example, the second stability threshold can be set to 2.0 Hz. The reference operating frequency can refer to the typical or center value of the inverter output frequency when the flavoring and feeding pump is operating under normal, healthy, and stable conditions. Typically, the reference operating frequency can be determined based on a pre-designed process flow, or it can be determined based on the long-term moving average or median of healthy operation over a historical period. For example, in this embodiment of the invention, the reference operating frequency can be set to 45.0 Hz. The pump frequency increase type can refer to information describing an abnormal situation where the average level of the pump's operating frequency is consistently and significantly higher than its normal reference value. Typically, a pump frequency increase is determined when the moving average is higher than the sum of the second stability threshold and the reference operating frequency.

[0044] S270. Based on the third stable threshold and the reference operating frequency, the moving average value is judged. If the moving average value is lower than the difference between the reference operating frequency and the third stable threshold, the pump frequency decrease type is taken as the abnormal state type corresponding to the target flavoring and feeding pump.

[0045] The third stability threshold can refer to a stability threshold used to assess the magnitude of a significantly low pump frequency. For example, the third stability threshold can be set to 2.0 Hz. The pump frequency decrease type can refer to information describing an anomaly where the average level of the pump's operating frequency is consistently and significantly lower than its normal reference value. Typically, a pump frequency decrease is determined when the moving average is less than the difference between the reference operating frequency and the third stability threshold.

[0046] Specifically, after calculating the target standard deviation and moving average of the target flavoring and feeding pump, a first stability threshold is used to determine the target standard deviation. If the target standard deviation exceeds the first stability threshold, the drastic fluctuation type is identified as the abnormal state type for the target flavoring and feeding pump. If the target standard deviation does not exceed the first stability threshold, a second stability threshold and a baseline operating frequency are used to determine the moving average. If the moving average exceeds the sum of the second stability threshold and the baseline operating frequency, the pump frequency increase type is identified as the abnormal state type for the target flavoring and feeding pump. If the moving average does not exceed the sum of the second stability threshold and the baseline operating frequency, a third stability threshold and a baseline operating frequency are used to determine the moving average. If the moving average is lower than the difference between the baseline operating frequency and the third stability threshold, the pump frequency decrease type is identified as the abnormal state type for the target flavoring and feeding pump. Thus, by transforming implicit human experience into automatically executable explicit rules, second-level diagnosis and alarms are achieved, greatly reducing troubleshooting time and production downtime.

[0047] It is worth noting that, in this embodiment of the invention, if neither the target standard deviation nor the moving average meets the aforementioned threshold conditions, the current state is determined to be normal, and the process returns to the first step to continue monitoring. Furthermore, the first, second, and third stability thresholds measure anomalies of entirely different natures, and their values ​​are set based on different physical meanings and process requirements; therefore, there is no fixed relationship between the three thresholds.

[0048] S280. Determine the target expert rule corresponding to the abnormal state type based on the preset expert rule base and preset logical priority.

[0049] Specifically, if the number of abnormal state types is not unique, the final abnormal state types are selected according to a preset logical priority. For example, the priority of the drastic fluctuation type is higher than that of the pump frequency increase type, and the priority of the pump frequency increase type is higher than that of the pump frequency decrease type. Furthermore, the final selected abnormal state types are used to determine the abnormal diagnosis branch, and the corresponding target expert rule is matched in the preset expert rule base to implement the abnormal diagnosis branch.

[0050] S290. If the abnormal state type is a violent fluctuation type, then the instantaneous flow rate of the electronic scale in the flow parameters is judged based on the preset flow rate threshold. If the instantaneous flow rate of the electronic scale exceeds the preset flow rate threshold, then a diagnostic reason for the instability of the electronic scale is generated.

[0051] The preset flow rate threshold refers to a pre-set value used to evaluate the stability of the electronic scale's flow rate. For example, the preset flow rate threshold could be 1.0 g / min. The instantaneous flow rate of the electronic scale refers to the weight of material flowing through or being weighed by the scale per unit time during continuous weighing. Typically, the instantaneous flow rate can be calculated using the formula: Instantaneous Flow Rate = (Current Weight - Previous Weight) / Time Interval.

[0052] S2100. Based on the diagnostic cause, determine the corresponding target processing suggestion and target alarm level in the target expert rules, and combine the diagnostic cause, target processing suggestion and target alarm level to obtain the abnormal diagnostic result corresponding to the target flavoring and feeding pump.

[0053] Specifically, while performing statistical characteristic calculations on the inverter's operating data, the short-term standard deviation of the electronic scale's instantaneous flow rate can be calculated to obtain flow fluctuations. When a severe fluctuation branch is triggered, it is further determined whether the flow fluctuation exceeds a preset flow threshold. If so, a diagnostic reason for "unstable instantaneous flow rate of the electronic scale" is generated, along with target handling suggestions for "checking the electronic scale system" and target alarm levels for advanced alarms.

[0054] S2110. If the abnormal state type is pump frequency increase type, then the instantaneous flow rate of the flow meter in the flow parameters is judged based on the set flow rate value and flow tolerance value, or the instantaneous accuracy of the flow meter in the flow parameters is judged based on the preset accuracy threshold.

[0055] The set flow rate value can refer to the target flow rate value that the process requires to be achieved and maintained. The flow tolerance value can refer to the maximum range within which the actual instantaneous flow rate is allowed to fluctuate around the set flow rate value. For example, the flow tolerance value can be 5% of the set flow rate value. The instantaneous flow rate of the flow meter can refer to the fluid flow rate measured and calculated by the flow meter at the current moment.

[0056] Instantaneous accuracy of a flow meter refers to the maximum allowable error range between its reading (instantaneous flow rate value) and the actual flow rate of the fluid passing through it when measuring real-time, dynamically changing flow rates. For example, it can be calculated using the formula: Calculate the instantaneous accuracy of the flow meter. This can indicate the actual proportion of added flavorings and ingredients. This can indicate the proportion of flavoring or additives added. The preset accuracy threshold refers to a pre-set value used to evaluate the instantaneous accuracy of the flow meter. Typically, the preset accuracy threshold can be set according to process quality requirements. For example, the preset accuracy threshold can be set to 98%.

[0057] S2120. If the instantaneous flow rate of the flow meter is lower than the sum of the set flow rate value and the flow tolerance value, or if the instantaneous accuracy of the flow meter is lower than the preset accuracy threshold, a diagnosis of pipeline blockage or filter clogging is generated.

[0058] S2130. If the instantaneous flow rate of the flow meter exceeds the sum of the set flow rate value and the flow tolerance value, and the instantaneous accuracy of the flow meter exceeds the preset accuracy threshold, then a diagnostic cause for leakage in the pipeline at the front end of the mass flow meter is generated.

[0059] S2140. Based on the diagnostic cause, determine the corresponding target processing suggestion and target alarm level in the target expert rules, and combine the diagnostic cause, target processing suggestion and target alarm level to obtain the abnormal diagnostic result corresponding to the target flavoring and feeding pump.

[0060] Specifically, when the pump frequency increase branch is triggered, it further determines whether the instantaneous flow rate of the mass flow meter is lower than the difference between the set flow rate value and the flow tolerance value, i.e., 95% of the set flow rate value, or whether the instantaneous accuracy of the flow meter is lower than the preset accuracy threshold. If either of the above conditions is met, a diagnostic cause of "pipeline blockage or filter clogging" is generated, along with a target handling suggestion of "checking the filter and pipeline" and a target alarm level for a medium-level alarm. If neither of the above conditions is met, a diagnostic cause of "pipeline leakage before the mass flow meter" is generated, along with a target handling suggestion of "checking the sealing of the flow meter front end" and a target alarm level for a high-level alarm.

[0061] S2150. If the abnormal state type is pump frequency decrease, then the valve state is diagnosed based on the preset state judgment rule. If the valve state is open, then a diagnostic reason for the test manual valve not being closed is generated.

[0062] The preset state judgment rule can refer to a pre-set rule used to judge the opening state of the test manual valve. For example, the preset state judgment rule can be to judge whether the valve state is 1, and if so, then judge the test manual valve to be in the open state.

[0063] S2160. Based on the diagnostic cause, determine the corresponding target processing suggestion and target alarm level in the target expert rules, and combine the diagnostic cause, target processing suggestion and target alarm level to obtain the abnormal diagnostic result corresponding to the target flavoring and feeding pump.

[0064] Specifically, when the pump frequency converter branch is triggered, it checks whether the valve is open. If so, it generates a diagnostic reason of "test manual valve not closed", a target handling suggestion for "close the manual valve", and a target alarm level for low-level alarms.

[0065] If not, determine whether the instantaneous flow rate of the flow meter is greater than the difference between the set flow rate value and the flow tolerance value, and whether the instantaneous accuracy of the flow meter is greater than the preset accuracy threshold. If yes, generate a diagnostic cause of "leakage in the pipeline after the mass flow meter", a target handling suggestion of "checking the connection at the back end of the mass flow meter", and a target alarm level for advanced alarms.

[0066] The technical solution of this invention acquires the inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump in real time. Further, based on preset data processing rules, the inverter operating data is cleaned to determine the target operating data. The standard deviation of the target operating data is calculated based on a first time period to determine the target standard deviation corresponding to the target flavoring and feeding pump. The average value of the target operating data is calculated based on a second time period and a preset time window to determine the moving average value corresponding to the target flavoring and feeding pump. Further, a threshold judgment is performed on the target standard deviation based on a first stability threshold. If the target standard deviation exceeds the first stability threshold, a drastic fluctuation type is identified as the abnormal state type corresponding to the target flavoring and feeding pump. A threshold judgment is performed on the moving average value based on a second stability threshold and a reference operating frequency. If the moving average value exceeds the sum of the second stability threshold and the reference operating frequency, a pump frequency increase type is identified as the abnormal state type corresponding to the target flavoring and feeding pump. Threshold judgment is performed on the moving average based on the third stability threshold and the reference operating frequency. If the moving average is lower than the difference between the reference operating frequency and the third stability threshold, the pump frequency decrease type is identified as the abnormal state type corresponding to the target flavoring and dispensing pump. The target expert rule corresponding to the abnormal state type is determined based on a preset expert rule library and preset logical priority. Finally, if the abnormal state type is a drastic fluctuation type, a threshold judgment is performed on the instantaneous flow rate of the electronic scale in the flow parameters based on a preset flow threshold. If the instantaneous flow rate of the electronic scale exceeds the preset flow threshold, a diagnostic reason for the electronic scale instability is generated. Based on the diagnostic reason, the corresponding target processing suggestion and target alarm level are determined in the target expert rule, and the diagnostic reason, target processing suggestion, and target alarm level are combined to obtain the abnormal diagnostic result corresponding to the target flavoring and dispensing pump. If the abnormal state type is a pump frequency increase type, a threshold judgment is performed on the instantaneous flow rate of the flow meter in the flow parameters based on the set flow value and flow tolerance value, or a threshold judgment is performed on the instantaneous accuracy of the flow meter in the flow parameters based on a preset accuracy threshold. If the instantaneous flow rate of the flow meter is lower than the sum of the set flow rate value and the flow tolerance value, or if the instantaneous accuracy of the flow meter is lower than the preset accuracy threshold, a diagnosis of pipeline blockage or filter clogging is generated. If the instantaneous flow rate of the flow meter exceeds the sum of the set flow rate value and the flow tolerance value, and the instantaneous accuracy of the flow meter exceeds the preset accuracy threshold, a diagnosis of leakage in the pipeline upstream of the mass flow meter is generated. Based on the diagnosis, the corresponding target handling suggestions and target alarm levels are determined in the target expert rules, and the diagnosis results for the target flavoring and feeding pump are obtained by combining the diagnosis, target handling suggestions, and target alarm levels. If the abnormal state type is pump frequency decrease, the valve status is diagnosed based on the preset status judgment rules. If the valve status is open, a diagnosis of test manual valve not closed is generated.Based on the diagnostic cause, the corresponding target handling suggestions and target alarm levels are determined in the target expert rules. These are then combined to obtain the abnormal diagnosis result for the target flavoring and feeding pump. By automatically triggering diagnosis using statistical features and calling an expert rule base built based on material balance and signal transmission relationships for reverse reasoning, the problem of low efficiency and accuracy in abnormal diagnosis of flavoring and feeding pumps is solved. This enables second-level automatic fault diagnosis and precise location, improving the efficiency and accuracy of abnormal diagnosis for flavoring and feeding pumps.

[0067] Figure 5The diagram shows a flowchart of an optional anomaly diagnosis method for a flavoring and additive pump provided by an embodiment of the present invention. Specifically, firstly, the inverter output frequency, electronic scale instantaneous flow rate, flow meter instantaneous flow rate, flow meter instantaneous accuracy, and valve status corresponding to the target flavoring and additive pump are collected in real time. Then, the inverter output frequency operating data is cleaned to determine the target operating data corresponding to the inverter operating data. The standard deviation of the target operating data is calculated to determine the target standard deviation corresponding to the target flavoring and additive pump. The average value of the target operating data is calculated to determine the moving average value corresponding to the target flavoring and additive pump, resulting in the inverter statistical characteristics including the target standard deviation and the moving average value. Simultaneously, the short-term standard deviation of the electronic scale instantaneous flow rate is calculated to obtain the flow fluctuation. Further, based on the inverter statistical characteristics, anomaly status judgment is performed on the target flavoring and additive pump to determine the anomaly status type corresponding to the target flavoring and additive pump, and the corresponding anomaly diagnosis branch is triggered. Further, based on a preset expert rule base and preset logical priority, the target expert rule corresponding to the anomaly status type is determined. Finally, if the anomaly branch is a drastic fluctuation branch, it is determined whether the flow fluctuation exceeds a preset flow threshold. Therefore, by checking the fluctuations in the electronic scale, the stability of the electronic scale can be diagnosed, generating diagnostic causes, target handling suggestions, and target alarm levels. If the abnormal branch is a pump frequency increase branch, it is determined whether the instantaneous flow rate of the mass flow meter is lower than the difference between the set flow rate value and the flow tolerance value, or whether the instantaneous accuracy of the flow meter is lower than the preset accuracy threshold. Thus, by checking the flow meter reading, blockage or upstream leakage can be determined, generating diagnostic causes, target handling suggestions, and target alarm levels. If the abnormal branch is a pump frequency decrease branch, it is determined whether the valve status is open, and whether the instantaneous flow rate of the flow meter is greater than the difference between the set flow rate value and the flow tolerance value, and whether the instantaneous accuracy of the flow meter is greater than the preset accuracy threshold. Thus, by checking the valve status and flow rate, valve or downstream leakage can be determined, generating diagnostic causes, target handling suggestions, and target alarm levels. The technical solution of this application, by embedding the diagnostic logic into the closed-loop control principle and by analyzing the abnormalities of the executed variables to infer the fault source, provides scientific and accurate diagnostic conclusions, fundamentally avoiding misjudgment problems and improving diagnostic accuracy. By transforming implicit human experience into explicit, automatically executable rules, second-level diagnosis and alarms are achieved, significantly reducing troubleshooting time and production downtime. By solidifying the understanding of control principles and troubleshooting experience of senior technicians into the system, the company's reliance on specific individuals is reduced, enabling effective transfer of operational knowledge and a significant leap in overall team capabilities. By quickly and accurately handling issues such as leaks and blockages, material waste is effectively reduced, product quality consistency is ensured, and overall equipment efficiency is improved.

[0068] It is worth noting that, in this embodiment of the invention, after obtaining the abnormal diagnosis result corresponding to the target flavoring and dispensing pump, alarm information can be highlighted in a pop-up window on the system's human-machine interface. The alarm information includes at least: a fault title, a snapshot of key data at the trigger time, a system diagnostic conclusion, handling suggestions, and an alarm level used to distinguish the degree of urgency. After operator confirmation, the system returns to step one and continues the next monitoring cycle.

[0069] Example 3 Figure 6 This is a schematic diagram of the abnormal diagnosis device for a flavoring and additive pump provided in Embodiment 3 of the present invention. Figure 6 As shown, the device includes: a data acquisition module 310, a status judgment module 320, and an anomaly diagnosis module 330.

[0070] Among them, the data acquisition module 310 is used to acquire the inverter operation data, flow parameters and valve status corresponding to the target flavoring and feeding pump in real time; The status judgment module 320 is used to calculate the inverter statistical characteristics corresponding to the target odorant and feed pump based on the inverter operating data, and to judge the abnormal status of the target odorant and feed pump based on the inverter statistical characteristics, and to determine the abnormal status type of the target odorant and feed pump. The anomaly diagnosis module 330 is used to determine the target expert rule corresponding to the anomaly state type based on the preset expert rule library and preset logical priority, and to perform anomaly diagnosis on the flow parameter or valve state based on the target expert rule, and determine the anomaly diagnosis result corresponding to the target flavoring and feeding pump.

[0071] The technical solution of this invention acquires the inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump in real time. Further, based on the inverter operating data, statistical characteristics of the inverter corresponding to the target flavoring and feeding pump are calculated, and based on these statistical characteristics, anomaly status judgment is performed on the target flavoring and feeding pump to determine the type of anomaly status. Finally, based on a preset expert rule base and preset logical priorities, target expert rules corresponding to the anomaly status type are determined, and anomaly diagnosis is performed on the flow parameters or valve status based on the target expert rules to determine the anomaly diagnosis result for the target flavoring and feeding pump. Because the diagnosis is automatically triggered using statistical characteristics, and reverse reasoning is performed by calling an expert rule base built based on material balance and signal transmission relationships, the problem of low efficiency and accuracy in anomaly diagnosis of flavoring and feeding pumps is solved. This enables second-level automatic fault diagnosis and precise location, improving the efficiency and accuracy of anomaly diagnosis for flavoring and feeding pumps.

[0072] Optional, the inverter's statistical characteristics include: target standard deviation and moving average; The status determination module 320 can be used specifically for: Based on preset data processing rules, the inverter operating data is cleaned to determine the target operating data corresponding to the inverter operating data. Based on the first time period, the standard deviation of the target operating data is calculated to determine the target standard deviation corresponding to the target flavoring and feeding pump; The average value of the target operating data is calculated based on the second time period and the preset time window to determine the moving average value corresponding to the target flavoring and feeding pump.

[0073] Optional, the status determination module 320 can be used for: The target standard deviation is judged based on the first stability threshold. If the target standard deviation exceeds the first stability threshold, the drastic fluctuation type is taken as the abnormal state type corresponding to the target flavoring and feeding pump. The moving average value is judged based on the second stable threshold and the reference operating frequency. If the moving average value exceeds the sum of the second stable threshold and the reference operating frequency, the pump frequency increase type is taken as the abnormal state type corresponding to the target flavoring and feeding pump. The moving average value is determined based on the third stable threshold and the reference operating frequency. If the moving average value is lower than the difference between the reference operating frequency and the third stable threshold, the pump frequency decrease type is taken as the abnormal state type corresponding to the target flavoring and feeding pump.

[0074] Optionally, if the abnormal state type is a drastic fluctuation type, the abnormal diagnosis module 330 can be specifically used to: perform threshold judgment on the instantaneous flow rate of the electronic scale in the flow parameters based on a preset flow rate threshold; if the instantaneous flow rate of the electronic scale exceeds the preset flow rate threshold, generate a diagnostic reason for the instability of the electronic scale; determine the corresponding target processing suggestion and target alarm level in the target expert rules based on the diagnostic reason, and combine the diagnostic reason, target processing suggestion and target alarm level to obtain the abnormal diagnosis result corresponding to the target flavoring and feeding pump.

[0075] Optionally, if the abnormal state type is a pump frequency increase type, the abnormal diagnosis module 330 can be specifically used to: perform threshold judgment on the instantaneous flow rate of the flow meter in the flow parameters based on the set flow value and flow tolerance value, or perform threshold judgment on the instantaneous accuracy of the flow meter in the flow parameters based on the preset accuracy threshold; if the instantaneous flow rate of the flow meter is lower than the sum of the set flow value and the flow tolerance value, or the instantaneous accuracy of the flow meter is lower than the preset accuracy threshold, then generate a diagnosis cause of pipeline blockage or filter clogging; if the instantaneous flow rate of the flow meter exceeds the sum of the set flow value and the flow tolerance value, and the instantaneous accuracy of the flow meter exceeds the preset accuracy threshold, then generate a diagnosis cause of pipeline leakage at the front end of the mass flow meter; based on the diagnosis cause, determine the corresponding target processing suggestion and target alarm level in the target expert rules, and combine the diagnosis cause, target processing suggestion and target alarm level to obtain the abnormal diagnosis result corresponding to the target flavoring and feeding pump.

[0076] Optionally, if the abnormal state type is a pump frequency decrease type, the abnormal diagnosis module 330 can be specifically used to: perform abnormal diagnosis on the valve state based on preset state judgment rules; if the valve state is open, generate a diagnostic reason for the test manual valve not being closed; determine the corresponding target processing suggestion and target alarm level in the target expert rules based on the diagnostic reason, and combine the diagnostic reason, target processing suggestion and target alarm level to obtain the abnormal diagnosis result corresponding to the target flavoring and feeding pump.

[0077] Optionally, the abnormal diagnosis device for the flavoring and feeding pump may further include: a cross-validation module, used to acquire pressure sensor data corresponding to the target flavoring and feeding pump in real time after acquiring the inverter operating data, flow parameters and valve status corresponding to the target flavoring and feeding pump in real time; and to calculate the confidence score of the abnormal diagnosis result based on the pressure sensor data and preset index trends, and determine the confidence score corresponding to the abnormal diagnosis result.

[0078] The malfunction diagnosis device for the flavoring and adding pump provided in this embodiment of the invention can execute the malfunction diagnosis method for the flavoring and adding pump provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0079] Example 4 Figure 7A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0080] like Figure 7 As shown, the electronic device 410 includes at least one processor 420 and a memory, such as a read-only memory (ROM) 430 or a random access memory (RAM) 440, communicatively connected to the at least one processor 420. The memory stores computer programs executable by the at least one processor. The processor 420 can perform various appropriate actions and processes based on the computer program stored in the ROM 430 or loaded into the RAM 440 from storage unit 490. The RAM 440 may also store various programs and data required for the operation of the electronic device 410. The processor 420, ROM 430, and RAM 440 are interconnected via a bus 450. An input / output (I / O) interface 460 is also connected to the bus 450.

[0081] Multiple components in electronic device 410 are connected to I / O interface 460, including: input unit 470, such as keyboard, mouse, etc.; output unit 480, such as various types of monitors, speakers, etc.; storage unit 490, such as disk, optical disk, etc.; and communication unit 4100, such as network card, modem, wireless transceiver, etc. Communication unit 4100 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0082] Processor 420 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 420 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 420 performs the various methods and processes described above, such as the anomaly diagnosis method for a flavoring and dispensing pump.

[0083] The method includes: Real-time acquisition of inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump; Based on the inverter operating data, the inverter statistical characteristics corresponding to the target odor-adding pump are calculated, and based on the inverter statistical characteristics, the abnormal state of the target odor-adding pump is judged to determine the abnormal state type of the target odor-adding pump. Based on a preset expert rule base and preset logical priority, the target expert rule corresponding to the abnormal state type is determined, and the abnormality diagnosis of the flow parameter or valve state is performed based on the target expert rule to determine the abnormal diagnosis result corresponding to the target flavoring and feeding pump.

[0084] In some embodiments, the malfunction diagnosis method for the flavoring and dispensing pump can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 490. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 410 via ROM 430 and / or communication unit 4100. When the computer program is loaded into RAM 440 and executed by processor 420, one or more steps of the malfunction diagnosis method for the flavoring and dispensing pump described above can be performed. Alternatively, in other embodiments, processor 420 can be configured to perform the malfunction diagnosis method for the flavoring and dispensing pump by any other suitable means (e.g., by means of firmware).

[0085] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0086] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0087] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0088] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0089] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0090] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0091] This application also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the abnormal diagnosis method for the flavoring and dispensing pump provided in any embodiment of this application. This program product and the abnormal diagnosis method for the flavoring and dispensing pump disclosed in the embodiments of this application belong to the same inventive concept, and therefore will not be described in detail here.

[0092] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0093] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for diagnosing malfunctions in a flavoring and additive pump, characterized in that, include: Real-time acquisition of inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump; Based on the inverter operating data, the inverter statistical characteristics corresponding to the target odor-adding pump are calculated, and based on the inverter statistical characteristics, the abnormal state of the target odor-adding pump is judged to determine the abnormal state type of the target odor-adding pump. Based on a preset expert rule base and preset logical priority, the target expert rule corresponding to the abnormal state type is determined, and the abnormality diagnosis of the flow parameter or valve state is performed based on the target expert rule to determine the abnormal diagnosis result corresponding to the target flavoring and feeding pump.

2. The method according to claim 1, characterized in that, The statistical characteristics of the frequency converter include: target standard deviation and moving average; The calculation of the inverter statistical characteristics corresponding to the target flavoring and feeding pump based on the inverter operating data includes: Based on preset data processing rules, the inverter operating data is cleaned to determine the target operating data corresponding to the inverter operating data. Based on the first time period, the standard deviation of the target operating data is calculated to determine the target standard deviation corresponding to the target flavoring and feeding pump; The average value of the target operating data is calculated based on the second time period and the preset time window to determine the moving average value corresponding to the target flavoring and feeding pump.

3. The method according to claim 2, characterized in that, The step of judging the abnormal state of the target flavoring and feeding pump based on the statistical characteristics of the frequency converter, and determining the abnormal state type of the target flavoring and feeding pump, includes: The target standard deviation is judged based on the first stability threshold. If the target standard deviation exceeds the first stability threshold, the drastic fluctuation type is taken as the abnormal state type corresponding to the target flavoring and feeding pump. The moving average value is judged based on the second stable threshold and the reference operating frequency. If the moving average value exceeds the sum of the second stable threshold and the reference operating frequency, the pump frequency increase type is taken as the abnormal state type corresponding to the target flavoring and feeding pump. The moving average value is determined based on the third stable threshold and the reference operating frequency. If the moving average value is lower than the difference between the reference operating frequency and the third stable threshold, the pump frequency decrease type is taken as the abnormal state type corresponding to the target flavoring and feeding pump.

4. The method according to claim 3, characterized in that, If the abnormal state type is a drastic fluctuation type, then the abnormal diagnosis of the flow parameter or valve state based on the target expert rule, and the determination of the abnormal diagnosis result corresponding to the target flavoring and feeding pump, includes: Based on a preset flow threshold, the instantaneous flow rate of the electronic scale in the flow parameters is judged. If the instantaneous flow rate of the electronic scale exceeds the preset flow threshold, a diagnostic reason for the instability of the electronic scale is generated. Based on the diagnostic reasons, the corresponding target processing suggestions and target alarm levels are determined in the target expert rules, and the diagnostic reasons, target processing suggestions and target alarm levels are combined to obtain the abnormal diagnostic results corresponding to the target flavoring and feeding pump.

5. The method according to claim 3, characterized in that, If the abnormal state type is a pump frequency increase type, then the abnormal diagnosis of the flow parameter or valve status based on the target expert rule, and the determination of the abnormal diagnosis result corresponding to the target flavoring and feeding pump, includes: The instantaneous flow rate of the flow meter in the flow parameters is judged based on the set flow rate value and flow tolerance value, or the instantaneous accuracy of the flow meter in the flow parameters is judged based on the preset accuracy threshold. If the instantaneous flow rate of the flow meter is lower than the sum of the set flow rate value and the flow tolerance value, or if the instantaneous accuracy of the flow meter is lower than the preset accuracy threshold, a diagnosis of pipeline blockage or filter clogging will be generated. If the instantaneous flow rate of the flow meter exceeds the sum of the set flow rate value and the flow tolerance value, and the instantaneous accuracy of the flow meter exceeds the preset accuracy threshold, then a diagnosis of leakage in the pipeline at the front end of the mass flow meter is generated. Based on the diagnostic reasons, the corresponding target processing suggestions and target alarm levels are determined in the target expert rules, and the diagnostic reasons, target processing suggestions and target alarm levels are combined to obtain the abnormal diagnostic results corresponding to the target flavoring and feeding pump.

6. The method according to claim 3, characterized in that, If the abnormal state type is a pump frequency decrease type, then the abnormal diagnosis of the flow parameter or valve state based on the target expert rule, and the determination of the abnormal diagnosis result corresponding to the target flavoring and feeding pump, includes: Based on preset state judgment rules, the valve state is abnormally diagnosed. If the valve state is open, a diagnostic reason for the test manual valve not being closed is generated. Based on the diagnostic reasons, the corresponding target processing suggestions and target alarm levels are determined in the target expert rules, and the diagnostic reasons, target processing suggestions and target alarm levels are combined to obtain the abnormal diagnostic results corresponding to the target flavoring and feeding pump.

7. The method according to claim 1, characterized in that, After acquiring the real-time inverter operating data, flow parameters, and valve status corresponding to the target flavoring and feeding pump, the method further includes: Real-time acquisition of pressure sensor data corresponding to the target flavoring and feeding pump; The confidence level of the abnormal diagnosis result is calculated based on the pressure sensor data and the preset index trend, and the confidence score corresponding to the abnormal diagnosis result is determined.

8. A diagnostic device for an malfunction of a flavoring and additive pump, characterized in that, include: The data acquisition module is used to acquire in real time the inverter operating data, flow parameters and valve status corresponding to the target flavoring and feeding pump; The status judgment module is used to calculate the inverter statistical characteristics corresponding to the target odor-adding pump based on the inverter operating data, and to judge the abnormal status of the target odor-adding pump based on the inverter statistical characteristics, and determine the abnormal status type of the target odor-adding pump. The anomaly diagnosis module is used to determine the target expert rule corresponding to the anomaly state type based on the preset expert rule library and preset logical priority, and to perform anomaly diagnosis on the flow parameter or valve state based on the target expert rule, and determine the anomaly diagnosis result corresponding to the target flavoring and feeding pump.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which is executed by the at least one processor to enable the at least one processor to perform the abnormal diagnosis method for the flavoring and dispensing pump according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the abnormal diagnosis method for the flavoring and dispensing pump as described in any one of claims 1-7.

Images